A hybrid manufacturing scheduling optimization strategy in collaborative edge computing

In the era of Industry 4.0, hybrid scheduling based on collaboration edge computing has the advantages of high computational power and low latency, which can meet the needs of smart manufacturing scheduling. However, existing scheduling schemes cannot strike a balance between algorithm complexity and performance. To address the above challenges, we propose a hybrid scheduling model based on collaborative edge computing. Our proposed scheduling model integrates cloud-edge scheduling (coarse-grained phase) and edge-edge scheduling (fine-grained phase) to meet dynamic and real-time requirements. Our work is as follows: (i) first, we use the Johnson Bellman algorithm (JBA) to deter- mine the task decomposition order in the coarse-grained phase; (ii) second, we propose an improved Q-network scheduling method (DQN) for the job assignment problem in the fine-grained phase; (iii) finally, we simulate the cooperation of the two phases to significantly reduce the maximum completion time through simulation experiments. The experimental results show that the method can significantly reduce the dynamic scheduling time and achieve the effect of real-time scheduling.