Journal of Beijing University of Posts and Telecommunications

  • EI核心期刊

JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM ›› 2008, Vol. 31 ›› Issue (2): 15-19.doi: 10.13190/jbupt.200802.15.linp

• Papers • Previous Articles     Next Articles

A Network Traffic Classification Algorithm Based on Flow Statistical Characteristics

LIN Ping, YU Xun-yi, LIU Fang, LEI Zhen-ming   

  1. Key Laboratory of Information Processing and Intelligent Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2007-06-19 Revised:1900-01-01 Online:2008-04-28 Published:2008-04-28
  • Contact: LIN Ping

Abstract:

Based on analysis of application protocols, a group of multi-flow characteristics with low complexity, high quality is proposed to mitigate the problem of low recognition rate and high implementation complexity associated with the traditional flow classification algorithms using single flow statistics. These characteristics can effectively identify peer-to-peer (P2P) traffic in network flow classification, and improve the recognition rate of the traditional algorithms. They also enable the use of multinomial logistic regression algorithm to classify the network flow, and reduce the complexity of the traditional algorithms. Experiment results show that the proposed characteristics can achieve good generalization, and only need a small number of training samples to get a model that can maintain good performance for a long time.

Key words: network traffic classification, flow, statistical characteristics, multinomial logistic regression

CLC Number: