Analysis off scheduling algorithms for integrated-services networks using a semi-fluid-flow model

An approach to evaluating performance with such algorithms as the cost-based scheduling, occupancy-based, priority token bank, and leaky bucket algorithms in the realistic case in which data arrivals are highly bursty, but voice and video packets are not, is presented. The mean queuing delay for data bursts is determined analytically in some important scenarios, and an efficient simulation approach based on the same model is described for cases in which analysis is not currently possible. The model is a semi-fluid-flow model in which voice or video packets are assumed to arrive as a continuous-bit-rate fluid flow, whereas bursts of data arrive according to a Poisson process. The extent to which performance for a given load can be improved by using one of the above algorithms, rather than the static priority algorithm, is shown