A Parallel-Batch Multi-Objective Job Scheduling Algorithm in Edge Computing
Xing-guang Zhao, Xing Lin Guo, Yiwen Zhang, Wei Li · 2018
Edge computing emerges as a novel technique to improve the quality of computation experience for mobile devices which offload computation-intensive jobs to the edge cloud. How to scheduling jobs with limited computation resource on edge servers is a significant scientific problem in edge computing. To handle this problem, in this paper, firstly we propose a Multi-objective job scheduling algorithm with parallel-batch job processing way which optimizes objectives: minimize the overhead and the number of fail jobs which overstep their deadline in edge cloud. Then, considering the unequal performance of the servers and the different slack of waiting for processing of jobs, we define two factors, the processing efficiency of the server and the priority of the job, to optimize the effectiveness of our algorithm. Finally, we design the simulation experiments to compare our algorithm with some existing scheduling algorithms. The results of experiments show our algorithm is efficient and reliable in reducing the overhead and guaranteeing the timeliness of jobs scheduling in edge cloud.