Real-Time Scheduling of Switching Nodes Based on Asynchronous Time Sharing

The performance of a real-time scheduling algorithm for Asynchronous Time Sharing based switching nodes is presented. Three classes of tra c sources are considered to load the switching nodes: real-time video sources, for which the maximum end-to-end delay S I is guaranteed for all the cells; real-time voice sources, for which the maximum end-to-end delay S II is guaranteed with a maximumof % cell loss rate and an average gap length of ; and data tra c for which a minimum average throughput and a maximumaverage time delay is guaranteed. The performance of the proposed algorithm is compared with other known algorithms in terms of complexity in implementation, knowledge structures and performance. Our investigations are supported throughout by simulation results.