Modeling Caching E ect in Continuous Media

Caching is one of the most important schemes for improving the performance of continuous media servers. Continuous object caching enables a server to support more clients simultaneously since it reduces the disk load imposed at each round. But, without a quan-tative analysis of the disk load reduction induced by caching, the caching eeect can not be reeected in the admission control scheme, which limits the number of simultaneous clients serviced. In this paper, we propose a probabilistic model of the caching eeect in a continuous media server. The proposed model divides the disk load reduction induced by caching into disk overhead reduction and block transfer reduction, and models each reduction stochastically to generate the overall reduction model. The proposed model enables the development of a lot of statistical admission control algorithms that can increase the number of clients serviced simultaneously. In this paper, we present a simple example of a statistical admission control algorithm and demonstrate the performance enhancement resulting from caching and the algorithm with an appropriate simulation.