P2P Streaming Traffic Classification in High-Speed Networks

作     者：陈陆颖 丛蓉 杨洁 于华 Chen Luying;Cong Rong;Yang Jie;Yu Hua

作者机构：School of Information and Communication EngineeringBeijing University of Posts and Telecommunications 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2011年第8卷第5期

页      面：70-78页

核心收录：

学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081001[工学-通信与信息系统] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by State Key Program of National Natural Science Foundation of China under Grant No.61072061 111 Project of China under Grant No.B08004 the Fundamental Research Funds for the Central Universities under Grant No.2009RC0122 

主　　题：traffic classification machine learning P2P streaming packet sampling deep flow inspection 

摘      要：The growing P2P streaming traffic brings a variety of problems and challenges to ISP networks and service providers.A P2P streaming traffic classification method based on sampling technology is presented in this *** analyzing traffic statistical features and network behavior of P2P streaming,a group of flow characteristics were found,which can make P2P streaming more recognizable among other *** from Netflow and those proposed by us are compared in terms of classification accuracy,and so are the results of different sampling *** is proved that the unified classification model with the proposed attributes can identify P2P streaming quickly and efficiently in the online *** with 1:50 sampling rate,the recognition accuracy can be higher than 94%.Moreover,we have evaluated the CPU resources,storage capacity and time consumption before and after the sampling,it is shown that the classification model after the sampling can significantly reduce the resource requirements with the same recognition accuracy.