Performance of batching schemes for multimedia-on-demand services

Recent advances in information and communication technologies have made multimedia-on-demand services technically and economically feasible. Important aspects of such systems are the resource sharing techniques, which allow the simultaneous service of a large number of users with considerable savings in terms of network bandwidth and server resources. In this paper, we report the results of a study which analyzes batching and buffering techniques, which involves serving all video requests issued during a short interval of time with a single stream. The mathematical model, based on queueing networks, allows the evaluation of the main system performance (average and probability distribution of the number of streams, percentage reduction of resources, and so on) as a function of load and batching interval duration. Simulation experiments confirm the analytical model in the whole range of considered conditions.