A performance analysis of the ATM multiplexer with space priority queueing management

Abstract

We present a discrete-time queueing analysis of the ATM multiplexer fed by independent binary Markov sources with two priority classes of cells. Each source alternates between on, off periods and each on period consists of a random number of sub-periods. Each sub-period generates geometrically distributed number of cells, the first cell of a sub-period is assigned high-priority while remaining cells are assigned low-priority. During congestion the system delivers only high-priority cells and discard low-priority cells. We present the probability generating function of the queue length, mean delay under infinite buffer assumption and approximate cell loss probabilities for the finite buffer case.