A NOVEL APPROACH FOR REAL TIME INTERNET TRAFFIC CLASSIFICATION

Real time internet traffic classification is imperative for service discrimination, network security and network monitoring. Classification of traffic depends on initial first few network packets of full flows of captured IP traffic. Practically, the real world framework situation expects correct conclusion of classification well before a flow has ended even if the start of the Traffic flow is missed. This is achieved by calculating features from few N network packets, taken at any random time instant at any random point in the duration of flow. This research proposes a novel parameter Relative Uncertainty (RU) to estimate the level of diversity of internet traffic and can then be used for characterization of internet traffic. Small sub-flows from Full-flows are selected based on minimum RU value (MRUB-SFs: Minimum RU Based Sub Flows), and then features are calculated for training the C4.5 ML classifier. Experimentation is carried out with various standard datasets and results stable accuracy of 99.3167% for different classes of applications.