基于行为特征加权的P2P流识别方法的研究  

Research on P2P flow identification based on weight of behavior characteristics

作　　者：崔燕[1] 汪斌强[1] 陈庶樵[1] 张震[1] 

机构地区：[1]国家数字交换系统工程技术研究中心,河南郑州450002

出　　处：《计算机工程与设计》2009年第20期4805-4807,F0003,共4页Computer Engineering and Design

基　　金：国家863高技术研究发展计划基金项目(2007AA01z2a1)

摘　　要：为识别网络中大量的P2P流,为网络管理提供技术支持,提出一种基于行为特征加权的P2P流识别模型。该方法不需深度报文检测(DPI),采用深度流行为检测(DFI),统计P2P应用的行为特征,并通过行为特征对P2P流识别的有效性的贡献进行分级,特征按所属级别被赋予不同的权值,通过特征匹配和加权,识别P2P流。仿真实验结果表明,该方法能够有效识别P2P业务流。For identifying large numbers of P2P flows in the Internet and giving technical support to the Internet, a new model for identifying P2P flows is developed using the weight of the sum of characteristics. This model dose not need deep packets inspection （DPI）, but only depends on the deep flow inspection （DFI）, classifies P2P behavior characteristics based on their contribution to the validity of identification and endows with the weight. It uses characteristic matching and sum of weight to identify P2P flow. The experiment results show that this method exhibits good performance for identifying P2P flow.

关 键 词：P2P流 深度流行为检测 深度报文检测 行为特征 匹配 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]