Queueing Dynamics and Maximal Throughput Scheduling in Switched Processing Systems
Queueing Systems: Theory and Applications
Universal stability results for greedy contention-resolution protocols
FOCS '96 Proceedings of the 37th Annual Symposium on Foundations of Computer Science
Achieving stability in networks of input-queued switches
IEEE/ACM Transactions on Networking (TON)
Job scheduling for maximal throughput in autonomic computing systems
IWSOS'06/EuroNGI'06 Proceedings of the First international conference, and Proceedings of the Third international conference on New Trends in Network Architectures and Services conference on Self-Organising Systems
| Hi-index | 0.00 |
Recent developments in computer and communication networks require scheduling decisions to be made under increasingly complex system dynamics. We model and analyze the problem of packet transmissions through an arbitrary network of buffered queues, and provide a framework for describing routing and migration. This paper introduces an intuitive geometric description of stability for these networks and describes some simple algorithms which lead to maximal throughput. We show how coordination over sequential timeslots by algorithms such as those based on a round robin can provide considerable advantages over a randomized scheme.