In Unmanned Aeronautical Ad hoc Networks (UAANETs), it is challenging for routing protocols such as ad hoc on-demand distance vector (AODV) routing and improved protocols to provide reliable communications due to limited wireless resources and high mobility. This paper proposes a modified AODV protocol applying multi-agent Q-learning(Modified-QLAODV) based on mobility prediction and load sensing. This protocol is a distributed multi-agent reinforcement routing strategy, which employs reinforcement learning algorithm. It introduces mobility prediction and node relative load to infer link state on the purpose of enhancing robustness of UAANETs. In the learning strategy, mobility prediction based on Kalman filter algorithm combined with Gaussian filter algorithm, and load sensing will have impacts on Q-values. The destination obtains routes with different Q-values and returns the one with the maximum average Q-value to the source, which realizes to select the optimal route from a global view. The simulation results demonstrate that Modified-QLAODV can outperform the Q-learning routing protocol(QLAODV) and AODV on network performance in UAANETs.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Modified Multi-Agent Reinforcement Learning Protocol Based on Prediction for UAANETs


    Beteiligte:
    Li, Chao (Autor:in) / Liu, Jing (Autor:in)


    Erscheinungsdatum :

    01.11.2020


    Format / Umfang :

    1988436 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Underwater Acoustic MAC Protocol for Multi-Objective Optimization Based on Multi-Agent Reinforcement Learning

    Jinfang Jiang / Yiling Dong / Guangjie Han et al. | DOAJ | 2025

    Freier Zugriff

    Collision prediction method and system based on multi-agent reinforcement learning

    YU ZHENG / LIN RONGSHENG / YU YONGQING et al. | Europäisches Patentamt | 2024

    Freier Zugriff


    Multi-agent Cooperative Search based on Reinforcement Learning

    Sun, Yinjiang / Zhang, Rui / Liang, Wenbao et al. | IEEE | 2020


    Experience generalization for multi-agent reinforcement learning

    Pegoraro, Renê / Costa, AHR / Ribeiro, CHC | BASE | 2001

    Freier Zugriff