Traffic shaping and traffic policing impacts on aggregate traffic behaviour in high speed networks

Abstract

Aggregate traffic in high speed networks is characterized by “burst within burst” structure over a wide range of time scales, heavy tailed inter-arrival time densities, self-similarity and long range dependence. These properties are followed by a degradation of quality of service in aggregate traffic. A high self-similarity grade will eventually fill up the network equipments memory and queues no matter how large they are designed. This paper compares the effect of traffic shaping and traffic policing on aggregate traffic dynamics especially stochastic properties on traffic time series. We propose a series of tests and compare the result obtained from OPNET Modeler simulation program to simulation with synthetic traffic generated by chaotic dynamic systems. We are interested in parameters such as Hurst parameter, autocorrelation function and variance for different shaping and policing techniques applied to input traffic in order to obtain smooth aggregate traffic trace.