一种新型结构化P2P网络路由模型的构建及其支撑技术研究
|
摘要
为提高边缘网对流媒体业务的的承载服务能力,满足流媒体业务可控制、可管理和可运营的综合要求,国家863计划高性能宽带信息网(3Tnet)启动了重大子项课题——“大规模接入汇聚路由器(ACR)系统性能和关键技术研究”。ACR对端口的可控制、可管理的特性以及带宽预留的功能,使得ACR可以实现对用户流量的监控、管理以及计费。作为“十一五”国家高科技发展支撑计划“中国互动新媒体网络与新业务科技工程”中的重要设备,ACR必须能够支持当前互联网应用最广泛的对等网络(P2P)技术,目标就是对P2P流量进行有效管理与监控,解决P2P的带宽高占用率以及计费困难等问题。而此项工作的前提就是要深入研究当前P2P技术及其应用的关键技术及思想。故针对ACR的研发需求,本文以结构化P2P网络路由模型为研究课题,依托ACR项目开展研究工作。
本文结合当前互联网以及P2P网络的特性,提出一种基于主题和物理位置相近原则新型结构化P2P网络路由模型,并研究影响结构化P2P网络路由性能的拓扑一致性问题、hotspot]问题以及异构节点的负载均衡问题在新模型下的解决方案,该方案可以推广应用到其它结构化P2P网络。本文主要包括如下几个方面的工作：
1、分析了当前P2P网络路由模型的两大分支,即非结构化P2P网络路由模型以及结构化P2P网络路由模型。由于结构化P2P网络路由模型定位算法效率高,可扩展性、可靠性和可维护性好等特点,成为未来P2P网络发展的方向。通过对当前流行的结构化P2P网络几大拓扑构成的分析,总结出结构化P2P网络路由模型面临拓扑一致性、hotspot以及负载均衡等方面的问题,这些问题严重影响了结构化P2P网络的路由性能。通过研究还发现,当前结构化P2P网络构建过程中存在由于没有充分考虑当前互联网的特征而导致无法优化实际运作过程中的路由性能的问题。
2、基于Internet网络架构以及节点兴趣区域化分布的特性构建基于主题和物理位置相近原则的新型结构化P2P网络路由模型(TPPH)。将兴趣相近物理距离也相近的节点组织在一起,提高节点近距离定位资源的成功率,同时降低节点定位资源的延迟。TPPH结构将相同主题的节点组织在一起构成主题区域,并在同一个主题区域内部将物理位置相近的节点构成组群。这种覆盖网络构建方式符合拓扑一致性原则,基于DHT机制组织构建的系统、主题、组群三级结构能够有效提高网络的查询性能。创新性的提出了标识符分段表示的方法,该方法可以简单高效的对系统内节点按照所包含资源情况归入对应的主题,并且可以将发布的资源也按照其归属主题存储在对应主题区域内。这种基于主题的标识符分段表示的方法是结构化P2P网络模型TPPH构建主题区域的基础。通过主题区域的构建,加速了系统内资源的查询过程,提高了系统的性能。
3、基于拓扑一致性问题的研究,根据覆盖网络层路由引发实际物理网络路由产生物理链路重复使用的问题,以实际网络路出为基本出发点,提出检测并降低重复链路使用的拓扑一致性解决方案(DDL),解决TPPH结构拓扑一致性问题。通过检测三点间路由经历的实际物理链路的重复利用情况,在满足一定条件下,向源节点发送重定向报文,建立源和目的节点之间的直接连接,降低路由过程经历的实际物理链路数目,减少骨干网络流量,节约系统带宽,提高路由性能。对重复链路的探测并通过修改覆盖网络层路由的方法可以做到一定程度上的拓扑匹配。在TPPH结构中利用DDL机制,获取临近节点信息,并将邻近节点在覆盖网络层面组织在一起,实现TPPH结构中主题内组群划分以及建立主题间超链接。
4、基于物理位置相近的节点感兴趣文件内容相似性也偏大的性质,针对query hotspot问题,基于TPPH结构,以组群为单位,提出了分布式资源发布及搜索机制。考虑到节点对资源的索取呈现地域趋势,将组群内节点查询过的资源在本组群范围内进行资源发布,在组群内其它节点发起对同一资源的查询时可以在本组群内得到响应,从而降低组群内其它节点对该资源查询的响应时间。基于DHT的组群构成方式使得节点可以在本组群内进行资源的高效查找,提高了系统的查询性能。同时该机制对资源的存储进行了分散,降低了系统范围内资源放置点唯一性导致的hotspot问题的发生。
5、针对TPPH结构中节点的异构性问题,提出了考虑节点异构性的结构化P2P网络负载均衡方案。通过资源分片降低大资源对单一节点的占用,解决单点失效问题。将资源分片通过DHT机制放置在根据系统内定义的HASH函数序列顺序计算得到的对应的节点上,可以有效的提高资源分片查找的效率；提出了异构网络负载均衡的衡量指标——负载平滑度,并在资源分片及放置策略基础上,以资源的节点标识符向量为范围,提出了基于负载平滑度的负载转移方案,带动整个系统逐步达到负载均衡状态。
To enhance the carrying capacity of edge network and to meet the controllable, manageable and operational requirements of streaming media traffic, "High Performance Broadband Information Networks" (3Tnet) of the National High-Tech Research and Development Program of China (863 Program) launches the project of "System Performance and Key Technology Researches on the Access and Convergence Router (ACR)". ACR can control the ports and reserve the bandwidth for each port, which makes it possible to monitor the user traffic. As the core equipment of "China Interactive New Media Network and New Business Projects" which belongs to "11th Five-Year Plan" National High-Tech Development Program, ACR must be able to support P2P technology which is used most extensively on the internet. It aims at effectively managing and monitoring the P2P traffic and solving the P2P high bandwidth occupancy and billing problems. And the premise of this work is to study in depth the current P2P technology and its applications. So against the development needs of ACR, this paper studied on structured P2P routing network based on ACR project.
Considering the features of internet and P2P network, this paper proposed a structured P2P network routing model based on topic and physical proximity principle. It also studied the solutions of topology-aware, hotspot and load balancing which affect the routing performance of structured P2P network in the new model. This program can be applied to other structured P2P network. This paper includes the following aspects:
1、To analyze the two major branches of P2P network routing model, that are unstructured and structured P2P network routing model. As structured P2P network routing model is with efficiency, scalability, reliability and maintainability features, it is becoming the future direction of the development of P2P networks. Based on the analysis of the popular structured P2P network topologies, it is concluded that structured P2P network routing topology model faces topology-aware, hotspot and load balancing problems, which affect the routing performance of structured P2P network deeply. There also exists a problem that the absence of full consideration of internet characteristics during the construction of structured P2P networks leads to incapable of optimizing routing performance in the process of routing.
2、A new structured P2P network routing model based on topic and physical proximity principle (TPPH) was constructed considering the internet framework and regional distribution of nodes' interests. To organize nodes with similar interests and short physical distances together to enhance the success rate of searching within short distance and deduce the delay. TPPH organized nodes with same topic together into a topic area and made physically adjacent nodes within a topic area form into a cluster. The construction of overlay network is consistent with the topology-aware principle. Three levels of overlay network, that is system, topic and cluster, which are organized based on DHT, can improve network performance effectively. An innovative sub-identifier proposal was presented. It can classify the nodes according to its resources simply, and also store the resources to the corresponding topic area. The sub-identifier proposal is the basis of topic area construction of TPPH. Construction of the topic area accelerates the process of searching and improves routing performance.
3、Based on researches on topology-aware, considering the duplicate physical links triggered by overlay routing, detect and decrease links overlapped (DDL) solution was proposed. It aimed at resolving topology-aware problem of TPPH. By detecting the overlapped physical links during routing among three nodes, redirect message was sent to the source when needed, thus established a direct link between the source and the destination. DDL can decrease the actual physical links traversed and reduce backbone network traffic, thus save system bandwidth and improve routing performance. The detection of duplicate links and modification of overlay routing can make overlay network and physical network topology-aware. TPPH connected adjacent nodes into cluster or with hyperlinks from the detection information.
4、Based on the feature that adjacent nodes have similar interests, in view of query hotspot issues, distributed resource publishing and searching mechanism was proposed on the basis of TPPH structure. Considering the regional distribution of nodes'interests, resources which had been searched by a node in cluster were republished within the cluster, therefore when the other node in this cluster searched for the same resource, it will be answered within the cluster, thus the response time is decreased. The cluster was constructed according to DHT principle which makes it possible for nodes to search efficiently within the cluster. At the same time, this mechanism decentralized the storage of resources and reduced the possibility of hotspot issues deduced by the single resource storage point in system-wide area.
5、Against the problem of heterogeneous nodes in TPPH structure, a load balancing mechanism considering the heterogeneous nodes for structured P2P network was proposed. Resource fragmenting can reduce the occupation of large resource to single node, thus resolve the single failure problem. Resource fragments were placed on the corresponding nodes according to DHT principle which were calculated from a sequence of HASH functions defined in system. A load balancing measure indicator of heterogeneous network—load smoothness was brought forward. Based on resource fragment and placement strategy, within the scope of node identifier vector, we proposed a load transfer program to lead the entire system to load balancing state step by step.
本文结合当前互联网以及P2P网络的特性,提出一种基于主题和物理位置相近原则新型结构化P2P网络路由模型,并研究影响结构化P2P网络路由性能的拓扑一致性问题、hotspot]问题以及异构节点的负载均衡问题在新模型下的解决方案,该方案可以推广应用到其它结构化P2P网络。本文主要包括如下几个方面的工作：
1、分析了当前P2P网络路由模型的两大分支,即非结构化P2P网络路由模型以及结构化P2P网络路由模型。由于结构化P2P网络路由模型定位算法效率高,可扩展性、可靠性和可维护性好等特点,成为未来P2P网络发展的方向。通过对当前流行的结构化P2P网络几大拓扑构成的分析,总结出结构化P2P网络路由模型面临拓扑一致性、hotspot以及负载均衡等方面的问题,这些问题严重影响了结构化P2P网络的路由性能。通过研究还发现,当前结构化P2P网络构建过程中存在由于没有充分考虑当前互联网的特征而导致无法优化实际运作过程中的路由性能的问题。
2、基于Internet网络架构以及节点兴趣区域化分布的特性构建基于主题和物理位置相近原则的新型结构化P2P网络路由模型(TPPH)。将兴趣相近物理距离也相近的节点组织在一起,提高节点近距离定位资源的成功率,同时降低节点定位资源的延迟。TPPH结构将相同主题的节点组织在一起构成主题区域,并在同一个主题区域内部将物理位置相近的节点构成组群。这种覆盖网络构建方式符合拓扑一致性原则,基于DHT机制组织构建的系统、主题、组群三级结构能够有效提高网络的查询性能。创新性的提出了标识符分段表示的方法,该方法可以简单高效的对系统内节点按照所包含资源情况归入对应的主题,并且可以将发布的资源也按照其归属主题存储在对应主题区域内。这种基于主题的标识符分段表示的方法是结构化P2P网络模型TPPH构建主题区域的基础。通过主题区域的构建,加速了系统内资源的查询过程,提高了系统的性能。
3、基于拓扑一致性问题的研究,根据覆盖网络层路由引发实际物理网络路由产生物理链路重复使用的问题,以实际网络路出为基本出发点,提出检测并降低重复链路使用的拓扑一致性解决方案(DDL),解决TPPH结构拓扑一致性问题。通过检测三点间路由经历的实际物理链路的重复利用情况,在满足一定条件下,向源节点发送重定向报文,建立源和目的节点之间的直接连接,降低路由过程经历的实际物理链路数目,减少骨干网络流量,节约系统带宽,提高路由性能。对重复链路的探测并通过修改覆盖网络层路由的方法可以做到一定程度上的拓扑匹配。在TPPH结构中利用DDL机制,获取临近节点信息,并将邻近节点在覆盖网络层面组织在一起,实现TPPH结构中主题内组群划分以及建立主题间超链接。
4、基于物理位置相近的节点感兴趣文件内容相似性也偏大的性质,针对query hotspot问题,基于TPPH结构,以组群为单位,提出了分布式资源发布及搜索机制。考虑到节点对资源的索取呈现地域趋势,将组群内节点查询过的资源在本组群范围内进行资源发布,在组群内其它节点发起对同一资源的查询时可以在本组群内得到响应,从而降低组群内其它节点对该资源查询的响应时间。基于DHT的组群构成方式使得节点可以在本组群内进行资源的高效查找,提高了系统的查询性能。同时该机制对资源的存储进行了分散,降低了系统范围内资源放置点唯一性导致的hotspot问题的发生。
5、针对TPPH结构中节点的异构性问题,提出了考虑节点异构性的结构化P2P网络负载均衡方案。通过资源分片降低大资源对单一节点的占用,解决单点失效问题。将资源分片通过DHT机制放置在根据系统内定义的HASH函数序列顺序计算得到的对应的节点上,可以有效的提高资源分片查找的效率；提出了异构网络负载均衡的衡量指标——负载平滑度,并在资源分片及放置策略基础上,以资源的节点标识符向量为范围,提出了基于负载平滑度的负载转移方案,带动整个系统逐步达到负载均衡状态。
To enhance the carrying capacity of edge network and to meet the controllable, manageable and operational requirements of streaming media traffic, "High Performance Broadband Information Networks" (3Tnet) of the National High-Tech Research and Development Program of China (863 Program) launches the project of "System Performance and Key Technology Researches on the Access and Convergence Router (ACR)". ACR can control the ports and reserve the bandwidth for each port, which makes it possible to monitor the user traffic. As the core equipment of "China Interactive New Media Network and New Business Projects" which belongs to "11th Five-Year Plan" National High-Tech Development Program, ACR must be able to support P2P technology which is used most extensively on the internet. It aims at effectively managing and monitoring the P2P traffic and solving the P2P high bandwidth occupancy and billing problems. And the premise of this work is to study in depth the current P2P technology and its applications. So against the development needs of ACR, this paper studied on structured P2P routing network based on ACR project.
Considering the features of internet and P2P network, this paper proposed a structured P2P network routing model based on topic and physical proximity principle. It also studied the solutions of topology-aware, hotspot and load balancing which affect the routing performance of structured P2P network in the new model. This program can be applied to other structured P2P network. This paper includes the following aspects:
1、To analyze the two major branches of P2P network routing model, that are unstructured and structured P2P network routing model. As structured P2P network routing model is with efficiency, scalability, reliability and maintainability features, it is becoming the future direction of the development of P2P networks. Based on the analysis of the popular structured P2P network topologies, it is concluded that structured P2P network routing topology model faces topology-aware, hotspot and load balancing problems, which affect the routing performance of structured P2P network deeply. There also exists a problem that the absence of full consideration of internet characteristics during the construction of structured P2P networks leads to incapable of optimizing routing performance in the process of routing.
2、A new structured P2P network routing model based on topic and physical proximity principle (TPPH) was constructed considering the internet framework and regional distribution of nodes' interests. To organize nodes with similar interests and short physical distances together to enhance the success rate of searching within short distance and deduce the delay. TPPH organized nodes with same topic together into a topic area and made physically adjacent nodes within a topic area form into a cluster. The construction of overlay network is consistent with the topology-aware principle. Three levels of overlay network, that is system, topic and cluster, which are organized based on DHT, can improve network performance effectively. An innovative sub-identifier proposal was presented. It can classify the nodes according to its resources simply, and also store the resources to the corresponding topic area. The sub-identifier proposal is the basis of topic area construction of TPPH. Construction of the topic area accelerates the process of searching and improves routing performance.
3、Based on researches on topology-aware, considering the duplicate physical links triggered by overlay routing, detect and decrease links overlapped (DDL) solution was proposed. It aimed at resolving topology-aware problem of TPPH. By detecting the overlapped physical links during routing among three nodes, redirect message was sent to the source when needed, thus established a direct link between the source and the destination. DDL can decrease the actual physical links traversed and reduce backbone network traffic, thus save system bandwidth and improve routing performance. The detection of duplicate links and modification of overlay routing can make overlay network and physical network topology-aware. TPPH connected adjacent nodes into cluster or with hyperlinks from the detection information.
4、Based on the feature that adjacent nodes have similar interests, in view of query hotspot issues, distributed resource publishing and searching mechanism was proposed on the basis of TPPH structure. Considering the regional distribution of nodes'interests, resources which had been searched by a node in cluster were republished within the cluster, therefore when the other node in this cluster searched for the same resource, it will be answered within the cluster, thus the response time is decreased. The cluster was constructed according to DHT principle which makes it possible for nodes to search efficiently within the cluster. At the same time, this mechanism decentralized the storage of resources and reduced the possibility of hotspot issues deduced by the single resource storage point in system-wide area.
5、Against the problem of heterogeneous nodes in TPPH structure, a load balancing mechanism considering the heterogeneous nodes for structured P2P network was proposed. Resource fragmenting can reduce the occupation of large resource to single node, thus resolve the single failure problem. Resource fragments were placed on the corresponding nodes according to DHT principle which were calculated from a sequence of HASH functions defined in system. A load balancing measure indicator of heterogeneous network—load smoothness was brought forward. Based on resource fragment and placement strategy, within the scope of node identifier vector, we proposed a load transfer program to lead the entire system to load balancing state step by step.
引文
[1]中国网管联盟.宽带网络流媒体技术的概念和应用[EB/OL].2007-9-30, http.// www.linuxpk.com/34830.html.
[2]动网论坛.构建可扩展宽带流媒体应用支撑环境[EB/OL].2006-4-18, http://www. dvbbs.net/tech/network/2006041844577.asp.
[3]新华网.宽带流媒体的应用时机成熟了吗?[EB/OL].2004-10-21,http://news. xinhuanet.com/newmedia/2004-10/21/content 2120264.htm.
[4]科技部863计划联合办公室.高性能宽带信息网(3Tnet)专项课题指南[EB/OL]. 2004-06-01,http://www.863.org.cn/863_105/applyguide/guide_infotech/200406010039 .html.
[5]邬江兴.中国高性能宽带信息网(3TNet)综述[EB/OL].2006-01-24, http://www. c114.net/ZHANHUI/863/jx.htm.
[6]汪斌强,邬江兴.基于IPv6的大规模接入汇聚路由器的设想和实现[J].电信科学,2006,22(1)：5-9.
[7]风行咨询网.P2P流量占国内总带宽过半,宽带资源过于紧张[EB/OL].2007-06-06, http://www.fengnews.com/article/2007/0606/news_5937.html.
[8]丛亮.5%收入占95%带宽,BT该管管了[EB/OL].2007-05-13,http://congliangbupt. blog.sohu.com/45833212.html.
[9]耶兰特.带宽不足不完全是P2P的问题[EB/OL].2007-09-26,http://www.ppcn.net/ n4208c74.aspx.
[10]M.Panti, L. Penserini.A P2P Approach to Land Warriors Coordination[C].In: International Symp.on Collaborative Technologies and Systems in conjunction with the 2003 Western Multi Conferences, Orlando, Florida, Kluwer Academic Press,2003.1:109-117.
[11]D.S Milojicic, V. Kalogeraki. Peer-to-Peer Computing[R]. HP Labs, Palo Alto. Tech Report:HPL-2002-57,2002.
[12]罗杰文Peer to Peer(P2P)综述[R].中科院计算技术研究所.2005-11-3.
[13]Jordan Ritter. Why Gnutella Can't Scale [EB/OL]. http://www.darkridge.com/～jpr5/doc/gnutella.html.
[14]The Gnutella Homepage [EB/OL].2001, http://www.gnutella.com.
[15]The Napster Homepage [EB/OL].2003-2007, http://free.napster.com/.
[16]C—NET NEWS. Napster among fastest-growing Net technologies [EB/OL]. October 2000, http://news.com.com/2100-1023-246648.html.
[17]Overnet/edonkey2000. [EB/OL].2000-2007, http://www.zeropaid.com/edonkey/
[18]BitTorrent C Library [EB/OL].2007,http://sourceforge.net/projects/libbt.
[19]Python Implementation of the BitTorrent Package [EB/OL].2001-2007, http://bitconjurer.org/BitTorrent/
[20]Instant Messenger-AIM [EB/OL].2007, http://www.aim.com/.
[21]Jabber Homepage [EB/OL].1999-2005, http://www.jabber.org/.
[22]Farsite Homepage [EB/OL].2007, http://research.microsoft.com/sn/Farsite/.
[23]OceanStore Homepage [EB/OL].2005-11-30, http://oceanstore.cs.berkeley.edu/.
[24]Infrasearch Homepage [EB/OL].2007, http://www.infrasearch.com/.
[25]Buyya, Rajkumar, Steve Chapin, and David DiNucci.2000. Architectural Models for Resource Management in the Grid[C]. In First IEEE/ACM International Workshop on Grid Computing (GRID 2000), Bangalore, India, December 2000.
[26]IBM GRID Computing Project [EB/OL].2007, http://www.research.ibm.com/autonomic/.
[27]D.P. Anderson. SETI@home:An Experiment in Public Resource Computing[C]. Communications of the ACM,2002, Vol.45, No.11:56-61.
[28]Groove Homepage [EB/OL].2007, http://www.groove.net/.
[29]Billpoint Homepage [EB/OL].1999-2007, https://www.billpoint.com/.
[30]Lightshare Homepage [EB/OL].2007, https://www.lightshare.com/.
[31]Free Haven Homepage [EB/OL].:2004-12-1, http://www.freehaven.net/.
[32]T. Chujo. Modeling Internet Traffic for Network Planning and Provisioning[C]. In:7th Asia-Pacific Network Operations and Management Symposium (APNOMS 2003). October 2003.
[33]C. Fraleigh, S. Moon, etc. Packet-level Traffic Measurements from the Sprint IP Backbone[C]. IEEE Network Magazine, Vol.17, No.6. November 2003.
[34]Pouwelse J A, Garbacki P, Epema D H J, et al. A measurement study of the bittorrent peer-to-peer file-sharing system[R]. Technical Report PDS-2004-003, April 2004.
[35]Sen, S., Wong, J.Analyzing peer-to-peer traffic across large networks [J]. Transactions on Networking. Volume 12, ACM Press 2004:219-232.
[36]Linux reviews.Peer to peer network traffic may account for up to 85% of Internets bandwidth usage [EB/OL].2004, http://linuxreviews.org/news/2004/11/05_p2p/.
[37]The Skype Homepage [EB/OL].2007, http://www.skype.com.
[38]KaZaA website [EB/OL].2002, http://www.kazaa.com/.
[39]Munindar P. Singh. Peering at Peer-to-Peer Computing [J]. IEEE Internet Computing, Vol.5, No.1, pp.4-5, January/February 2001.
[40]Flooding algorithm [EB/OL].2007, http://en.wikipedia.org/wiki/Flooding_algorithm.
[41]Random walk [EB/OL].2007, http://en.wikipedia.org/wiki/Random_walk.
[42]Distributed hash table [EB/OL].2007, http://en.wikipedia.org/wiki/Distributed_hash table.
[43]K.Kant, R.Iyer, V.Tewari. A Framework for Classifying Peer-to-Peer Technologies[C]. In:2nd IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID'02), IEEE Society Press,2002.5:368-376.
[44]A. Agrawal, H.Casanova. Clustering Hosts in P2P and Global Computing Platforms[C]. In:Third International Workshop on Global and Peer-to-Peer Computing on Large Scale Distributed Systems, ACM Press, Tokyo,2003.5:367-343.
[45]Lua EK, Crowcroft J, Pias M, Sharma R, Lim S. A survey and comparison of peer-to-peer overlay network schemes [J]. Journal of. IEEE Communications Survey and Tutorial,2005.7:1-2.
[46]B. Y. Zhao, J. D. Kubiatowicz, and A. D. Joseph. Tapestry:An Infrastructure for Fault-Resilient Wide-area Location and Routing[R]. Technical Rept: UCB//CSD-011141, U. C. Berkeley,2001.4.
[47]Peter Druschel, Anthony Rowstron. Pastry:Scalable, distributed object location and routing for large-scale peer-to-peer systems[C]. In:IFIP/ACM International Conference on Distributed Systems Platforms, Kluwer Academic Press, Nov 2001: 329-350.
[48]I. Stoica, R. Morris, D. Karger, M. F. Kaashoek, and H. Balakrishnan. Chord:A scalable peer-to-peer lookup service for Internet applications[R]. Technical Rept:TR-819, MIT,2001.3
[49]S. Ratnasamy, Paul Francis, Mark Handley, Richard Karp, Scott Schenker. A Scalable Content-Addressable Network[C]. In:Proceeding of ACM SIGCOMM, ACM Press, New York,2001.8:161-172.
[50]Shansi Ren, Lei Guo, Song Jiang, et al. SAT-match:a self-adaptive topology matching method to achieve low lookup latency in structured P2P overlay networks[C]. In: Proceedings of the 18th International Parallel and Distributed Processing Symposium (IPDPS'04), Santa Fe, New Mexico, USA, April 2003.
[51]Consistent hashing [EB/OL].2007, http://en.wikipedia.org/wiki/Consistent_hashing.
[52]C.Greg Plaxton, Rajmohan Rajaraman, and Andrea W. Richa. Accessing nearby copies of replicated objects in a distributed environment [C]. In:Proceedings of ACM SPAA. ACM, June 1997.
[53]H.J. Siegel. Interconnection networks for SIMD machines [J]. Computer 12(6):57-65, 1979.
[54]M.Datar. Butterflies and peer-to-peer networks [R].Technial Report, January 2002. [online]:http://dbpubs.stanford.edu:8090/pub/2002-5
[55]D. Malkhi, M. Naor, and D. Ratajczak. Viceroy:A Scalable Dynamic Emulation of the Butterfly[C]. In:15th International Conference on Parallel and Distributed Computing Systems (PODC 2002). July 2002.
[56]Bermond J.-C., Fraigniaud P. Broadcasting and gossiping in de Bruijn networks [J]. SIAM Journal on Computing 23,1(1994),212-225.
[57]Samatham M, Pradham D. The de bruijn multiprocessor network:a versatile parallel processing and sorting network for VLSI [J]. IEEE Trans. on Computers 38,4 (1989), 567-581.
[58]M.F. Kaashoek, D.R. Karger. Koorde:A Simple Degree-optimal Hash Table[C].In: 2nd International Workshop on Peer-to-Peer Systems (IPTPS'03).February 2003.
[59]Gummadi K,Gummadi R,Gribble S,Ratnasamy S,Shenker S,Stoica Ⅰ. The Impact of DHT Routing Geometry on Resilience and Proximity[C]. In:Proc. ACM SIGCOMM, Karlsruhe, Germany:ACM Press,2003.381-394.
[60]田瑞雄.自组织覆盖网络建模与优化[D].北京：清华大学,2005.3：26-27.
[61]Saroiu S, Gummadi P K, Gribble S D.A measurement study of peer-to-peer file sharing systems[C]. In:Proceedings of Multimedia Computing and Networking Conference (MMCN).San Jose, CA,2002.
[62]Dan S Wallach. A survey of Peer-to-Peer security issues[C]. In:Lecture Notes in Computer Science, Volume 2609, SpringerVerlag Heidelberg,2003:42-57.
[63]Castro, M., Druschel, P., Ganesh, A., Rowstron, A., Wallach, D.S. Secure routing for structured peer-to-peer overlay networks[C]. In:Proc. OSDI 2002, Boston, Massachusetts (2002).
[64]Sit, E., Morris, R. Security considerations for peer-to-peer distributed hash tables[C]. In:Proceedings for the 1st International Workshop on Peer-to-Peer Systems (IPTPS'02), Cambridge, Massachusetts (2002)
[65]Douceur, J.R. The Sybil attack [J]. In:Proceedings for the 1st International Workshop on Peer-to-Peer Systems (IPTPS'02), Cambridge, Massachusetts (2002)
[66]Denial of Service [EB/OL].:http://en.wikipedia.org/wiki/Denial-of-service_attack.
[67]Ripeanu M, Foster I. Iamnitchi A. Mapping the Gnutella network Properties of large-scale peer-to-peer systems and implications for system design[J].IEEE Internet Computing Journal,2002,6(1):50-57
[68]M. Naor and U. Wieder. Novel architectures for P2P applications:the continuous-discrete approach[C]. In:ACM SPAA,2003:13.
[69]S. Saroiu, P. K. Gummadi, and S. D. Gribble. A measurement study of peer-to-peer file sharing systems [C]. In:Proceedings of Multimedia Computing and Networking, IEEE Society Press 2002.1:50-59.
[70]Ratnasamy S, Shenker S, Stoica I. Routing algorithms for DHTs:Some open questions[C]. In:Druschel P, ed. Proc. of the 1st Int'l Workshop on P2P Systems. Berlin:Springer-Verlag,2002:45-52.
[71]Schlosser M, Condie T, Kamvar S. Simulating a file-sharing P2P network[C]. In:Proc. of the 1st Workshop on Semantics in P2P and Grid Computing. 2002.:http://www.stanford.edu/～sdkamvar/papers/simulator.pdf
[72]Fessant FL, Handurukande S, Kermarrec AM, et al. Clustering in Peer-to-Peer File Sharing Workloads[C]. In:Proceedings of the 3rd International Workshop on Peer-to-Peer Systems (IPTPS).San Diego, USA,2004.
[73]Cohen E, Fiat A, Kaplan H. A Case for Associative Peer to Peer Overlays[C]. In: Proc.of Workshop on Hot Topics in Networks, USA,2002.
[74]Sripanidkulchai K, Maggs B, Zhang H. Efficient content location using Interest-based locality in peer-to-peer systems[C]. In:Proc IEEE INFOCOM, San Francisco, CA, March 2003.
[75]Iamnitchi A I. Resourc Discovery in Large-Scale Distributed Environments [D]. Ph.D. thesis, The University of Chicago,2003.
[76]Gummadi KP, Dunn RJ, Saroiu S, Gribble SD, Levy HM, Zahorjan J. Measurement, modeling, and analysis of a peer-to-peer file-sharing workload [C]. In:Proc. of the 19th ACM Symp. on Operating Systems Principles (SOSP-19).2003:314-329.
[77]C. Faloutsos, P. Faloutsos, and M. Faloutsos. On PowerLaw Relationships of the Internet Topology[C]. In:Proceedings of the ACM SIGCOMM, ACM Press,1999.9:251-262.
[78]S. Saroiu, K. P. Gummadi, and S. D. Gribble. Measuring and analyzing the characteristics of napster and gnutell hosts [J]. Multimedia Systems,9:170-184,2003.
[79]J. A. Pouwelse, P. Garbaki, and et al. The bittorrent p2p file-sharing system: Measurement and analysis[C]. In:IPTPS'05, Feb.2005.
[80]GT-ITM Homepage [EB/OL].2000-7-26, http://www.cc.gatech.edu/projects/gtitm/.
[81]A. Medina, A. Lakhina, I. Matta, and J. Byers. BRITE:An Approach to Universal Topology Generation[C]. In:International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunications Systems- MASCOTS,2001.
[82]Palmer CR, Steffan JG. Generating network topologies that obey power laws[C]. In: Kero TEF, ed. Proceedings of the IEEE Global Telecommunications Conference. San Francisco, CA:IEEE Computer Society Press,2000.434-438.
[83]Zegura E, Calvert KL, Donahoo M. A quantitative comparison of graph-based models for Internet topology [J]. IEEE/ACM Transactions on Networking,1997,5(6):770-83.
[84]傅向华,冯博琴,马兆丰等.基于主题划分的有组织P2P搜索算法[J].西安交通大 学学报,2005,39(12)：1327-1330.
[85]Ricardo B Y, Berthier R N. Modern Information Retrieval [M]. New York:Addison Wesley,1999.
[86]Witten I, Frankl E. Data mining:Practical Machine Learning Tools and Techniques with Java Implementations [M]. San Francisco, CA:Morgan Kaufmann,1999.
[87]陈汉华,金海等.SemreX:一种基于语义相似度的P2P覆盖网络[J].软件学报,Vol.17,No.5,2006年5月,pp.1170□1181.
[88]Balachander Kri.shnamurthy, Jia Wang. On Network Aware Clustering of Web Clients[C]. In:Proc. SIGCOMM'00, Stockholm, Sweden.2000:97-110.
[89]Crespo, A., Garcia-Molina, H. Semantic Overlay Networks for P2P Systems [R]. Technical report, Stanford University (2002).
[90]Shen HT, Shu Y, Yu B. Efficient semantic-based content search in P2P network [J]. IEEE Trans, on Knowledge and Data Engineering,2004,16 (7):813-826.
[91]Doulkeridis, K. Nrvag, and M. Vazirgiannis. DESENT:Decentralized and Distributed Semantic Overlay Generation in P2P Networks [R]. Technical report, AUEB,2005, http://www.db-net.aueb.gr/index.php/publications/technical reports/.
[92]R. Siebes. pnear:combining content clustering and distributed hash tables[C]. In:The Second International Workshop on to-Peer Knowledge Management (P2PKM05),2005. www.p2pkm.org.
[93]宋建涛,沙朝锋,杨智应,朱洪.语义对等网构造及搜索机制研究[J].计算机研究与发展,41(4),Apr.2004.pp.645-652.
[94]Ratnasamy S, Handley M, Karp R, Shenker, S. Topologically-aware overlay construction and server selection[C]. In:Proceedings of INFOCOM 2002, New York. 2002:1190-1199.
[95]WInter R, Zahn T, Schiller J. Random landmarking in mobile, topology-aware peer-to-peer networks[C]. In:Proceedings of the 10th IEEE International Workshop on Future Trends of Distributed Computing Systems (FTDCS04).2004.
[96]Liu Y, Liu X, Xiao L, Ni LM, Zhang X. Location-Aware topology matching in P2P systems[C]. In:Proc. of the IEEE INFOCOM 2004. Hong Kong,2004. http://www.cse.msu.edu/～liuyunha/INFOCOM04-yunhao.pdf.
[97]Qiu T, Wu F, Chen G. A generic approach to make structured P2P systems topology-aware[C]. In:Third International Symposium on Parallel and Distributed Processing and Applications (ISPA2005), Vol.3758, Nanjing, China, November 2-5, 2005:816-826.
[98]R. Braden. Requirements for Internet Hosts-Communication Layers[S]. STD 3, RFC 1122, USC/Information Sciences Institute, October 1989.
[99]Zipf's_law [EB/OL].2007, http://en.wikipedia.org/wiki/Zipf's_law.
[100]Wentian Li. Random Texts Exhibit Zipf's-Law-Like Word Frequency Distribution [J]. IEEE Transactions on Information Theory 38 (6),1992:1842-1845.
[101]Karger D, Lehman E, Leighton T, Levine M, Lewin D, Panigraphy R. Consistent hashing and random trees:Distributed caching protocols for relieving hot spots on the World Wide Web[C]. In:Proc. the 29th Annual ACM Symposium on Theory of Computing,1997, pp.654-663.
[102]Anh-Tuan Gai, Laurent Viennot. Optimizing and Balancing Load in Fully Distributed P2P File Sharing Systems[C]. In:International Conference on Internet and Web Applications and Services (ICIW), February 2006.
[103]Moni Naor, Udi Wieder. Novel architectures for p2p applications:the continuous-discrete approach[C]. In:Fifteenth ACM Symposium on Parallelism in Algorithms and Architectures (SPAA),2003:50-59.
[104]Sylvia Ratnasamy, Scott Shenker, and Ion Stoica. Routing algorithms for dhts:Some open questions[C]. In:First International Workshop on Peer-to-Peer Systems (IPTPS), 2002:45-52.
[105]K. Ranganathan, Adriana Iamnitchi, and I. Foster. Improving Data Availability through Dynamic Model-Driven Replication in Large Peer-to-Peer Communities[C]. In: Proceedings of Global and Peer-to-Peer Computing on Large Scale Distributed Systems Workshop, Berlin, Germany, May 2002.
[106]K. Ranganathan and I. Foster. Design and Evaluation of Dynamic Replication Strategies for High Performance Data Grids[C]. In:Proceedings of International Conference on Computing in High Energy and Nuclear Physics, Beijing, China, September 2001.
[107]E. Cohen and S. Shenker, Replication strategies in unstructured peer-to-peer networks[C]. In:The ACM SIGCOMM'02 Conference, August 2002.
[108]Lu Q, Cao P, Cohen E, Li K, Shenker S. Search and replication in unstructured peer-to-peer networks[C]. In:Proc. of the Int'l Conf. on Measurements and Modeling of Computer Systems. ACM Press,2002:84-95.
[109]PC Magazine. Load balancing [EB/OL].2007, http://www.pcmag.com/encyclopedia_term/ 0,2542,t=load+balancing&i=46210,00.asp
[110]D.R. Karger and M. Ruhl. Simple Efficient Load Balancing Algorithms for Peer-to-Peer Systems[C]. In:Proc. Third Int'l Workshop Peer-to-Peer Systems (IPTPS), Feb.2004.
[111]S. Saroiu, P.K. Gummadi, and S.D. Gribble. A Measurement Study of Peer-to-Peer File Sharing Systems[C]. In:Proc. Multimedia Computing and Networking (MMCN), Jan. 2002.
[112]F. Dabek, F. Kaashoek, D. Karger, R. Morris, and I. Stoica. Wide-area cooperative storage with CFS[C]. In:Proc. ACM SOSP,2001.
[113]B. Godfrey, K. Lakshminarayanan, S. Surana, R. Karp, and 1. Stoica. Load balancing in dynamic structured P2P systems[C]. In:Proc. IEEE INFOCOM, Hong Kong,2004.
[114]A Rao, K Lakshminarayanan, S Surana, et al. Load balancing in structured P2P system [C]. In:IPTPS, Berkeleg, CA, USA,2003.
[115]John Byers, Jerey Considine, Michael Mitzenmacher. Simple load balancing for distributed hash tables[C]. In:2nd International Workshop on Peer-to-Peer. Systems (IPTPS), Feb.2003:80-87
[116]Mitzenmacher M, Richa A and Sitaraman R. The Power of Two Choices:A Survey of Techniques and Results [M]. Kluwer Academic Publishers, Norwell, MA, 2001:255-312.
[117]Chris Riley, Christian Scheideler. Local Load Balancing in Distributed Hash Tables [DB/OL]. www.cs.jhu.edu/-scheideler/papers/balancing.ps.gz.
[118]K. Kenthapadi and G. Manku. Decentralized Algorithms using both Local and Random Probes for P2P Load Balancing [C]. In:Proc.17th ACM Symposium on Parallel Algorithms and Architectures (SPAA'05), July 18-20,2005, Las Vegas, Nevada, USA
[119]Anh-Tuan Gai, Laurent Viennot. Optimizing and Balancing Load in Fully Distributed P2P File[C]. In:International Conference on Internet and Web Applications and Services (ICIW), February 2006.
[120]Kleinberg J. The small-world phenomenon:an algorithmic perspective [R]. Cornell Computer Science Technical Report,2000:99-1776.
[121]Resnick P, Zeckhauser R. Reputation systems:Facilitating trust in Internet Interactions [J]. Communications of the ACM,2000,43(12):45-48.
[122]Kamvar SD, Schlosser MT, Garcia-Molina H. The EigenTrust algorithm for reputation management in P2P networks[C]. In:Proc. of the 12th Int'l World Wide Web Conf. New York:ACM Press,2003.640-651.
[123]Aberer K, Despotovic Z. Managing trust in a peer-2-peer information system[C]. In: Ninth International conference on information and knowledge Management. Georgia, ACM Press,2001:310-317.
[124]Michal Feldman, Christos Papadimitriou, John Chuang, et al. Free-riding and whitewashing in peer-to-peer systems[C]. In:ACM SIGCOMM'04 Workshop, Sept 2004.
[2]动网论坛.构建可扩展宽带流媒体应用支撑环境[EB/OL].2006-4-18, http://www. dvbbs.net/tech/network/2006041844577.asp.
[3]新华网.宽带流媒体的应用时机成熟了吗?[EB/OL].2004-10-21,http://news. xinhuanet.com/newmedia/2004-10/21/content 2120264.htm.
[4]科技部863计划联合办公室.高性能宽带信息网(3Tnet)专项课题指南[EB/OL]. 2004-06-01,http://www.863.org.cn/863_105/applyguide/guide_infotech/200406010039 .html.
[5]邬江兴.中国高性能宽带信息网(3TNet)综述[EB/OL].2006-01-24, http://www. c114.net/ZHANHUI/863/jx.htm.
[6]汪斌强,邬江兴.基于IPv6的大规模接入汇聚路由器的设想和实现[J].电信科学,2006,22(1)：5-9.
[7]风行咨询网.P2P流量占国内总带宽过半,宽带资源过于紧张[EB/OL].2007-06-06, http://www.fengnews.com/article/2007/0606/news_5937.html.
[8]丛亮.5%收入占95%带宽,BT该管管了[EB/OL].2007-05-13,http://congliangbupt. blog.sohu.com/45833212.html.
[9]耶兰特.带宽不足不完全是P2P的问题[EB/OL].2007-09-26,http://www.ppcn.net/ n4208c74.aspx.
[10]M.Panti, L. Penserini.A P2P Approach to Land Warriors Coordination[C].In: International Symp.on Collaborative Technologies and Systems in conjunction with the 2003 Western Multi Conferences, Orlando, Florida, Kluwer Academic Press,2003.1:109-117.
[11]D.S Milojicic, V. Kalogeraki. Peer-to-Peer Computing[R]. HP Labs, Palo Alto. Tech Report:HPL-2002-57,2002.
[12]罗杰文Peer to Peer(P2P)综述[R].中科院计算技术研究所.2005-11-3.
[13]Jordan Ritter. Why Gnutella Can't Scale [EB/OL]. http://www.darkridge.com/～jpr5/doc/gnutella.html.
[14]The Gnutella Homepage [EB/OL].2001, http://www.gnutella.com.
[15]The Napster Homepage [EB/OL].2003-2007, http://free.napster.com/.
[16]C—NET NEWS. Napster among fastest-growing Net technologies [EB/OL]. October 2000, http://news.com.com/2100-1023-246648.html.
[17]Overnet/edonkey2000. [EB/OL].2000-2007, http://www.zeropaid.com/edonkey/
[18]BitTorrent C Library [EB/OL].2007,http://sourceforge.net/projects/libbt.
[19]Python Implementation of the BitTorrent Package [EB/OL].2001-2007, http://bitconjurer.org/BitTorrent/
[20]Instant Messenger-AIM [EB/OL].2007, http://www.aim.com/.
[21]Jabber Homepage [EB/OL].1999-2005, http://www.jabber.org/.
[22]Farsite Homepage [EB/OL].2007, http://research.microsoft.com/sn/Farsite/.
[23]OceanStore Homepage [EB/OL].2005-11-30, http://oceanstore.cs.berkeley.edu/.
[24]Infrasearch Homepage [EB/OL].2007, http://www.infrasearch.com/.
[25]Buyya, Rajkumar, Steve Chapin, and David DiNucci.2000. Architectural Models for Resource Management in the Grid[C]. In First IEEE/ACM International Workshop on Grid Computing (GRID 2000), Bangalore, India, December 2000.
[26]IBM GRID Computing Project [EB/OL].2007, http://www.research.ibm.com/autonomic/.
[27]D.P. Anderson. SETI@home:An Experiment in Public Resource Computing[C]. Communications of the ACM,2002, Vol.45, No.11:56-61.
[28]Groove Homepage [EB/OL].2007, http://www.groove.net/.
[29]Billpoint Homepage [EB/OL].1999-2007, https://www.billpoint.com/.
[30]Lightshare Homepage [EB/OL].2007, https://www.lightshare.com/.
[31]Free Haven Homepage [EB/OL].:2004-12-1, http://www.freehaven.net/.
[32]T. Chujo. Modeling Internet Traffic for Network Planning and Provisioning[C]. In:7th Asia-Pacific Network Operations and Management Symposium (APNOMS 2003). October 2003.
[33]C. Fraleigh, S. Moon, etc. Packet-level Traffic Measurements from the Sprint IP Backbone[C]. IEEE Network Magazine, Vol.17, No.6. November 2003.
[34]Pouwelse J A, Garbacki P, Epema D H J, et al. A measurement study of the bittorrent peer-to-peer file-sharing system[R]. Technical Report PDS-2004-003, April 2004.
[35]Sen, S., Wong, J.Analyzing peer-to-peer traffic across large networks [J]. Transactions on Networking. Volume 12, ACM Press 2004:219-232.
[36]Linux reviews.Peer to peer network traffic may account for up to 85% of Internets bandwidth usage [EB/OL].2004, http://linuxreviews.org/news/2004/11/05_p2p/.
[37]The Skype Homepage [EB/OL].2007, http://www.skype.com.
[38]KaZaA website [EB/OL].2002, http://www.kazaa.com/.
[39]Munindar P. Singh. Peering at Peer-to-Peer Computing [J]. IEEE Internet Computing, Vol.5, No.1, pp.4-5, January/February 2001.
[40]Flooding algorithm [EB/OL].2007, http://en.wikipedia.org/wiki/Flooding_algorithm.
[41]Random walk [EB/OL].2007, http://en.wikipedia.org/wiki/Random_walk.
[42]Distributed hash table [EB/OL].2007, http://en.wikipedia.org/wiki/Distributed_hash table.
[43]K.Kant, R.Iyer, V.Tewari. A Framework for Classifying Peer-to-Peer Technologies[C]. In:2nd IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID'02), IEEE Society Press,2002.5:368-376.
[44]A. Agrawal, H.Casanova. Clustering Hosts in P2P and Global Computing Platforms[C]. In:Third International Workshop on Global and Peer-to-Peer Computing on Large Scale Distributed Systems, ACM Press, Tokyo,2003.5:367-343.
[45]Lua EK, Crowcroft J, Pias M, Sharma R, Lim S. A survey and comparison of peer-to-peer overlay network schemes [J]. Journal of. IEEE Communications Survey and Tutorial,2005.7:1-2.
[46]B. Y. Zhao, J. D. Kubiatowicz, and A. D. Joseph. Tapestry:An Infrastructure for Fault-Resilient Wide-area Location and Routing[R]. Technical Rept: UCB//CSD-011141, U. C. Berkeley,2001.4.
[47]Peter Druschel, Anthony Rowstron. Pastry:Scalable, distributed object location and routing for large-scale peer-to-peer systems[C]. In:IFIP/ACM International Conference on Distributed Systems Platforms, Kluwer Academic Press, Nov 2001: 329-350.
[48]I. Stoica, R. Morris, D. Karger, M. F. Kaashoek, and H. Balakrishnan. Chord:A scalable peer-to-peer lookup service for Internet applications[R]. Technical Rept:TR-819, MIT,2001.3
[49]S. Ratnasamy, Paul Francis, Mark Handley, Richard Karp, Scott Schenker. A Scalable Content-Addressable Network[C]. In:Proceeding of ACM SIGCOMM, ACM Press, New York,2001.8:161-172.
[50]Shansi Ren, Lei Guo, Song Jiang, et al. SAT-match:a self-adaptive topology matching method to achieve low lookup latency in structured P2P overlay networks[C]. In: Proceedings of the 18th International Parallel and Distributed Processing Symposium (IPDPS'04), Santa Fe, New Mexico, USA, April 2003.
[51]Consistent hashing [EB/OL].2007, http://en.wikipedia.org/wiki/Consistent_hashing.
[52]C.Greg Plaxton, Rajmohan Rajaraman, and Andrea W. Richa. Accessing nearby copies of replicated objects in a distributed environment [C]. In:Proceedings of ACM SPAA. ACM, June 1997.
[53]H.J. Siegel. Interconnection networks for SIMD machines [J]. Computer 12(6):57-65, 1979.
[54]M.Datar. Butterflies and peer-to-peer networks [R].Technial Report, January 2002. [online]:http://dbpubs.stanford.edu:8090/pub/2002-5
[55]D. Malkhi, M. Naor, and D. Ratajczak. Viceroy:A Scalable Dynamic Emulation of the Butterfly[C]. In:15th International Conference on Parallel and Distributed Computing Systems (PODC 2002). July 2002.
[56]Bermond J.-C., Fraigniaud P. Broadcasting and gossiping in de Bruijn networks [J]. SIAM Journal on Computing 23,1(1994),212-225.
[57]Samatham M, Pradham D. The de bruijn multiprocessor network:a versatile parallel processing and sorting network for VLSI [J]. IEEE Trans. on Computers 38,4 (1989), 567-581.
[58]M.F. Kaashoek, D.R. Karger. Koorde:A Simple Degree-optimal Hash Table[C].In: 2nd International Workshop on Peer-to-Peer Systems (IPTPS'03).February 2003.
[59]Gummadi K,Gummadi R,Gribble S,Ratnasamy S,Shenker S,Stoica Ⅰ. The Impact of DHT Routing Geometry on Resilience and Proximity[C]. In:Proc. ACM SIGCOMM, Karlsruhe, Germany:ACM Press,2003.381-394.
[60]田瑞雄.自组织覆盖网络建模与优化[D].北京：清华大学,2005.3：26-27.
[61]Saroiu S, Gummadi P K, Gribble S D.A measurement study of peer-to-peer file sharing systems[C]. In:Proceedings of Multimedia Computing and Networking Conference (MMCN).San Jose, CA,2002.
[62]Dan S Wallach. A survey of Peer-to-Peer security issues[C]. In:Lecture Notes in Computer Science, Volume 2609, SpringerVerlag Heidelberg,2003:42-57.
[63]Castro, M., Druschel, P., Ganesh, A., Rowstron, A., Wallach, D.S. Secure routing for structured peer-to-peer overlay networks[C]. In:Proc. OSDI 2002, Boston, Massachusetts (2002).
[64]Sit, E., Morris, R. Security considerations for peer-to-peer distributed hash tables[C]. In:Proceedings for the 1st International Workshop on Peer-to-Peer Systems (IPTPS'02), Cambridge, Massachusetts (2002)
[65]Douceur, J.R. The Sybil attack [J]. In:Proceedings for the 1st International Workshop on Peer-to-Peer Systems (IPTPS'02), Cambridge, Massachusetts (2002)
[66]Denial of Service [EB/OL].:http://en.wikipedia.org/wiki/Denial-of-service_attack.
[67]Ripeanu M, Foster I. Iamnitchi A. Mapping the Gnutella network Properties of large-scale peer-to-peer systems and implications for system design[J].IEEE Internet Computing Journal,2002,6(1):50-57
[68]M. Naor and U. Wieder. Novel architectures for P2P applications:the continuous-discrete approach[C]. In:ACM SPAA,2003:13.
[69]S. Saroiu, P. K. Gummadi, and S. D. Gribble. A measurement study of peer-to-peer file sharing systems [C]. In:Proceedings of Multimedia Computing and Networking, IEEE Society Press 2002.1:50-59.
[70]Ratnasamy S, Shenker S, Stoica I. Routing algorithms for DHTs:Some open questions[C]. In:Druschel P, ed. Proc. of the 1st Int'l Workshop on P2P Systems. Berlin:Springer-Verlag,2002:45-52.
[71]Schlosser M, Condie T, Kamvar S. Simulating a file-sharing P2P network[C]. In:Proc. of the 1st Workshop on Semantics in P2P and Grid Computing. 2002.:http://www.stanford.edu/～sdkamvar/papers/simulator.pdf
[72]Fessant FL, Handurukande S, Kermarrec AM, et al. Clustering in Peer-to-Peer File Sharing Workloads[C]. In:Proceedings of the 3rd International Workshop on Peer-to-Peer Systems (IPTPS).San Diego, USA,2004.
[73]Cohen E, Fiat A, Kaplan H. A Case for Associative Peer to Peer Overlays[C]. In: Proc.of Workshop on Hot Topics in Networks, USA,2002.
[74]Sripanidkulchai K, Maggs B, Zhang H. Efficient content location using Interest-based locality in peer-to-peer systems[C]. In:Proc IEEE INFOCOM, San Francisco, CA, March 2003.
[75]Iamnitchi A I. Resourc Discovery in Large-Scale Distributed Environments [D]. Ph.D. thesis, The University of Chicago,2003.
[76]Gummadi KP, Dunn RJ, Saroiu S, Gribble SD, Levy HM, Zahorjan J. Measurement, modeling, and analysis of a peer-to-peer file-sharing workload [C]. In:Proc. of the 19th ACM Symp. on Operating Systems Principles (SOSP-19).2003:314-329.
[77]C. Faloutsos, P. Faloutsos, and M. Faloutsos. On PowerLaw Relationships of the Internet Topology[C]. In:Proceedings of the ACM SIGCOMM, ACM Press,1999.9:251-262.
[78]S. Saroiu, K. P. Gummadi, and S. D. Gribble. Measuring and analyzing the characteristics of napster and gnutell hosts [J]. Multimedia Systems,9:170-184,2003.
[79]J. A. Pouwelse, P. Garbaki, and et al. The bittorrent p2p file-sharing system: Measurement and analysis[C]. In:IPTPS'05, Feb.2005.
[80]GT-ITM Homepage [EB/OL].2000-7-26, http://www.cc.gatech.edu/projects/gtitm/.
[81]A. Medina, A. Lakhina, I. Matta, and J. Byers. BRITE:An Approach to Universal Topology Generation[C]. In:International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunications Systems- MASCOTS,2001.
[82]Palmer CR, Steffan JG. Generating network topologies that obey power laws[C]. In: Kero TEF, ed. Proceedings of the IEEE Global Telecommunications Conference. San Francisco, CA:IEEE Computer Society Press,2000.434-438.
[83]Zegura E, Calvert KL, Donahoo M. A quantitative comparison of graph-based models for Internet topology [J]. IEEE/ACM Transactions on Networking,1997,5(6):770-83.
[84]傅向华,冯博琴,马兆丰等.基于主题划分的有组织P2P搜索算法[J].西安交通大 学学报,2005,39(12)：1327-1330.
[85]Ricardo B Y, Berthier R N. Modern Information Retrieval [M]. New York:Addison Wesley,1999.
[86]Witten I, Frankl E. Data mining:Practical Machine Learning Tools and Techniques with Java Implementations [M]. San Francisco, CA:Morgan Kaufmann,1999.
[87]陈汉华,金海等.SemreX:一种基于语义相似度的P2P覆盖网络[J].软件学报,Vol.17,No.5,2006年5月,pp.1170□1181.
[88]Balachander Kri.shnamurthy, Jia Wang. On Network Aware Clustering of Web Clients[C]. In:Proc. SIGCOMM'00, Stockholm, Sweden.2000:97-110.
[89]Crespo, A., Garcia-Molina, H. Semantic Overlay Networks for P2P Systems [R]. Technical report, Stanford University (2002).
[90]Shen HT, Shu Y, Yu B. Efficient semantic-based content search in P2P network [J]. IEEE Trans, on Knowledge and Data Engineering,2004,16 (7):813-826.
[91]Doulkeridis, K. Nrvag, and M. Vazirgiannis. DESENT:Decentralized and Distributed Semantic Overlay Generation in P2P Networks [R]. Technical report, AUEB,2005, http://www.db-net.aueb.gr/index.php/publications/technical reports/.
[92]R. Siebes. pnear:combining content clustering and distributed hash tables[C]. In:The Second International Workshop on to-Peer Knowledge Management (P2PKM05),2005. www.p2pkm.org.
[93]宋建涛,沙朝锋,杨智应,朱洪.语义对等网构造及搜索机制研究[J].计算机研究与发展,41(4),Apr.2004.pp.645-652.
[94]Ratnasamy S, Handley M, Karp R, Shenker, S. Topologically-aware overlay construction and server selection[C]. In:Proceedings of INFOCOM 2002, New York. 2002:1190-1199.
[95]WInter R, Zahn T, Schiller J. Random landmarking in mobile, topology-aware peer-to-peer networks[C]. In:Proceedings of the 10th IEEE International Workshop on Future Trends of Distributed Computing Systems (FTDCS04).2004.
[96]Liu Y, Liu X, Xiao L, Ni LM, Zhang X. Location-Aware topology matching in P2P systems[C]. In:Proc. of the IEEE INFOCOM 2004. Hong Kong,2004. http://www.cse.msu.edu/～liuyunha/INFOCOM04-yunhao.pdf.
[97]Qiu T, Wu F, Chen G. A generic approach to make structured P2P systems topology-aware[C]. In:Third International Symposium on Parallel and Distributed Processing and Applications (ISPA2005), Vol.3758, Nanjing, China, November 2-5, 2005:816-826.
[98]R. Braden. Requirements for Internet Hosts-Communication Layers[S]. STD 3, RFC 1122, USC/Information Sciences Institute, October 1989.
[99]Zipf's_law [EB/OL].2007, http://en.wikipedia.org/wiki/Zipf's_law.
[100]Wentian Li. Random Texts Exhibit Zipf's-Law-Like Word Frequency Distribution [J]. IEEE Transactions on Information Theory 38 (6),1992:1842-1845.
[101]Karger D, Lehman E, Leighton T, Levine M, Lewin D, Panigraphy R. Consistent hashing and random trees:Distributed caching protocols for relieving hot spots on the World Wide Web[C]. In:Proc. the 29th Annual ACM Symposium on Theory of Computing,1997, pp.654-663.
[102]Anh-Tuan Gai, Laurent Viennot. Optimizing and Balancing Load in Fully Distributed P2P File Sharing Systems[C]. In:International Conference on Internet and Web Applications and Services (ICIW), February 2006.
[103]Moni Naor, Udi Wieder. Novel architectures for p2p applications:the continuous-discrete approach[C]. In:Fifteenth ACM Symposium on Parallelism in Algorithms and Architectures (SPAA),2003:50-59.
[104]Sylvia Ratnasamy, Scott Shenker, and Ion Stoica. Routing algorithms for dhts:Some open questions[C]. In:First International Workshop on Peer-to-Peer Systems (IPTPS), 2002:45-52.
[105]K. Ranganathan, Adriana Iamnitchi, and I. Foster. Improving Data Availability through Dynamic Model-Driven Replication in Large Peer-to-Peer Communities[C]. In: Proceedings of Global and Peer-to-Peer Computing on Large Scale Distributed Systems Workshop, Berlin, Germany, May 2002.
[106]K. Ranganathan and I. Foster. Design and Evaluation of Dynamic Replication Strategies for High Performance Data Grids[C]. In:Proceedings of International Conference on Computing in High Energy and Nuclear Physics, Beijing, China, September 2001.
[107]E. Cohen and S. Shenker, Replication strategies in unstructured peer-to-peer networks[C]. In:The ACM SIGCOMM'02 Conference, August 2002.
[108]Lu Q, Cao P, Cohen E, Li K, Shenker S. Search and replication in unstructured peer-to-peer networks[C]. In:Proc. of the Int'l Conf. on Measurements and Modeling of Computer Systems. ACM Press,2002:84-95.
[109]PC Magazine. Load balancing [EB/OL].2007, http://www.pcmag.com/encyclopedia_term/ 0,2542,t=load+balancing&i=46210,00.asp
[110]D.R. Karger and M. Ruhl. Simple Efficient Load Balancing Algorithms for Peer-to-Peer Systems[C]. In:Proc. Third Int'l Workshop Peer-to-Peer Systems (IPTPS), Feb.2004.
[111]S. Saroiu, P.K. Gummadi, and S.D. Gribble. A Measurement Study of Peer-to-Peer File Sharing Systems[C]. In:Proc. Multimedia Computing and Networking (MMCN), Jan. 2002.
[112]F. Dabek, F. Kaashoek, D. Karger, R. Morris, and I. Stoica. Wide-area cooperative storage with CFS[C]. In:Proc. ACM SOSP,2001.
[113]B. Godfrey, K. Lakshminarayanan, S. Surana, R. Karp, and 1. Stoica. Load balancing in dynamic structured P2P systems[C]. In:Proc. IEEE INFOCOM, Hong Kong,2004.
[114]A Rao, K Lakshminarayanan, S Surana, et al. Load balancing in structured P2P system [C]. In:IPTPS, Berkeleg, CA, USA,2003.
[115]John Byers, Jerey Considine, Michael Mitzenmacher. Simple load balancing for distributed hash tables[C]. In:2nd International Workshop on Peer-to-Peer. Systems (IPTPS), Feb.2003:80-87
[116]Mitzenmacher M, Richa A and Sitaraman R. The Power of Two Choices:A Survey of Techniques and Results [M]. Kluwer Academic Publishers, Norwell, MA, 2001:255-312.
[117]Chris Riley, Christian Scheideler. Local Load Balancing in Distributed Hash Tables [DB/OL]. www.cs.jhu.edu/-scheideler/papers/balancing.ps.gz.
[118]K. Kenthapadi and G. Manku. Decentralized Algorithms using both Local and Random Probes for P2P Load Balancing [C]. In:Proc.17th ACM Symposium on Parallel Algorithms and Architectures (SPAA'05), July 18-20,2005, Las Vegas, Nevada, USA
[119]Anh-Tuan Gai, Laurent Viennot. Optimizing and Balancing Load in Fully Distributed P2P File[C]. In:International Conference on Internet and Web Applications and Services (ICIW), February 2006.
[120]Kleinberg J. The small-world phenomenon:an algorithmic perspective [R]. Cornell Computer Science Technical Report,2000:99-1776.
[121]Resnick P, Zeckhauser R. Reputation systems:Facilitating trust in Internet Interactions [J]. Communications of the ACM,2000,43(12):45-48.
[122]Kamvar SD, Schlosser MT, Garcia-Molina H. The EigenTrust algorithm for reputation management in P2P networks[C]. In:Proc. of the 12th Int'l World Wide Web Conf. New York:ACM Press,2003.640-651.
[123]Aberer K, Despotovic Z. Managing trust in a peer-2-peer information system[C]. In: Ninth International conference on information and knowledge Management. Georgia, ACM Press,2001:310-317.
[124]Michal Feldman, Christos Papadimitriou, John Chuang, et al. Free-riding and whitewashing in peer-to-peer systems[C]. In:ACM SIGCOMM'04 Workshop, Sept 2004.