FRACTAL TRAFFIC FLOWS IN HIGH-SPEED COMMUNICATIONS NETWORKS

Abstract

Traditional queueing models for traffic flows in communications networks are based on Markovian assumptions. However, recent studies within Bellcore of large sets of real-time network traffic measurements have revealed that traffic in computer and emerging high-speed networks has features that are more accurately and more efficiently described in terms of fractal models, rather than traditional Markovian models. This paper briefly reviews these measurement studies, and motivates the application of fractals to describe and analyze traffic flows in modern communications networks.