Optimal Design of Flexible Job Shop Scheduling Under Resource Preemption Based on Deep Reinforcement Learning

Abstract

With the popularization of multi-variety and small-batch production patterns, the flexible job shop scheduling problem (FJSSP) has been widely studied. The sharing of processing resources by multiple machines frequently occurs due to space constraints in a flexible shop, which results in resource preemption for processing workpieces. Resource preemption complicates the constraints of scheduling problems that are otherwise difficult to solve. In this paper, the flexible job shop scheduling problem under the process resource preemption scenario is modeled, and a two-layer rule scheduling algorithm based on deep reinforcement learning is proposed to achieve the goal of minimum scheduling time. The simulation experiments compare our scheduling algorithm with two traditional metaheuristic optimization algorithms among different processing resource distribution scenarios in static scheduling environment. The results suggest that the two-layer rule scheduling algorithm based on deep reinforcement learning is more effective than the meta-heuristic algorithm in the application of processing resource preemption scenarios. Ablation experiments, generalization, and dynamic experiments are performed to demonstrate the excellent performance of our method for FJSSP under resource preemption.

Dynamic Scheduling of Multi-agent Electromechanical Production Lines based on Iterative Algorithms

“…Compared with simply using static genetic algorithms, it saves 22.3% in production costs. By comparing the scheduling results of static genetic algorithms, it can be concluded that using the multi agent and genetic algorithm proposed by the author to combine the hierarchical scheduling design of dyeing vats, considering the dynamic changes in the production site, the optimal solution for dyeing vat scheduling can be obtained [19,20]. After actual production workshop operation testing, the algorithm in this article has a good optimization efficiency when dealing with production lines with 60 dyeing tanks producing 8 product types.…”

Research on collaborative and integrated resource schedulingalgorithm in heterogeneous cloud environment

“…The specific flow of the resource system scheduling strategy proposed in this paper is shown in the figure 1 [6]. By adopting the hierarchical scheduling strategy to allocate and process the heterogeneous cloud resources, not only can the operation speed of the algorithm be effectively improved, but also will have a high information metric effect because this paper provides a hierarchical processing of the heterogeneous cloud quality and achieves comprehensive scheduling based on the attribute prediction results [7]. Therefore, in order to classify the quality of resource information in the heterogeneous cloud environment, we need to sample the resource information first, so as to obtain the heterogeneous cloud resource data attribute parameters.…”

Research on Digital Medical Resource Scheduling Method Considering Data Interoperability

“…Combined with the interoperability mechanism of digital medical data constructed in part 1.1, this paper schedules digital medical resources according to the task status between the target node and the digital center, so as to realize the analysis of the scheduling relationship adjustment model structure [21][22] and ensure that the scheduled resources can be fully utilized. When decomposing the data tasks matched by the medical system, the influence of allocation and scheduling interval on the actual implementation of task data transmission and the influence of waiting time on scheduling efficiency in the space computing system are fully considered [23][24] . For the setting of data clustering center, this paper is based on the interoperability mechanism of digital medical data constructed in part 1.1, and through the interoperability relationship between different data, the calculation method of clustering center is expressed as follows…”