期刊名称:International Journal of Computer Science Issues
印刷版ISSN:1694-0784
电子版ISSN:1694-0814
出版年度:2011
卷号:8
期号:2
出版社:IJCSI Press
摘要:Over the years, grid computing has emerged as one of the most viable and scalable alternatives to high performance supercomputing, tapping into computing power of the order of Gigaflops. However, the inherent dynamicity in grid computing has made it extremely difficult to come up with near-optimal solutions to efficiently schedule tasks in grids. The present paper proposes a novel grid-scheduling heuristic that adaptively and dynamically schedules tasks without requiring any prior information on the workload of incoming tasks. The approach models the grid system in the form of a state-transition diagram, employing a prioritized round-robin algorithm with task replication to optimally schedule tasks, using prediction information on processor utilization of individual nodes. Simulations, comparing the proposed approach with the round-robin heuristic, have shown the given heuristic to be more effective in scheduling tasks as compared to the latter.