MinPSL: A high-performance scheduling protocol based on intelligent global message reordering in WDM star networks

Abstract

Several well-known scheduling schemes like EATS and MSL seem to suffer notable performance degradation under the realistic conditions of non-uniform destinations and non-negligible transceiver tuning latencies that apply in practical WDM star networks. Our EMPS protocol has been shown to noticeably increase the performance of practical networks of this kind. Nonetheless, EMPS tries to balance the offered load by only considering the heads of the message queues maintained by the source nodes; therefore, its performance is degraded, especially for medium to high offered loads and for rather slowly tunable transceivers. In this article we propose the Minimization of Probability and Size of scheduling Latency (MinPSL) protocol, which examines each source node's message queue at a certain depth and reorders messages intelligently on the basis of receiver availability. MinPSL perfectly minimizes the probability of having to schedule two or more messages intended for the same destination simultaneously or at close times. The proposed scheme also minimizes the actual performance penalty incurred, when scheduling of consecutive messages with the same destination cannot be avoided. Extensive simulations are carried out in order to study the performance of MinPSL and compare it to EMPS under various conditions. The simulation results ascertain the fact that MinPSL always brings about a considerable performance improvement.