一种基于复杂网络的P2P流媒体拓扑构建算法

发布时间：2018-04-24 10:45

本文选题：对等网络 + 流媒体　；参考：《计算机应用研究》2013年04期

【摘要】：按照何种拓扑结构来构建覆盖网络是P2P流媒体网络中的热点问题,而已有的拓扑构建算法大多采用启发式算法,参数由经验值确定,缺乏理论分析。针对此问题,运用复杂网络中小世界效应的理论知识和簇结构的概念,提出了一种基于复杂网络的P2P流媒体拓扑构建算法,用所有的簇头节点构成一个小世界网络,利用小世界网络的特性来改善P2P流媒体网络的性能。对该算法和经典的CoolStreaming方法分别进行了仿真实验,比较了启动延迟、服务器负载、消息开销和抖动率等参数。实验结果表明新提出的算法相对于CoolStreaming方法具有显著的性能提高。复杂网络理论的运用是P2P流媒体系统研究的一个新方向,对今后的工作有重要的指导意义。
[Abstract]:It is a hot issue in P2P streaming media network to construct overlay network according to which topology structure, but most of the existing topology construction algorithms use heuristic algorithm, parameters are determined by experience value, lack of theoretical analysis. To solve this problem, using the theory of small-world effect and the concept of cluster structure in complex networks, a P2P streaming media topology construction algorithm based on complex networks is proposed, which uses all cluster heads to form a small-world network. Using the characteristics of small world network to improve the performance of P2P streaming media network. The algorithm is simulated with the classical CoolStreaming method, and the parameters such as startup delay, server load, message overhead and jitter rate are compared. Experimental results show that the proposed algorithm has a significant performance improvement compared with the CoolStreaming method. The application of complex network theory is a new direction of P2P streaming media system research, which has important guiding significance for future work.
【作者单位】：西安科技大学计算机科学与技术学院;
【基金】：陕西省教育厅科研计划项目(2010JK665) 陕西省自然科学基础研究计划项目(2012JQ8030)
【分类号】：TP393.02

【参考文献】