Network Traffic Classification Schema Research And Implementation Based On Semi-Supervised Support Vector Machine

A variety of network applications are running on network currently and new applications are still emerging. The traffic classification of application layer is the premise and basis of identifying network applications, which helps to analyze trend, control dynamic access, study differences of services, detect intrusion, monitor traffic, manage billing and analyze users'behavior. Moreover, it is also the important reference of network security and traffic engineering. So how to classify applications accurately and identify new applications has an important significance for network administrators, researchers, service providers and users.Current popular methods of traffic classification mainly include machine learning algorithm based on supervised and unsupervised and the method based load. In practical applications, the above methods have high complexity or low accuracy degree, so we propose a semi-supervised support vector machine method only based on flow statistics to identify and classify network applications. In this method, SVM, constant flow and co-training algorithm are the key to obtain a classifier rapidly. The classifier got by this method has three advantages contrast to the previous classical methods:1) high classification degree; 2) high generalization performance; 3) rapid computational performance. As a proof of concept, we implement the classification algorithm based on open-resource, and show the characteristics and feasibility of our method in the campus and resident network.