无线Mesh网络流量自相似性研究

Traffic Self-similarity in Wireless Mesh Network

近年来,无线Mesh网络已成为一个倍受关注的研究领域。对无线Mesh网络流量特性的研究将有助于网络协议的研究、评估,以及网络结构的规划和建设。本文通过对无线Mesh测试网上采集的数据包进行统计分析,揭示了网络流量具有自相似的特性。同时,解释了无线Mesh网络流量自相似性是由网络中具有重尾分布特性的多个流叠加形成的,并通过仿真进一步分析了节点移动性对流量自相似性的影响。

Wireless mesh network (WMN) has received continuous attention in recent years. Research on traffic characteristics is helpful for the design and evaluation of network protocols as well as network deployment. Through statistical analysis of millions of packets collected in a WMN testbed, it shows that WMN has the characteristic of traffic self-similarity. The statistical result also shows that the superposition of many heavy-tailed flows cause the self-similarity in WMN. Moreover, the impact of mobility of nodes is also discussed through a series of simulations.