In this paper, a real-time scheduling problem of a dual-resource flexible job shop with robots is studied. Multiple independent robots and their supervised machine sets form their own work cells. First, a mixed integer programming model is established, which considers the scheduling problems of jobs and machines in the work cells, and of jobs between work cells, based on the process plan flexibility. Second, in order to make real-time scheduling decisions, a framework of multi-task multi-agent reinforcement learning based on centralized training and decentralized execution is proposed. Each agent interacts with the environment and completes three decision-making tasks: job sequencing, machine selection, and process planning. In the process of centralized training, the value network is used to evaluate and optimize the policy network to achieve multi-agent cooperation, and the attention mechanism is introduced into the policy network to realize information sharing among multiple tasks. In the process of decentralized execution, each agent performs multiple task decisions through local observations according to the trained policy network. Then, observation, action, and reward are designed. Rewards include global and local rewards, which are decomposed into sub-rewards corresponding to tasks. The reinforcement learning training algorithm is designed based on a double-deep Q-network. Finally, the scheduling simulation environment is derived from benchmarks, and the experimental results show the effectiveness of the proposed method.

In the process of the integrated scheduling of multi-variety and small-batch complex products, the process structure and attribute characteristics are often ignored, which affects the overall scheduling effect. Aiming at solving this problem, a heuristic integrated scheduling algorithm (HIS-IDA) based on the improved Dijkstra algorithm is proposed. The algorithm takes the processing time of the process itself as the path value of the preceding and the following adjacent processes. Firstly, the improved Dijkstra algorithm prioritized the scheduling of the process sequence with long longitudinal paths and realized the “longitudinal optimization” of the integrated scheduling. Secondly, the layer priority strategy is used to shorten the interval time of process processing and realize the “horizontal optimization” of integrated scheduling. On the basis of “vertical and horizontal optimization”, the idle time of the equipment is further reduced by using the process priority strategy of the leaf node, and the “idle optimization” of the integrated scheduling is realized, so as to optimize the overall effect of the integrated scheduling. The effectiveness and superiority of the algorithm are proved using comparison analysis.

To solve the problem of task scheduling in the cloud computing system, this paper proposes a scheduling algorithm for cloud computing based on the driver of dynamic essential path (DDEP). This algorithm applies a predecessor-task layer priority strategy to solve the problem of constraint relations among task nodes. The strategy assigns different priority values to every task node based on the scheduling order of task node as affected by the constraint relations among task nodes, and the task node list is generated by the different priority value. To address the scheduling order problem in which task nodes have the same priority value, the dynamic essential long path strategy is proposed. This strategy computes the dynamic essential path of the pre-scheduling task nodes based on the actual computation cost and communication cost of task node in the scheduling process. The task node that has the longest dynamic essential path is scheduled first as the completion time of task graph is indirectly influenced by the finishing time of task nodes in the longest dynamic essential path. Finally, we demonstrate the proposed algorithm via simulation experiments using Matlab tools. The experimental results indicate that the proposed algorithm can effectively reduce the task Makespan in most cases and meet a high quality performance objective.