A Highly Efficient M/G/α Generator of Self-Similar Traces

Several traffic measurements reports have convincingly shown the presence of self-similarity in current networks, inducing a revolution in the stochastic modeling of traffic. The essence of this behavior can be captured by several classes of self-similar processes. But the use of these processes in performance analysis has opened new problems and research issues in simulation studies, where the efficient generation of synthetic sample paths with self-similar properties is one of the main topics. In this paper, we present an M/G/α generator of self-similar traces, based on a highly efficient simulation model using the decomposition property of Poisson processes and the memoryless property of geometric random variables.