Parallelising the Mean Value Analysis algorithm

The Mean Value Analysis (MVA) algorithm is one of the most popular for eval uating the performance of separable (or product-form) queueing networks. Al though its complexity is modest when jobs are indistinguishable, the introd uction of different customer classes rapidly increases is computational cos t. The problems of parallelising the algorithm while retaining its conceptu al simplicity are examined. In particular, a parallel implementation of MVA on a distributed memory machine is developed using the MPI library for com munication.