A study on flow based classification models using machine learning techniques

Abstract

Network traffic management facing a lot of challenges in the recent years because of the continuous and fast development in network scale, number of consumers and type of known and unknown applications over the network. Traffic classification is a key factor for providing the quality of network services (QoS), handling the delay and congestion during the transmission. In the field of network traffic classification, Machine learning algorithms are playing key role. In this paper, we would like to discuss widely used techniques such as port based, pay-load based, behavioural based and statistical based classification models have been discussed and sample data sets are produced with graphical notations to strengthen the analysis process. So the comprehensive study on these classification models will provide the clarity on how the traffic is classified, quality of service on the various types of applications and issues of each classification model. Classification used for monitoring the security over the traffic and core element for network intrusion detection system. There are many network servicing areas where we need to identify and classify the traffic such as routing, firewall access-control, policy based routing, traffic billing need to be differentiated and their quality of service has to be assured.