中文摘要：

为了使网络管理员能更好地监控和管理P2P流量数据，分析了运行不同P2P应用时的主机行为特征，提出一种基于端口特征的P2P应用识别方案．该方案利用P2P应用的UDP监听端口产生的数据报长度及其分布特征，通过机器学习的方法对监听端口进行分类，进而识别出对应的P2P应用．实验结果表明，该方案能有效地识别节点主机运行的不同的P2P应用，尤其对于视频类P2P应用的识别准确率可以达到99．9l％．

英文摘要：

To make the network administrators to monitor and manage P2P traffic data efficiently, a port feature based P2P application identification method was proposed, following with the analysis of behavioral characteristics of diverse P2P applications. In the proposed method, both of the packet length and the distribution of packet size with respect to each UDP port were employed to form a vector for each P2P application, and then the work of P2P application identification could be done effectively by a machine learning method, i. e. , support vector machine. Results show that the proposed method can distinguish the different P2P applications effectively, especially for the video applications which can be achieved for a precision of 99.91%.