Self-Similar Traffic Models

With the advent of broadband communications characterized by a heterogeneous traffic mix (e.g. video conferencing applications, ftp, browsing the web....), commonly held assumptions of traditional traffic models have been put into question. Essentially the present type of traffic is of a highly bursty nature, which is not captured by the traditional traffic models (e.g. Poisson Process). This has a major impact on the design of a network. New models that characterize this burstiness effect are required for the analysis, design, planning, engineering and congestion management of broad-band networks [1].Measurements using high-resolution traffic equipments of wide area network traffic have confirmed this particular traffic phenomenon. The features shown by the traffic have been called "self-similar or fractal traffic". Their important properties are stated below [1] :- Distributions of the actual traffic processes decay more slowly (heavy tailed, e.g. of such a distribution is the Pareto distribution) than exponentially (light tailed e.g. a Poisson distribution). See definition of heavy tail and light tailed distribution in the appendix. Correlations exhibit a hyperbolic (long range dependence) rather than an exponential (short range dependence) decay. Traditional traffic models used in queueing analysis assume variations only in limited time scales while long-range dependent or self-similar processes fluctuate over a wide range of time scales. This report tries to present various traffic models that represent these properties and the important parameters that need to be estimated which will hopefully enable the design of an optimum network