Efficient semi-supervised learning bittorrent traffic detection - an extended summary
ICDCN'12 Proceedings of the 13th international conference on Distributed Computing and Networking
Hi-index | 0.00 |
Increasing amount of P2P services not only consuming a lot of bandwidth but also influencing the performance of other business. In order to identify and control P2P flow better, this paper introduced the common methods of P2P traffic identification and proposed a high efficient method to identify P2P traffic which based on both Payload character in application layer and flow characteristics in transport layer, and then introduced some p2p flow characteristics which summed as formula, introduce system flow-chart ,the implement of the port matching module ,the flow character matching module and the payload character matching module minutely. In the end, paper particular introduce the test result of this method.