Solving P2P Traffic Identification Problems Via Optimized Support Vector Machines

Since the emergence of peer-to-peer (P2P) networking in the last 90s, P2P traffic has become one of the most significant portions of the network traffic. Accurate identification of P2P traffic makes great sense for efficient network management and reasonable utility of network resources. Application level classification of P2P traffic, especially without payload feature detection, is still a challenging problem. This paper proposes a new method for P2P traffic identification and application level classification, which merely uses transport layer information. The method uses support vector machines which have been optimized for performing large learning tasks, rendering that this method become more suitable for large network traffic. The experimental results show that this method achieved high efficiency and is suitable for real-time identification. And carefully tuning the parameters could make the method achieve high accuracy.