基于统计特征的P2P流量实时识别方法  

Method for real-time P2P traffic identification based on statistical features

作　　者：田朔玮 杨岳湘[1] 何杰[1] 王晓磊[1] 

机构地区：[1]国防科学技术大学计算机学院,湖南长沙410073

出　　处：《计算机工程与设计》2016年第2期281-285,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(61170286)

摘　　要：为有效监管网络,快速精确识别P2P流量,在分析P2P网络的本质特性基础上,提出P2P流量的3个流量特征,借助机器学习方法实现对P2P流量和非P2P流量的实时分类。实验结果表明,这3个特征都具备良好的区分性,综合使用3个特征时,能在5s的时间窗口内实现对P2P流量的实时识别,识别准确率达到98.79%,误报率为0.36%。To effectively manage the network,quickly and accurately identify P2P（peer-to-peer）traffic.Through analyzing the essential characteristics of P2 Pnetwork,three statistical features of P2 Ptraffic were proposed,which were able to identify P2 P traffic in real-time by means of machine learning algorithm.The experimental results demonstrate that each proposed feature has strong discrimination to distinguish P2 Ptraffic from non-P2 Ptraffic.After combining three features,P2 Ptraffic is identified with an accuracy of 98.79% and a false positive below 0.36% within 5seconds.

关 键 词：P2P流量识别 统计特征 机器学习 实时 准确 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]