Research of P2P Traffic Identification Based on Neural Network

P2P traffic has become one of the most significant portions of the network traffic. How to improve the accuracy of the traffic identification efficiently is still a difficult problem. A promising approach that has recently received some attention is traffic classification using machine learning techniques. In this paper, we propose a BP neural network algorithm for P2P traffic classification problem. We implement a P2P traffic identification prototype system which can realize offline learning and online classification of P2P traffic effectively. The results show that the method provides a promising way to measure aggregate P2P traffic.