SVM-based Classification Mechanism and Its Application in SDN Networks

Abstract

In recent year, as growth of the cloud computing, mobile network, and Internet-of-Things technology, user requirements for network services, real-time data processing and resource management are becoming more and more diverse. Software defined networking (SDN) and network functions virtualization (NFV) technologies are not only transforming network infrastructure from complicated physical entities to virtual and programmable nodes, but also centralizing the network control to decrease the complexity of network topology. Network security is being questioned because many application traffic hidden in the HTTP and HTTPS protocol, so support vector machine (SVM) based internet traffic identification and classification (STIC) are proposed to identify application traffic. In this paper, STIC mechanism, is addressed to classify 28 application traffic such as Facebook, Line, and YouTube etc. STIC mechanism can not only classify YouTube traffic type, but also classify YouTube streaming in length and quality. Classification accuracies can reach 99.00% accuracy and 92.78% accuracy respectively.