Identifying P2P flow with behavior characteristics

With the development of Internet, P2P applications sometimes represent most of Internet traffic. This phenomenon effects on network performance worse. However, more and more P2P protocols can dynamically hop to different ports and use encryption techniques, in order to make them difficult to detect. In this paper, we develop a new model to identify P2P flow using behavior characteristics. This model doesn´t depend on the deep packets inspection (DPI), only use the behavior characteristics. And the experiment results show that this method exhibits good performance for identifying P2P flow.