COMPUTATIONAL METHODS FOR PERFORMANCE EVALUATION OF A STATISTICAL MULTIPLEXER SUPPORTING BURSTY TRAFFIC

A statistical multiplexer supporting a number of bursty sources is mod eled as a discrete time, single server queueing system with an infinit e buffer. The probability generating function (PGF) method is used to analyze the queueing behavior. The PGF method requires the determinati on of a large number of boundary values and, hence, the roots of the c haracteristic equation. An iterative algorithm to evaluate the charact eristic roots is proposed. When the arrival process is a superposition of independent processes, a decomposition approach is used to reduce the state space involved in the computational algorithm. Additionally, the computational algorithm is made efficient through the establishme nt of conditions under which all the roots are either real or nonnegat ive real numbers. A set of equations to recursively compute the moment s of the queue length are established. Sample applications of the comp utational methods to evaluate the performance of a multiplexer support ing voice and video sources, modeled by two-state Markov and L-state M MPP processes, respectively, demonstrate the viability of the proposed methods.