Online Wireless Mesh Network Traffic Classification using Machine Learning

Abstract

Internet traffic classification based on flow statistics using machine learning has attracted great attention. Wireless mesh networks (WMNs) facilitate the extension of wireless local area networks into wide areas and have emerged as a key technology for next-generation wireless networking. Online and accurate traffic classification is a key challenge for wirless mesh network management. We propose an online wireless mesh network traffic classfication using C4.5. We evaluate the effectiveness of our proposed method through the experiments on real mesh traffic traces. Experiment results illustrate this method can classify online wireless mesh network traffic with high accuracy.