An Efficient Memetic Algorithm for Job Scheduling in Computing Grid

Grid job scheduling is an NP complete problem, concerning the large-scale resource and job scheduling, and the adoptive and efficient job scheduling algorithm is required. Genetic algorithms show good capability to solve the problem of the small-scale, but with the increase in the number of jobs and resources, genetic algorithm is hard to convergence or slow convergence. This paper proposed a Memetic Algorithm which designed crossover operators and mutation operator with hill-climbing algorithm and Tabu search algorithm for processing grid job scheduling. Hill Climbing scheduling usually can enhance processor utilization, and Tabu search algorithm have shorter completion times for job scheduling in computing grid. And then the algorithms' search ability and convergence speed were compared. The simulation results shown that the proposed algorithm can effectively solve the grid job scheduling problem.