Practical aspects of simulating systems having arrival processes with long-range dependence
Robert Geist, James M. Westall · 2000
Analysis of network traffic indicates that packet arrival processes have significant stochastic dependence. It has been suggested that this dependence is so strong as to be wellmodeled by long-range dependent processes. The fact that no finite process can be said to be truly long-range dependent poses potentially serious obstacles to simulation modeling. In this paper, we explore some of these obstacles and propose practical methods for obtaining useful results with simulations of manageable duration. Keywords: Analysis methodology; network traffic models; stochastic dependence; long-range dependence.