P2P应用层数据流量优化.pdfVIP

第40 卷 第1 期 电 子 科 技 大 学 学 报 Vol.40 No. 1 20 11年1月 Journal of University of Electronic Science and Technology of China Jan. 20 11 P2P应用层数据流量优化 任立勇，雷 明，张 磊 ( 电子科技大学计算机科学与工程学院 成都 610054) 【摘要】为减少对主干网络带宽的消耗，提出了一套数据流量优化方法。首先通过把Peer 间的邻居关系明确划分为物理 邻居关系和逻辑邻居关系，并用探路者算法来发现Peer的物理邻居，实现拓扑匹配；然后在数据调度算法中，引入通报/退避 机制，把大部分数据传输控制在城域网络内部。通过建立模拟仿真环境进行实验分析，证实了该方法可以减少90%以上的网 络数据流量。 关 键 词 邻居; 优化; P2P; 调度算法; 拓扑 中图分类号 TP311 文献标识码 A doi:10.3969/j.issn.1001-0548.2011.01.021 Data Traffic Optimization in P2P Application Layer REN Li-yong, LEI Ming, and ZHANG Lei (School of Computer Science and Engineering, University of Electronic Science and Technology of China Chengdu 610054) Abstract At present, too much network bandwidth has been occupied by a variety of P2P applications that greatly affect the backbone of the network. A scheme for data flow optimization is presented to reduce the consumption of the network bandwidth. In the scheme, the peers relationship is divided into physical and logical neighbors, the pathfinder algorithm is used to determine the relationship between peers and achieve topology matching, and the notice/drawback mechanism is introduced in the data scheduling algorithms to make most data transmission under the control of metropolitan area network. The experiment results of a simulation environment prove that the scheme mentioned above is an effect way of reducing the network traffic by 90%. Key words neighbor; optimization; P2P; scheduling algorithms; topology P2P应用的迅速发展，大量消耗着网络带宽资 及形成数据孤岛节点群等问题。 源。有关资料显示，中国电信现有骨干网流量有很 目前在拓扑匹配方面的研究可分为：1) 依靠特