A Parallelized Dynamic Task Scheduling for Batch of Task in a computational grid

Abstract

ABSTRACTThe emerging computational grid (CG) system is used for effective utilization of geographically dispersed computing resources in order to fulfill the compute-intensive requirement of the users. Mapping and scheduling of a Batch of Task (BoT) on CG resources have been proved to be NP-complete. In this paper, we propose a Parallelized Dynamic Task Scheduling (PDTS) approach for BoT to minimize job completion time and improving resource utilization by enhancing task level parallelism. The algorithm works in two phases; the first phase divides the task into subtasks to exploit parallelism while in the second phase when the task is available in the memory for execution, it allocates it to the most suitable and available resources dynamically. A simulation study has been carried out to evaluate PDTS by comparing with other heuristic approaches with similar objectives by using the GridSim toolkit. The obtained empirical results show that PDTS outperforms than other considered scheduling strategies in all the cases under study.