Job Scheduling in Computational Grid Using a Hybrid Algorithm Based on Genetic Algorithm and Particle Swarm Optimization

Grid computing has been treated as a new paradigm for solving large and complex scientific problems using resource sharing technique through many distributed administrative domains. The dynamic nature of Grid resources and the demands of users create challenge in the Grid scheduling problem that cannot be addressed by deterministic algorithms with polynomial time complexity. Thus, the use of meta-heuristic is more appropriate option in obtaining optimal results. The Genetic Algorithm (GA) has been proven as one of the best methods for Grid scheduling. The GA explores the problem space globally, but is sometimes unable to search locally. Thus, a hybrid algorithm is proposed which combines intelligently the GA with Particle Swarm Optimization (PSO) for the Grid job scheduling. The hybrid GA-PSO aims to reduce the schedule makespan and flow-time. The proposed hybrid algorithm is compared with the standard GA and PSO on both parameters. The comparison results exhibit that the proposed algorithm outperforms other two algorithms.