Joint Optimization of Resource Allocation and User QoS Satisfaction Control for Efficient Grid Resource Management and Scheduling

This paper exploits the interlayer coupling of a cross-layer design concept in Grid computing environment. An algorithm for joint optimization of resource allocation and user quality-of-service (QoS) satisfaction control that combines both application-centric and system-centric scheduling benefits is proposed. The algorithm aims to maximize the global utility as well as the QoS is guaranteed. We formulate the problem into a constrained optimization problem. The simulations demonstrate the advantage of the proposed scheduling algorithm by comparing with application-centric and system-centric scheduling algorithm, respectively.