A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) are envisaged to provide a global coverage SAT network in beyond fifth-generation (5G) cellular systems. However, such wide coverage rather makes it difficult to apply existing multiple access protocols, such as random access channel (RACH). To overcome this issue, in this paper, we propose a novel random access solution for LEO SAT networks, called as S-RACH. In contrast to existing standardized protocols, S-RACH is a model-free approach using deep reinforcement learning (DRL). Compared to RACH, we show from various simulations that our proposed S-RACH yields around 2x lower average access delay.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Random Access Protocol Learning in LEO Satellite Networks via Reinforcement Learning


    Beteiligte:
    Lee, Ju-Hyung (Autor:in) / Seo, Hyowoon (Autor:in) / Park, Jihong (Autor:in) / Bennis, Mehdi (Autor:in) / Ko, Young-Chai (Autor:in) / Kim, Joongheon (Autor:in)


    Erscheinungsdatum :

    01.06.2022


    Format / Umfang :

    472196 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Multi-agent Reinforcement Learning for Green Energy Powered IoT Networks with Random Access

    Han, Mengqi / Del Castillo, Luis Arocas / Khairy, Sami et al. | IEEE | 2020


    Multichannel Relay assisted NOMA-ALOHA with Reinforcement Learning based Random Access

    Lee, Haeyoung / Lee, Sunyoung / Ko, Youngwook | IEEE | 2023


    Collision Resolution with Deep Reinforcement Learning for Random Access in Machine-Type Communication

    Jadoon, Muhammad Awais / Pastore, Adriano / Navarro, Monica | IEEE | 2022


    Random Interleaving Multiplexing based Random Access in IoT-Oriented Satellite Networks

    Su, Jingrui / Ren, Guangliang / Zhang, Huining | IEEE | 2020