Unstructured P2P Systems Research Articles

Structured P2P technologies for distributed command and control

The utility of Peer-to-Peer (P2P) systems extends far beyond traditional file sharing. This paper provides an overview of how P2P systems are capable of providing robust command and control for Distributed Multi-Agent Systems (DMASs). Specifically, this article presents the evolution of P2P architectures to date by discussing supporting technologies and applicability of each generation of P2P systems. It provides a detailed survey of fundamental design approaches found in modern large-scale P2P systems highlighting design considerations for building and deploying scalable P2P applications. The survey includes unstructured P2P systems, content retrieval systems, communications structured P2P systems, flat structured P2P systems and finally Hierarchical Peer-to-Peer (HP2P) overlays. It concludes with a presentation of design tradeoffs and opportunities for future research into P2P overlay systems.

HICUS: A quasi-structured P2P system based on hierarchical interest

The key problem in unstructured P2P system is how to control “Flood”. Some studies focus on constructing more efficient topology while others focus on better query algorithms. This paper presents HICUS (Hierarchical Interest-driven Community-based Unstructured System) motivated by a basic thought—whether the resources correlate with topology distinguishes structured and unstructured P2P essentially. By introducing hierarchical “interest”, HICUS organizes a quasi-structured topology through a pure distributed way, and provides a new platform for query algorithms. We study the procedure and performance of topology organization, and the simulations show that HICUS forms a small-world which can significantly improve the routing efficiency.

An Efficient and Robust Self-Storage P2P Reputation System

For the large scale of the network and unreliable nature of peers in most P2P (Peer-to-Peer) systems, it is a challenging task to implement an efficient and robust P2P reputation system. Self-storage P2P reputation systems provide an efficient way to retrieve rating values. Since each peer locally stores its own rating values given by all other peers, it takes only one query message to collect all the rating values of a peer. However, it also gives the owner control over its rating values. One of the challenges of this type of system is to protect the rating values from being maliciously modified by their owners. In existing self-storage P2P reputation systems, other participants are involved in order to ensure the integrity and reliability of the rating values. However, because at least one participant must be contacted during the rating and rating values retrieval processes, they create a high message overhead when deployed in unstructured P2P systems. In this article, we address the efficiency and robustness of P2P reputation systems in fully distributed environments. We propose an innovative self-storage P2P reputation system. In our system, each peer locally stores its own positive rating values given and signed by other peers. On one hand, since it is not likely for a peer to discard any part of the positive rating values or forge the raters' signatures, the integrity and reliability of the self-storage rating values are preserved. On the other hand, based on the self-storage rating values and our reputation value computing algorithm, one step is enough to rate or obtain the whole positive rating values of a peer without other participants or broadcasting messages. Extensive simulations have been conducted to evaluate the performance of our system. Simulation results show that the message overhead of our system is reduced significantly (4 messages for each transaction) compared with existing self-storage P2P reputation systems, which makes our system a scalable reputation system for handling a large number of P2P services. Our system is also robust to malicious behaviors of peers. Simulation results show that the service selection success ratio is greater than 0.8 even when there are 70% malicious peers. Moreover, when those participants are not reachable in existing self-storage P2P reputation systems, the rating values verification process fails, while in our system, no other peer is involved and this type of threat can be totally avoided.

A protocol for reliably, flexibly, and efficiently making agreement among peers

In Peer-to-Peer (P2P) applications, peers exchange their opinions with each other and make an agreement on one opinion. Agreement procedures have to be so flexible that persons can change their opinions, withdraw previous opinions under some constraints on the opinions, and use various types of agreement conditions like majority-condition in our society. We discuss a flexible agreement protocol of multiple peers by taking into account human behaviours in a fully unstructured P2P system model. We discuss forward, backward, mining, and observation strategies to efficiently make agreement. We discuss how peers cooperate to take consistent strategies at each round.

Summary management in unstructured P2P systems

In this paper, we propose managing data summaries in unstructured P2P systems. Our summaries are intelligible views with two main virtues. First, they can be directly queried and used to approximately answer a query. Second, as semantic indexes, they support locating relevant nodes based on data content. The performance evaluation of our proposal shows that the cost of query routing is minimized, while incurring a low cost of summary maintenance.

The expansion and mixing time of skip graphs with applications

We prove that with high probability a skip graph contains a 4-regular expander as a subgraph and estimate the quality of the expansion via simulations. As a consequence, skip graphs contain a large connected component even after an adversarial deletion of nodes. We show how the expansion property can be used to sample a node in the skip graph in a highly efficient manner. We also show that the expansion property can be used to load balance the skip graph quickly. Finally, it is shown that the skip graph could serve as an unstructured P2P system, making it a good candidate for a hybrid P2P system.

Partition Nodes: Topologically-Critical Nodes of Unstructured Peer-to-Peer Networks

Although nodes in peer-to-peer networks are viewed as equal entities in function, some of them have much more importance than others in the aspect of overlay topology. This paper introduces the concept of "partition node" to describe the topologically-critical nodes, whose failure may potentially lead to overlay partitioning. Then a simple, effective and distributed method to detect and avoid partition nodes, is proposed. The results of simulation show that the proposed method can optimize the overlay topology and remarkably improve the fault tolerance of unstructured P2P systems under a dynamic environment.

Continually Answering Constraint k-NN Queries in Unstructured P2P Systems

We consider the problem of efficiently computing distributed geographical k-NN queries in an unstructured peer-to-peer (P2P) system, in which each peer is managed by an individual organization and can only communicate with its logical neighboring peers. Such queries are based on local filter query statistics, and require as less communication cost as possible, which makes it more difficult than the existing distributed k-NN queries. Especially, we hope to reduce candidate peers and degrade communication cost. in this paper, we propose an efficient pruning technique to minimize the number of candidate peers to be processed to answer the k-NN queries. Our approach is especially suitable for continuous k-NN queries when updating peers, including changing ranges of peers, dynamically leaving or joining peers, and updating data in a peer. In addition, simulation results show that the proposed approach outperforms the existing Minimum Bounding Rectangle (MBR)-based query approaches, especially for continuous queries.

DCMP: A Distributed Cycle Minimization Protocol for Peer-to-Peer Networks

Broadcast-based peer-to-peer (P2P) networks, including flat (for example, Gnutella) and two-layer superpeer implementations (for example, Kazaa), are extremely popular nowadays due to their simplicity, ease of deployment, and versatility. The unstructured network topology, however, contains many cyclic paths, which introduce numerous duplicate messages in the system. Although such messages can be identified and ignored, they still consume a large proportion of the bandwidth and other resources, causing bottlenecks in the entire network. In this paper, we describe the distributed cycle minimization protocol (DCMP), a dynamic fully decentralized protocol that significantly reduces the duplicate messages by eliminating unnecessary cycles. As queries are transmitted through the peers, DCMP identifies the problematic paths and attempts to break the cycles while maintaining the connectivity of the network. In order to preserve the fault resilience and load balancing properties of unstructured P2P systems, DCMP avoids creating a hierarchical organization. Instead, it applies cycle elimination symmetrically around some powerful peers to keep the average path length small. The overall structure is constructed fast with very low overhead. With the information collected during this process, distributed maintenance is performed efficiently even if peers quit the system without notification. The experimental results from our simulator and the prototype implementation on PlanetLab confirm that DCMP significantly improves the scalability of unstructured P2P systems without sacrificing their desirable properties. Moreover, due to its simplicity, DCMP can be easily implemented in various existing P2P systems and is orthogonal to the search algorithms.

Dynamic and scalable storage management architecture for Grid Oriented Storage devices

Most of currently deployed Grid systems employ hierarchical or centralized approaches to simplify system management. However, the approaches cannot satisfy the requirements of complex Grid applications which involve hundreds or thousands of geographically distributed nodes. This paper proposes a Dynamic and Scalable Storage Management (DSSM) architecture for Grid Oriented Storage (GOS) devices. Since large-scale data intensive applications frequently involve a high degree of data access locality, the DSSM divides GOS nodes into multiple geographically distributed domains to facilitate the locality and simplify the intra-domain storage management. Dynamic GOS agents selected from the domains are organized as a virtual agent domain in a Peer-to-Peer (P2P) manner to coordinate multiple domains. As only the domain agents participate in the inter-domain communication, system wide information dissemination can be done far more efficiently than flat flooding. Grid service based storage resources are adopted to stack simple modular service piece by piece as demand grows. The decentralized architecture of DSSM avoids the hierarchical or centralized approaches of traditional Grid architectures, eliminates large-scale flat flooding of unstructured P2P systems, and provides an interoperable, seamless, and infinite storage pool in a Grid environment. The DSSM architecture is validated by a proof-of-concept prototype system.

Comparison of image similarity queries in P2P systems

Given some of the recent advances in Distributed Hash Table (DHT) based Peer-To-Peer (P2P) systems, and some of the well-known potential scalability and search problems associated with unstructured P2P systems, we ask the following questions: are there applications where unstructured queries are still necessary (i.e. the underlying queries do not efficiently map onto any structured framework), and are there unstructured P2P systems that can deliver the high bandwidth and computing performance necessary to support such applications. Toward this end, we consider an image search application which supports queries based on image similarity metrics, such as color histogram intersection, and discuss why in this setting, standard DHT approaches are not directly applicable. We then study the feasibility of implementing such an image search system on two different unstructured P2P systems: power–law topology with percolation search, and an optimized super-node topology using structured broadcasts. We examine the average and maximum values for node bandwidth, storage and processing requirements in the percolation and super-node models, and show that current high-end computers and high-speed links have sufficient resources to enable deployments of large-scale complex image search systems, using these unstructured P2P technologies.

Resource search in unstructured peer-to-peer system based on multiple-tree overlay structure

We propose a multiple-tree overlay structure for resource discovery in unstructured P2P systems. Peers that have similar interests or hold similar type of resources will be grouped into a tree-like cluster. We exploit the heterogeneity of peers in each cluster by connecting peers with more capacities closer to the root of the tree. The capacity of a peer can be defined in different ways (e.g. higher network bandwidth, larger disk space, more data items of a certain type etc.) according to different needs of users or applications.

Assisted Peer-to-Peer Search with Partial Indexing

In the past few years, peer-to-peer (P2P) networks have become a promising paradigm for building a wide variety of distributed systems and applications. The most popular P2P application till today is file sharing, e.g., Gnutella, Kazza, etc. These systems are usually referred to as unstructured, and search in unstructured P2P networks usually involves flooding or random walking. On the other hand, in structured P2P networks (DHTs), search is usually performed by looking up a distributed inverted index. The efficiency of the search mechanism is the key to the scalability of a P2P content sharing system. So far, neither unstructured nor structured P2P networks alone can solve the search problem in a satisfactory way. In this paper, we propose to combine the strengths of both unstructured and structured P2P networks to achieve more efficient search. Specifically, we propose to enhance search in unstructured P2P overlay networks by building a partial index of shared data using a structured P2P network. The index maintains two types of information: the top interests of peers and globally unpopular data, both characterized by data properties. The proposed search protocol, assisted search with partial indexing, makes use of the index to improve search in three ways: first, the index assists peers to find other peers with similar interests and the unstructured search overlay is formed to reflect peer interests. Second, the index also provides search hints for those data difficult to locate by exploring peer interest locality, and these hints can be used for second-chance search. Third, the index helps to locate unpopular data items. Experiments based on a P2P file sharing trace show that the assisted search with a lightweight partial indexing service can significantly improve the success rate in locating data than Gnutella and a hit-rate-based protocol in unstructured P2P systems, while incurring low search latency and overheads.

PFusion: A P2P Architecture for Internet-Scale Content-Based Search and Retrieval

The emerging peer-to-peer (p2p) model has become a very powerful and attractive paradigm for developing Internet-scale systems for sharing resources, including files and documents. The distributed nature of these systems, where nodes are typically located across different networks and domains, inherently hinders the efficient retrieval of information. In this paper, we consider the effects of topologically aware overlay construction techniques on efficient p2p keyword search algorithms. We present the peer fusion (pFusion) architecture that aims to efficiently integrate heterogeneous information that is geographically scattered on peers of different networks. Our approach builds on work in unstructured p2p systems and uses only local knowledge. Our empirical results, using the pFusion middleware architecture and data sets from Akamai's Internet mapping infrastructure (AKAMAI), the active measurement project (NLANR), and the text retrieval conference (TREC) show that the architecture we propose is both efficient and practical

A Trace Label Based Consistency Maintenance Algorithm in Unstructured P2P Systems

Replication is an effective way to improve the scalability, fault-tolerance, and availability as well as to reduce the query responding time in P2P system. With the P2P applications transferring from read-only static files sharing to read-write dynamical files interacting, maintaining consistency between frequently-updated files and their replicas is a fundamental reliability requirement for P2P system. This paper presents a trace label based consistency maintenance algorithm. It modifies the message datagram by attaching the address list of peers to which message has been sent. This can help to tell the duplicated message from the source peer by the aid of the attached address list in message datagram. Considering that the address list can become longer with the update time lapsing and the degree of P2P increasing, this paper presents a new Bloom Filter denoting the address list algorithm. The Bloom Filter can succinctly present the address list and simplify the query actions in the list by “OR” operations. The experimental results show that the new trace label based consistency maintenance algorithm can largely reduce the number of the duplicated messages. Moreover, the higher the degree of P2P, the more reduction of the number of duplicated messages and bandwidth utilization. The idea of consistency maintenance in this paper can also be applied to sensor network and other ad hoc networks.

An Overlay Topology Based Proactive Replication in Unstructured P2P Systems

The overlay network of unstructured P2P system is neither regular network,nor pure random network. The peers are usually not completely equivalent.They usually play different roles in the overlay network.This paper firstly investigates the relation among the degree distribution,the access frequency mode and the success rate, and then presents an optimal degree distribution model in terms of the popularity of data items.Finally,a feasible proactive replication is proposed to reach the expected degree distribution.The simulation shows that the proactive replication can improve the performance of the unstructured P2P.

Multi-Dimensional Range Search in Unstructured Peer-to-Peer Systems

It is an important problem to efficiently support similarity search for multi-dimensional data spaces in peer-to-peer (P2P) data management environment. Current unstructured P2P data sharing systems provide only a very rudimentary facility in query processing, i.e., matching-based query processing. This paper therefore presents a simple, yet effective index structure called EVARI (extended vector approximation routing index) to address the problem of multi-dimensional range search in unstructured P2P systems, by means of both data approximation and routing index techniques. With the aid of the EVARI, each peer can not only process range queries with its local dataset, but also route queries to promising peers with the desired data objects. In the proposed scheme, each peer summarizes its local content using space-partitioning technique, and exchanges the summarized information with neighboring peers to construct the EVARI. Furthermore, each peer can reconfigure its neighboring peers to keep the relevant peers nearby so as to optimize system resource configuration and improve system performance. Extensive experiments show the good performance of the proposed approach.

Improving Query Response Delivery Quality in Peer-to-Peer Systems

Unstructured peer-to-peer (P2P) system is the prevalent model in today's P2P systems. In such systems, a response is sent along the same path that carried the incoming query message. To guarantee the anonymity of the requestor, no requestor information is included in the response message, and each node in the query's incoming path only knows its direct neighbors who sent the query request to it. This mechanism introduces response loss when any one node or connection in the path fails, which is a common occurrence in the P2P system due to its dynamic feature. In this paper, we address the response loss problem and show that peers' oscillation can cause up to a 35 percent response loss in an unstructured P2P system. We also present three techniques to alleviate this problem: the redundant response delivery (RRD) scheme as a proactive approach, the adaptive response delivery (ARD) scheme as a reactive approach, and the extended adaptive response delivery scheme to render ARD to function in an unstructured P2P system with limited or no flooding-based search mechanism. We have evaluated our techniques in a large-scale network simulation. With limited traffic overhead, all three techniques reduce response loss rate by more than 65 percent and are fully distributed. We have designed our techniques to be simple to develop and implement in existing P2P systems.

Exploiting Geographical and Temporal Locality to Boost Search Efficiency in Peer-to-Peer Systems

As a hot research topic, many search algorithms have been presented and studied for unstructured peer-to-peer (P2P) systems during the past few years. Unfortunately, current approaches either cannot yield good lookup performance, or incur high search cost and system maintenance overhead. The poor search efficiency of these approaches may seriously limit the scalability of current unstructured P2P systems. In this paper, we propose to exploit two-dimensional locality to improve P2P system search efficiency. We present a locality-aware P2P system architecture called Foreseer, which explicitly exploits geographical locality and temporal locality by constructing a neighbor overlay and a friend overlay, respectively. Each peer in Foreseer maintains a small number of neighbors and friends along with their content filters used as distributed indices. By combining the advantages of distributed indices and the utilization of two-dimensional locality, our scheme significantly boosts P2P search efficiency while introducing only modest overhead. In addition, several alternative forwarding policies of Foreseer search algorithm are studied in depth on how to fully exploit the two-dimensional locality

Reducing network traffic in unstructured P2P systems using Top-k queries

A major problem of unstructured P2P systems is their heavy network traffic. This is caused mainly by high numbers of query answers, many of which are irrelevant for users. One solution to this problem is to use Top-k queries whereby the user can specify a limited number (k) of the most relevant answers. In this paper, we present FD, a (Fully Distributed) framework for executing Top-k queries in unstructured P2P systems, with the objective of reducing network traffic. FD consists of a family of algorithms that are simple but effective. FD is completely distributed, does not depend on the existence of certain peers, and addresses the volatility of peers during query execution. We validated FD through implementation over a 64-node cluster and simulation using the BRITE topology generator and SimJava. Our performance evaluation shows that FD can achieve major performance gains in terms of communication and response time.