Admission Control and Q0S Negotiations for Soft-Real Time

Date of Submission: 
October 9, 1998
Report Number: 
Systems are increasingly supporting a new class of multimedia applications that allow degradation of the application quality so that they use reduced amounts of resources. Management of such applications require new mechanisms to be developed for admission control, negotiation, allocation and scheduling. In this paper we present a new admission control algorithm that exploits the degradability property of applications to improve the performance of the system. The algorithm is based on setting aside a portion of the resources as reserves and managing it intelligently so that the total utility of the system is maximized. The mixed greedy and predictive strategy leads to an efficient protocol that also improves the performance of the system. We use the constructs of application benefit functions and resource demand functions in the integrated admission control and negotiation protocol. Extensive simulation experiments are presented in the paper to evaluate the performance of the novel mechanisms and compare it to some of the other methods used in the past.