A fast computational algorithm for simulating round-robin service

An efficient computation-based algorithm for effecting round-robin (RR) service in discrete-event simulation systems is presented. The new algorithm improves upon an older computational algorithm which itself is an improvement over naive RR scheduling currently in use in process-oriented simulation systems. The naive approach can be prohibitively expensive due to process context switch overhead. The original computational algorithm avoids much of this context switching but offers a run-time complexity of only O(n²), where n is the size of the job pool. This is because the processing of each arrival and departure event requires a traversal of the entire pool. In this paper, we propose an improved algorithm which reduces run-time complexity to O(n log n) by using tree-based data structures. The expected computation to process each arrival or departure event is proportional to O(log n). Empirical evidence suggests that, except for very small size of job pool, this algorithm is considerably faster than other methods.