Modeling of Network Traffic Student : Aditya Dua ( 97 D 07003 ) Guide

Traffic models are at the heart of any performance evaluation of telecommunication networks. An accurate estimation of network performance is critical for the success of broadband networks, which need to guarantee acceptable quality of service (QoS) to the users. A good traffic model should be accurate enough to capture the statistical characteristics of actual traffic, and at the same time should be computationally efficient. Recent analysis of network traffic reveals the presence of long-range dependence (LRD), a statistical property which traditional traffic models cannot capture. This report discusses modeling of traffic with both short-range and long-range dependent models. The relatively new field of multifractal modeling has also been explored. Keywords—Network Traffic, Short Range and Long Range Dependence, Self Similarity, Wavelets, Point Processes, Multifractals .