A P2P Traffic Classification Method Based on SVM

A method to realize the P2P network traffic classification based on the SVM is proposed. This method uses the network traffic statistical characteristic and SVM method that based on the statistical theory to classifies the different P2P traffic application. Mainly research on four kind of network traffic classification, in document sharing BitTorrent, in media flows PPLive, in network telephone Skype, in immediate communication MSN. Introduced P2P traffic classification overall framework based on the SVM. Described how gain the traffic sample and the processing method. And introduced the experimental results and constructs the traffic classifier. The experimental result confirmed the validity of proposed method; average precise rate is 92.38%.