Network traffic modeling and the transmission control protocol

The discovery of the self-similar nature of network traffic in 1993 led to radical changes in traffic modeling and our understanding of network behavior. With the long-range dependence and bursty nature of self-similar traffic, network performance degrades significantly and traditional network design and management techniques become insufficient. Accurate characterization of network traffic and understanding the causes behind its self-similarity is thus of utmost importance to understanding and alleviating the undesirable effects of long-range dependence.; In this thesis we look at various aspects of network traffic modeling with a particular emphasis on TCP traffic. Our approach is based on understanding and modeling the causes behind the way traffic sources behave rather than to just characterize them. We begin with some of the practical issues and develop a more realistic traffic generator for the network simulator ns. We then derive two convergence results which show the weak convergence of MMPP and FARIMA based long range dependent sources to fractional Brownian motion. The remainder of the thesis concentrates on TCP traffic where we first model the steady-state throughput and latency of various versions of TCP under both correlated and independent losses. Using these derivations as the basis to model the packet transmission pattern of TCP sources, we then explore the effect of TCP on the self-similar and multifractal nature of network traffic. Our results show that TCP's congestion control mechanism, in particular its exponential backoff and slow start mechanism can lead to long range dependence and the degree of self-similarity is directly proportional to the loss rates experienced by the flow.; We then develop a cascade based multifractal model for TCP traffic which relates network parameters like loss rates and round trip times to the scaling exponents. A Markov chain model for TCP flows is developed and analyzed next for lightweight and efficient simulation of TCP traffic. Finally, we propose and demonstrate the effectiveness of various ways of reducing the self-similarity in network traffic by eliminating the TCP related causes of self-similarity.