Solving Job Scheduling Problem in Computational Grid Systems Using a Hybrid Algorithm

Abstract

Grid computing is a high performance distributed computing system that consists of different types of resources such as computing, storage, and communication. The main function of the job scheduling problem is to schedule the resource-intensive user jobs to available grid resources efficiently to achieve high system throughput and to satisfy user requirements. The job scheduling problem has become more challenging with the ever-increasing size of grid systems. The optimal job scheduling is an NP-complete problem which can easily be solved by using meta-heuristic techniques. This chapter presents a hybrid algorithm for job scheduling using genetic algorithm (GA) and cuckoo search algorithm (CSA) for efficiently allocating jobs to resources in a grid system so that makespan, flowtime, and job failure rate are minimized. This proposed algorithm combines the advantages of both GA and CSA. The results have been compared with standard GA, CSA, and ant colony optimization (ACO) to show the importance of the proposed algorithm.