A Task Duplication Based Efficient Multi-Objective Grid Workflow Scheduling Algorithm

Abstract

Grid computing facilitates global infrastructure for user to consume the services over the network. To achieve the promising potentials of enormous distributed resources, effective and efficient scheduling algorithms have to be used. Most of the parallel applications in grid computing fall into interdependent task model called workflow. Grid workflow scheduling represented by Directed Acyclic Graph (DAG) is a typical NP-Complete problem. The performance of the workflow scheduling is based on efficient scheduling. Scheduling is a process that maps and manages the execution of interdependent tasks on the distributed resources. In this paper, a new algorithm, named Task Duplication Based Efficient Multi-Objective Scheduling (TDB-EMOS) algorithm is proposed to satisfy multi objective functions. It maximizes the resource utilization in a grid, minimizes makespan and communication cost/time by reserving the resources in advance and schedules the task on priority. The proposed algorithm has been implemented with arbitrary task graphs and application graphs in a simulated environment. The results are compared with the well known Min-Min, HEFT, EDOS (Efficient Dual Objective Scheduling) and EDS-G (Economical Duplication Scheduling in grid) scheduling algorithms and showing that the proposed algorithm is yielding better results. Keywords: Grid Computing; DAG; Workflow scheduling; Heterogeneous systems; Parallel processing.