LEO satellite network (LEO-SN) constitutes an indispensable part of the space-air-ground integrated network (SAGIN). However, the characteristics of unbalanced traffic load, intricate orbits, high mobility, frequent link handovers, diverse storage and communication capabilities of nodes gradually lead to the ineffectiveness of the central routing planning methods. In order to enhance the flexibility and agility of the planning process, this paper presents an intelligent decentralized load balancing routing algorithm using deep reinforcement learning for the LEO-SN, which takes into consideration the queuing delay, storage space, communication bandwidth and propagation delay of merely one-hop satellite node. Simulation and analysis demonstrate that the proposed load balancing routing algorithm could converge quickly for both training and test sets, and possesses better performance than the comparison methods in terms of both the packet loss rate and transmission latency.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Deep Reinforcement Learning Based Load Balancing Routing for LEO Satellite Network


    Contributors:
    Zuo, Peiliang (author) / Wang, Chen (author) / Wei, Zhanzhen (author) / Li, Zhaobin (author) / Zhao, Hong (author) / Jiang, Hua (author)


    Publication date :

    2022-06-01


    Size :

    2561740 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Reinforcement Learning Based Mobility Load Balancing with the Cell Individual Offset

    Asghari, Muhammad Zeeshan / Ozturk, Metin / Hamalainen, Jyri | IEEE | 2021


    Deep Reinforcement Learning based Routing in an Air-to-Air Ad-hoc Network

    Wang, Zhe / Han, Ruixuan / Li, Hongxiang et al. | IEEE | 2022


    Deep Reinforcement Learning-Based Routing for Space-Terrestrial Networks

    Tsai, Kai-Chu / Yao, Ting-Jui / Huang, Pin-Hao et al. | IEEE | 2022