In this paper, we study joint beamforming and resource allocation in downlink multi-cell orthogonal frequency division multiple access (OFDMA) systems. We design a multi-agent deep Q-network (MADQN) algorithm to solve this problem. Furthermore, in order to improve the adaptability of neural networks for different wireless environment, we propose a transfer learning framework based on MADQN called TL-MADQN to dynamically output optimal beamforming and resource allocation policy. Finally, we adjust the allocation policy to maximize the sum-rate of all users by updating the weights of each neural network. Simulation results illustrate that the proposed TL-MADQN algorithm has higher sum-rate and faster convergence speed compared with the baseline algorithms.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Beamforming and Resource Allocation in Multi-cell OFDMA Systems based on Deep Transfer Reinforcement Learning


    Contributors:
    Sun, Gaoxiang (author) / Wang, Xiaoming (author) / Jiang, Rui (author) / Xu, Youyun (author)


    Publication date :

    2022-06-01


    Size :

    613153 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English





    Fairness aware chunk-based resource allocation in multi-cell OFDMA networks

    Selim, Mahmoud M. / Muta, Osamu / Shalaby, Hossam et al. | IEEE | 2014


    Fair Resource Allocation Algorithm for Chunk Based OFDMA Multi-User Networks

    Shen, Yanyan / Huang, Xiaoxia / Yang, Bo et al. | IEEE | 2017


    Deep Reinforcement Learning-Based Resource Allocation for Cellular V2X Communications

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