P2P语义搜索研究进展

P2P语义搜索方法多种多样。首先,制定了一套综述方案,从语义描述方法、覆盖网络结构、查询扩展技术、资源聚类方式以及本体数量等5个角度对现有方法进行综述。然后,选择10种典型语义搜索方法进行分析比较,总结P2P语义搜索的主要特征。最后,指出下一步研究应探索新的资源组织与搜索机制,并着重关注P2P语义搜索性能评价、查询扩展技术完善、搜索结果排序等方面。     

PHIRST: A distributed architecture for P2P information retrieval

Recent progress in peer to peer (P2P) search algorithms has presented viable structured and unstructured approaches for full-text search. We posit that these existing approaches are each best suited for different types of queries. We present PHIRST, the first system to facilitate effective full-text search within P2P databases. PHIRST works by effectively leveraging between the relative strengths of these approaches. Similar to structured approaches, agents first publish terms within their stored documents. However, frequent terms are quickly identified and not exhaustively stored, resulting in a significant reduction in the system's storage requirements. During query lookup, agents use unstructured search to compensate for the lack of fully published terms. Additionally, they explicitly weigh between the costs involved in structured and unstructured approaches, allowing for a significant reduction in query costs. Finally, we address how node failures can be effectively addressed through storing multiple copies of selected data. We evaluated the effectiveness of our approach using both real-world and artificial queries. We found that in most situations our approach yields near perfect recall. We discuss the limitations of our system, as well as possible compensatory strategies.     

VQ-based algorithms extended to non-embedded watermarking for multimedia ownership prevention systems

This paper presents some novel watermarking approaches that are based on vector quantization and provide ownership protection in gray-level images. Nowadays, information sharing in P2P architecture is immensely involved with knowledge-learning on the Internet. Copyright protection is therefore considered in the studies of P2P systems. The proposed approaches combine images, watermarks, and codebooks together by generating key streams to claim ownership and guarantee the integrity of images. Non-embedded approaches that generate claimed key streams have the benefit of maintaining the authorized image in its original state without any modifications. Compared to Lin et al.’s method, our approaches save both running time and space for storage. Moreover, in order to provide broader applications of image protection, robust watermark and fragile watermark strategies are proposed. The experimental results show that these strategies are effective.     

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.     

无结构P2P网络搜索方法及其改进

对等(P2P)计算是未来网络中的关键技术,对等网络是实现下一代互联网的重要组成部分。如何高效地搜索P2P网络上的资源是P2P网络实现的最为关键的问题。在讲述对等网络的基本搜索方法的基础上,分析了许多改进的搜索方法,包括基于转发的改进方法、基于缓存的改进方法和基于覆盖网拓扑优化的改进方法。     

对等网络中的搭便车行为分析与抑制机制综述

搭便车(freeriding)行为在对等网络(Peer-to-Peernetwork)中日趋严重,它对网络健壮性、可用性和生命周期等造成了负面影响.设计、应用合理的搭便车行为抑制机制是当前对等网络研究的一个重要方向.文中首先描述搭便车行为的测量方法和发展趋势,然后分析搭便车行为的基本原理以及对对等网络性能的影响.依据数学建模和分析工具的差异,将已有搭便车行为抑制机制分为激励机制、博弈论方法、社会网络与经济模型三大类.文中归纳了三类抑制机制的建模方法,对其优、缺点进行了分析和比较,最后对搭便车行为抑制机制的未来研究方向进行了展望.     

A multi-dimensional trust evaluation model for large-scale P2P computing

In large-scale peer-to-peer (P2P) computing, trust management technology has become a key requirement for network security. However, trust is one of the most complex concepts in network communities. It involves many factors, such as, assumptions, expectations, behaviors, risks, and so on. As a result, trustworthiness has multi-dimensional properties. In this paper, an innovative trust model is proposed for large-scale P2P computing, in which multiple factors are incorporated to reflect the complexity of trust. More importantly, the properties (weights) of these factors are dynamically assigned by weighted moving average and ordered weighted averaging (WMA-OWA) combination algorithms. This model surpasses the limitations of existing approaches, wherein weights are assigned subjectively. The simulation results show that, compared with the existing approaches, the proposed model provides greater accuracy and a more detailed analysis in trust evaluation.     

EDA: an enhanced dual-active algorithm for location privacy preservation inmobile P2P networks

Various solutions have been proposed to enable mobile users to access location-based services while preserving their location privacy. Some of these solutions are based on a centralized architecture with the participation of a trustworthy third party, whereas some other approaches are based on a mobile peer-to-peer (P2P) architecture. The former approaches suffer from the scalability problem when networks grow large, while the latter have to endure either low anonymization success rates or high communication overheads. To address these issues, this paper deals with an enhanced dual-active spatial cloaking algorithm (EDA) for preserving location privacy in mobile P2P networks. The proposed EDA allows mobile users to collect and actively disseminate their location information to other users. Moreover, to deal with the challenging characteristics of mobile P2P networks, e.g., constrained network resources and user mobility, EDA enables users (1) to perform a negotiation process to minimize the number of duplicate locations to be shared so as to significantly reduce the communication overhead among users, (2) to predict user locations based on the latest available information so as to eliminate the inaccuracy problem introduced by using some out-of-date locations, and (3) to use a latest-record-highest-priority (LRHP) strategy to reduce the probability of broadcasting fewer useful locations. Extensive simulations are conducted for a range of P2P network scenarios to evaluate the performance of EDA in comparison with the existing solutions. Experimental results demonstrate that the proposed EDA can improve the performance in terms of anonymity and service time with minimized communication overhead.     

Flexible security in peer-to-peer applications: Enabling new opportunities beyond file sharing

The widespread adoption of P2P applications in environments beyond ordinary file sharing demands the fulfillment of several security requirements. Important steps have been taken towards security in P2P systems, with relevant mechanisms being proposed in the past to address specific vulnerabilities. However, existing approaches lack flexibility, since they do not (include enough mechanisms to) tackle a wide range of requirements in an integrated fashion. In addition, they oblige the user/application to manipulate a complex programming interface, as well as going through a cumbersome configuration process. To address these issues, we present P2PSL (P2P Security Layer), a software architecture that allows gradual and flexible integration of security functionality into P2P applications. To show concept and technical feasibility, we have implemented P2PSL, assessed the overhead it induces, and estimated the feasibility of incorporating the layer into two categories of real world P2P applications.     

P2P和CDN中MDC流媒体的性能对比

文中检测并对比了基于多重描述编码(MDC)的流媒体在对等网(P2P)和内容分发网络(CDN)中的性能。多个服务器同时为一个客户请求提供相同的描述,这样提高了网络传输的可靠性,并增加了服务器的数据传输率。用ns-2网络模拟器实现了这两种方法,实验结果表明:虽然P2P网络存在高度不稳定的情况,但是基于P2P的MDC流视频的质量明显比CDN上的好。     

Evaluation of P2P multimedia clustering techniques in JXTA-Overlay

Efficient file searching is an essential feature in P2P systems. While many current approaches use brute force techniques to search files by meta information (file names, extensions or user-provided tags), the interest is in implementing techniques that allow content-based search in P2P systems. Recently, clustering techniques have been used for searching text documents to increase the efficiency of document discovery and retrieval. Integrating such techniques into P2P systems is important to enhance searching in P2P file sharing systems. While some effort has been taken for content-based searching for text documents in P2P systems, there has been few research work for applying these techniques to multimedia content in P2P systems. In this paper, we introduce two P2P content-based clustering techniques for multimedia documents. These techniques are an adaptation of the existing Class-based Semantic Search algorithm for text documents. The proposed algorithms have been integrated into a JXTA-based Overlay P2P platform, and evaluation results are provided. The JXTA-Overlay together with the considered clustering techniques is thus very useful for developing P2P multimedia applications requiring efficient searching of multimedia contents in peer nodes.     

BitTorrent-like P2P approaches for VoD: A comparative study

The enormous popularity of Video on Demand (VoD) has attracted substantial research attention into the effective use of peer-to-peer (P2P) architectures to provide solutions at large-scale. In particular, the high efficiency of BitTorrent has inspired many P2P protocols for VoD. However, these protocols use different approaches to adapt the design of Bittorrent to VoD, and in most cases their performance has been evaluated separately and in limited scenarios. As a consequence, the research community still lacks a clear understanding of how these protocols compare against each other and how well each of them would work in real world conditions, where, for instance, peers have heterogeneous bandwidths, may freeride or may be located behind NAT/firewall.In this paper, we propose a simulation based methodology which aims at putting forward a common base for comparing the performance of these different protocols under a wide range of conditions. We show that, despite their considerable differences: (i) existing BitTorrent-like VoD approaches all share some characteristics, such as that their bandwidth reciprocity based methods to incentivize cooperation do not always yield an optimal overall performance. Furthermore, we demonstrate that (ii) in these protocols there is a trade-off between QoS and resilience to freeriding and malicious attacks. We also discover that, (iii) when peers doing streaming coexist with peers doing traditional file transfer, the latter actually benefit from this coexistence, at the expenses of the former. Finally, we show that (iv) early departures of peers from the system do not significantly affect the QoS delivered, while jumping to a different position in the file has a bigger negative impact. Overall, our findings provide important implications for both VoD service providers and future system designers. On the one hand, our results can guide VoD service providers in selecting the most appropriate protocol for a given environment. On the other hand, exposing the flaws of current approaches will help researchers in improving them and/or designing better ones.     

Collaborative SVM classification in scale-free peer-to-peer networks

Distributed classification in large-scale P2P networks has gained relevance in recent years and support applications like distributed intrusion detection in P2P monitoring environments, online match-making, personalized information retrieval, distributed document classification in a P2P media repository and P2P recommender systems to mention a few. However, classification in a P2P network is a challenging task due to the constraints such as centralization of data is not feasible, scarce communication bandwidth, scalability, synchronization and peer dynamism. Moreover, without considering data distributions and topological scenarios of real world P2P systems, most of the existing distributed classification approaches lack in their predictive and network-cost performance. In this paper, we investigate a collaborative classification method (TRedSVM) based on Support Vector Machines (SVM) in Scale-free P2P networks. In particular, we demonstrate how to construct SVM classifier in real world P2P networks which exhibit inherently skewed distribution of node links and eventually data. The proposed method propagates the most influential instances of SVM models to the vast majority of scarcely connected peers in a controlled way that improves their local classification accuracy and, at the same time, keeps the communication cost low throughout the network. Besides using benchmark Machine Learning data sets for extensive experimental evaluations, we have evaluated the proposed method particularly for music genre classification to exhibit its performance in a real application scenario. Additionally, performance analysis is carried out with respect to centralized approaches, data replication in P2P networks and cost accuracy trade-off. TRedSVM outperforms baseline approaches of model propagation by improving the overall classification performance substantially at the cost of a tolerable increase in communication.     

Building Efficient Overlays

Peer-to-peer (P2P) and Grid computing systems have emerged as popular models aiming at further utilizing Internet information and resources, complementing the available client–server services. However, the mechanism of peers randomly choosing logical neighbors without any knowledge about underlying physical topology can cause a serious topology mismatch problems between the overlay network and the physical underlying network. The topology mismatch problem brings a great stress in the Internet infrastructure and greatly limits the performance gain from various search or routing techniques in P2P and Grid systems. Aiming at alleviating the mismatch problem and reducing the unnecessary traffic, we have proposed two approaches, adaptive overlay topology optimization (AOTO) and location-aware topology matching (LTM) techniques, to reduce the total traffic cost and average query response time. Both AOTO and LTM are scalable and completely distributed in the sense that they do not require any global knowledge of the whole overlay network when each node is optimizing the organization of its logical neighbors. This paper shows the effectiveness of AOTO and LTM and compares the performance of these two approaches through simulation studies.     

Modeling and analysis of passive worm propagation in the P2P file-sharing network

A number of worms, named P2P (peer-to-peer) passive worms, have recently surfaced, which propagate in P2P file-sharing networks and have posed heavy threats to these networks. In contrast to the majority of Internet worms, it is by exploiting users’ legitimate activities instead of vulnerabilities of networks in which P2P passive worms propagate. This feature evidently slows down their propagation, which results in them not attracting an adequate amount of attention in literature. Meanwhile, this feature visibly increases the difficulty of detecting them, which makes it very possible for them to become epidemic. In this paper, we propose an analytical model for P2P passive worm propagation by adopting epidemiological approaches so as to identify their behaviors and predict the tendency of their propagation accurately. Compared with a few existing models, dynamic characteristics of P2P networks are taken into account. Based on this proposed model, the sufficient condition for the global stability of the worm free equilibrium is derived by applying epidemiological theories. Large scale simulation experiments have validated both the proposed model and the condition.     

On Game Theoretic Peer Selection for Resilient Peer-to-Peer Media Streaming

Peer-to-peer (P2P) media streaming quickly emerges as an important application over the Internet. A plethora of approaches have been suggested and implemented to support P2P media streaming. In our study, we first classified existing approaches and studied their characteristics by looking at three important quantities: number of upstream peers (parents), number of downstream peers (children), and average number of links per peer. In existing approaches, peers are assigned with a fixed number of parents without regard to their contributions, measured by the amount of outgoing bandwidths. Obviously, this is an undesirable arrangement as it leads to highly inefficient use of the P2P links. This observation motivates us to model the peer selection process as a cooperative game among peers. This results in a novel peer selection protocol such that the number of upstream peers of a peer is related to its outgoing bandwidth. Specifically, peers with larger outgoing bandwidth are given more parents, which make them less vulnerable to peer dynamics. Simulation results show that the proposed protocol improves delivery ratio using similar number of links per peer, comparing with existing approaches under a wide range of system parameters.     

Peer sampling gossip-based distributed clustering algorithm for unstructured P2P networks

Clustering, as an unsupervised learning method and an important process in data mining, is an aspect of large and distributed data analysis. In many applications, such as peer-to-peer systems, huge volumes of data are distributed between multiple sources. Analysis of these volumes of data and identifying appropriate clusters is challenging due to transmission, processing and storage costs. In this paper, a gossip-based distributed clustering algorithm for P2P networks called Efficient GBDC-P2P is proposed, based on an improved gossip communicative approach by combining the peer sampeling and CYCLON protocol and the idea of partitioning-based data clustering. This algorithm is appropriate for data clustering in unstructured P2P networks, and it is adapted to the dynamic conditions of these networks. In the Efficient GBDC-P2P algorithm, distributed peers perform clustering operation in a distributed way only through local communications with their neighbors. Our approach does not rely on the central server to carry out data clustering task and without the need to synchronize operations. Evaluation results verify the efficiency of our proposed algorithm for data clustering in unstructured P2P networks. Furthermore, comparative analyses with other well-established distributed clustering approaches demonstrate the superior accuracy of the proposed method.

     

UR-aware: Streaming videos over BitTorrent with balanced playback urgency and rareness distribution

In recent years, the BitTorrent (BT) has been one of the most efficient mechanisms for Peer-to-Peer (P2P) non-realtime content distribution. Many approaches for streaming videos over BT have been proposed by modifying the piece selection policy to cope with the real time requirement. Most of them provide the continuity of video playback at the cost of the variety of pieces on P2P streaming networks. In this paper, we propose the novel urgency-aware BT streaming mechanism, called UR-Aware, which intends to enhance the video streaming efficiency over BT on P2P networks by balancing playback continuity and distribution of piece rareness. There are two sets for piece downloading, called Uset and Rset. The Uset contains the most urgent pieces of video playback, while the Rset contains the rarest pieces. Downloading bandwidth of a peer is dynamically allocated to the two sets based on the number of consecutive pieces beyond these playback position in Uset. Furthermore, to implicitly preserve the continuity of pieces for future playback, consecutive k pieces are grouped as a section which would be selected to insert into Rset based on its rareness. The experimental results show that the UR-Aware has the best performance among other BT streaming approaches in terms of video download time, piece late rate, and network throughput. In addition, the accumulated standard deviation of UR-Aware is closest to that of the native BT among those approaches, which also confirms the superiority of UR-Aware on video streaming over BT.     

Maintenance strategies for routing indexes

Query processing in large-scale unstructured P2P networks is a crucial part of operating such systems. In order to avoid expensive flooding of the network during query processing so-called routing indexes are used. Each peer maintains such an index for its neighbors. It provides a compact representation (data summary) of data accessible via each neighboring peer. An important problem in this context is to keep these data summaries up-to-date without paying high maintenance costs. In this paper, we investigate the problem of maintaining distributed data summaries in P2P-based environments without global knowledge and central instances. Based on a classification of update propagation strategies, we discuss several approaches to reduce maintenance costs and present results from an experimental evaluation.