Recent findings from detailed studies of traffic measurements from variety of different packet network, have brougbt up a surprising discrepancy between the traditional traffic modelling techniques and the actual network traffic The studies have shown the actual network traffic to be statistically s~~ with significant implications for the design of future multi-senice integrated networks. This new traffic feature can be effectively captured within frsetal models like: f i d Brownian motion (fBm) and fredional ARIu.1 processesAlthough these formal mathematical models provide an elegant solution to the modelling of the se&sbn&u phenomena, an comprehensive queuing analysis of these modeis is still lacTherefore simulations with synthetic s e @ W input trafic are essential for gaining better uoderstandiag of the queuing problems and some initial experience with the performance of the future networks. Consequently fast generation of long traces of se&simih proceses becomes an important task In this paper we will use an fBm generation method called Suxessk RMdom At&&h (SRA) algorithm and carry out a rigorous statistical analysis on the generated t r a~ Our pesults will show that the traces are indeed ~$kbdur, although the parameters obtained may slightly differ from their target values. Our conclusion is that for qualitative studies the SRA algorithm provides a very good traffi source, whereas for quantitative analysis some caution is recommended. W e will also mention some possible applications of the algorithm in performance-related network implementations
I. I "In the last decade networking technology has experienced a tremendous growth and development.Much of this attention is thanks to the enormous popularity of the Broadband Integrated Services Digital Network (B-ISDN) based on the Asynchronous Transfer Mode (ATM) technology, or better known under the well publicised name of the "Information Superhighway". B-ISDN promises to be a single, high speed, seMce independent, flexible and efficient network, that will be able to transport voice, data video and multimedia over the same infrastructure. ATh4 provides the technology needed for carrying out this task; it is supposed to efficiently handle aggregate traffic streams with very different QoS requirements and provide essentially infinitely scaleable connectivity. From traffic modelling point of view, the emergence of modern high speed networks and the prevailing trend towards B-ISDN, combines drastically new and different transmission and switching technologies with a very heterogeneous mixture of seMces and applications. The traditional approach b a d almost exclusively on Poisson (or more generally, Markovian) assumptions, that has worked so well in the past, has undergone an extensive criticism in the new environment, especially because of the complete absence of any practical validation of the increasingly more complex models (e.g., Markovian Arrival Process [3] or Batch-Markovian Amval Process [4]) and their apparent differences with the traffic behaviour seen i...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.