Performance evaluation of threshold-based ATM cell scheduling policies under Markov modulated Poisson traffic using stochastic Petri nets

This paper addresses the modelling and evaluation of cell scheduling policies in ATM multiplexers using stochastic Petri nets. In particular, we compare four cell scheduling policies: a FIFO policy with and without non-preemptive priorities, a threshold priority policy as recently proposed by Lee and Sengupta, and an extension thereof. The aim of this paper is twofold. First, we want to stress the suitability of stochastic Petri nets as a versatile tool for modelling and evaluating ATM-related performance issues. Secondly, we like to point out that under fairly realistic traac conditions, i.e., under a combination of Poisson nonreal-time (data) traac and MMPP real-time (video) traac, our proposed extension of the threshold priority scheduling policy not only reduces the average delay for real-time traac at the cost of only a slight increase of the average delay of nonreal-time traac, but also reduces the delay jitter in the real-time traac.