A Novel P2P Traffic Identification Scheme Based on Support Vector Machine Fuzzy Network
Zhong Gao, Guanming Lu, Daquan Gu · 2009
With the rapid development of the Internet, the P2P (Peer-to-Peer) technology which is characterized by no utilization of any servers with centralized functions has kept advancing apace. However, how to improve the accuracy of the P2P traffic identification efficiently is still a challenging problem. In this paper, we propose a new approach for P2P traffic identification, which uses a novel Support Vector Machine Fuzzy Network (SVMFN) to make the identification more suitable and accurate in various network environments with different rates. The experimental results show that the generalization performance and the accuracy of identification are improved significantly compared to that of the traditional methods, and adapt to engineering applications.