An Effective Network Traffic Classification Method英文文献资料.pdfVIP

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, VOL. 10, NO. 2, JUNE 2013 133 An Effective Network Traffic Classification Method with Unknown Flow Detection Jun Zhang, Member, IEEE, Chao Chen, Student Member, IEEE, Yang Xiang, Senior Member, IEEE, Wanlei Zhou, Senior Member, IEEE, and Athanasios V. Vasilakos Senior Member, IEEE Abstract—Traffic classification technique is an essential tool flow level statistical properties [1], [10]. Substantial attention for network and system security in the complex environments has been paid on the application of machine learning tech- such as cloud computing based environment. The state-of-the- niques to flow statistical features based traffic classification art traffic classification methods aim to take the advantages of flow statistical features and machine learning techniques, [2]. However, the performance of the existing flow statistical however the classification performance is severely affected by feature based traffic classification is still unsatisfied in real limited supervised information and unknown applications. To world environments. achieve effective network traffic classification, we propose a A number of supervised classification algorithms and un- new method to tackle the problem of unknown applications supervised clustering algorithms have been applied to net- in the crucial situation of a small supervised training set. The proposed method possesses the superior capability of detecting work traffic classification. In supervised traffic classification unknown flows genera