AbIx: An Approach to Content-Based Approximate Query Processing in Peer-to-Peer Data Systems

In recent years there has been a significant interest in peer-to-peer （P2P） environments in the community of data management. However, almost all work, so far, is focused on exact query processing in current P2P data systems. The autonomy of peers also is not considered enough. In addition, the system cost is very high because the information publishing method of shared data is based on each document instead of document set. In this paper, abstract indices （AbIx） are presented to implement content-based approximate queries in centralized, distributed and structured P2P data systems. It can be used to search as few peers as possible but get as many returns satisfying users＇ queries as possible on the guarantee of high autonomy of peers. Also, abstract indices have low system cost, can improve the query processing speed, and support very frequent updates and the set information publishing method. In order to verify the effectiveness of abstract indices, a simulator of 10,000 peers, over 3 million documents is made, and several metrics are proposed. The experimental results show that abstract indices work well in various P2P data systems.     

OntoZilla: An ontology-based, semi-structured, and evolutionary peer-to-peer network for information systems and services

We present a system called “OntoZilla”, which combines ontologies and peer-to-peer (P2P) technology, with a vision of improving the information search process and facilitating greater integration as well as interoperability. In OntoZilla, peers supporting the same concept are grouped into the same cluster, and the relationships between clusters are modeled according to the concepts they specialize in. Therefore, a query belonging to a specific concept can be routed to the suitable group of peers in a systematic way, thus supporting efficient concept search. Moreover, since peer relationships are based on peers’ expertises which may change over time, our semi-structured system can flexibly cope with the changing environment as peers evolve.     

基于语义扩展的P2P网络

针对当前P2P系统中多数为媒体文件,而对应描述信息有限的问题,提出了一个通过Web信息挖掘来扩展语义的算法.同时提出了一个基于语义跳表的多层环网络结构,帮助用户进行相关内容推荐.实验表明,用本文所提出的方法,在消息量很小的情况下,与传统的基于中心服务器的检索精度很相近,具有实用价值.     

HAPS: Supporting Effective and Efficient Full-Text P2P Search with Peer Dynamics

Recently, peer-to-peer (P2P) search technique has become popular in the Web as an alternative to centralized search due to its high scalability and low deployment-cost. However, P2P search systems are known to suffer from the problem of peer dynamics, such as frequent node join/leave and document changes, which cause serious performance degradation. This paper presents the architecture of a P2P search system that supports full-text search in an overlay network with peer dynamics. This architecture, namely HAPS, consists of two layers of peers. The upper layer is a DHT (distributed hash table) network interconnected by some super peers (which we refer to as hubs). Each hub maintains distributed data structures called search directories, which could be used to guide the query and to control the search cost. The bottom layer consists of clusters of ordinary peers (called providers), which can receive queries and return relevant results. Extensive experimental results indicate that HAPS can perform searches effectively and efficiently. In addition, the performance comparison illustrates that HAPS outperforms a flat structured system and a hierarchical unstructured system in the environment with peer dynamics.     

Free riding-aware forwarding in Content-Addressable Networks

Research on P2P data structures has tacitly assumed that peers readily participate in the work, i.e., are cooperative. But such participation is voluntary, and free riding is the dominant strategy. This article describes a protocol that renders free riding unattractive, for one particular P2P data structure. The protocol is based on feedback that adjacent nodes exchange. This induces transitive logical networks of nodes that rule out uncooperative peers. The protocol uses proofs of work to deter free riding. To show that cooperative behavior dominates, we have come up with a cost model that quantifies the overall cost of peers, depending on their degree of cooperativeness and many other parameters. The cost model tells us that we can achieve a good discrimination against peers that are less cooperative, with moderate additional cost for cooperative peers. Extensive experiments confirm the validity of our approach.     

Ad-hoc limited scale-free models for unstructured peer-to-peer networks

Several protocol efficiency metrics (e.g., scalability, search success rate, routing reachability and stability) depend on the capability of preserving structure even over the churn caused by the ad-hoc nodes joining or leaving the network. Preserving the structure becomes more prohibitive due to the distributed and potentially uncooperative nature of such networks, as in the peer-to-peer (P2P) networks. Thus, most practical solutions involve unstructured approaches while attempting to maintain the structure at various levels of protocol stack. The primary focus of this paper is to investigate construction and maintenance of scale-free topologies in a distributed manner without requiring global topology information at the time when nodes join or leave. We consider the uncooperative behavior of peers by limiting the number of neighbors to a pre-defined hard cutoff value (i.e., no peer is a major hub), and the ad-hoc behavior of peers by rewiring the neighbors of nodes leaving the network. We also investigate the effect of these hard cutoffs and rewiring of ad-hoc nodes on the P2P search efficiency.     

Linking identical neighborly partitions for efficient high-dimensional similarity search in unstructured peer-to-peer systems

Peer-to-Peer (P2P) computing has recently attracted a great deal of research attention. In a P2P system, a large number of nodes can potentially be pooled together to share their resources, information, and services. However, existing unstructured P2P systems lack support for content-based search over data objects which are generally represented by high-dimensional feature vectors. In this paper, we propose an efficient and effective indexing mechanism to facilitate high-dimensional similarity query in unstructured P2P systems, named Linking Identical Neighborly Partitions (LINP), which combines both space partitioning technique and routing index technique. With the aid of LINP, each peer can not only process similarity query efficiently over its local data, but also can route the query to the promising peers which may contain the desired data. In the proposed scheme, each peer summarizes its local data using the space partitioning technique, and exchanges the summarized index with its neighboring peers to construct routing indices. Furthermore, to improve the system performance with peer updates, we propose an extension of the LINP, named LINP⁺, where each peer can reconfigure its neighboring peers to keep relevant peers nearby. The performance of our proposed scheme is evaluated over both synthetic and real-life high-dimensional datasets, and experimental results show the superiority of our proposed scheme.     

RNP2P——一种基于复本网络的非结构化P2P系统

根据非结构化P2P系统中资源分布的特点，提出一种基于复本网络的非结构化P2P系统，即RNP2P。通过查询反馈、主动探测和反向探测三种方式协调复本节点之间的相互感知，构建数据结构存储每种资源的其他复本节点信息，针对每种资源均构成一个复本网络。基于这种复本管理机制，RNP2P平均能够以命中3~5个复本的消息开销获得100%的命中率，其他查询方法均可以和RNP2P有效结合。模拟结果表明RNP2P的查询性能远远高于其他查询方案。当采用k-随机游走进行查询，RNP2P的消息开销为普通非结构化P2P中k-随机游走查询的5%,并且远远低于泛洪查询,RNP2P的查询时延也相应降低。     

一种基于本地聚类的P2P资源查找算法*

资源检索是P2P系统研究的热点之一,非结构化P2P资源查找普遍采用泛洪机制。随着查询请求的增加,消息数量呈指数增长,网络拥塞和带宽浪费严重,查询效率得不到保障。针对这一问题,给出了一种基于本地聚类的非结构化P2P资源查找算法。通过对资源特征向量的本地Kmeans聚类和相似链接的建立,有效地提高了资源检索效率,避免了查询消息的扩散对网络带宽的浪费。实验表明,该方法能有效缩短资源的平均检索长度,提高查找成功率。     

P2P搜索新技术：智能搜索技术

在P2P网络中正确高效地搜索信息十分重要,然而现有的搜索技术并不能很好地满足用户要求。文中提出了由历史记录、相似度和站点优先级3部分组成的新的信息搜索技术———智能搜索技术。在智能搜索技术中每个站点都各自记录以往搜索的历史记录,以此结合搜索要求计算出最可能拥有所需结果的站点,最后仅向这些站点发送搜索请求。通过在中间件上的测试,比较了不同信息搜索技术的性能,智能搜索技术能在使用较少搜索消息的情况下得到较高的搜索成功率。     

基于物理拓扑的双向搜索Chord路由

Chord模型未充分利用逆时针上的路由信息,并且未考虑实际网络拓扑结构,使P2P系统存在高延迟、低效率的问题。针对该问题,充分利用节点路由表信息和节点在物理网络上的邻近性,并用超级节点存储最近同一簇内的查询结果,提出路由算法TBChord。模拟实验结果表明,该算法在路径长度、访问延迟方面的性能较Chord有一定的提高。     

用于对等全文检索的安全覆盖网

对等全文检索充分利用对等节点的资源实现检索,其关键是控制检索请求传播的节点范围。结合全文检索的安全要求提出安全覆盖网(Secure Overlay Network, SON),按安全级支配关系将对等节点组成网络。SON中节点发起的检索请求只能向下传递到安全级受其支配的节点,涉及节点是整个覆盖网中节点的子集,检索结果也是符合安全要求的。给出了SON的定义并分析了其性质,介绍了基于SON的对等全文检索原理和算法并分析了其安全性。实验表明,基于安全覆盖网的对等全文检索具有良好的检索效率。     

基于一簇多超级节点的混合P2P网络模型

超级节点为其他节点提供各种服务,包括信息的收集与检索、数据传送及穿越NAT等,但P2P系统的高动态性为设计一个有超级节点的混合P2P网络带来困难。该文设计一种均衡、健壮、具有自适应能力的混合P2P网络模型,研究超级节点的负载均衡、健壮性及自我调整策略,提出新策略以解决超级节点失效时带来的问题。     

P2P环境中基于信任度的服务路由系统的研究*

随着网络的飞速发展,基于P2P结构的分布式应用越来越多。P2P系统节点之间的资源高度共享,节点之间的信息搜索和交换往往需要第三方节点进行信息中转,这为信息窃取和信息窜改类型的网络攻击带来了便利。为了提高P2P应用的可用性,提出了在P2P环境下一种新的以可信度为标准的服务路由系统的模型,阐述了模型的设计思想,并详细介绍了其实现机制。对仿真系统进行了性能测试,并对测试结果进行了分析。该模型对于信息窜改、信息窃听及路由功能失效等类型的恶意攻击有较好的抑制作用。     

ReMIS：面向再制造信息共享的P2P网络模型*

针对当前再制造生产的特点和实际需求,设计了一种面向再制造信息共享的P2P网络模型ReMIS。为适应再制造网络的高度动态性,模型采用基于自然簇和主题簇构成的两层混合结构,上层由主题对等体组成结构化的主题网络,下层由普通对等体组成P2P网络。ReMIS采用基于主题簇的资源分类和检索机制,能够确保在处理海量再制造资源信息的检索请求时具有较高的路由性能和查询性能,并能减少再制造生产中的词汇语义冲突;同时,发布/订阅机制的应用使再制造企业获取实时信息成为可能。相关性能分析表明,ReMIS网络是高效可行的,可以适应再     

P2P网络中基于文件路由模型搜索方法的改进

资源搜索和共享是P2P网络中重要的应用。针对当前P2P网络中现有共享资源搜索方法还存在诸多不足之处的问题,提出了一种基于文件路由模型改进的搜索方法。该搜索方法选取多个稳定对等体共同作为共享信息的载体,在利用哈希函数分配共享信息及其索引的基础上,提出了一种新的数据结构来记录所有存储了同一共享信息的稳定对等体信息,增强了系统的健壮性,同时均衡分配共享信息载体的负荷,合理利用网络带宽,使P2P网络在资源搜索和共享方面得到了一些改善。     

一种基于节点可选度的P2P点播流媒体数据调度算法

当前的P2P(Peer-to-Peer)点播流媒体系统中数据调度算法未能充分利用每个用户节点自身的特性.在分析典型数据调度算法基础上提出一种基于节点可选度的数据调度算法(SSP算法).该算法一方面在调度下载数据块时综合考虑了邻居节点带宽能力及其所拥有的数据信息.另一方面对服务节点的请求处理过程进行了优化.SSP算法有利于提高用户节点播放视频的连续性,降低流媒体服务器的负载压力,从而改善P2P点播流媒体系统的整体服务质量.仿真结果和实际应用表明算法性能良好,适用于用户节点能力差异较大的P2P点播流媒体环境.     

P2P系统的资源质量评价策略研究

P2P系统中,请求资源的节点发出搜索请求,并从提供资源的节点接收资源信息列表。而目前实际应用的许多P2P系统都忽略了资源质量的信息。请求资源的节点无从获知资源列表中资源的质量信息,导致用户往往对众多相似的资源感到无所适从,常常需要作多次尝试才找到满意的资源)。文章根据P2P系统的特征,结合传统Web搜索引擎和现实中超市服务的模型的优点,提出了一种资源质量评价策略,较好地解决了上述问题。     

面向系统吞吐率最大化的P2P自适应覆盖网络

P2P系统的本质任务在于提高资源利用率和系统吞吐量,满足更多用户的数据请求。在无结构P2P中,通常分配高权重节点以较多连接,使之收到并命中更多查询,以提高搜索成功率。但高搜索成功率本身却未必能够提高系统吞吐量,因为受带宽因素影响,高权重节点的负载较重,造成服务可用性降低。提出了一种覆盖网络优化方案,即根据带宽负载和存储权重自适应性调整节点连接度,优化覆盖网络结构,提高系统吞吐量。模拟实验数据表明,基于带宽和搜索成功率的覆盖网络优化方案可以以很小代价提高系统吞吐量,当文件体积较小时提高比例可高达22%。     

移动环境中一种基于Hash的P2P覆盖网

目前提出的大多数基于哈希（hash—based）的P2P网络都集中于固定的对等节点。当节点移动到网络中一个新的位置时,这种结构在消息传递等方面的效率就会下降。文章提出一种移动环境中的基于哈希的P2P覆盖网（Hash—based P2P Overlay in Mobile Environment,H—MP2P）,允许节点在网络中自由移动。一个节点可通过P2P网络广播其位置信息,其他节点通过网络可以获知该节点的移动信息并进行定位。通过理论分析和实验可知H—MP2P在扩展性、可靠性和效率方面都可以取得较好的结果,可以很好的应用在移动环境中。