Joint Application-Fabric Layer Optimization in Grid Computing

The paper exploits the interlayer coupling of across-layer design concept in grid computing environment. A joint application and fabric layer resource scheduling algorithm which combines both application-centric and system-centric scheduling benefits is proposed. We formulate the integrated design of resource allocation and user QoS satisfaction control into a constrained optimization problem. The application layer adaptively adjusts user´ s resource demand based on the current resource conditions, while the fabric layer adaptively allocates CPU, storage and bandwidth required by the upper layer.