Dynamic Scheduling With Task Migration in Cloud Manufacturing Using Hybrid Federated Deep Reinforcement Learning and Graph Neural Network Model

Cloud Manufacturing (CMfg) serves as a pivotal platform, seamlessly integrating enterprise resources and consumer demands, thus playing a central role in task scheduling and service allocation. However, the dynamic nature of cloud environments, especially during service interruptions, necessitates systems capable of promptly responding to real-time changes and demands, presenting formidable challenges for task migration. Traditional methods often struggle to adapt swiftly, leading to suboptimal real-time decision-making. To address these challenges, we introduce the DRL-GNN-FL SynergyNet model, a hybrid solution that prioritizes both time efficiency and cost-effectiveness. This model leverages advanced technologies, including Deep Reinforcement Learning (DRL), Graph Neural Networks (GNN), and Federated Learning (FL). DRL enables rapid adaptability and real-time decision-making, GNN effectively processes complex network structures, and FL facilitates distributed learning and knowledge sharing. This comprehensive approach effectively tackles the intricacies of task migration in CMfg environments. Experimental results demonstrate the model’s exceptional performance, adaptability, and scalability in real-time scenarios, showcasing its potential as a practical and effective solution to the dynamic task migration challenges encountered in CMfg. The DRL-GNN-FL SynergyNet model offers a promising avenue for enhancing the resilience and responsiveness of cloud manufacturing systems. Note to Practitioners—To optimize production planning in the domain of smart manufacturing systems, it is imperative to streamline the utilization of manufacturing resources effectively. This paper centers its focus on addressing the challenges associated with task migration within the context of dynamic scheduling in cloud manufacturing, presenting a robust solution by introducing Deep Reinforcement Learning (DRL), Graph Neural Networks (GNN), and Federated Learning (FL). Conventional dynamic scheduling methods often struggle to swiftly adapt to real-time fluctuations and demands while frequently falling short in formulating effective task migration strategies. To overcome these limitations, this paper introduces an innovative DRL-GNN-FL SynergyNet model. This model amalgamates the rapid adaptability and real-time decision-making capabilities offered by DRL, the adept handling of complex network structures by GNN, and the benefits of distributed learning and knowledge sharing inherent to FL. Through comprehensive simulation experiments conducted in our study, we conclusively demonstrate that the proposed approach surpasses existing scheduling techniques in terms of operational efficiency and the proficiency to make well-informed decisions regarding task migration. Moreover, our approach readily lends itself to practical implementation within real production environments. Looking forward, future research endeavors could further refine this methodology by service broken associated with point-to-point and hub-and-spoke networks across diverse transportation routes.