Dynamic Window-constrained Scheduling of Loss and Delay Constrained Traac Streams

This paper describes an algorithm, called Dynamic Window-Constrained Scheduling (DWCS), designed to meet the service constraints on packets from multiple, network-bound media streams with diierent performance objectives. Using only two attributes, a deadline and a loss-tolerance per packet stream, DWCS: (1) can limit the number of late packets over nite numbers of consecutive packets in loss-tolerant or delay-constrained, heterogeneous traac streams, (2) does not require a-priori knowledge of the worst-case loading from multiple streams to establish the necessary bandwidth allocations to meet per-stream delay and loss-constraints, and (3) can exhibit both fairness and unfairness properties when necessary. In fact, DWCS can perform fair-bandwidth allocation, static priority (SP) and earliest-deadline rst (EDF) scheduling. We show: (1) the eeectiveness of DWCS using a streaming video application, running over ATM, and (2) how DWCS can be eeciently implemented to provide service guarantees to hundreds of streams. We also compare the costs of diierent algorithm implementations, including an approximation algorithm, which trades service quality for speed of execution.