Optimizing Job Scheduling using Deep Reinforcement Learning

In automated systems, job scheduling efficiently allocates jobs to a system to maximize resource utilization and minimize completion time. In this paper, we consider the problem of job scheduling to minimize the makespan time of jobs and maximize resource utilization. To solve this problem, we propose a deep Q-learning model. To assess the efficacy of the proposed model, we compare it against four existing models over two different data sets. The experimental results show that our model outperforms the existing models or yields commensurable results.