Bi-Objective Workflow Scheduling on Heterogeneous Computing Systems Using a Memetic Algorithm

Due to the high power bills and negative environmental impacts, workflow scheduling with energy consciousness has been an emerging need for modern heterogeneous computing systems. A number of approaches have developed find suboptimal schedules through heuristics by means slack reclamation or trade-off functions. In this article, a memetic algorithm energy-efficient is proposed quality-guaranteed solution runtime efficiency. The basic idea retain advantages population-based, heuristic-based, local search methods while avoiding their drawbacks. Specifically, incorporates improved non-dominated sorting genetic (NSGA-II) explore potential task priorities allocates tasks processors earliest finish time (EFT)-based heuristic provide time-efficient candidate. Then, method integrated pruning technique launched low possibility, exploit feasible region indicated candidate schedule. Experimental results on workflows from both randomly-generated real-world applications suggest that achieves bi-objective optimization, improving makespan, saving 4.9% 24.3%, respectively. Meanwhile, it complexity compared similar work HECS.