A Global Benefit Maximization Task-Bundle Allocation

Obtaining maximal benefit is usually the most important goal pursued by Grid resource/service provider. As providers and users being noncooperative inherently, it is a fundamental challenge to design a resource allocation strategy which seems to be fair. In order to adapt to large-scale Grid environment, we adopted a hierarchical grid structure with bundle tasks to describe the Grid system. A model called Intra-Site Cooperative-game of Taskbundle (ISCT) was proposed, in which all subordinate resources participated in making profits. We calculated task market price based on the theoretical proof that the system would gain maximal global benefit if and only if it was in a balanced state. Then we determined the task allocation solution with solving the task assignment amount vector. An Intra-Site Global Benefit Maximization Allocation for Task-bundle (ISGBMAT) was presented, which converted the Grid task-bundle allocation problem into an iteration process involving retail price, market price and assignment amount of tasks. Extensive simulation experiments with real workload traces were conducted to verify our algorithm. The experimental results indicated that ISGBMAT could provide an effective solution with global benefit and completion time optimization and also adapt to dynamic Grid market.