A study on cost-effective P2P traffic classification

Tao Ban, Shanqing Guo, Masashi Eto, Daisuke Inoue, Koji Nakao

Abstract: Characterization of Peer-to-Peer (P2P) traffic is an essential step to develop workload models towards capacity planning and cyber-threat countermeasure over P2P networks. In this paper, we present a new scheme for characterizing P2P file sharing hosts based on transport layer statistical features. The proposed scheme is featured by its tunability over monitoring cost, system response time, and prediction accuracy. We further employ feature selection to identify the most essential discriminators for the analysis. Experimental results show that an equally accurate system could be obtained using only 3 out of the 18 defined discriminators, which further enhances the adaptability and reduces the monitoring cost of the system.