Applying Support Vector Machine to P2P Traffic Identification with Smooth Processing

Since the emergence of peer-to-peer (P2P) networking in the last 90s, P2P traffic, being a significant portion of the network traffic today, has constituted a highly desirable class for identification. How to improve the accuracy of the P2P traffic identification efficiently is still a challenging problem. The support vector machine (SVM) is a powerful learning mechanism and has shown remarkable success in many applications. In this paper, we propose a new approach for P2P traffic identification, which uses the support vector machine and a new technology called smooth processing. The experiments of identifying P2P traffic show that the generalization performance and the accuracy of identification are improved significantly compared to that of the traditional methods