Real Time Traffic Recognition

The rapid growth of Internet in size and complexity, and frequent emergence of new network applications have made it necessary to develop techniques that can monitor and control the traffic. Efficient and accurate recognition of traffic is the key to the management in real time. This thesis work accomplishes the performance evaluation and optimization of a traffic recognition tool called Traffic Analyzer Module (TAM) which implements a technique that is based on passively observing and identifying signature patterns of the packet payload at the application layer, says signature-based payload recognition. This technique has two highlighted features. Firstly, in contrast to most of previous works which perform classification with offline trace files; this technique applies in online mode which can identify the traffic in real time. Secondly, instead of packet inspection, this technique adopts flow inspection, i.e. identifying traffic in terms of flows each of which consists of the well-known 5-tuple, which canproduce more accurate and reliable results. To demonstrate this technique, its throughput is evaluated in online mode within a high bandwidth network. Besides throughput measurement, optimizing the recognition algorithm in order to improve its performance is also a task of this thesis work. The results of performance measurement demonstrate the feasibility and reliability of this technique, as well as indicate some clues for future work