Research And Implement Of DFI Traffic Classification

Network traffic analysis and classification is a fundamental technology enabling network operators to monitor network usage and manage network effectively. It is of great significance to classify network traffic accurately. However, with the great development of Internet, network traffic becomes various, new traffic emerges in endlessly and private traffic is widely used. All these make traffic classification more difficult. Port, DPI and DFI are main methods to classify traffic. With the advent of new traffic and private traffic, Port and DPI are not suitable. DFI is a new method to traffic classification. We don't have to analyze packet deeply, information got from general network monitoring equipment is enough. More and more DFI technology is used in traffic classification. Besides, Machine Learning is introduced in this paper.Currently, P2P application accounts for a majority of the network traffic. It is significant to study P2P recognition for network monitoring and management, as well as the improvement of service quality. There are many ways to identify P2P traffic, but it is difficult to identify effectively with only one method. To obtain the optimal classification, different methods should be used comprehensively. Take the consideration of efficiency and cost, a comprehensive classification system based on DPI and DFI is proposed which can effectively identify P2P applications.