<p>Unstructured P2P systems have gained great popularity in recent years and are currently used by millions of users. One fundamental property of these systems is the lack of structure, which allows decentralized operation and makes it easy for new users to join and participate in the system. However, the lack of structure can also be abused by malicious users. We explore one such attack, that enables malicious users to use unstructured P2P systems to perform Denial of Service (DoS) attacks to third parties. Specifically, we show that a malicious node can coerce a large number of peers to perform requests to a target host that may not even be part of the P2P network, including downloading unwanted files from a target Web Server. This is a classic form of denial-of-service which also has two interesting characteristics: (a) it is hard to identify the originator of the attack, (b) it is even harder to stop the attack. The second property comes from the fact that certain unstructured P2P systems seem to have a kind of "memory", retaining knowledge about (potentially false) queries for many days. In this paper we present real-world experiments of Gnutella-based DoS attacks to Web Servers. We explore the magnitude of the problem and present a solution to protect innocent victims against this attack.</p>
<p>The World-Wide Web allows users to quickly and easily publish information in the form of web pages. Pages are linked to other pages already on the web using a hyperlink inserted into a web page by the page's author that contains the URL address of another existing web page. This model of web publishing, although simple and efficient, also has the effect that links between pages must be created manually and only to pages that are known to the author of the links. This can be a disadvantage if, for example, information in a particular field is incomplete and expanding rapidly over time, and where a page author cannot be expected to know which pages are the most appropriate to link to and when they become available.</p>
<p>In this paper, we look at a radically different model of web publishing in which the author of a web page does not specify links using URLs. Instead, the page author expresses an interest about the kind of content the page should link to and as new content comes online that matches that interest, links are inserted automatically into the original page to point to the new content. This leads to the possibility that a hyperlink from a particular location in a web page can lead to multiple destinations, something we call a multi-valued hyperlink.</p>
<p>We also describe a prototype implementation of our web architecture, based on the CHORD-based peer-to-peer overlay network, which uses publish/subscribe to communicate page author interests to other peers in order to create links between pages.</p>
<p>Searching social networks is determined by two factors: reputation and relevance. Reputation is the memory and summary of behavior from past transactions. Relevance is the probability that useful information can be obtained from a person. Search in social networks is performed by asking persons of high relevance and a good reputation or persons who are supposed to know somebody like that. We describe how these social aspects can be used in peer-to-peer networks in order to increase efficiency and scalability. Based on a social peer-to-peer network a knowledge management application with advantages over centralized approaches can be implemented.</p>
<p>A number of structured peer-to-peer (P2P) lookup protocols have been proposed recently. A P2P lookup protocol routes a lookup request to its target node in a P2P distributed system. Existing protocols achieve balanced routing traffic among nodes by assuming that lookup requests are evenly targeted at every node. However, when lookup requests concentrate on a few nodes simultaneously, these nodes become hot spots. Due to uneven routing patterns in existing protocols, hot spots cause unbalanced routing traffic which leads to routing bottlenecks. In this paper, we present a novel structured P2P lookup protocol called SCALLOP that delivers balanced routing and avoids routing bottlenecks at occurrences of hot spots. Among existing protocols, SCALLOP is the first one to accomplish this goal at the fundamental nature of a routing protocol. SCALLOP achieves balanced routing by uniquely constructing a balanced lookup tree for each node. The balanced tree evenly distributes routing traffic among sibling nodes and, therefore, avoids or reduces routing bottlenecks. In addition, as a load-balanced protocol, SCALLOP delivers asymptotically optimal lookup performance at the tradeoff between routing path and routing table size. We conducted a set of simulations to demonstrate the effectiveness of SCALLOP. The results show that, compared with a most-referenced and representative structured P2P lookup protocol and a graph-based extension of this protocol, SCALLOP significantly reduces routing bottlenecks while all three protocols deliver comparable lookup performance.</p>
<p>In this paper, we present a theoretical framework for design and analysis of distributed flocking algorithms. Two cases of flocking in free-space and presence of multiple obstacles are considered. We present three flocking algorithms: two for free-flocking and one for constrained flocking. A comprehensive analysis of the first two algorithms is provided. We demonstrate the first algorithm embodies all three rules of Reynolds. This is a formal approach to extraction of interaction rules that lead to the emergence of collective behavior. We show that the first algorithm generically leads to regular fragmentation, whereas the second and third algorithms both lead to flocking. A systematic method is provided for construction of cost functions (or collective potentials) for flocking. These collective potentials penalize deviation from a class of lattice-shape objects called alpha-lattices. We use a multi-species framework for construction of collective potentials that consist of flock-members, or alpha-agents, and virtual agents associated with alpha-agents called beta- and gamma-agents. We show that migration of flocks can be performed using a peer-to-peer network of agents, i.e., "flocks need no leaders." A "universal" definition of flocking for particle systems with similarities to Lyapunov stability is given. Several simulation results are provided that demonstrate performing 2-D and 3-D flocking, split/rejoin maneuver, and squeezing maneuver for hundreds of agents using the proposed algorithms.</p>
<item_title>Solving abduction by computing joint explanations: Logic programming formalization, applications to P2P data integration, and cmplexity results</item_title>
<p>An extension of abduction is investigated where explanations for bunches of observations may be jointly computed by sets of interacting agents. At one hand, agents are allowed to partially contribute to the reasoning task, so that joint explanations can be singled out even if each agent does not have enough knowledge for carrying out abduction on its own. At the other hand, agents maintain their autonomy in choosing explanations, each one being equipped with a weighting function reflecting its perception about the reliability of set of hypotheses. Given that different agents may have different and possibly contrasting preferences, some reasonable notions of agents' agreement are introduced, and their computational properties are thoroughly studied. As an example application of the framework discussed in the paper, it is shown how to handle data management issues in Peer-to-Peer systems and, specifically, how to provide a repair-based semantics to inconsistent ones.</p>
<p>This article presents an architecture to automatically create ad-hoc processes for complex value-added services and to execute them in a reliable way. The uniqueness of ad-hoc processes is to support users not only in standardized situations like traditional workflows do, but also in unique non-recurring situations. Based on user requirements, a service composition engine generates such ad-hoc processes, which integrate individual services in order to provide the desired functionality. Our infrastructure executes ad-hoc processes by transactional agents in a peer-to-peer style. The process execution is thereby performed under transactional guarantees. Moreover, the service composition engine is used to re-plan in the case of execution failures.</p>
<rp_address>Univ New S Wales, Sch Comp Sci & Engn, Sydney, NSW 2052, Australia</rp_address>
<rp_organization>Univ New S Wales</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Sch Comp Sci & Engn</rp_suborganization>
</rp_suborganizations>
<rp_city>Sydney</rp_city>
<rp_state>NSW</rp_state>
<rp_country>Australia</rp_country>
<rp_zips count="1">
<rp_zip location="AP">2052</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Univ New S Wales, Sch Comp Sci & Engn, Sydney, NSW 2052, Australia</rs_address>
<rs_organization>Univ New S Wales</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Sch Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Sydney</rs_city>
<rs_state>NSW</rs_state>
<rs_country>Australia</rs_country>
<rs_zips count="1">
<rs_zip location="AP">2052</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Performing business processes normally requires dynamic and casual collaborations among enterprises that are not centrally controlled. Enterprise application integration and Peer-to-Peer computing provide a solution to the business processes. Web service integration and agent-based middleware constitute the paradigms to implement enterprise application integration on Peer-to-Peer networks because of the loosely-coupled property of Web services and the autonomous, adaptive, and interactive properties of agents. Previous Web service integration researches focused on Web service integration based on client/server network architecture. However, along with the highly demands of Web service quality, Web services are not always provided on client/server networks. This research aims to construct an agent-based middleware for Web service dynamic integration on Peer-to-Peer networks to pursue the integration of optimal quality of Web services for enterprise application integration. The paper introduces the agent-based middleware including the formalization, Web service dynamic integration model, agent reasoning model, and the application.</p>
<p>Distributed Ascending Proxy Auction - A Cryptographic Approach. In recent years, auctions have become a very popular price discovery mechanism in the Internet. The common auction formats are typically centralized in nature. The peer-to-peer paradigm demands gearing up auctions for decentralized infrastructures. In this context, this paper proposes a distributed mechanism for ascending second-price auctions that relies on standard cryptographic algorithms. in essence, the auction protocol has the capability of preserving the privacy of the winning bidder's true valuation.</p>
<p>The auction protocol makes use of a high number of auctioneers divided into several groups. A bidder creates an encrypted chain of monotonously increasing bidding steps, where each bidding step can be decrypted by a different auctioneer group. This considerably reduces the attack and manipulation possibilities of malicious auctioneers. In addition, this secure approach does not require bidders to be online unless they are submitting their bid chain to the auctioneers.</p>
<p>In this paper, we describe the SomeWhere semantic peer-to-peer data management system that promotes a "small is beautiful" vision of the Semantic Web based on simple personalized ontologies (e.g., taxonomies of classes) but which are distributed at a large scale. In this vision of the Semantic Web, no user imposes to others his own ontology. Logical mappings between ontologies make possible the creation of a web of people in which personalized semantic marking up of data cohabits nicely with a collaborative exchange of data. In this view, the Web is a huge peer-to-peer data management system based on simple distributed ontologies and mappings.</p>
<rp_address>Univ Oregon, Eugene, OR 97402 USA</rp_address>
<rp_organization>Univ Oregon</rp_organization>
<rp_city>Eugene</rp_city>
<rp_state>OR</rp_state>
<rp_country>USA</rp_country>
<rp_zips count="1">
<rp_zip location="AP">97402</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Univ Oregon, Eugene, OR 97402 USA</rs_address>
<rs_organization>Univ Oregon</rs_organization>
<rs_city>Eugene</rs_city>
<rs_state>OR</rs_state>
<rs_country>USA</rs_country>
<rs_zips count="1">
<rs_zip location="AP">97402</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="2">
<p>The recent success of Internet-based computing projects, coupled with rapid developments in peer-to-peer systems, has stimulated interest in the notion of harvesting idle cycles under a peer-to-peer model. The problem we address in this paper is the development of scheduling strategies to achieve faster turnaround time in an open peer-based desktop grid system. The challenges for this problem are two-fold: How does the scheduler quickly discover idle cycles in the absence of global information about host availability? And how can faster turnaround time be achieved within the opportunistic scheduling environment offered by volunteer hosts? We propose a novel peer-based scheduling method, Wave Scheduler, which allows peers to self organize into a timezone-aware overlay network using structured overlay network, The Wave Scheduler then exploits large blocks of idle night-time cycles by migrating jobs to hosts located in night-time zones around the globe, which are discovered by scalable resource discovery methods.</p>
<p>Simulation results show that the slowdown factors of all migration schemes are consistently lower than the slowdown factors of the nonmigration schemes. Compared to traditional migration strategies we tested, the Wave Scheduler performs best. However under heavy load conditions, there is contention for those night-time hosts. Therefore, we propose an adaptive migration strategy for Wave Scheduler to further improve performance.</p>
<p>To efficiently deliver streaming media, researchers have developed technical solutions that fall into three categories, each of which has its merits and limitations. Infrastructure-based CDNs with dedicated network bandwidths and hardware supports can provide high-quality streaming services, but at a high cost. Server-based proxies are cost-effective but not scalable due to the limited proxy capacity in storage and bandwidth, and its centralized control also brings a single point of failure. Client-based P2P networks are scalable, but do not guarantee high-quality streaming service due to the transient nature of peers. To address these limitations, we present a novel and efficient design of a scalable and reliable media proxy system assisted by P2P networks, called PROP. In the PROP system, the clients' machines in an intranet are self-organized into a structured P2P system to provide a large media storage and to actively participate in the streaming media delivery, where the proxy is also embedded as an important member to ensure the quality of streaming service. The coordination and collaboration in the system are efficiently conducted by our P2P management structure and replacement policies. Our system has the following merits: 1) It addresses both the scalability problem in centralized proxy systems and the unreliable service concern by only relying on the P2P sharing of clients. 2) The proposed content locating scheme can timely serve the demanded media data and fairly dispatch media streaming tasks in appropriate granularity across the system. 3) Based on the modeling and analysis, we propose global replacement policies for proxy and clients, which well balance the demand and supply of streaming data in the system, achieving a high utilization of peers' cache. We have comparatively evaluated our system through trace-driven simulations with synthetic workloads and with a real-life workload extracted from the media server logs in an enterprise network, which shows our design significantly improves the quality of media streaming and the system scalability.</p>
<p>Despite the leaps and bounds made by the P2P research field in the last few years, the benefit of this innovation has been constrained to a few areas; search and file-sharing and storage to name a few. In particular, this innovation has had little significant impact in the field of distributed computing.</p>
<p>There are several obstacles to be overcome in the development of any distributed computer, most notably: scalability, fault tolerance, security and load balancing. The difficulty of these is compounded in the dynamic, decentralized environment which characterizes the P2P arena. This paper presents a method of recovering from faults which exploits the distributed hash table functionality provided by modem overlay networks. Its effectiveness is evaluated experimentally using a proof of concept P2P distributed computer.</p>
<p>It is hoped that by providing a solution to one of the obstacles, global, decentralized, dependable distributed computers will be one step closer to reality.</p>
<p>With the increasingly developed technology of mobile devices and wireless networks, more and more users share resources by mobile devices via wireless networks. Compared to traditional C/S architecture, P2P network is more appropriate for mobile computing environment. However, all existing P2P protocols have not well considered the characteristics and constraints of mobile devices and wireless networks. In this paper, we will present a novel mobile P2P protocol, M-Chord, by adopting hierarchical structure and registering mechanism on the basis of Chord. The experimental results show that M-Chord system has high-efficiency and good robustness in mobile P2P network.</p>
<rp_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China</rp_address>
<rp_organization>Huazhong Univ Sci & Technol</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Cluster & Grid Comp Lab</rp_suborganization>
</rp_suborganizations>
<rp_city>Wuhan</rp_city>
<rp_country>Peoples R China</rp_country>
<rp_zips count="1">
<rp_zip location="AC">430074</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China</rs_address>
<rs_organization>Huazhong Univ Sci & Technol</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Cluster & Grid Comp Lab</rs_suborganization>
</rs_suborganizations>
<rs_city>Wuhan</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">430074</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>A semantic Peer-to-Peer (P2P) scientific references sharing system, SemreX, is introduced in this paper. As a P2P application system based on JXTA, the implementation technologies of the P2P communication layer of SemreX are illustrated, including the software architecture and the classes in P2P communication layer. Some lessons about JXTA, from the system development practices and software testing, are also concluded, such as peer automatic discovery, program robustness and bug report.</p>
<p>Peer-to-Peer (P2P) networks have emerged as a prime research topic, partly due to the vast unexploited possibilities unrestricted distribution of the workload provides. The main hindrance for unrestricted exploitation of the P2P topology is, due to lack of security-related issues, the gullible attitude taken towards unknown agents. Therefore, the severity of the vulnerabilities caused by gullibility must be mended by other means, for example, by an effective incentive scheme encouraging agents to trustworthy behaviour. This paper presents an abstract model for incentive enhanced trust, to progressively assign the participating agents rights for accessing distributed resources, emphasising consistent behaviour. The model consists of a degrading formula, an illustrative incentive triangle and a best-effort distributed supervision model. Moreover, the same incentive model facilitates anticipation of future behaviour concerning any given agent founded on several distinct agents' opinion, suggesting that any knowledge concerning the counterpart is better than none.</p>
<p>This paper proposes a novel distributed routing system for integration between peer-to-peer (P2P) applications and mobile ad hoc networks (MANETs). This system takes advantage of the "zone" concept to reduce the multicast flooding. Significantly, the system investigates a mechanism to integrate key lookup in the application layer with routing in the link layer. The routing method provides a general-purpose technique that is not limited to any specific P2P applications. This paper presents the design of the routing system and sketches the layered architecture built according to the system functions.</p>
<rs_suborganization>Dept Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Shanghai</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">200030</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Recent unstructured Peer-to-Peer systems, represented by Gnutella and Freenet, offer an administration-free and fault-tolerant application-level overlay network. While elegant from a theoretical perspective, these systems have some serious disadvantages. First, due to knowing very little about the nature of the network topology, the search algorithms operating on these networks result in fatal scaling problems. Second, these systems rely on application-level routing, which may be inefficient with respect to network delays and bandwidth consumption. In this paper, we propose a novel search algorithm, called Split-Prober, to explore the small-world-like topologies of these networks efficiently and scalablely, by turning the power-law degree distributions in these networks to an advantage, and by making discriminative use of nodes according to their different roles in the network. As a result, we are able to reconcile the conflict of remedying the mismatch between the overlay topology and its projection on the underlying physical network, while at the same time navigating these networks with a guaranteed high efficiency and using only local knowledge as cues. Our simulation results indicate that the proposed algorithm outperforms several other well-known methods with significant performance gains.</p>
<p>This paper provides a survey of searchable, peer-to-peer file-sharing systems that offer the user some form of anonymity. We start this survey by giving a brief description of the most popular methods of providing anonymous communication. These include the Ants protocol, Onion routing, Multicasting, MIXes and UDP address spoofing. We then describe a number of implemented systems based on one, or a combination of, these methods. Finally, we discuss possible attacks on the anonymity of these systems and give examples of particular attacks and defences used by the systems we describe.</p>
<p>Most of current structured P2P systems exploit Distributed Hash Table (DHT) to archive an administration-free, fault tolerant overlay network and guarantee to deliver a message to its destination within O(logN) hops. While elegant from a theoretical perspective, those systems face difficulties in a realistic environment. Instead of building P2P overlays from a theoretical perspective, this design tries to construct an overlay from the physical network. By combining different network topology aware techniques, a distinctive overlay structure closely matching the Internet topology is created. The P2P overlay based on this structure is not only highly efficient for routing, but also keeps maintenance overhead very low even under highly dynamic environment.</p>
<p>Micro-payment systems have the potential to provide non-intrusive, high-volume and low-cost pay-as-you-use services for a wide variety of web-based applications. We propose an extension, P2P-NetPay, a micro-payment protocol characterized by off-line processing, suitable for peer-to-peer network services sharing. Our approach provides high performance and security using one-way hashing functions for e-coin encryption. In our P2P-NetPay protocol, each peer's transaction does not involve any broker and double spending is detected during the redeeming transaction. We describe the motivation for P2P-NetPay and describe three transactions of the P2P-NetPay protocol in detail to illustrate the approach. We then discuss future research on this protocol.</p>
<rs_address>Univ Roma La Sapienza, Dipartimento Informat & Sistemist, I-00198 Rome, Italy</rs_address>
<rs_organization>Univ Roma La Sapienza</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Dipartimento Informat & Sistemist</rs_suborganization>
</rs_suborganizations>
<rs_city>Rome</rs_city>
<rs_country>Italy</rs_country>
<rs_zips count="1">
<rs_zip location="BC">I-00198</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>We study peer-to-peer data integration, where each peer models an autonomous system that exports data in terms of its own schema, and data interoperation is achieved by means of mappings among the peer schemas, rather than through a global schema. We propose a multi-modal epistemic semantics based on the idea that each peer is conceived as a rational agent that exchanges knowledge/belief with other peers, thus nicely modeling the modular structure of the system. We then address the issue of dealing with possible inconsistencies, and distinguish between two types of inconsistencies, called local and P2P, respectively. We define a nonmonotonic extension of our logic that is able to reason on the beliefs of peers under inconsistency tolerance. Tolerance to local inconsistency essentially means that the presence of inconsistency within one peer does not affect the consistency of the whole system. Tolerance to P2P inconsistency means being able to resolve inconsistencies arising from the interaction between peers. We study query answering and its data complexity in this setting, and we present an algorithm that is sound and complete with respect to the proposed semantics, and optimal with respect to worst-case complexity.</p>
<rs_suborganization>Dept Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Bombay</rs_city>
<rs_state>Maharashtra</rs_state>
<rs_country>India</rs_country>
<rs_zips count="1">
<rs_zip location="AC">400076</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>In this paper, we present techniques to maintain temporal consistency of replicated objects in data-centric peer-to-peer overlay applications. We consider both structured and unstructured overlay networks, represented by Chord and Gnutella, respectively, and present techniques for maintaining consistency of replicated data objects in the presence of dynamic joins and leaves. We present extensions to the Chord and Gnutella protocol to incorporate our consistency techniques and implement our extensions to Gnutella into a Gtk-Gnutella prototype. Ail experimental evaluation of our techniques shows that: (i) a push-based approach achieves near-perfect fidelity in a stable overlay network, (ii) a hybrid approach based on push and pull achieves high fidelity in highly dynamic overlay networks and (iii) the run-time overheads of our techniques are small, making them it practical choice for overlay networks. (c) 2005 Elsevier B.V. All rights reserved.</p>
<rp_address>Osaka Univ, Grad Sch Informat Sci & Technol, Osaka 5670851, Japan</rp_address>
<rp_organization>Osaka Univ</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Grad Sch Informat Sci & Technol</rp_suborganization>
</rp_suborganizations>
<rp_city>Osaka</rp_city>
<rp_country>Japan</rp_country>
<rp_zips count="1">
<rp_zip location="AC">5670851</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Osaka Univ, Grad Sch Informat Sci & Technol, Osaka 5670851, Japan</rs_address>
<rs_organization>Osaka Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Grad Sch Informat Sci & Technol</rs_suborganization>
</rs_suborganizations>
<rs_city>Osaka</rs_city>
<rs_country>Japan</rs_country>
<rs_zips count="1">
<rs_zip location="AC">5670851</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>As the name suggests, epidemic protocols mimic spread of virus to implement broadcasting with high reliability and low communication cost in peer-to-peer (P2P) overlay networks. In this paper, we study the reliability of epidemic protocols in scale-free networks, an important class of P2P overlay network topologies. In order to improve the robustness of epidemic protocols, we optimize the basic epidemic protocol in the following two ways. One optimization is to introduce an adaptive mechanism that allows each node to retransmit a broadcast message adaptively to the environment. The other optimization is to modify the protocol such that nodes will forward broadcast messages preferentially to neighbor nodes of small degree. The usefulness of these optimizations is demonstrated through simulation results.</p>
<p>In this paper we propose an analytical model for file diffusion in a peer-to-peer (P2P) file-sharing network based on biological epidemics. During the downloading process, the peer shares the downloaded parts of the file and, thus, contributes to distributing it in the network. This behavior is similar to the spreading of epidemic diseases which is a well researched subject in mathematical biology. Unlike other P2P models based on epidemics, we show that steady state assumptions are not sufficient and that the granularity of the diffusion model may be appropriately selected.</p>
<rp_address>Osaka Univ, Grad Sch Informat Sci & Technol, 1-3 Machikaneyama, Toyonaka, Osaka 5608531, Japan</rp_address>
<rp_organization>Osaka Univ</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Grad Sch Informat Sci & Technol</rp_suborganization>
</rp_suborganizations>
<rp_street>1-3 Machikaneyama</rp_street>
<rp_city>Toyonaka</rp_city>
<rp_state>Osaka</rp_state>
<rp_country>Japan</rp_country>
<rp_zips count="1">
<rp_zip location="AP">5608531</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Osaka Univ, Grad Sch Informat Sci & Technol, Toyonaka, Osaka 5608531, Japan</rs_address>
<rs_organization>Osaka Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Grad Sch Informat Sci & Technol</rs_suborganization>
</rs_suborganizations>
<rs_city>Toyonaka</rs_city>
<rs_state>Osaka</rs_state>
<rs_country>Japan</rs_country>
<rs_zips count="1">
<rs_zip location="AP">5608531</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>The interest-based clustering is one of promising approaches to achieve low-cost search in peer-to-peer file sharing. It organizes the logical overlay network where peers having similar interests are closely located. In this paper, we propose an interest-based peer clustering algorithm using ant paradigm. Our algorithm is inspired by the ant-based clustering algorithm, which is one of heuristic methods to categorize many data items. We also evaluate this algorithm by simulations.</p>
<rp_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China</rp_address>
<rp_organization>Huazhong Univ Sci & Technol</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Cluster & Grid Comp Lab</rp_suborganization>
</rp_suborganizations>
<rp_city>Wuhan</rp_city>
<rp_country>Peoples R China</rp_country>
<rp_zips count="1">
<rp_zip location="AC">430074</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China</rs_address>
<rs_organization>Huazhong Univ Sci & Technol</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Cluster & Grid Comp Lab</rs_suborganization>
</rs_suborganizations>
<rs_city>Wuhan</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">430074</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>The decentralized structure together with the features of self-organization and fault-tolerance makes peer-to-peer network a promising information-sharing model. However, the efficient content-based location remains a challenge of large scale peer-to-peer network. In this paper we present SemreX, a semantic overlay for desktop literature documents sharing in peer-to-peer networks. We present a semantic overlay algorithm by which peers are locally clustered together according to their semantic similarity and long-range connections are rewired for short-cut in the peer-to-peer networks. Experiment results show that routing in the semantic overlay greatly improves the recall of search as well as reduces routing hops and messages.</p>
<rs_suborganization>Sch Elect & Informat Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Beijing</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">100044</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Recent measurement studies show that the object popularity distribution in Kazaa file sharing systems deviates significantly from the Zipf distribution which is commonly seen for the World Wide Web, We measure a real BitTorrent network and we figure its object popularity distribution, which also shows, on a log-log scale, a non-Zipf curve with flattened head. The fetch-at-most-once behavior of peer-to-peer (P2P) client is responsible for such a non-Zipf distribution and we propose two mathematical models to describe this. The models are based on different probability assumptions, though both indicate flatter heads in object popularity distribution curves than Zipf would predict. Our models provide theoretic tools to analyze differences between P2P File-sharing system and Web systems.</p>
<rs_suborganization>Sch Comp Sci & Technol</rs_suborganization>
</rs_suborganizations>
<rs_city>Harbin</rs_city>
<rs_country>Peoples R China</rs_country>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>The process to explore application integration for enterprise information system is called Enterprise Application Integration (EAI). Generally, EAI that based on the peer-to-peer has many limitations, such as poor extensibility, difficulty of management, and high-cost etc. These disadvantages can be overcome by Web services technology which helps to integrate large-scale, distributed enterprise applications together. This paper presents a framework of EAI which based on Web services, and gives discussions on its major functional modules.</p>
<p>In a peer-to-peer inferencesystem, each peer can reason locally but can also lso solicit licit some of its acquatances, which are peers sharing part of its vocabulary. In this paper, we consider peer-to-peer inference systems in which the local theory of each peer is a set et of propositional clauses defined upon a local vocabulary. An important characteristic of peer-to peer infererence systems is that the global theory (the union of all peer theories) is not known (as opposed to partition-based reasoning systems). The main contribution of this paper is to provide the first consequence finding algorithm in a peer-to-peer setting: DeCA. It is anytime and computes consequences gradually from the solicited peer to peers that are more and more distant. We exhibit a sufficient condition on the acquaintance graph of the peer-to-peer inference system for guaranteeing the completeness of this algorithm. Another important contribution is to apply this general distributed reasoning setting to the setting etting of the Semantic Web through the Somewhere semantic peer-to-peer data management system. The last contribution of this paper is to provide an experimental analysis of the scalability of the peer-to-peer infrastructure that we propose, on large networks of 1000 peers.</p>
<p>We describe a new prototype for a zoo information system. The system is based on RFID and allows to retrieve information about the zoo animals in a quick and easy way. RFID tags identifying the respective animals are placed near the animal habitats. Zoo visitors are equipped with PDAs containing RFID readers and WLAN cards. The PDAs may then read the RFID tag IDs and retrieve respective HTML-documents from a zoo Web server showing information about the animals at various levels of detail and languages. Additionally, the system contains a JXTA and XML based peer-to-peer subsystem, enabling zoos to share their content with other zoos in an easy way. This way, the effort for creating multimedia content can be reduced drastically.</p>
<p>Network architectures for collaborative virtual reality have traditionally been dominated by client-server and peer-to-peer approaches, with peer-to-peer strategies typically being favored where minimizing latency is a priority, and client-server where consistency is key. With increasingly sophisticated behavior models and the demand for better support for haptics, we argue that neither approach provides sufficient support for these scenarios and, thus, a hybrid architecture is required. We discuss the relative performance of different distribution strategies in the face of real network conditions and illustrate the problems they face. Finally, we present an architecture that successfully meets many of these challenges and demonstrate its use in a distributed virtual prototyping application which supports simultaneous collaboration for assembly, maintenance, and training applications utilizing haptics.</p>
<p>Previous research, primarily in North America, has found that individual factors (e.g., 'internalising problems') and social factors (e.g., friendship) interact to influence children's levels of peer victimisation. Some research has found that the identity of children's friends and friendship quality (as 'protective factors') are more important than the sheer number of friends. However, studies have produced conflicting findings. A peer nomination inventory was used to assess social skills problems, peer victimisation, peer acceptance, and several different aspects of friendship. Four hundred and forty-nine children aged 9 to 11 years completed the inventory at two time points over the course of an academic year. Social skills problems were found to predict an increase in peer victimisation over time. Two friendship variables were found to moderate this relationship: a) number of friends, and b) the peer acceptance of the very best-friend. The relationship was found to be weaker for those children with lots of friends and for those children with a 'popular' best-friend. The findings advance understanding of the factors that promote peer victimisation.</p>
<rs_address>Univ Bergamo, Dipartimento Gest & Informaz, Bergamo, Italy</rs_address>
<rs_organization>Univ Bergamo</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Dipartimento Gest & Informaz</rs_suborganization>
</rs_suborganizations>
<rs_city>Bergamo</rs_city>
<rs_country>Italy</rs_country>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Peer-to-peer (P2P) applications are rapidly gaining acceptance among users of Internet-based services, especially because of their capability of exchanging resources while preserving the anonymity of both requesters and providers. However, concerns have been raised about the possibility that malicious users can exploit the network to spread tampered-with resources (e.g., malicious programs and viruses). A considerable amount of research has thus focused on the development of trust and reputation models in P2P networks. In this article, we propose to use fuzzy techniques in the design of reputation systems based on collecting and aggregating peers' opinions. Fuzzy techniques are used in the evaluation and synthesis of all the opinions expressed by peers. The behavior of the proposed system is described by comparison with probabilistic approaches.</p>
<rs_address>Ohio State Univ, Dept Comp Sci & Engn, Columbus, OH 43210 USA</rs_address>
<rs_organization>Ohio State Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Dept Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Columbus</rs_city>
<rs_state>OH</rs_state>
<rs_country>USA</rs_country>
<rs_zips count="1">
<rs_zip location="AP">43210</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="2">
<p>The Organic Grid is a biologically inspired and fully decentralized approach to the organization of computation that is based on the autonomous scheduling of strongly mobile agents on a peer-to-peer network. Through the careful design of agent behavior, the emerging organization of the computation can be customized for different classes of applications. In this paper, we report on our experience in adapting the general framework to run two representative applications on our Organic Grid prototype: the National Center for Biotechnology Information (NCBI) basic local alignment search tool (BLAST) code for sequence alignment, and the Cannon's algorithm for matrix multiplication. The first is an example of independent task application, a type of application commonly used for grid scheduling research because of its easily decomposable nature and absence of intra-node communication. The second is a popular block algorithm for parallel matrix multiplication, and represents a challenging application for grid platforms because of its highly structured and synchronous communication pattern.</p>
<p>Agent behavior completely determines the way computation is organized on the Organic Grid. We intentionally chose two applications at opposite ends of the distributed computing spectrum having very different requirements in terms of communication topology, resource use, and response to faults. We detail the design of the agent behavior and show how the different requirements can be satisfied. By encapsulating application code and scheduling functionality into mobile agents, we decouple both computation and scheduling from the underlying grid infrastructure. In the resulting system, every node can inject a computation onto the grid; the computation naturally organizes itself around available resources.</p>
<rs_suborganization>Dept Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Shanghai</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">200240</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Routing efficiency is the critical issue when constructing peer-to-peer overlay. However, Chord has often been criticized on its careless of routing locality. A routing efficiency enhancement protocol on top of Chord is illustrated in this paper, which is called PChord. PChord aims to achieve better routing efficiency than Chord by exploiting proximity of the underlying network topology. The simulation shows that PChord has achieved lower RDP per message routing.</p>
<rp_address>Tsing Hua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China</rp_address>
<rp_organization>Tsing Hua Univ</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Dept Comp Sci & Technol</rp_suborganization>
</rp_suborganizations>
<rp_city>Beijing</rp_city>
<rp_country>Peoples R China</rp_country>
<rp_zips count="1">
<rp_zip location="AC">100084</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Tsing Hua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China</rs_address>
<rs_organization>Tsing Hua Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Dept Comp Sci & Technol</rs_suborganization>
</rs_suborganizations>
<rs_city>Beijing</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">100084</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Flash bulk files downloading in style of P2P through perpendicular pattern becomes more popular recently. Many peers download different pieces of shared files from the source in parallel. They try to reconstruct complete files by exchanging needed pieces with other downloading peers. The throughput of entire downloading community, as well as the perceived downloading rate of each peer, greatly depends on uploading bandwidth contributed by every individual peer. Unfortunately, without proper built-in incentive mechanism, peers inherently tend to relentlessly download while intentionally limiting their uploading bandwidth. In this paper, we propose a both effective and efficient incentive approach-Reciprocity, which is only based on end-to-end measurement and reaction: a peer caps uploading rate to each of its peers at the rate that is proportional to its downloading rate from that one. It requires no centralized control, or electronic monetary payment, or certification. Preliminary experiments' results reveal that this approach offers favorable performance for cooperative peers, while effectively punishing defective ones.</p>
<rs_suborganization>Fac Elect Engn & Comp Sci</rs_suborganization>
</rs_suborganizations>
<rs_city>Berlin</rs_city>
<rs_country>Germany</rs_country>
<rs_zips count="1">
<rs_zip location="BC">D-10587</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>The paper presents HiPeer, a robust resource distribution and discovery algorithm that can be used for fast and fault-tolerant location of resources in P2P network environments. HiPeer defines a concentric multi-ring overlay networking topology, whereon dynamic network management methods are deployed. In terms of performance, HiPeer delivers of number of lowest bounds. We demonstrate that for any De Bruijn digraph of degree* d >= 2 and diameter** D-DB HiPeer constructs a highly reliable network, where each node maintains a routing table with at most 2d+2 entries independent of the number N of nodes in the system. Further, we show that any existing resource in the network with at most d nodes can be found within at most D-HiPeer = log(d)(N(d - 1) + d) - 1 overlay hops. This result is as close to the Moore bound[1] as the query path length in other outstanding P2P proposals based on the De Bruijn digraphs. Thus, we argue that HiPeer defines a highly connected network with connectivity d and the lowest yet known lookup bound D-HiPeer. Moreover, we show that any node's "join or leave" operation in HiPeer implies a constant expected reorganization cost of the, magnitude order of O(d) control messages.</p>
<p>A fundamental problem in a pure Peer-to-Peer (P2P) file sharing system is how to protect the anonymity of peer nodes when providing efficient data access services. Most of existing work mainly focus on how to provide the initiator anonymity, but neglect the anonymity of the responder. In this paper, we propose a multicast-based protocol, called Mapper, for efficient file sharing with mutual anonymity. By seamlessly combining the technologies of multi-proxy and IP multicast together, the proposed protocol guarantees mutual anonymity during the entire session of file retrieval. Furthermore, Mapper replicates requested files inside the multicast group, so file distribution can be adjusted adaptively and the cost for multicast can be further reduced. Results of both simulations and theoretical analyses demonstrate that Mapper possesses the merits of scalability, reliability, and high adaptability.</p>
<p>Developing a massively multiplayer online game which utilizes physically based simulation to provide realistic behaviors requires numerical integration functions with inherently high computational costs. This simulation, performed on the individual clients of a peer-to-peer networked game or for a client/server online game, presents challenges due to many factors, including limited computing resources at the client level and network latency in the propagation of a client's state to other clients. Computationally intensive simulation may adversely affect performance and result in a situation in which little processing capacity is left for other aspects of the game. in this paper, we explore how a game developer who is aware of these issues might create a game for IBM's recently announced Cell Broadband Engine (TM) processor; we also present an example of the development of a game in which multiple human and robotic characters interact with static and dynamic objects in a virtual environment. Although our experience suggests that porting code to the Cell Broadband Engine core with minimal use of its synergistic processing elements (SPEs) should not be expected to produce significant performance gains at this time, the potential of the Cell SPEs to improve performance is considerable. We discuss performance and design and implementation decisions, with programmability issues being especially noted.</p>
<p>The disruptive advent of peer-to-peer (P2P) file sharing in 2000 attracted significant interest. P2P networks have matured from their initial form, unstructured overlays, to structured overlays like distributed hash tables (DHTs), which are considered state-of-the-art. There are huge efforts to improve their performance. Various P2P applications like distributed storage and application-layer multicast were proposed.</p>
<p>However, little effort was spent to understand the communication abstraction P2P overlays supply. Only when it is understood, the reach of P2P ideas will significantly broaden. Furthermore, this clarification reveals novel approaches and highlights future directions.</p>
<p>In this paper, we reconsider well-known P2P overlays, linking them to insights from distributed systems research. We conclude that the main communication abstraction is that of a virtual address space or application-specific naming. On this basis, P2P systems build a functional layer implementing, for example lookup, indirection and distributed processing. Our insights led us to identify interesting and unexplored points in the design space. Copyright (c) 2004 AEI.</p>
<p>Today, work collaboration is normal practice in developing modern products. Engineering collaborative work involves a number of team members that need to share and exchange design ideas while working with engineering analysis tools such as mechanical computer aided engineering systems. This work presents the M-Sync prototype system that uses an active database approach to enable exchange of engineering information among distributed team members in a timely manner. The distributed data is fully accessible by the local member and is automatically synchronised between different places using a database management system that support event-condition-action (ECA) database rules. Only updates introduced at one location are distributed to other locations, thereby minimizing information transfer and enhancing performance. Members working at different locations can therefore work in a peer-to-peer (P2P) manner and interactively manipulate the same set of information at the same time. (C) 2005 Civil-Comp Ltd and Elsevier Ltd. All rights reserved.</p>
<p>This paper proposes iMobile, a proxy-based platform for developing mobile services for various mobile devices and wireless access technologies. iMobile acts as a message gateway that allows mobile devices to relay messages to each other through various protocols on different access networks. It allows mobile devices to access internet services, corporate databases and to control various network devices. iMobile implements three key abstractions: dev-let, info-let and app-let. An info-let provides abstract view of information space. An app-let implements service or application logic by processing information from various info-lets. A dev-let receives and sends messages through any particular protocols for mobile devices. The let engine supports user and device profiles for personalization and transcoding, and invokes proper app-lets and info-lets to answer requests from a dev-let. The Mobile modular architecture allows developers to write device drivers, information access methods and application logic independently from each other. Copyright (c) 2005 John Wiley & Sons, Ltd.</p>
<rp_suborganization>Dept Sci & Technol Studies</rp_suborganization>
</rp_suborganizations>
<rp_street>Box 510</rp_street>
<rp_city>Gothenburg</rp_city>
<rp_country>Sweden</rp_country>
<rp_zips count="1">
<rp_zip location="BC">S-40530</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Calif State Univ, Hayward, CA USA</rs_address>
<rs_organization>Calif State Univ</rs_organization>
<rs_city>Hayward</rs_city>
<rs_state>CA</rs_state>
<rs_country>USA</rs_country>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>This paper studies the conversations and activities of an online support group for breast cancer Sufferers and survivors and their supporters. Using communications medium theory and social capital theory, it examines the mundane and profound exchanges, the poignant self-disclosures, the creative expressions of solidarity, and the minor but not-insignificant political actions of people-initially strangers-who come together as a 'virtuous circle,' not only to assist with medical issues but also to meet emotional and even material needs. Sponsored by the Canadian nonprofit organization Breast Cancer Action Nova Scotia (BCANS), this virtual community has logged over a half million messages since 1996. Not every BCANS participant is an activist-many are just trying to grapple with their disease but some find ways to shatter the professional "information monopoly," and to press for healthcare improvements. The study illustrates the scope, passion, and complexity of peer-to-peer medical communication in a virtual environment that promotes "thick trust". BCANS participants discuss with candor, warmth and even humor Such painful topics as death and dying and the crises in intimate relationships brought about by a terminal illness. The sharing of confidences and fears enables participants to pool their 'collective intelligence' about many things, from how to cope with swelling, to how to think about end-of-life issues, to how to improve social policy. (c) 2005 Elsevier Ltd. All rights reserved.</p>
<p>This paper proposes a stochastic fluid flow model to compute the transfer time distribution of resources in peer-to-peer file sharing applications. The amount of bytes transferred among peers is represented by a continuous quantity (the fluid level) whose flow rate is modulated by a set of discrete states representing the Concurrent. upload and download operations on the peers participating to the transfer. A transient solution of the model is then performed to compute the probability that a peer can download a given resource in less than t units of time as a function of several system parameters. In particular, the impact of file popularity, bandwidth characteristics, concurrent downloads and uploads, cooperation level among peers, and user behavior are included in our model specification.</p>
<p>We also provide numerical results timing at proving the potentialities of the approach we adopted as well as to investigate interesting issues related to the effect of incentive mechanisms on the user cooperation. (C) 2005 Elsevier B.V. All rights reserved.</p>
<p>In this paper we model and Study the performance of peer-to-peer (P2P) file sharing systems in terms of their service capacity'. We identify two regimes of interest: the transient and stationary regimes. We show that in both regimes, the performance of P2P systems exhibits a favorable scaling with the offered load. P2P systems achieve this by efficiently leveraging the service capacity of other peers, who possibly are concurrently downloading the same file. Therefore to improve the performance, it is important to design mechanisms to give peers incentives for sharing/cooperation. One approach is to introduce mechanisms for resource allocation that are 'fair', such that a peer's performance improves with his contributions. We find that some intuitive 'fairness' notions may unexpectedly lead to 'unfair' allocations, which do not provide the right incentives for peers. Thus, implementation of P2P systems may want to compromise the degree of 'fairness' in favor of maintaining system robustness and reducing overheads. (C) 2005 Elsevier B.V. All rights reserved.</p>
<p>There are many structured P2P systems that use DHT technologies to map data items onto the nodes in various ways for scalable routing and location. Most of the systems require 0(log it) hops per lookup request with 0(log it) neighbors per node, where n is the network size. In this paper, we present a constant-degree P2P architecture, namely Cycloid, which emulates a cube-connected cycles (CCC) graph in the routing of lookup requests. It achieves a time complexity of O(d) per lookup request by using O(l) neighbors per node, where n = d x 2(d). We compare Cycloid with other two constant-degree systems, Viceroy and Koorde in various architectural aspects via simulation. Simulation results show that Cycloid has more advantages for large scale and dynamic systems that have frequent node arrivals and departures. In particular, Cycloid delivers a higher location efficiency in the average case and exhibits a more balanced distribution of keys and query loads between the node.,,. (D (C) 2005 Elsevier B.V. All Rights Reserved.</p>
<p>Most P2P systems that provide a DHT abstraction distribute objects randomly among "peer nodes" in a way that results in some nodes having Theta(log N) times as many objects as the average node. Further imbalance may result due to nonuniform distribution of objects in the identifier space and a high degree of heterogeneity in object loads and node capacities. Additionally, a node's load may vary greatly over time since the system can experience continuous insertions and deletions of objects, skewed object arrival patterns, and continuous arrival and departure of nodes.</p>
<p>In this paper, we propose an algorithm for load balancing in such heterogeneous, dynamic P2P systems. Our simulation results show that in the face of rapid arrivals and departures of objects of widely varying load, our algorithm improves load balance by more than an order of magnitude for system utilizations as high as 80% while incurring an overhead of only about 6%. We also show that our distributed algorithm performs only negligibly worse than a similar centralized algorithm, and that node heterogeneity helps, not hurts, the scalability of our algorithm. Although many of these results are dependent on the workload, we believe the efficiency and performance improvement demonstrated over the case of no load balancing shows that our technique holds promise for deployed systems. (C) 2005 Elsevier B.V. All rights reserved.</p>
<p>We quantify the effectiveness of random walks for searching and construction of unstructured peer-to-peer (P2P) networks. We have identified two cases where the use of random walks for searching achieves better results than flooding: (a) when the overlay topology is clustered, and (b) when a client re-issues the same query while its horizon does not change much. Related to the Simulation of random walks is also the distributed computation of aggregates, such as averaging. For construction, we argue that an expander can be maintained dynamically with constant operations per addition. The key technical ingredient Of Our approach is a deep result of stochastic processes indicating that samples taken from consecutive steps of a random walk on an expander graph can achieve statistical properties similar to independent sampling. This property has been previously used in complexity theory for construction of pseudorandom number generators. We reveal another facet of this theory and translate savings in random bits to savings in processing overhead. (C) 2005 Elsevier B.V. All rights reserved.</p>
<rp_address>Rutgers State Univ, Dept Elect & Comp Engn, 628 CORE,94 Brett Rd, Piscataway, NJ 08854 USA</rp_address>
<rp_organization>Rutgers State Univ</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Dept Elect & Comp Engn</rp_suborganization>
</rp_suborganizations>
<rp_street>628 CORE,94 Brett Rd</rp_street>
<rp_city>Piscataway</rp_city>
<rp_state>NJ</rp_state>
<rp_country>USA</rp_country>
<rp_zips count="1">
<rp_zip location="AP">08854</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Rutgers State Univ, Dept Elect & Comp Engn, Piscataway, NJ 08854 USA</rs_address>
<rs_organization>Rutgers State Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Dept Elect & Comp Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Piscataway</rs_city>
<rs_state>NJ</rs_state>
<rs_country>USA</rs_country>
<rs_zips count="1">
<rs_zip location="AP">08854</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Distributed denial of service (DDoS) attacks on the Internet have become an immediate problem. As DDoS streams do not have common characteristics, currently available intrusion detection systems (IDS) cannot detect them accurately. As a result, defend DDoS attacks based on current available IDS will dramatically affect legitimate traffic. In this paper, we propose a distributed approach to defend against distributed denial of service attacks by coordinating across the Internet. Unlike traditional IDS, we detect and stop DDoS attacks within the intermediate network. In the proposed approach, DDoS defence systems are deployed in the network to detect DDoS attacks independently. A gossip based communication mechanism is used to exchange information about network attacks between these independent detection nodes to aggregate information about the overall network attacks observed. Using the aggregated information, the individual defence nodes have approximate information about global network attacks and can stop them more effectively and accurately. To provide reliable, rapid and widespread dissemination of attack information, the system is built as a peer to peer overlay network on top of the internet.</p>
<p>Motivated by the needs and success of projects such as SETI@home and genome@home, we propose an architecture for a sustainable large-scale peer-to-peer environment for distributed cycle sharing among Internet hosts. Such networks are characterized by highly dynamic state due to high arrival and departure rates. This makes it difficult to build and maintain structured networks and to use state-based resource allocation techniques. We build our system to work in an environment similar to Current file-sharing networks such as Gnutella and Freenet. In doing so, we are able to leverage vast network resources while providing resilience to random failures, low network overhead, and an open architecture for resource brokering. This paper describes the underlying analytical and algorithmic substrates based on randomization for job distribution, replication, monitoring, aggregation and oblivious resource sharing and communication between participating hosts. We support our claims of robustness and scalability analytically with high probabilistic guarantees. Our algorithms do not introduce any state dependencies, and hence Lire resilient to dynamic node arrivals, departures, and failures. We Support all analytical claims with a detailed simulation-based evaluation of our distributed framework. (c) 2005 Elsevier B.V. All rights reserved.</p>
<p>Peer-to-Peer (P2P) systems are known to provide excellent scalability in a networked environment. One peer is introduced to the system by each participant. However current P2P applications can only provide file sharing and other forms of relatively simple data communications, and, in this paper, we demonstrate how this limitation can be bridged by indexing and querying a 3D virtual-world on a dynamic distributed network. We present an algorithm for 3D range queries as well as an algorithm for nearest neighbor queries. We also show how to build such a complex application from the ground level of a P2P routing algorithm.</p>
<p>Monitoring a distributed system to detect a stable property is an important problem with many applications. The problem is especially challenging for a dynamic distributed system because the set of processes in the system may change with time. In this paper, we present an efficient algorithm to determine whether a stable property has become true in a system in which processes can join and depart the system at any time. Our algorithm is based on maintaining a spanning tree of processes that are currently part of the system. The spanning tree, which is dynamically changing, is used to periodically collect local states of processes such that: (1) all local states in the collection axe consistent with each other, and (2) the collection is complete, that is, it contains all local states that are necessary to evaluate the property and derive meaningful inferences about the system state.</p>
<p>Unlike existing algorithms for stable property detection in a dynamic environment, our algorithm is general in the sense that it can be used to evaluate any stable property. Further, it does not assume the existence of any permanent process. Processes can join and leave the system while the snapshot algorithm is in progress.</p>
<p>In this paper, we discuss the use of ontologies for data integration. We consider two different settings depending on the system architecture: central and peer-to-peer data integration. Within those settings, we discuss five different cases studies that illustrate the use of ontologies in metadata representation, in global conceptualization, in high-level querying, in declarative mediation, and in mapping support. Each case study is described in detail and accompanied by examples.</p>
<p>In a real-time database system, the conventional method of transaction method can not be used. In these methods, the deadlock detection is based on (a) use of delay to cause and watch deadlocks, (b) high overheads of periodic checking (c) Non-deterministic nature of the delays, and lastly, (d) difficulties to scale up the existing solutions (centralized). The proposal is based on enhanced local processing and peer-to-peer (P2P) communication for distributed transaction process. The earlier procedures incorporate additional steps for handling wait-for states and deadlocks. This activity is carried out by methods based on wait-for-graphs or probes. These methods introduce a centralized computation at source (for each occurrence of a delay). The proposal introduces asynchronous operations in transaction processing. As a result the detection processes do not wait for occurrences of delays (time-out). These start the delay elimination process instantaneously. The technique incurs low overheads and eliminates the possibility of occurrence of waiting.</p>
<rs_suborganization>Dept Comp Sci & Informat Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Jhongli</rs_city>
<rs_country>Taiwan</rs_country>
<rs_zips count="1">
<rs_zip location="AC">320</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>A ubiquitous learning environment provides an interoperable, pervasive, and seamless learning architecture to connect, integrate, and share three major dimensions of learning resources: learning collaborators, learning contents, and learning services. Ubiquitous learning is characterized by providing intuitive ways for identifying right learning collaborators, right learning contents and right learning services in the right place at the right time. Our context aware ubiquitous learning environment consists of three systems, namely peer-to-peer content access and adaptation system, personalized annotation management system, and multimedia real-time group discussion system. Since the effectiveness and efficiency of ubiquitous learning heavily relies on learners' surrounding context, in this paper, we will address a context model and context acquisition mechanism for collecting contextual information at run time. We have built a context aware ubiquitous learning environment and in this paper we will address how this newly designed environment can fully support the needs of peer-to-peer collaborative learning.</p>
<rs_suborganization>Sch Elect & Informat Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Xian</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">710049</rs_zip>
</rs_zips>
</research>
<research>
<rs_address>Lanzhou Univ, Sch Informat Sci & Engn, Lanzhou, Peoples R China</rs_address>
<rs_organization>Lanzhou Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Sch Informat Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Lanzhou</rs_city>
<rs_country>Peoples R China</rs_country>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>The issues of trust are especially of great importance in peer-to-peer electronic online communities [5]. One way to address these issues is to use community-based reputations to help estimate the trustworthiness of peers. This paper presents a reputation-based trust supporting framework which includes a mathematical trust model, a decentralized trust data dissemination scheme and a distributed implementation algorithm of the model over a structured P2P network. In our approach, each peer is assigned a unique trust value, computed by aggregating the similarity-filtered recommendations of the peers who have interacted with it. The similarity between peers is computed by a novel simplified method. We also elaborate on decentralized trust data management scheme ignored in existing solutions for reputation systems. Finally, simulation-based experiments show that the system based on our algorithm is robust even against attacks from groups of malicious peers deliberately cooperating to subvert it.</p>
<p>The World Wide Web can be viewed as a gigantic distributed database including millions of interconnected hosts some of which publish information via web servers or peer-to-peer systems. We present here a novel method for the extraction of semantically rich information from the web in a fully automated fashion. We illustrate our approach via a proof-of-concept application which scrutinizes millions of web pages looking for clues as to the trend of the Chinese stock market. We present the outcomes of a 210-day long study which indicates a strong correlation between the information retrieved by our prototype and the actual market behavior.</p>
<p>The advent of XML as a universal exchange format and of Web services as a basis for distributed computing, has fostered the emergence of a new class of documents that we call Active XML documents (AXML in short). These are XML documents where some of the data is given explicitly while other parts are given only intentionally by means of embedded calls to web services, that can be called to generate the required information. We argue that AXML provides powerful means for the modeling and integration of distributed dynamic Web data. AXML can capture various integration scenarios including peer-to-peer data mediation and warehousing, while providing support for new features of Web services such as subscription, service directories, and controlling data changes. Moreover, by allowing service call parameters and responses to contain calls to other services, AXML enables distributed computation over the web. We overview here the AXML project, considering the new possibilities that Active XML brings to Web data management and the fundamental challenges it raises.</p>
<p>A dynamic hybrid DVE architecture is presented in this paper. It's an extension of client-server architecture. It combines the advantages of client-server architecture and peer-to-peer architecture. By utilizing users' hardware resources system can support more users. Compaired with the traditional multi-server architecture it holds lower system cost. Theory analysis and simulation results prove its correctness and validity. The flaws of this architecture are also checked and the settlement is discussed.</p>
<rp_address>NE Univ, Natl Engn Res Ctr Comp Software, Shenyang 110004, Peoples R China</rp_address>
<rp_organization>NE Univ</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Natl Engn Res Ctr Comp Software</rp_suborganization>
</rp_suborganizations>
<rp_city>Shenyang</rp_city>
<rp_country>Peoples R China</rp_country>
<rp_zips count="1">
<rp_zip location="AC">110004</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>NE Univ, Natl Engn Res Ctr Comp Software, Shenyang 110004, Peoples R China</rs_address>
<rs_organization>NE Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Natl Engn Res Ctr Comp Software</rs_suborganization>
</rs_suborganizations>
<rs_city>Shenyang</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">110004</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>This paper addresses the efficient top-k queries in pure peer-to-peer (P2P) networks. Top-k receives much attention in the search engine and gains Or great success. However, processing top-k query in pure P2P network is very challenging due to unique characteristics of P2P environments, for example, skewed collection statistics, and higher communication costs. Inspired by the success of ranking algorithms in Web search engine, we propose a decentralized algorithm to answer top-k queries in pure peer-to-peer networks which makes use of local rankings, rank merging, and minimizes both answer set size and network traffic among peers.</p>
<p>This paper presents a peer-to-peer based execution model to improve the availability and reliability of Geospatial Web Services (GWS) composition. A service community concept and a QoS model of GWS are proposed to discover the best quality GWS engines in the peer-to-peer network. The engines coordinate other participants in charge of initiating, controlling, monitoring the associated GWS execution, and adopt an alternative approach for failure recovery. The paper also presents the implementation of a peer-to-peer GWS composition system prototype based on JXTA platform.</p>
<rp_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China</rp_address>
<rp_organization>Huazhong Univ Sci & Technol</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Cluster & Grid Comp Lab</rp_suborganization>
</rp_suborganizations>
<rp_city>Wuhan</rp_city>
<rp_country>Peoples R China</rp_country>
<rp_zips count="1">
<rp_zip location="AC">430074</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China</rs_address>
<rs_organization>Huazhong Univ Sci & Technol</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Cluster & Grid Comp Lab</rs_suborganization>
</rs_suborganizations>
<rs_city>Wuhan</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">430074</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Service discovery is a key step during Peer-to-Peer (P2P) converging with Web Service. In this paper, a semantic-P2P based approach is presented for web service discovery. To enable the semantic web service, service profile is used to describe web service and as the service data source. The service-expertise based model is proposed for service node selection.</p>
<rs_address>Florida Int Univ, High Performance Database Res Ctr, Miami, FL 33199 USA</rs_address>
<rs_organization>Florida Int Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>High Performance Database Res Ctr</rs_suborganization>
</rs_suborganizations>
<rs_city>Miami</rs_city>
<rs_state>FL</rs_state>
<rs_country>USA</rs_country>
<rs_zips count="1">
<rs_zip location="AP">33199</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>In this paper we examine the benefit of reports about resources in mobile ad-hoc networks. Each disseminated report represents information about a spatio-temporal event, such as the availability of a parking slot or a cab request. Reports are disseminated by a peer-to-peer broadcast paradigm, in which an object periodically broadcasts the reports it carries to encountered objects. We evaluate the value of resource information in terms of how much time is saved when using the information to discover resources, compared to the case when the information is not used.</p>
<p>Many emerging group oriented and collaborative applications such as audio/video conferences use the peer-to-peer (P2P) paradigm. Confidentiality is an often demanded feature for such applications, e.g. in business meetings, to provide group privacy. How to build a secure P2P video conference system is still an open issue. In this paper several possible solutions are discussed. We present a security architecture used for P2P video conferences that ensures confidential talks in an enterprise environment whose branches might be geographically dispersed.</p>
<rp_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China</rp_address>
<rp_organization>Huazhong Univ Sci & Technol</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Cluster & Grid Comp Lab</rp_suborganization>
</rp_suborganizations>
<rp_city>Wuhan</rp_city>
<rp_country>Peoples R China</rp_country>
<rp_zips count="1">
<rp_zip location="AC">430074</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Wuhan 430074, Peoples R China</rs_address>
<rs_organization>Huazhong Univ Sci & Technol</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Cluster & Grid Comp Lab</rs_suborganization>
</rs_suborganizations>
<rs_city>Wuhan</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">430074</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Peer-to-Peer (P2P) architectures are very prevalent in today's Internet. Lots of P2P file sharing systems using Gnutella protocol emerge out and draw attractions of millions of people. The "flooding" search mechanism of Gnutella makes it easy to be deployed, but also spawns numerous messages which leads to serious scalability problems. However, the locality discovered in both user's share files and queries, enables us to use query-caching to shorten the search length and reduce the messages traffic. This paper makes an extensive study of query-caching in P2P systems and proposes an adaptive query-caching mechanism to manage the cached query reply messages according to the heterogeneity of the uptime of different peers. Along with several other techniques we proposed, our approach achieves a 30% reduction of average search length and a 61% reduction of query message traffic comparing with the previous query-caching mechanisms in the simulation, which indicates that our approach makes Gnutella more scalable.</p>
<rp_address>Univ Hong Kong, Dept Elect & Elect Engn, Pokfulam Rd, Hong Kong, Hong Kong, Peoples R China</rp_address>
<rp_organization>Univ Hong Kong</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Dept Elect & Elect Engn</rp_suborganization>
</rp_suborganizations>
<rp_street>Pokfulam Rd</rp_street>
<rp_city>Hong Kong</rp_city>
<rp_state>Hong Kong</rp_state>
<rp_country>Peoples R China</rp_country>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Univ Hong Kong, Dept Elect & Elect Engn, Hong Kong, Hong Kong, Peoples R China</rs_address>
<rs_organization>Univ Hong Kong</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Dept Elect & Elect Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Hong Kong</rs_city>
<rs_state>Hong Kong</rs_state>
<rs_country>Peoples R China</rs_country>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Thanks to the highly popular dual channel capabilities (e.g., GSM plus Bluetooth) in modern handheld personal communication devices, an integrated cellular and ad hoc peer-to-peer network (i.e., a quasi-ad hoc wireless network) has already been widely reckoned as a readily practicable and attractive mobile computing environment. In this paper, we propose a co-operative relaying scheme, called ceRelay, for such a quasi-ad hoc network, to extend the life-time of low energy level users significantly. More importantly, the energy efficiency of the whole network is also remarkably increased.</p>
<p>Distributed hash tables (DHTs), used in a number of structured peer-to-peer (P2P) systems, provide efficient mechanisms for resource placement and location. A key distinguishing feature of current DHT systems, such as Chord, Pastry, CAN and Tapestry, is the way they handle locality in the underlying network. Topology-based node identifier assignment, proximity routing, and proximity neighbor selection are examples of heuristics used to minimize message delays in the underlying network. While these heuristics are sometimes effective, they all rely on a single global overlay that may install the key of a popular object at a node far from most of the nodes accessing it. Furthermore, a response to a lookup message does not contain any locality information about the nodes holding a copy of the object. We address these issues in Plethora, a novel two-level overlay P2P network. A local overlay in Plethora acts as a locality-aware cache for the global overlay, grouping nodes close together in the underlying network. Local overlays are constructed by exploiting the organization of the Internet into autonomous systems (ASs). We present a detailed experimental study that demonstrates performance gains in response time of up to 60% compared to a single global Pastry overlay. We also present efficient distributed algorithms for maintaining local overlays in the presence of node arrivals and departures. (c) 2005 Elsevier Inc. All rights reserved.</p>
<p>As more and more P2P applications being popular in Internet, one of important problem to be solved is inspiring users to cooperate each other actively and honestly, the reputation mechanism which is a hot spot for P2P research has been proposed to conquer it. Because of the characters of virtuality and anonymous in the network, it is very easy for users with bad reputations to reenter the system with new identities to regain new reputations in the reputation systems. In order to get rid of the impact of whitewashers and improve the system performance and efficiency, we propose a new probability-based adaptive initial reputation mechanism. In this new mechanism, newcomers will be trusted based on system's trust-probability which can be adjusted according to the actions of the newcomers. To avoid the system fluctuating for actions of a few whitewashers, we realize the new reputation mechanism in system with group-based architecture, which can localize the impact of whitewashers in their own groups. Both performance analysis and simulation show that this new adaptive reputation mechanism is more effective.</p>
<rs_address>Michigan State Univ, Dept Comp Sci & Engn, E Lansing, MI 48824 USA</rs_address>
<rs_organization>Michigan State Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Dept Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>E Lansing</rs_city>
<rs_state>MI</rs_state>
<rs_country>USA</rs_country>
<rs_zips count="1">
<rs_zip location="AP">48824</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>We study the phenomenon of free-riding in peer-to-peer (P2P) systems via an abstract model of a public good provision game with incomplete information. Each user in the model has an intrinsic contribution cost and decides whether to contribute or free-ride based on the expected benefit derived from the system. We first consider the impact of positive network externalities-common in P2P settings-on the equilibrium level of free riding and show that such network effects reduce free riding slightly but are insufficient to prevent it. We then consider the use of an incentive mechanism based on the detection and punishment of selfish peers, explicitly modelling key design tradeoffs inherent in any realistic detection mechanism. We show that detection and punishment can reduce free riding, but that the risk of falsely accusing cooperative peers can diminish their effectiveness. Finally, we consider what level of detection would maximize the social welfare of the network. We find that a surprisingly low level of detection can be optimal and that the residual level of free riding at optimum depends critically on the overhead of detecting selfishness and the probability of falsely identifying cooperative peers.</p>
<rs_suborganization>Dept Elect & Comp Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Pittsburgh</rs_city>
<rs_state>PA</rs_state>
<rs_country>USA</rs_country>
<rs_zips count="1">
<rs_zip location="AP">15213</rs_zip>
</rs_zips>
</research>
<research>
<rs_address>Harvard Univ, Cambridge, MA 02138 USA</rs_address>
<rs_organization>Harvard Univ</rs_organization>
<rs_city>Cambridge</rs_city>
<rs_state>MA</rs_state>
<rs_country>USA</rs_country>
<rs_zips count="1">
<rs_zip location="AP">02138</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>The LOCKSS (Lots Of Copies Keep Stuff Safe) system allows users to store and preserve electronic content through a system of inexpensive computers arranged in an ad hoc peer-to-peer network. These peers cooperate to detect and repair damage by voting in "opinion polls." We develop a more accurate view of how the network will perform over time by simulating the system's behavior using dynamic models in which peers can be subverted and repaired. These models take into account a variety of parameters, including the rate of peer subversion, the rate of repair, the extent of subversion, and the responsiveness of each peer's system administrator. These models reveal certain systemic vulnerabilities not apparent in our static simulations: A typical adversary that begins with a small foothold within the system (e.g., 20 percent of the population) will completely dominate the voting process within 10 years, even if he only exploits one vulnerability each year. In light of these results, we propose and evaluate countermeasures. One technique, Ripple Healing, performs remarkably well. For models in which all system administrators are equally likely to repair their systems, it eliminates nearly systemic levels of corruption within days. For models in which some administrators are more likely to repair their systems, Ripple Healing limits corruption, but proves less effective, since these models already demonstrate superior performance.</p>
<p>In this paper we propose a mobile-agent-based web service composition (MAWSC) model for the dynamic web service composition (WSC). As compared with the traditional WSC models, our model avoids bottleneck of data transfer by peer-to-peer approach. As it achieves the composition without a centralized control, there is no center needed and every WSC portal can offer services for a large quantity of clients. In MAWSC model, WSC client inputs the specification and the initial parameters through WSC portal; then, system creates mobile agents to achieve the task and return the final results back to the client. In this paper, we define "planning" to specify the logic actions of mobile agent so as to execute the WSC automatically. And we also give the process mapping rules to convert the specification of WSC to the planning, and the behavior matching algorithms to map the planning to the physical behaviors of agents.</p>
<p>The resource management system is one of the essential components of Grids. A resource management system may be made up of one or many resource management nodes. The organization manner of the resource management nodes, i.e. the topology of a resource management system, is a key factor that should be considered carefully during the architecture design of resource management systems with respect to some specified requirements (e.g., performance, survivability). In this paper, a new survivability definition is proposed and the survivability of three typical Grid resource management system topologies (centralized, hierarchical, and peer-to-peer) is analyzed.</p>
<p>The structured peer-to-peer system, which is based on the distributed hash table, offers an administration-free and fault-tolerant application-level overlay network. However, a randomly structured overlay can not reflect the heterogeneity of a peer-to-peer system. In this paper, we propose a two-phase approach to exploit the heterogeneity in structured peer-to-peer systems. First, by exploiting the effects of both connections and nodes, we adjust the structure of overlay to reduce the lookup latency. And then a novel load balancing scheme based on lottery scheduling is proposed to balance not only the load but also the movement cost of the load. Our simulation results show that the performance, including query quality from the users' view and load balance from the system's view, can be greatly improved in a heterogeneous environment.</p>
<p>In a peer to peer grid computing environment, volunteers have heterogeneous properties and dynamically join and leave during execution. Therefore, it is essential to adapt to an unstable and widely distributed environment. However, existing scheduling and result certification mechanisms do not adapt to such a dynamic environment. As a result, they undergo high overhead, performance degradation, and scalability problems.</p>
<p>To solve the problems, we propose a new scheduling mechanism for result certification. The proposed mechanism applies different scheduling and result certification algorithms to different volunteer groups that are classified on the basis of their properties such as volunteering service time, availability, and credibility. It also exploits mobile agents in a distributed way in order to adapt to a dynamic peer to peer grid computing environment.</p>
<p>In this paper, we present a media streaming service architecture over peer-to-peer network for large scale media streaming service. The proposed architecture is hybrid in that it combines both pure peer-to-peer streaming model and centralized server model in order to take advantages of them. We first describe overall streaming operation based on the hybrid architecture. Then, we deal with streaming load allocation problem under the proposed scheme. Extensive performance study based on simulation is carried out. The results show that the performance of the proposed system is much better than that of existing streaming system in numerous streaming performance metrics.</p>
<rs_suborganization>Coll Comp & Software</rs_suborganization>
</rs_suborganizations>
<rs_city>Hangzhou</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">310018</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Event-based, Publish/Subscribe, systems are receiving increasingly greater attention as a prevalent approach to decouple various large-scale distributed applications such as Internet wide systems. However, their efficiency is closely tied to the architecture of the underlying notification service, which conveys the event notifications from publishers to subscribers. Peer-to-Peer network topology can offer inherently bounded delivery depth, load sharing and self-organization. In this paper, we present a content-based notification service system over peer-to-peer network topology, and couple it with an efficient filter model and routing algorithms. We also study the performance of our approaches, comparing them with corresponding works. The result shows that our approaches greatly reduce network bandwidth for subscription or filter update propagation, and storage requirement for keeping filter routing information.</p>
<p>In peer-to-peer (P2P) overlay networks, the mechanism of a peer randomly joining and leaving a network, causes a topology mismatch between the overlay and the underlying physical topology. This causes a large volume of redundant traffic in the underlying physical network as well as an extra delay in message delivery in the overlay network. Topology mismatch occurs because overlay networks are not aware of their underlying physical networks. In this paper we present a mathematical model for topology awareness of overlay networks (degree of matching between an overlay and its underlying physical network) and the efficiency of message delivery on them. We also after determining the computational complexity of the model, propose an optimization heuristic algorithm to increase topology awareness of P2P overlay networks. Then we present the results of running the algorithm on different kinds of random graphs and show, how we can implement the algorithm over P2P networks.</p>
<rs_suborganization>Dept Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Shanghai</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">200030</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Peer-to-peer systems are distinguished from traditional distributed systems in that nodes join and leave the p2p system at high rates, called churn problem. SChord, a p2p system, is illustrated in this paper, which is constructed on Chord system and aims to handle churn. We analyze the past experimental studies on churn of p2p systems and do some theoretical analysis on the probability distribution of node session time. SChord is based on such analysis which can distinguish nodes of long session time from other p2p nodes and exploit these long session nodes with its special routing algorithm. The simulation shows that SChord has achieved better performance of churn handling than Chord.</p>
<p>The resource discovery algorithms in Peer-to-Peer networks are based on the assumption that reliable resources are provided by each peer. The feather that significantly contributes to the success of many P2P applications is dynamic, anonymity and self-organization. However, they also bring about some malicious nodes to provide untrustworthy and pseudo services. To address this problem, this paper introduces a robust and flexible reputation mechanism in unstructured P2P and presents the heuristic resource discovery algorithm based on reputation-aware to ensure that resource requester can obtain reliable resources and services. This new resource discovery algorithm can effectively suppress the deceptive and fake services of P2P network, improve the reliability and security and decrease network load.</p>
<rp_address>Univ Elect Sci & Technol China, Coll Comp Sci & Engn, Chengdu 610054, Peoples R China</rp_address>
<rp_organization>Univ Elect Sci & Technol China</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Coll Comp Sci & Engn</rp_suborganization>
</rp_suborganizations>
<rp_city>Chengdu</rp_city>
<rp_country>Peoples R China</rp_country>
<rp_zips count="1">
<rp_zip location="AC">610054</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Univ Elect Sci & Technol China, Coll Comp Sci & Engn, Chengdu 610054, Peoples R China</rs_address>
<rs_organization>Univ Elect Sci & Technol China</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Coll Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Chengdu</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">610054</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>In P2P systems, every user can release files freely, which makes the large-scale file-sharing feasible. However, with malicious nodes increasing, lots of faked files and deceptive behaviors restrict the development of P2P application. Current P2P trust models can't guarantee the Quality of Service(QoS), and take no consideration for trust decay and cooperative cheat. To address these problems, this paper presents a novel behavior-based P2P trust model. The direct trust and reputation trust are considered, and the time decay function and reputation adjustment factor are provided in the model. Results of simulations show that compared to the current trust models, the proposed model is more efficient and scalable.</p>
<rs_suborganization>Dept Comp Sci & Technol</rs_suborganization>
</rs_suborganizations>
<rs_city>Shanghai</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">200030</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Peer-to-peer networks can be divided into structured and unstructured based on their overlay topologies. In reality, unstructured p2p networks with superpeers have proved their capacities to support millions of users simultaneously. However, applications deployed on this kind of overlay networks, such as file-sharing, require flooding or gossip-based message routing, which puts more overhead on underlying networks and provides no guarantee on resource discovery. In this paper we propose an overlay adaptation protocol which allows structured superpeer overlay construction from unstructured p2p overlay networks with the potential to leverage the advantages of structured p2p overlay networks such as efficiency, scalability and guaranteed look-up services. The simulation result shows that our protocol can build the structured superpeer overlay with efficiency and scalability.</p>
<p>Ad hoc network is a peer-to-peer grid system. The combination of the Knowledge Grid and ad hoc network could have a great effect on the future interconnection environment. In the existed researches about ad hoc routing protocols, knowledge with trusted requirements is not supported. In this paper, the trust level is used as knowledge for routing. The security rather than shortest path is the primary concern of the method. The performance evaluation via simulations shows that the method is a promising trust routing algorithm for MANETs. The effects of this trust model on DSR route discovery mechanism are analyzed. Results show that our model can improve the performance of DSR route discovery.</p>
<p>Building a topology-aware peer-to-peer overlay network can bring many advantages, such as providing locality-aware connectivity and reducing routing path length. While its benefits on performance have been recognized, an uneven overlay zone distribution has emerged. Recent work has shown that topology-aware neighbor selection during construction can aggravate the unbalance of zone distribution while it reduces routing path length. The imbalance in zone sizes may lead to performance decrease and an unfair load distribution.</p>
<p>In this paper, we present an even topology-aware peer-to-peer network based on De Bruijn Graph by developing a dynamic zone-balancing approach.</p>
<rs_suborganization>Dept Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Shanghai</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">200030</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>In this paper, we design a new routing algorithm using SkipNet and Small-World for peer-to-peer system. The algorithm divides the routing space into two layers, SkipNet layer and Small-World layer. In the SkipNet layer, the routing method using numeric ID is discussed. In the Small-World layer, the routing method using small-world theoretical results is discussed. We also consider the dynamic circumstance-the node's join and departure. The comparison of our algorithm with other algorithms is presented. Our algorithm supports content and path locality, it is very important for security consideration. In our algorithm, a few shortcuts to distant peers are inserted with some probabilities and the average path length is reduced. The preliminary simulation results show that our algorithm is efficient.</p>
<rs_suborganization>Dept Comp Sci & Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Shanghai</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">200030</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Gnutella-like peer-to-peer networks exhibit strong small-world properties and power-law node degree distributions. However, the existing flooding-based query algorithms used in such overlay networks, knowing very little about these inherent natures, scale poorly with inefficient search and heavy traffic load, which is always a challenging problem to solve. In this paper, we eye our viewpoints upon the role of overlay topology in the search performance and propose a novel solution towards scalable and efficient peer-to-peer distributed file sharing, by making better use of such emergent topological properties of these networks. We first, by examining what inspirations can be taken from these properties, provide several helpful guidelines as the design rationale of our solution, and we then propose a new technique for constructing Desirable Topologies and a novel Smart Search algorithm operating on them, as two key components of our solution. To justify the performance gains of our techniques, we also conduct extensive experiments under realistic network conditions and make an all-around comparison with currently well-known systems.</p>
<p>Challenges revealed in constructing a peer-to-peer (P2P) file system are due to the difficulties of version control. There have appeared no P2P systems, which can solve these problems smoothly. In this paper we show our efforts towards solving the problems by developing a new application, SVCL (a Scalable Version Control Layer in P2P file system), in which version control servers are woven into a peer-to-peer network so that the system will not crash under single node failure. As a result, users can carry out both file updating and reading operations. Experiments have demonstrated the high performance of the proposed system.</p>
<rs_suborganization>Dept Elect & Comp Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Roorkee</rs_city>
<rs_state>Uttar Pradesh</rs_state>
<rs_country>India</rs_country>
<rs_zips count="1">
<rs_zip location="AC">247667</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Peer-to-peer systems and applications are distributed systems without any centralized control. P2P systems form the basis of several applications, such as file sharing systems and event notification services. P2P systems based on Distributed Hash Table (DHT) such as CAN, Chord, Pastry and Tapestry, use uniform hash functions to ensure load balance in the participant nodes. But their evenly distributed behaviour in the virtual space destroys the locality between participant nodes. The topology-based hierarchical overlay networks like Grapes and Jelly, exploit the physical distance information among the nodes to construct a two-layered hierarchy. This highly improves the locality property, but disturbs the concept of decentralization as the leaders in the top layer get accessed very frequently, becoming a performance bottleneck and resulting in a single point of failure. In this paper, we propose an enhanced m-way search tree (EMST) based P2P overlay infrastructure, called Oasis. It is shown through simulation that Oasis can achieve both the decentralization and locality properties along with high fault tolerance and a logarithmic data lookup time.</p>
<rp_address>Univ Roma La Sapienza, DIS, Via Salaria 113, Rome, Italy</rp_address>
<rp_organization>Univ Roma La Sapienza</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>DIS</rp_suborganization>
</rp_suborganizations>
<rp_street>Via Salaria 113</rp_street>
<rp_city>Rome</rp_city>
<rp_country>Italy</rp_country>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Univ Roma La Sapienza, DIS, Rome, Italy</rs_address>
<rs_organization>Univ Roma La Sapienza</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>DIS</rs_suborganization>
</rs_suborganizations>
<rs_city>Rome</rs_city>
<rs_country>Italy</rs_country>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Partitioning is one of the main problems in p2p group membership. This problem rises when failures and dynamics of peer participation, or chum, occur in the overlay topology created by a group membership protocol connecting the group of peers. Solutions based on Gossip-based Group Membership (GGM) cope well with the failures while suffer from network dynamics. This paper shows a performance evaluation of SCAMP, one of the most interesting GGM protocol. The analysis points out that the probability of partitioning of the overlay topology created by SCAMP increases with the chum rate. We also compare SCAMP with DET - another membership protocol that deterministically avoids partitions of the overlay. The comparison points out an interesting trade-off between (i) reliability, in terms of guaranteeing overlay connectivity at any chum rate, and (ii) scalability in terms of creating scalable overlay topologies where latencies experienced by a peer during join and leave operations do not increase linearly with the number of peers in the group.</p>
<rp_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Sch Comp Sci & Technol, Wuhan 430074, Peoples R China</rp_address>
<rp_organization>Huazhong Univ Sci & Technol</rp_organization>
<rp_suborganizations count="2">
<rp_suborganization>Cluster & Grid Comp Lab</rp_suborganization>
<rp_suborganization>Sch Comp Sci & Technol</rp_suborganization>
</rp_suborganizations>
<rp_city>Wuhan</rp_city>
<rp_country>Peoples R China</rp_country>
<rp_zips count="1">
<rp_zip location="AC">430074</rp_zip>
</rp_zips>
</reprint>
<research_addrs count="2">
<research>
<rs_address>Huazhong Univ Sci & Technol, Cluster & Grid Comp Lab, Sch Comp Sci & Technol, Wuhan 430074, Peoples R China</rs_address>
<rs_organization>Huazhong Univ Sci & Technol</rs_organization>
<rs_suborganizations count="2">
<rs_suborganization>Cluster & Grid Comp Lab</rs_suborganization>
<rs_suborganization>Sch Comp Sci & Technol</rs_suborganization>
</rs_suborganizations>
<rs_city>Wuhan</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">430074</rs_zip>
</rs_zips>
</research>
<research>
<rs_address>Hubei Univ, Sch Math & Comp Sci, Wuhan 430062, Peoples R China</rs_address>
<rs_organization>Hubei Univ</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Sch Math & Comp Sci</rs_suborganization>
</rs_suborganizations>
<rs_city>Wuhan</rs_city>
<rs_country>Peoples R China</rs_country>
<rs_zips count="1">
<rs_zip location="AC">430062</rs_zip>
</rs_zips>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Peer-to-peer (P2P) overlay networks, such as CAN, Chord, Pastry and Tapestry, lead to high latency and low efficiency because they are independent of underlying physical networks. A well-routed lookup path in an overlay network with a small number of logical hops can result in a long delay and excessive traffic due to undesirably long distances in some physical links. In these DHT-based P2P systems, each data item is associated with a key and the key/value pair is stored in the node to which the key maps, not considering the data semantic. In this paper, we propose an effective P2P routing algorithm, called Uinta, to adaptively construct a structured P2P overlay network. Uinta not only takes advantages of physical characteristics of the network, but also places data belonging to the same semantic into a cluster and employs a class cache scheme to reduce the lookup routing latency. Simulations make some comparisons between Chord and our Uinta algorithm all running on the GT-ITM transit stub topology. The results show Uinta routing algorithm significantly improves P2P system lookup performance.</p>
<p>The need for efficient computation of approximate global state lies at the heart of a wide range of problems in distributed systems. Examples include routing in the Internet, sensor fusion, search in peer-to-peer networks, coordinated intrusion detection, and Top-K queries in stream-oriented databases. Efficient algorithms that determine approximate global state could enable near-optimal local decision-making with little overhead. In this position paper, we model this problem and summarize recent work on randomized algorithms that navigate a four-way tradeoff between accuracy, robustness, performance and overhead. Despite these recent successes, many open problems remain. We believe that solving these problems can radically improve the design of robust, efficient and self-managed distributed systems.</p>
<p>This paper presents the SkipTree, anew balanced, distributed data structure for storing data with multidimensional keys in a peer-to-peer network. The SkipTree supports range queries as well as single point queries which are routed in O(log n) hops. SkipTree is fully decentralized with each node being connected to O(log n) other nodes. The memory usage for maintaining the links at each node is O(log n log log n) on average and O(log(2) n) in the worst case. Load balance is also guaranteed to be within a constant factor.</p>
<p>Motivated by the peer-to-peer content sharing systems in large-scale networks, we will study interval routing schemes in Erdos-Renyi random graphs. C. Gavoille and D. Peleg [13] posed an open question of whether almost all networks support a shortest-path interval routing scheme with 1 interval. In this paper, we answer this question partially by proving that in almost all networks, there is an interval routing scheme with 1 interval up to additive stretch 2. Our proof is based on the properties of dominating cliques in random graphs.</p>
<p>In this paper, we describe SPiDeR, a peer-to-peer (P2P) based framework that supports a variety of Web service discovery operations. SPiDeR organizes the service providers into a structured P2P overlay and allows them to advertise and lookup services in a completely decentralized and dynamic manner. It supports three different kinds of search operations: For advertising and locating services, service providers can use keywords extracted from service descriptions (keyword-based search), categories from a global ontology (ontology-based search), and/or paths from the service automaton (behavior-based search). The users can also rate the quality of the services they use. The ratings are accumulated within the system so that users can query for the quality ratings of the discovered services. Finally, we present the performance of SPiDeR in terms of routing using a simulator.</p>
<p>In this paper, we present a framework for implicit service calls in data centric Peer to Peer Active XML language. Active XML is a language devoted to the management of distributed data by embedding Web service calls into XML document. The aim of implicit calls is to allow dynamic data sources discovey through dynamic services discovery and composition. Implicit service calls are based on the use of ontologies for describing the domain and functionality of services to call and an Active XML engine for calls evaluation. The evaluation process deals mainly with dynamic service composition. It consists in matching OWLS descriptions contained in a query with service descriptions in a peer-to-peer network. Such a network is structured in such a way that peers with similar functionalities are grouped together and each peer makes itself acquainted with matching relationships between its inputs/outputs and those of other peers.</p>
<p>Web services technology standards enable description, publication, discovery of and binding to services distributed towards the Internet. However, current standards do not address the service selection issue : how did a consumer select the service that matches its functional (e.g. operations' semantics) and non-functional (e.g. price, reputation, response time) properties ? Most projects advocate automatic selection mechanism, advising adaptation or modification of the web-services model and its entities (UDDI, WSDL, Client, Provider). These proposals also do not take advantage of distributed-systems' state of the art, mainly with respect to the collection and the dissemination of services' QoS. This paper presents an extension of the initial model that permits automatic service selection, late binding and collection of metrics that characterize the quality of service. The extension consists on a web-service access infrastructure, made of web service proxies and a peer to peer network of QoS metrics repository (the proposal does not impose modification on UDDI registries or services). The proxies interact with common UDDI registries to find suitable services for selection and to publish descriptions. They collect QoS metrics and store them on a p2p network.</p>
<p>Ad-hoc networks are an emerging technology with immense potential. Providing support for large-scale service and application deployment in these networks, however is crucial to make them a viable alternative. The lack of infrastructure, coupled with the time-varying characteristics of ad-hoc networks, brings about new challenges to the design and deployment of applications. This paper addresses these challenges and presents a unified, overlay-based service architecture to support large-scale service and application deployment in ad-hoc networks. We discuss the main functionalities of the architecture and describe the algorithms for object registration and discovery. Finally, the proposed architecture was evaluated using simulations and the results show that the architecture performs well under different network conditions.</p>
<rp_address>Univ Hong Kong, Dept Elect & Elect Engn, Pokfulam, Hong Kong, Hong Kong, Peoples R China</rp_address>
<rp_organization>Univ Hong Kong</rp_organization>
<rp_suborganizations count="1">
<rp_suborganization>Dept Elect & Elect Engn</rp_suborganization>
</rp_suborganizations>
<rp_street>Pokfulam</rp_street>
<rp_city>Hong Kong</rp_city>
<rp_state>Hong Kong</rp_state>
<rp_country>Peoples R China</rp_country>
</reprint>
<research_addrs count="1">
<research>
<rs_address>Univ Hong Kong, Dept Elect & Elect Engn, Hong Kong, Hong Kong, Peoples R China</rs_address>
<rs_organization>Univ Hong Kong</rs_organization>
<rs_suborganizations count="1">
<rs_suborganization>Dept Elect & Elect Engn</rs_suborganization>
</rs_suborganizations>
<rs_city>Hong Kong</rs_city>
<rs_state>Hong Kong</rs_state>
<rs_country>Peoples R China</rs_country>
</research>
</research_addrs>
<abstract avail="Y" count="1">
<p>Toward a new era of "Ubiquitous Networking" where people are interconnected in anywhere and at anytime via, the wired and wireless Internet, we have witnessed an increasing level of impromptu interactions among human beings in recent years. One important aspect of these interactions is the Peer-to-Peer (P2P) Networking that is becoming a dominant traffic source in the wired Internet. In these Internet overlay networks, users are allowed to exchange information through instant messaging and file sharing. Unfortunately, most of the previous work proposed in the literature on P2P networking is designed for the traditional wired Internet, without much regard to important issues pertinent to wireless communications. In this paper, we attempt to provide some insight into P2P networking with respect to a wireless environment. We focus on P2P file sharing, already a hot application in the wired Internet, and will be equally important in the wireless counterpart. We propose a greedy server-peer selection algorithm to decide from which peer should a client download files so that the level of fairness of the whole network is increased and expected service life of the whole file sharing network is extended. We also propose a new performance metric called Energy-Based Data Availability, EBDA, which is an important performance metric for improving the effectiveness of a wireless P2P file sharing network.</p>