UAV-relayed cellular network is one of the promising applications of UAV systems. UAV can be used to increase the coverage of cellular networks or provide service to areas where infrastructure installation is difficult or impossible. However, unlike existing infrastructure-based cellular networks, the resources allocated to user terminals may be unbalanced due to the limited number of UAVs and change in coverage due to the movements of UAVs. To solve this problem, we propose a path planning that minimizes the unfairness using reinforcement learning. The UAV evaluates the local fairness according to the information of user terminal within the communication range of the UAV, then it determines the appropriate path to increase the global fairness.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    UAV Path Planning Based on Reinforcement Learning for Fair Resource Allocation in UAV-Relayed Cellular Networks


    Weitere Titelangaben:

    Lect. Notes Electrical Eng.


    Beteiligte:
    Kim, Kuinam J. (Herausgeber:in) / Kim, Hye-Young (Herausgeber:in) / Lee, Wooyeob (Autor:in) / Park, Gyubong (Autor:in) / Joe, Inwhee (Autor:in)


    Erscheinungsdatum :

    19.12.2019


    Format / Umfang :

    11 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Deep Reinforcement Learning-Based Resource Allocation for Cellular V2X Communications

    Chung, Yi-Ching / Chang, Hsin-Yuan / Chang, Ronald Y. et al. | IEEE | 2023


    Fair Resource Allocation in Wireless Networks

    Ron, Dara / Bang, Jung-Hyun / Lee, Jung-Ryun | IEEE | 2018


    Federated Reinforcement Learning for Resource Allocation in V2X Networks

    Xu, Kaidi / Zhou, Shenglong / Li, Geoffrey Ye | IEEE | 2024



    Deep Reinforcement Learning Based Computing Resource Allocation in Fog Radio Access Networks

    Tong, Zhaowei / Li, Zhuoran / Gendia, Ahmad et al. | IEEE | 2024