Research on Network Traffic Identification Based on Improved BP Neural Network
Shi Dong, Dingding Zhou, Wengang Zhou, Wei Ding, Jian Gong · Applied Mathematics & Information Sciences · 2013
Traffic identification is a key task for any Internet Service Providers (ISP) or network administrators. Neural network is an important research method on traffic classification, this paper introduces the important methods of traffic classification,through study on Principal Component Analysis(PCA) and BP neural network. An improved BP neural network to identify traffic is proposed and M OORE SET is used as dataset, meanwhile, building N OC SET dataset based on CERNET(China Education and Research Network).the experiment results show that the accuracy rate of traffic classification based on the improved BP neural network model is relatively high.Finally,this paper analyzes packet sampling impact on traffic identification.