Identification of Peer-to-Peer Applications' Flow Patterns

Abstract

Peer-to-peer file-sharing systems have gained tremendous popularity in the past few years. More users are continually joining such systems and more objects are being made available, seducing even more users to join. Today, the traffic generated by P2P systems accounts for a major fraction of the Internet traffic and is bound to increase. An accurate mapping of traffic to their applications can be very important for a broad range of network management and measurement tasks including traffic engineering, service differentiation, performance/failure monitoring, and security. Traditional mapping approaches have become increasingly inaccurate because many applications use non-default or ephemeral port numbers, use well-known port numbers associated with other applications, change application signatures or use traffic encryption. This paper presents a new approach, based on neural networks, that is able to identify flow patterns generated by P2P Internet applications while overcoming the limitations of existing approaches. The results obtained show that, when conveniently trained, neural networks constitute a valuable tool to identify P2P Internet applications since they are able to achieve good performance results while, at the same time, avoid the most important disadvantages presented by the other identification methods.