基于SVM的P2P流量识别研究

SVM Based P2P Traffic Identification

p2p技术的快速发展一方面丰富了网络的应用形式,同时也给网络管理带来了很多安全问题。因此,研究有效的P2P流识别方法成为P2P流管理的重要课题。论文提出一种基于SVM的P2P网络流量分类的方法,该方法利用基于统计理论的SVM方法,通过网络流量特征以区分不同P2P业务。实验中选择四种常用的P2P业务(Bittorrent,Gnutella,Kazaa和Edonkey),平均分类准确率达到92.2%。

The rapid growth of p2p technology has enriched application forms of network,at the same time,it also brings many security problems to the network management.Research on P2P flow identification has become the most important problem of P2P flow management.Paper proposed a method to realize the P2P network traffic classification based on the SVM.This method uses SVM method based on the statistical theory and analyzes the characteristics of network traffic to classify the different P2P traffic application,the average precise rate is 92.2%.