A novel state cache scheme in structured P2P systems

Large-scale P2P systems typically have hundreds of thousands of peers that involve frequent dynamic activities. Current structured overlays do not identify well the rhythm in the dynamic activities, thus resulting in high maintenance overhead. In this paper, we present a new state cache system, called SCS, that solves the problem by exploiting the access patterns of dynamic activities in P2P systems. SCS partitions the whole P2P network into clusters and dynamically chooses a “super” node in each cluster to selectively record and maintain the routing information for departed nodes most likely to arrive back in the near future. The cached routing information enables SCS to simplify self-organization, reduce system maintenance overhead and provide high quality routing service. The experimental results show that SCS reduces the maintenance overhead by up to 66% while delivering much better routing performance, as compared to current structured 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.     

基于路由学习的非结构化P2P搜索技术研究

针对无结构化P2P环境下P2P泛洪搜索的盲目性和高资源消耗性,提出一个基于路由学习的非结构化P2P搜索算法,建立两个索引表,存储三类节点信息,通过学习关联节点的信息,建立路由表,并定时与路由表内节点交换信息,减少搜索时间,降低搜索开销。理论和仿真实验证明该算法能有效地提高搜索速度,降低搜索开销。     

Zone indexing: Optimizing the balance between searching and indexing in a loosely structured overlay

While structured peer-to-peer systems are efficient in terms of overhead, they still lack the unstructured system’s flexibility and ability to support a wide range of complex queries. This paper examines systems supporting complex queries, deterministic operation, and a fair load distribution between nodes. The aim is to minimize the bandwidth and node load using an optimal level of indexing. The paper first theoretically examines the optimal balance of search and index messages using a search/index space model. This balance is fundamentally determined by the frequency of search requests and index updates. Based on this study, the paper proposes a novel loosely structured peer-to-peer system, Zone indexing, that can balance between index update traffic and search traffic in order to minimize the bandwidth overhead. Nodes are organized into a ring structure. The ring is divided into overlapping zones, within which index updates are distributed. We present an overlay maintenance algorithm with low-cost join and leave operations and a high churn resistance. We further propose a method to dynamically adjust the zone size in order to maintain optimal performance when the network size or user behavior changes. Additionally, we propose a method to limit the search delay by introducing parallel searching. The proposed solutions are evaluated mathematically and the analysis is verified with simulation.     

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.     

Chord2: A two-layer Chord for reducing maintenance overhead via heterogeneity

Empirical studies have shown that participating nodes in peer-to-peer (P2P) systems are not equivalent. Some nodes, known as “super peers”, are more powerful and stable than the others. Such heterogeneity has been taken into account in the design of P2P systems in two ways: by employing super peers to serve as index servers for query, and by routing through super peers to speed up query. In this paper, we use super peers to reduce maintenance cost in Chord—a DHT network which, like other DHT-based systems, is often praised for its guaranteed search feature but has relatively higher maintenance overhead than Gnutella-like unstructured P2P networks.     

主题重叠网络的构造与搜索算法研究

结构化P2P网络虽然具有扩展性良好的数据查找机制,但只支持基于键的准确匹配搜索.为提供更丰富的数据查询能力,本文提出一种基于主题重叠网络的结构化P2P搜索算法--主题重叠网络搜索算法(TONS).其基本思想是在结构化P2P网络之上,将结点按主题组织成分层的重叠网络,使含有相似主题的结点相互链接在一起;利用主题中继结点所具有的全局导航能力,TONS能够基于内容将查询限定在P2P网络的局部范围内,并且通过在重叠网络中随机添加一些长距离链接,使重叠网络具有Small-World特性,改善TONS的搜索性能.实验结果表明,TONS大大提高了搜索的查全率,减少了P2P网络信息搜索时的平均路径距离和平均消息数目.     

A flabellate overlay network for multi-attribute search

Peer-to-peer (P2P) technology provides a popular way of distributing resources, sharing, and locating in a large-scale distributed environment. However, most of the current existing P2P systems only support queries over a single resource attribute, such as file name. The current multiple resource attribute search methods often encounter high maintenance cost and lack of resilience to the highly dynamic environment of P2P networks. In this paper, we propose a Flabellate overlAy Network (FAN), a scalable and structured underlying P2P overlay supporting resource queries over multi-dimensional attributes. In FAN, the resources are mapped into a multi-dimensional Cartesian space based on the consistent hash values of the resource attributes. The mapping space is divided into non-overlapping and continuous subspaces based on the peer’s distance. This paper presents strategies for managing the extended adjacent subspaces, which is crucial to network maintenance and resource search in FAN. The algorithms of a basic resource search and range query over FAN are also presented in this paper. To alleviate the load of the hot nodes, a virtual replica network (VRN) consisting of the nodes with the same replicates is proposed for replicating popular resources adaptively. The queries can be forwarded from the heavily loaded nodes to the lightly loaded ones through VRN. Theoretical analysis and experimental results show that FAN has a higher routing efficiency and lower network maintenance cost over the existing multi-attribute search methods. Also, VRN efficiently balances the network load and reduces the querying delay in FAN while invoking a relatively low overhead.     

基于非结构化的P2P信息检索关键技术研究

如何在缺少集中控制、大规模、分布式的P2P（peer-to-peer）网络中找到并定位信息是所有的P2P共享系统面临的一个难题．现有的P2P信息检索机制存在着种种不足：基于结构化P2P网络的检索效率很高,然而由于构造过于严格,难以在Internet上普及,而且仅能支持粗粒度的文件共享;非结构化P2P网络实现简单,是P2P共享系统的主要实现方式,但是由于搜索的盲目性,其检索效率又普遍低下．建立了一个新的非结构化P2P共享原型系统．该系统利用改进的蚁群算法进行检索路由,使检索总是倾向于有利的方向．同时,有针对性的推荐服务能够减少盲目搜索,提高文件共享水平．仿真实验的结果表明,该系统所采用的信息检索与信息推荐相结合的策略能够有效地提高P2P信息检索的成功率,降低网络负载．     

Combining search and trust models in unstructured peer-to-peer networks

Effectiveness of Peer-to-Peer (P2P) systems highly depends on efficiency and scalability of their search algorithms. Moreover, managing trust is a key issue for wide acceptance of P2P computing. Surprisingly, the majority of the available trust systems ignore the underlying search algorithm and assume it is preexisting. We claim that combining search and trust systems yields significant performance gains in terms of network traffic and query success rate. In this paper, we propose a robust and efficient trust based search framework for unstructured P2P networks. Our framework maintains limited size routing indexes combining search and trust data to guide queries to most reputable nodes. By dynamically selecting reputable nodes as score managers, our scheme tracks the reputation of participating peers. In an alternative approach, we aggregate partial reputation values obtained from reverse query paths to introduce a low overhead method for estimating reputation scores of peers. Through P2P network simulation experiments, we find significant performance gains in using our framework.     

基于节点兴趣和Q-learning的P2P网络搜索机制

将智能手机设备加入基于非结构化P2P网络的资源共享系统中能够满足人们对资源共享的多样化、便利性、高频性、实时性、高效性等要求,但是该系统网络规模的扩张和网络节点互异性的加大,必将导致系统资源搜索效率的降低、冗余信息的剧增以及网络更加不稳定。为了解决这些问题,文中设计了一种改进的基于节点兴趣和Q-learning的资源搜索机制。首先将节点根据兴趣相似度进行兴趣聚类,划分兴趣集,然后根据兴趣集中节点的能力值构建兴趣树,该结构避免了消息环路的产生,极大地降低了冗余信息;在资源搜索中,兴趣树内采用洪泛算法转发消息,兴趣树之间采用基于Q-learning的消息转发机制,不断强化最可能获取目标资源的路径,查询消息优先在这些路径上传播。另外,针对“热点”资源问题,设计了自适应热点资源索引机制,减少了重复路径搜索,进一步减少了冗余消息量;针对节点失效的问题,给出了根节点冗余机制和捎带检测的策略方法,分别解决了根节点失效和普通节点失效导致的兴趣树的不完整性问题,分析表明该方法能够减少消息冗余量。仿真实验结果表明,与GBI-BI算法和Interest CN算法相比,所提搜索算法能够提高命中率,缩短响应时间,减少冗余信息,具有较好的综合性能,最终解决了由于智能手机设备加入P2P网络导致的资源搜索效率下降、网络流量开销大的问题。     

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     

具有社会网络特性的P2P分层搜索机制

无结构P2P网络中基于泛洪法的搜索机制会给系统带来极大的网络负载,结构化P2P网络则需要较大的开销来维护其拓扑结构。针对该问题,给出一种具有社会网络特性的P2P分层搜索机制。根据社会网络的基本原理,将语义相似度高的节点分布在同一个虚拟社区,节点在虚拟社区内能动地建立搜索链接。实验结果证明,该搜索机制能有效地提高P2P网络的资源搜索效率。     

面向非结构化P2P 网络的双向随机漫步搜索机制

为解决目前Random Walk改进算法中过于依赖历史搜索记录而导致动态网络环境下搜索命中率低、网络开销过高和稀有资源的搜索成功率提高不明显等问题,通过分析随机漫步的基本性质和易转向高度数节点的搜索特性,提出了一种双向随机漫步搜索机制——BRWS(bidirectional random walk search),并证明了其能够提高包括稀有资源在内的搜索成功率,抗扰动性强.分别在静态和动态网络环境中,将Random Walk,APS(adaptive probabilistic search),PQR(path-traceable query routing),P2PBSN(peer-to-peer based on social network)和BRWS基于Random Graph、Scale Free网络、Small World网络3种拓扑进行了对比实验.结果表明,BRWS可以以较少的网络搜索代价,极大地提高搜索成功率;并在动态网络环境中,对稀有资源的搜索成功率也有显著提高.所提出的方法可适用于P2P文件分发网络应用中.     

双向主从式Chord资源搜索算法的研究

Chord是一种结构化的P2P网络模型,它具有速度快、无需中心控制、可扩展性强、负载平衡、高容错性能等优点。但是,Chord查找算法为单向查找,当目的节点与当前节点距离较远时,需经多次跳转,增加了路由延迟;Chord中能力较弱的节点来负责系统中大量的查询和下载,以及节点随时加入或离开系统的频繁变迁情况,这样会造成网络查询效率明显下降。改进的算法即双向主从式Chord算法支持双向搜索,并将网络中的节点分为超级节点和普通节点,由评估结果值较高的超级节点组成Chord主环。通过实验证明,改进算法有效地减少了路由跳数,降低了网络延迟。     

基于蚁群算法的非结构化P2P网络资源搜索策略

针对非结构化P2P网络资源搜索算法中冗余消息数过多、搜索效率低等问题,提出一种基于蚁群算法的非结构化P2P网络资源搜索策略,该策略利用蚂蚁信息素的正反馈原理,同时综合考虑邻居节点度和邻居-邻居节点信息,选择下一条邻居节点路径转发查询消息,有效地指导资源搜索路径的生成。实验结果表明,该算法在一定程度上减少了大量的冗余查询消息,提高了资源搜索的成功率,是一种有效的非结构化P2P网络资源搜索策略。     

An advertisement-based peer-to-peer search algorithm

Most of the existing search algorithms for unstructured peer-to-peer (P2P) systems share one common approach: the requesting node sends out a keyword search query and the query message is repeatedly routed and forwarded to other peers in the overlay network. Due to multiple hops involved in query forwarding, the search may result in a long delay before it is answered. Furthermore, some incapable nodes may be overloaded when the query traffic becomes intensive or bursty.     

一种结构化P2P网络拓扑匹配的通用算法

与非结构化P2P网络相比,结构化P2P网络具有良好的可扩展性、鲁棒性。但是结构化P2P覆盖网络是直接建立在逻辑网络之上,没有过多地考虑底层物理网络拓扑结构,导致逻辑拓扑结构与物理拓扑结构严重不匹配。本文提出一种新的协议无关的拓扑匹配算法,将现有的界标节点、自适应匹配算法与IP分配策略相结合构建初始拓扑结构,优化节点交换算法来维护拓扑结构。模拟实验表明,本算法提高了网络的拓扑匹配度,具有更低的通信开销。     

Direction-aware resource discovery in large-scale distributed computing environments

As a system scales up, the peer-to-peer (P2P) approach is attractive to distributed computing environments, such as Grids and Clouds, due to the amount of resources increased. The major issue in large-scale distributed systems is to prevent the phenomenon of a communication bottleneck or a single point of failure. Conventional approaches may not be able to apply directly to such environments due to restricted queries and varied resource characteristics. Alternatively, a fully decentralized resource discovery service based on an unstructured overlay, which relies only on the information of resource attributes and characteristics, may be a feasible solution. One major challenge of such service is to locate desired and suitable resources without the global knowledge of distributed sharing resources. As a consequence, the more nodes the resource discovery service involves, the higher the network overhead incurs. In this paper, we proposed a direction-aware strategy which can alleviate the network traffic among unstructured information systems for distributed resource discovery service. Experimental results have demonstrated that the proposed approach achieves higher success rate at low cost and higher scalability.     

主题驱动的P2P分布式信息搜索机制研究

Peer—to—Peer（P2P）对于分布式文件共享具有很好的前景，但当前的P2P系统仍然缺乏有效的信息搜索机制．本文提出一种主题驱动的P2P信息搜索机制，通过对节点上的文档进行聚类获得全局主题，然后将包含有相似主题的节点组织到一起构成主题覆盖网络．当在P2P网络中进行信息搜索时，根据查询与主题的相关性路由查询，从而改善搜索效率．本文详细阐述了进行主题驱动搜索的索引结构、主题聚类方法、主题覆盖网络的构造与维护算法．在Chord上的模拟实验结果表明，主题驱动的P2P信息搜索机制可以减少信息搜索时的平均网络带宽和平均搜索路径长度，提高搜索的成功率．