Structured P2P Networks Research Articles

Dynamic Load Sharing in Peer-to-Peer Systems: When Some Peers Are More Equal than Others

Object caching and replication are the primary mechanisms for addressing load balancing in peer-to-peer systems. In structured P2P networks, object popularity is an important challenge because it can adversely impact both the request and forwarding loads in the network. To balance loads across P2P networks, the authors propose a method for dynamically updating routing tables to balance the load induced by forwarding traffic in the neighborhood of nodes holding popular objects.

Verification of Peer-to-peer Algorithms: A Case Study

The problem of maintaining structured peer-to-peer (P2P) overlay networks in the presence of concurrent joins and failures of nodes is the subject of intensive research. The various algorithms underlying P2P systems are notoriously difficult to design and analyse. Thus, when verifying P2P algorithms, a real challenge is to find an adequate level of abstraction at which to model the algorithms and perform the verifications. In this paper, we propose an abstract model for structured P2P networks with ring topology. Our model is based on process algebra, which, with its well-developed theory, provides the right level of abstraction for the verification of many basic P2P algorithms. As a case study, we verify the correctness of the stabilization algorithm of Chord, one of the best-known P2P overlay networks. To show the correctness of the algorithm, we provide a specification and an implementation of the Chord system in process algebra and establish bisimulation equivalence between the two.

FileTrust: Reputation Management for Reliable Resource Sharing in Structured Peer-to-Peer Networks

In peer-to-peer (P2P) networks, reputation is used to estimate the trustworthiness of servents** and to help prevent untrustworthy resources from spreading by malicious servents. However, in dynamic scenarios with arrivals and departures of servents and resources, servent reputation is not enough to reduce the impacts of malicious behaviors such as lying, whitewashing, etc. In this paper, we propose a new reputation management model using both servent and resource reputation and demonstrate detail protocols to implement our model in structured P2P networks. Simulation results show that our model can reduce the rate of downloading untrustworthy resources more rapidly than the previous models even in dynamic scenarios where servents can rejoin with new identities, introduce new untrustworthy resources, and send wrong feedbacks. Also, we show that the proposed model and protocol can effectively share the load between servents.

Sampling cluster endurance for peer-to-peer based content distribution networks

Several types of Content Distribution Networks are being deployed over the Internet today, based on different architectures to meet their requirements (e.g., scalability, efficiency and resiliency). Peer-to-peer (P2P) based Content Distribution Networks are promising approaches that have several advantages. Structured P2P networks, for instance, take a proactive approach and provide efficient routing mechanisms. Nevertheless, their maintenance can increase considerably in highly dynamic P2P environments. In order to address this issue, a two-tier architecture called Omicron that combines a structured overlay network with a clustering mechanism is suggested in a hybrid scheme. In this paper, we examine several sampling algorithms utilized in the aforementioned hybrid network that collect local information in order to apply a selective join procedure. Additionally, we apply the sampling algorithms on Chord in order to evaluate sampling as a general information gathering mechanism. The algorithms are based mostly on random walks inside the overlay networks. The aim of the selective join procedure is to provide a well balanced and stable overlay infrastructure that can easily overcome the unreliable behavior of the autonomous peers that constitute the network. The sampling algorithms are evaluated using simulation experiments as well as probabilistic analysis where several properties related to the graph structure are revealed.

Keyword search in DHT-based peer-to-peer networks

Although search by keywords is particularly important for resource and service discovery in P2P networks, existing techniques for keyword search in structured P2P overlays suffer from several problems: unbalanced load, hot spots, fault tolerance, storage redundancy, and unable to facilitate ranking and keyword expansion. In this paper, we present a general keyword index and search scheme for structured P2P networks that avoids these problems, and in which object insert, delete, and search can be efficiently performed. Some experimental results are also presented to support our claim.

Security challenges for peer-to-peer SIP

Recent research activities have proposed using a peer-to-peer network for user registration and user location in session initiation protocol (SIP)-based voice-over-IP (VoIP) networks. The main motivation for peer-to-peer (P2P) SIP is higher robustness as well as easy configuration and maintenance (compared to client-server SIP). However, these advantages come at the price of security. In this article the security challenges of using a P2P network as a substrate for SIP communication are explored. After a short introduction to SIP and structured P2P networks, the different approaches that have been proposed for using P2P technology in conjunction with SIP are compared. We focus on design issues that affect security in order to identify the security implications of using a structured overlay network for SIP registration and location lookup. Finally, possible solutions for securing P2P SIP are examined and explicit suggestions on how to improve the security of P2P SIP are given

Multidimensional data querying on tree-structured overlay

Multidimensional data query has been gaining much interest in database research communities in recent years, yet many of the existing studies focus mainly on centralized systems. A solution to querying in Peer-to-Peer(P2P) environment was proposed to achieve both low processing cost in terms of the number of peers accessed and search messages and balanced query loads among peers. The system is based on a balanced tree structured P2P network. By partitioning the query space intelligently, the amount of query forwarding is effectively controlled, and the number of peers involved and search messages are also limited. Dynamic load balancing can be achieved during space partitioning and query resolving. Extensive experiments confirm the effectiveness and scalability of our algorithms on P2P networks.

Storing and retrieving XPath fragments in structured P2P networks

In this paper, we address the problem of storing and retrieving XML data over structured Peer-to-Peer (P2P) networks. These are becoming popular because of their access efficiency. An open problem with such networks is represented by the kinds of queries they can handle. In fact, file name lookups, used in popular unstructured networks, are not suitable for many new data formats. Keyword-based searches are also not appropriate for XML data, which must be identified by the whole path leading to an element, rather than by the sole element name. We discuss the extensions needed to properly identify XML data in structured P2P networks. A global document is split into various fragments, which are locally stored within the peers according to their own themes. Each fragment is enhanced with a set of few lightweight path expressions that have the convenient side effect of yielding a decentralized catalog. Since a mediated global schema would not be a reasonable assumption in an highly dynamic P2P network, we show that XPath query evaluation only relying on this catalog effectively biases the search towards particular peers. Our approach does not suffer the network and data size limits of previous proposals and is scalable for large P2P networks. To validate our ideas, we have devised XP2P, namely XPath for P2P, on which we have conducted a comprehensive experimental study using various XML datasets.

Agyaat: mutual anonymity over structured P2P networks

PurposeTo provide mutual anonymity over traditionally un‐anonymous Distributed Hash Tables (DHT) based Peer‐to‐Peer overlay networks, while maintaining the desired scalability and guaranteed lookup properties of the DHTs.Design/methodology/approachAgyaat uses a novel hybrid‐overlay design, a fully decentralized topology without any trusted proxies. It anonymizes both the querying and responding peers through the use of unstructured topologies, called clouds, which are added onto the structured overlays. In addition, it regulates the cloud topologies to ensure the guaranteed location of data and scalability of routing. A unique characteristic of the design is the ability of users to tradeoff between desired anonymity and performance. The paper presents a thorough performance and anonymity analysis of the system, and also analyzes few anonymity compromising attacks and countermeasures.FindingsThe results indicate that Agyaat is able to provide mutual anonymity while maintaining the scalability of lookups, affecting the costs only by a constant factor.Research limitations/implicationsWhile Agyaat is able to meet its mutual anonymity and performance goals, there exist other security vulnerabilities like possible Denial‐of‐Service (DoS) attacks, both due to its design and the underlying DHT overlay. This is fertile ground for future work.Originality/valueAgyaat uses a novel topology architecture and associated protocols that are conducive to providing mutually anonymous services.

Failure recovery for structured p2p networks: Protocol design and performance under churn

Measurement studies indicate a high rate of node dynamics in p2p systems. In this paper, we address the question of how high a rate of node dynamics can be supported by structured p2p networks. We confine our study to the hypercube routing scheme used by several structured p2p systems. To improve system robustness and facilitate failure recovery, we introduce the property of K-consistency, K ≥ 1, which generalizes consistency defined previously. (Consistency guarantees connectivity from any node to any other node.) We design and evaluate a failure recovery protocol based upon local information for K-consistent networks. The failure recovery protocol is then integrated with a join protocol that has been proved to construct K-consistent neighbor tables for concurrent joins. The integrated protocols were evaluated by a set of simulation experiments in which nodes joined a 2000-node network and nodes (both old and new) were randomly selected to fail concurrently over 10,000 s of simulated time. In each such experiment, we took a snapshot of neighbor tables in the network once every 50 s and evaluated connectivity and consistency measures over time as a function of the churn rate, timeout value in failure recovery, and K. We found our protocols to be effective, efficient, and stable for an average node lifetime as low as 8.3 min. Experiment results also show that the average routing delay of our protocols increases only slightly even when the churn rate is greatly increased.

Simple efficient mutual anonymity protocols for peer-to-peer network based on primitive roots

In this paper, we present two types of protocols that can achieve mutual anonymity in peer-to-peer (P2P) network environments, which means the identities of the service, requesters and providers, are anonymous to each other, to other peers, and even to the trusted third party (TTP). One of the two types of protocols is for hybrid P2P systems where there is a TTP to construct the transmission paths and look up the query files. The other type of protocol is for pure P2P environments where no TTP is involved in the session network. These two new protocols are based on primitive roots for three main reasons: simplicity, flexibility, and efficiency. Other issues concerning the P2P network structure as well as the security analyses of the proposed protocols will also be covered in this paper.

Building Reliable Content-Based Routing Protocol over Structured P2P Networks

Much work has been done on building content-based publish/subscribe systems over structured P2P networks, so that the two technologies can be combined together to better support large-scale and highly dynamic systems. However, existing content-based routing protocols can only provide weak reliability guarantees over P2P networks. Based on the routing protocols of structured P2P networks, a new type of content-based routing protocol for pub/sub systems is designed, which is called Identifier Range Based Routing (IRBR) protocol. The IRBR protocol guarantees that the subscribing nodes always receive the interested events exactly once as long as the message from publishing nodes to subscribing nodes is arrivable in the P2P network. At the same time, it can also disseminate an event to all interested subscribers with less network traffic. A prototype pub/sub system has been developed on Pastry, and the experimental results demonstrate the fault-tolerance and routing efficiency of the protocol.

An Advanced Algorithm to P2P Semantic Routing Based on the Topologically-Aware Clustering in Self-Organizing Mode

Structured P2P Networks create a virtual topology on top of the physical topology. The only relation between the two layers is the hashing algorithm, which makes the node’s logical ID independent of its physical location. By analyzing the Hash function, some novel logical connections among the destination node, the traditional semantic routing relay node sequence, and the ID of the clustering neighboring nodes are found. In this paper, the SCSRAA (self-organizing clustering semantic routing advanced algorithm) is resented to improve the efficiency of semantic routing. Since the clustering nodes only have local views in self-organizing mode, some rules are proposed for a node to learn other nodes’ physical location. The SCSRAA’s routing algorithm is described completely. Simulations have verified that the method can improve the semantic routing efficiently.

A scalable P2P platform for the knowledge grid

The knowledge grid needs to operate with a scalable platform to provide large-scale intelligent services. A key function of such a platform is to efficiently support various complex queries in a dynamic large-scale network environment. This paper proposes a platform to support index-based path queries by incorporating a semantic overlay with an underlying structured P2P network that provides object location and management services. Various distributed indexing structures can be dynamically formed by publishing, semantic objects as indexing nodes. Queries are forwarded along the chains of semantic object pointers to search for objects. We investigate the deployment of a scalable distributed trie index for broadcast queries on key strings, propose a decentralized load balancing method for solving the problem of uneven load distribution incurred by heterogeneity of loads and node capacities and by the distributed trie index, and give an approach for improving the availability of the semantic overlay and its trie index. Experiments demonstrate the scalability of the proposed platform.

Small-world overlay P2P networks: Construction, management and handling of dynamic flash crowds

We consider how to construct and maintain a structured overlay P2P network based on the small-world paradigm. Two main attractive properties of a small-world network are (1) a low average hop distance between any two randomly chosen nodes, and (2) a high clustering coefficient. A network with a low average hop distance implies small latency for object lookup. A network with a high clustering coefficient implies the ability to provide efficient object lookup even under heavy object traffic loadings, such as in a flash crowd scenario. We present the SWOP protocol for constructing a small-world overlay P2P network. We compare our system's performance with other structured P2P networks, such as Chord. Whereas the Chord protocol already provides a scalable object lookup latency of O(log(N)), where N is the number of nodes in a P2P network, we show that the SWOP protocol can further improve the object lookup performance. We also take advantage of the high clustering coefficient of a small-world P2P network to design an object replication algorithm that can handle heavy object traffic loading situations. We show that the SWOP network can efficiently deliver popular, possibly dynamic, objects to all the requesting nodes. To the best of our knowledge, ours is the first work that addresses how to handle dynamic flash crowds in a structured P2P network.

PeerTrust: Supporting Reputation-Based Trust for Peer-to-Peer Electronic Communities

Peer-to-peer (P2P) online communities are commonly perceived as an environment offering both opportunities and threats. One way to minimize threats in such communities is to use community-based reputations to help estimate the trustworthiness of peers. We present PeerTrust - a reputation-based trust supporting framework, which includes a coherent adaptive trust model for quantifying and comparing the trustworthiness of peers based on a transaction-based feedback system, and a decentralized implementation of such a model over a structured P2P network. PeerTrust model has two main features. First, we introduce three basic trust parameters and two adaptive factors in computing trustworthiness of peers, namely, feedback a peer receives from other peers, the total number of transactions a peer performs, the credibility of the feedback sources, transaction context factor, and the community context factor. Second, we define a general trust metric to combine these parameters. Other contributions of the paper include strategies used for implementing the trust model in a decentralized P2P environment, evaluation mechanisms to validate the effectiveness and cost of PeerTrust model, and a set of experiments that show the feasibility and benefit of our approach.

Failure recovery for structured P2P networks

Measurement studies indicate a high rate of node dynamics in p2p systems. In this paper, we address the question of how high a rate of node dynamics can be supported by structured p2p networks. We confine our study to the hypercube routing scheme used by several structured p2p systems. To improve system robustness and facilitate failure recovery, we introduce the property of K- consistency , K ≥ 1, which generalizes consistency defined previously. (Consistency guarantees connectivity from any node to any other node.) We design and evaluate a failure recovery protocol based upon local information for K-consistent networks. The failure recovery protocol is then integrated with a join protocol that has been proved to construct K-consistent neighbor tables for concurrent joins. The integrated protocols were evaluated by a set of simulation experiments in which nodes joined a 2000-node network and nodes (both old and new) were randomly selected to fail concurrently over 10,000 seconds of simulated time. In each such "churn" experiment, we took a "snapshot" of neighbor tables in the network once every 50 seconds and evaluated connectivity and consistency measures over time as a function of the churn rate, timeout value in failure recovery, and K . Storage and communication overheads were also evaluated. We found our protocols to be effective, efficient, and stable for an average node lifetime as low as 8.3 minutes (the median lifetime measured for Napster and Gnutella was 60 minutes [10]).