The Internet of Vehicles (10V) brings significant economic benefits to countries. However, large-scale smart vehicle production planning remains challenging in the 10V. Currently, heuristic algorithms and solvers commonly used for these problems often lack scalability and fall into local optima. Moreover, security concerns about wireless data transfer arising from multi-factory manufacturing processes are garnering attention. To address these issues, this paper introduces an algorithm, TRL, which is a Transformer-based Reinforcement Learning for vehicle production planning problems. Furthermore, we propose a Transformer-based Federated Reinforcement Learning algorithm, named TFRL, tailored for large-scale manufacturing and secure wireless communication. Experimental results showcase the high performance and security of TFRL. It schedules 1000 orders in about 14 seconds and avoids exchanging plaintext during the interaction. Compared to Non-dominated Sorting Genetic Algorithm II(NSGA-II), the TFRL enhances computational speed by 95.12% and reduces constraint violation scores by 93.18%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Enhancing Production Planning in the Internet of Vehicles: A Transformer-based Federated Reinforcement Learning Approach


    Contributors:


    Publication date :

    2024-06-24


    Size :

    1361186 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    An Enhancing Semi-Supervised Federated Learning Framework for Internet of Vehicles

    Su, Xiangqing / Huo, Yan / Wang, Xiaoxuan et al. | IEEE | 2023


    Vehicles Control: Collision Avoidance using Federated Deep Reinforcement Learning

    Elallid, Badr Ben / Abouaomar, Amine / Benamar, Nabil et al. | ArXiv | 2023

    Free access


    Enhancing WiFi Multiple Access Performance with Federated Deep Reinforcement Learning

    Zhang, Lyutianyang / Yin, Hao / Zhou, Zhanke et al. | IEEE | 2020