Distributed Graph Neural Network Design for Sum Ergodic Spectral Efficiency Maximization in Cell-Free Massive MIMO

被引:0
作者
Tung, Nguyen Xuan [1 ]
Chien, Trinh Van [2 ]
Ngo, Hien Quoc [3 ]
Hwang, Won Joo [4 ]
机构
[1] Pusan Natl Univ, Dept Informat Convergence Engn, Busan 46241, South Korea
[2] Hanoi Univ Sci & Technol HUST, Sch Informat & Commun Technol SoICT, Hanoi 100000, Vietnam
[3] Queens Univ Belfast, Ctr Wireless Innovat CWI, Belfast BT7 1NN, North Ireland
[4] Pusan Natl Univ, Ctr Artificial Intelligence Res, Sch Comp Sci & Engn, Busan 46241, South Korea
基金
新加坡国家研究基金会;
关键词
Massive MIMO; Training; Graph neural networks; Resource management; Central Processing Unit; Downlink; Optimization; Computational modeling; Wireless communication; Uplink; Cell-free massive MIMO; distributed learning; graph neural network; POWER ALLOCATION;
D O I
10.1109/TVT.2024.3493235
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper proposes a distributed learning-based framework to tackle the sum ergodic rate maximization problem in cell-free massive multiple-input multiple-output (MIMO) systems by utilizing the graph neural network (GNN). Different from centralized schemes, which gather all the channel state information (CSI) at the central processing unit (CPU) for calculating the resource allocation, the local resource of access points (APs) is exploited in the proposed distributed GNN-based framework to allocate transmit powers. Specifically, APs can use a unique GNN model to allocate their power based on the local CSI. The GNN model is trained at the CPU using the local CSI of one AP, with partially exchanged information from other APs to calculate the loss function to reflect system characteristics, capturing comprehensive network information while avoiding computation burden. Numerical results show that the proposed distributed learning-based approach achieves a sum ergodic rate close to that of centralized learning while outperforming the model-based optimization.
引用
收藏
页码:5181 / 5186
页数:6
相关论文
共 50 条
  • [1] Graph Neural Network Aided Power Control in Partially Connected Cell-Free Massive MIMO
    Mishra, Shashwat
    Salaun, Lou
    Yang, Hong
    Chen, Chung Shue
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (09) : 12412 - 12423
  • [2] Energy Efficiency Maximization in Large-Scale Cell-Free Massive MIMO: A Projected Gradient Approach
    Mai, Trang C.
    Ngo, Hien Quoc
    Tran, Le-Nam
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2022, 21 (08) : 6357 - 6371
  • [3] Spectral Efficiency Maximization for Uplink Cell-Free Massive MIMO-NOMA Networks
    Zhang, Yao
    Cao, Haotong
    Zhou, Meng
    Yang, Longxiang
    2019 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC WORKSHOPS), 2019,
  • [4] Graph Neural Network Performance Analysis in the Cell-Free Massive MIMO Wireless Systems
    Rahman, Md Habibur
    Sejan, Mohammad Abrar Shakil
    Aziz, Md Abdul
    Tabassum, Rana
    Song, Hyoung-Kyu
    2024 21ST INTERNATIONAL JOINT CONFERENCE ON COMPUTER SCIENCE AND SOFTWARE ENGINEERING, JCSSE 2024, 2024, : 412 - 417
  • [5] Combined DL-UL Distributed Beamforming Design for Cell-Free Massive MIMO
    Gouda, Bikshapathi
    Arvola, Antti
    Atzeni, Italo
    Tolli, Antti
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2024, 13 (06) : 1621 - 1625
  • [6] Spectral Efficiency Analysis of Hybrid Relay-Reflecting Intelligent Surface-Assisted Cell-Free Massive MIMO Systems
    Nguyen, Nhan Thanh
    Nguyen, Van-Dinh
    Nguyen, Hieu Van
    Ngo, Hien Quoc
    Chatzinotas, Symeon
    Juntti, Markku
    IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2023, 22 (05) : 3397 - 3416
  • [7] Spectral Efficiency Analysis of Cell-Free Distributed Massive MIMO Systems With Imperfect Covariance Matrix
    Ye, Feng
    Li, Jiamin
    Zhu, Pengcheng
    Wang, Dongming
    Wu, Hao
    You, Xiaohu
    IEEE SYSTEMS JOURNAL, 2022, 16 (04): : 5402 - 5412
  • [8] Downlink Spectral Efficiency of Cell-Free Massive MIMO Systems With Multi-Antenna Users
    Mai, Trang C.
    Ngo, Hien Quoc
    Duong, Trung Q.
    IEEE TRANSACTIONS ON COMMUNICATIONS, 2020, 68 (08) : 4803 - 4815
  • [9] Graph Neural Network Based Access Point Selection for Cell-Free Massive MIMO Systems
    Ranasinghe, Vismika
    Rajatheva, Nandana
    Latva-aho, Matti
    2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
  • [10] On the Sum Spectral Efficiency of Dynamic TDD-Enabled Cell-Free Massive MIMO Systems
    Chowdhury, Anubhab
    Murthy, Chandra R.
    IEEE WIRELESS COMMUNICATIONS LETTERS, 2023, 12 (03) : 481 - 485