Abstract
Grid computing is a computational paradigm that emerged to left-to-right markleft-to-right markhandle the increasing demand for left-to-right markcomputational resources. Several metaheuristics methods left-to-right markleft-to-right markhave been applied left-to-right markto tackle the grid task scheduling problem. left-to-right markleft-to-right markThese metaheuristics generally generate good but not optimal left-to-right markleft-to-right marktask left-to-right markschedules. The aim of this paper is to design and left-to-right markleft-to-right markimplement a grid task scheduling mechanism to map clients' tasks to left-to-right markleft-to-right mark left-to-right markavailable resources in order to finish the submitted tasks left-to-right markleft-to-right markwithin the optimal execution time. The paper proposes left-to-right markan left-to-right markleft-to-right markenhanced time shared metaheuristics mechanism based on left-to-right markleft-to-right markFirefly Algorithm to left-to-right markleft-to-right markimprove the grid job scheduling process. The proposed mechanism utilizes the Smallest Position left-to-right markValue (SPV) technique to handle the scheduling problem as left-to-right markpermutations. Experiments using left-to-right markleft-to-right marksimulations and real workload traces were left-to-right markconducted to study left-to-right markleft-to-right markthe performance of the proposed enhanced time shared left-to-right markleft-to-right markmetaheuristic scheduling mechanism. left-to-right markEmpirical results revealed left-to-right markleft-to-right markthat the proposed timed shared left-to-right markmetaheuristic algorithm can efficiently reduce the makespan time to 1851 compared with 3482, 3185 for Tabu search and genetic algorithm, respectively.