Research On P2P Traffic Identification Based On SVM

Recent years, with the development of the Internet, the application of P2P(peer-to-peer) has taken up 60% to 80% of the total Internet traffic and has became the killer application of Broad Band Internet. And it Seriously affects normal network operation, aroused congestion of network and reduce the performance of other operations. As the same time, some Existing methods of P2P traffic identification, such as port scaning, application signature matching and based on behavior characterization of traffic, can't identify Increasing P2P with Dynamic port and Encrypted, which make the identification of P2P traffic becomes more and more difficult. It is a very urgent resolved problem that how to identify and control P2P traffic rapidly, exactly and effectively.SVM has special advantages with avoiding local optimum, overcoming dimension disaster, resolving small samples and high dimension for P2P Classification Problems, it injects new vitalities for P2P traffic identification technology.In this thesis, we begin with the operating principle of P2P traffic identification. then, we analyze the problem in the identification of P2P traffic and the needed technology to realize the effective P2P identification scheme, and propose the technique on P2P traffic identification based on SVM. The works in this paper has been done is as follows:1. Several kind of solutions in P2P flow identification are researched, analyzed their advantages and disadvantages in the identification process.2. In order to improves effectively identification rate and speed of P2P traffic identification, the paper provided flow identification model with flow characteristics and Feedback Incremental Learning Function. It overcomes the disadvantage of present P2P traffic identification project.3. A kind of algorithm is proposed for P2P flow feature extraction, at the basis of determining SVM input vector, which determines expression as input of SVM. 4. In order to test the new P2P traffic identification solution,this paper designed and implemented a SVM for traffic recognizer in the popular modeling software LIBSVM in MATLAB, and then designed and implemented the P2P flow identification solution on it, and we have made a comparison between P2P flow identification technology proposed and an application signature method introduced by S.Sen.