Traffic identification method based on multiple probabilistic neural network model

Abstract

Traffic identification is currently an important challenge for network management and security. In this paper, we propose a novel application identification method named as MPNN to improve the efficiency and flexibility of application identification. MPNN is based on a structure of multiple neural networks, and it uses an individual neural network module to handle a single application; therefore, it can effectively utilize the characteristics of every application; meanwhile, the minimum Bayes method is used in every neural network module. The MPNN method has the following advantages: it can handle more complex network behavior and extend the identified object from complete TCP flows to all TCP+UDP flows. It can improve the identification accuracy of every application, especially for those applications which containing much less traffic than others. The process of changing identified applications become much easier. Due to adopting parallel processing, it has much lower time and space complexity. The theoretical analysis and experimental results show that MPNN could achieve 95% identification accuracy.