In cases of natural disasters, air-borne base stations mounted on Unmanned Aerial Vehicles (UAVs) are capable to provide fast and flexible communication restoration for ground users. Previous studies have shown that the deployment location and number of UAVs have a large impact on the quality of service, and this is an NP-hard problem. Due to the sudden nature of accidents, UAVs may be provided by multiple rescue groups and thus have different performances. In this paper, we propose DDPGPSO, which combines particles swarms optimization (PSO) and deep reinforcement learning (DRL) to optimize the selection and deployment of heterogeneous UAVs, taking into account the number of deployed UAVs, the portion of served users, and the link quality. This combination enables PSO to adaptively and intelligently adjust parameters. The simulation results show that the proposed method can obtain excellent heterogeneous UAVs selection and deployment in various scenarios.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Reinforcement Learning Empowered Particle Swarm Optimization for Aerial Base Station Deployment


    Beteiligte:
    Song, Jinpeng (Autor:in) / Zhang, Bo (Autor:in) / Lia, Junfeng (Autor:in)


    Erscheinungsdatum :

    23.01.2023


    Format / Umfang :

    476087 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch