期刊文献+

对等网络的临界负载研究

Critical load of peer-to-peer networks
下载PDF
导出
摘要 不同于传统的网络拥塞研究方法,从拓扑属性节点介数出发,分析了网络拥塞与介数之间的关系,以排队论为模型,从理论上给出了导致网络拥塞的临界负载与网络拓扑属性介数的公式解.并且以Gnutella网络拓扑结构为模型进行了仿真实验,假设Gnutella网络中的网络流量由搜索请求和搜索响应构成,搜索请求采用k邻居随机路由方式.仿真结果不仅验证了公式解的正确性,而且证明了临界负载和介数之间的必然联系. Being different from traditional research, on the basis of the betweenness of topological attribution nodes, the relationship between the networks and the betweenness were analyzed. Taken queuing theory as theoretical model, a closed-form solution to the critical load leading the network congestion and the betweenness of the topology attribution in networks was obtained. Assuming that the network traffic was composed of search requests and responses and k-neighbor random walk was used as routing algorithm of search requests, the simulation was carried out by Gnutella network topology. The simulation results validated the solution to the critical load and testified the necessary relation between the betweenness of the nodes and the critical loads.
出处 《华中科技大学学报(自然科学版)》 EI CAS CSCD 北大核心 2007年第3期35-37,共3页 Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金 国家自然科学基金资助项目(60433040)
关键词 对等网络 拓扑 网络拥塞 临界负载 peer-to-peer networks topology network congestion critical load
  • 相关文献

参考文献5

  • 1陶军,林辉.非合作流速与拥塞控制博弈的应用[J].东南大学学报(自然科学版),2006,36(1):52-57. 被引量:3
  • 2綦朝晖,孙济洲,李小图.基于队列的模糊拥塞控制算法[J].软件学报,2005,16(2):286-294. 被引量:16
  • 3Chen H,Jin H,Sun J H,et al.Analysis of large-scale topological properties for peer-to-peer networks[C]∥Proc of International Symposium on Cluster Computing and the Grid (CCGird04).Los Angeles:IEEE Press,2004:27-34.
  • 4Fuks H,Lawniczak A T,Volkov S.Packet delay in data network models[J].ACM Transactions on Modeling and Computer Simulation,2001,11(3):233-250.
  • 5Kleinrock L.Queueing systems,Vol.1:Theory[M].New York:Wiley,1976.

二级参考文献30

  • 1La R J,Anantharam V.Utility-based rate control in the Internet for elastic traffic [J].IEEE/ACM Transactions on Networking,2002,10(2):272-286.
  • 2Mo J,La R J,Anantharam V,et al.Analysis and comparison of TCP reno and vegas[C]// IEEE INFOCOM'99 .New York,NY,1999:1556-1563.
  • 3La R J,Anantharam V.Window-based congestion control with heterogeneous users [C]//Proc IEEE INFOCOM 2001.Anchorage,Alaska,2001:1320-1329.
  • 4Chandrayana K,Kalyanaraman S.Uncooperative congestion control [C]// Proc of ACM SIGMETRICS Joint International Conference on Measurement and Modeling of Computer Systems.New York,2004:258-269.
  • 5Fayek D,Kesidis G,Vannelli A.Hierarchical virtual paths allocation in large-scale ATM networks using noncooperative game models [EB/OL].[1999-10-18)[2004-11-08].http://www.cse.psu.edu/~kesidis/papers/default.htm.
  • 6Odlyzko A.A modest proposal for preventing internet congestion [R].Technical Report TR 97.35.1,AT&T Research,1997.
  • 7Mitra D.Asymptotically optimal design of congestion control for high speed data network [J].IEEE Transactions on Communications,1992,40(2):301-311.
  • 8Mitra D,Mitrani I.Efficient window flow control for high speed data networks with small buffers [J].Annals of Operations Research,1994,49(6):1-24.
  • 9Fendick K,Mitra D,Mitrani I,et al.An approach to high-performance,high-speed data networks [J].IEEE Communications Magazine,1991,29(10):74-82.
  • 10Cohen J E.Cooperation and self-interest:pareto-inefficiency of Nash equilibria in finite random games [J].Proc Natl Acad Sci USA,1998,95(17):9724-9731.

共引文献17

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部