In multi-hop networks, packet schedulers at downstream nodes have an opportunity to make up for excessive latencies due to congestion at upstream nodes. Similarly, when packets incur low delays at upstream nodes, downstream nodes can reduce priority and schedule other packets first. The goal of this paper is to define a framework for design and analysis of Coordinated Network Scheduling (CNS) which exploit such inter-node coordination. We first provide a general CNS definition which enables us to classify a number of schedulers from the literature including, FIFO+, CEDF, and work-conserving CJVC as examples of CNS schedulers. We then develop a distributed theory of traffic envelopes which enables us to derive end-to-end statistical admission control conditions for CNS schedulers. We show that CNS schedulers are able to limit traffic distortion to within a narrow range resulting in improved endto-end performance and more efficient resource utilization.
Chengzhi Li, Edward W. Knightly