计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231200125-5.doi: 10.11896/jsjkx.231200125

• 网络&通信 • 上一篇    下一篇

基于深度学习智能反射面辅助通信系统的联合波束成形

陈晓1,4, 张权淏2, 施建锋3,4, 朱建月3,4   

  1. 1 南京信息工程大学人工智能学院(未来技术学院) 南京 210044
    2 南京信息工程大学计算机学院 南京 210044
    3 南京信息工程大学电子与信息工程学院 南京 210044
    4 东南大学移动通信国家重点实验室 南京 210096
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 施建锋(jianfeng.shi@nuist.edu.cn)
  • 作者简介:(x.chen@nuist.edu.cn)
  • 基金资助:
    国家自然科学基金(62101273,62201274);江苏省自然科学基金项目(BK20210641,BK20220439)

Deep Learning Based Joint Beamforming in Intelligent Reflecting Surface Enhanced WirelessCommunication Systems

CHEN Xiao1,4, ZHANG Quanhao2, SHI Jianfeng3,4, ZHU Jianyue3,4   

  1. 1 School of Artificial Intelligence/School of Future Technology,Nanjing University of Information Science and Technology,Nanjing 210044,China
    2 School of Computer Science,Nanjing University of Information Science and Technology,Nanjing 210044,China
    3 School of Electronic and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China
    4 National Mobile Communications Research Laboratory,Southeast University,Nanjing 210096,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:CHEN Xiao,born in 1993,Ph.D,lectu-rer.Her main research interests include massive multiple-input and multiple-output wireless communication systems,deep-learning based communication systems,beamforming design and channel estimation technologies.
    SHI Jianfeng,born in 1994,Ph.D,associate professor.His main research interests include 5G/6G communication wireless resource management,earth integrated networks,user-centered networks,beamforming theory and machine learning-based communication technologies.
  • Supported by:
    National Natural Science Foundation of China(62101273,62201274) and Natural Science Foundation of Jiangsu Province(BK20210641,BK20220439).

PDF (PC)

169

摘要： 智能反射面(Intelligent Reflecting Surface,IRS)技术被认为是下一代无线通信中颇具潜力的技术之一。现有的IRS辅助多输入多输出(Multiple Input Multiple Output,MIMO)系统的波束成形设计对天线的计算能力要求很高,仍然是一个极具挑战的难题。为了克服这一难题,提出了一种用于IRS辅助多用户MIMO系统的基于深度学习的联合波束成形设计方案,以实现系统多用户和数据传输速率的最大化。该方案利用深度学习卷积神经网络学习和优化了基站端数字波束成形,同时设计出最优IRS端反射波束成形。所提方案克服了神经网络直接预测波束成形矩阵的困难,仅预测从波束成形矩阵中提取的关键特征,对神经网络预测能力的需求大大降低,并将线下训练及优化的结果用于线上,显著降低了实时计算复杂度。仿真结果显示,提出的最优波束成形能获得超过0.5~1bit/s/Hz的系统和速率性能提升,且该优势会随着用户数增多而增大。

关键词: 智能反射面, 深度学习, 波束成形, 和速率

Abstract: Intelligent reflecting surface(IRS),as one of the most potential technologies in the next-generation wireless communication,plays a significant role.However,the existing IRS-assisted multiple-input multiple-output(MIMO) systems face a challenging problem that the beamforming methods require high computational capabilities of the antennas.To address this challenge,a deep learning(DL)-based joint beamforming design has been proposed for IRS-aided multi-user MIMO communication systems aiming to maximize the sum data rate of all users.The proposed DL-based beamforming scheme utilizes convolutional neural network to jointly optimize digital beamforming at base station and reflection beamforming at IRS.The proposed DL-based beamforming method forecasts the essential features extracted from the beamforming matrix,which overcomes the challenge of direct prediction of beamforming matrix by neural network.This method significantly reduces the demand on the predictive capability of the neural network,and the trained and optimized beamforming designs are using online that can significantly reduce the real-time computational complexity.Simulation results demonstrate that the proposed beamforming design can achieve over 0.5~1bit/s/Hzdata rate improvement,which will be enhanced with the growth of user number.

Key words: Intelligent reflecting surface, Deep learning, Joint beamforming, Sum rate

中图分类号: 

  • TN929.5
[1]OU L,LIAO S,QIN Z,et al.Millimeter Wave Wireless Ha-damard Image Transmission for MIMO Enabled 5G and Beyond[J].IEEE Wireless Communications,2020,27(6):134-139.
[2]GUI G,LIU M,TANG F,et al.6G:Opening New Horizons forIntegration of Comfort,Security,and Intelligence[J].IEEE Wireless Communications,2020,27(5):126-132.
[3]WU Q,ZHANG R.Intelligent Reflecting Surface EnhancedWireless Network via Joint Active and Passive Beamforming[J].IEEE Transactions on Wireless Communications,2019,18(11):5394-5409.
[4]HUANG C,ZAPPONE A,ALEXANDROPOULOS G C,et al.Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication[J].IEEE Transactions on Wireless Communications,2019,18(8):4157-4170.
[5]XIE H,XU J,LIU Y F.Max-Min Fairness in IRS-Aided Multi-Cell MISO Systemswith Joint Transmit and Reflective Beamforming[J].IEEE Transactions on Wireless Communications,2021,20(2):1379-1393.
[6]MUNAWAR M,LEE K.Low-Complexity Adaptive SelectionBeamforming for IRS-Assisted Single-User Wireless Networks[J].IEEE Transactions on Vehicular Technology,2023,72(4):5458-5462.
[7]LIN T,CONG J,ZHU Y,et al.Hybrid Beamforming for Millimeter Wave Systems Using the MMSE Criterion[J].IEEE Transactions on Communications,2019,67(5):3693-3708.
[8]SOHRABI F,YU W.Hybrid Digital and Analog Beamforming Design for Large-Scale Antenna Arrays[J].IEEE Journal of Selected Topics in Signal Processing,2016,10(3):501-513.
[9]AYACH O E,RAJAGOPAL S,ABU-SURRA S,et al.Spatially Sparse Precoding in Millimeter Wave MIMO Systems[J].IEEE Transactions on Wireless Communications,2014,13(3):1499-1513.
[10]LIN T,ZHU Y.Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning[J].IEEE Wireless Communications Letters,2020,9(1):103-107.
[11]GAO J,ZHONG C,CHEN X,et al.Unsupervised Learning for Passive Beamforming[J].IEEE Communications Letters,2020,24(5):1052-1056.
[12]SHI Y,KINAR A,SIDIROPOULOS N D,et al.Learning to Beamform for Minimum Outage[J].IEEE Transactions on Signal Processing,2018,66(19):5180-5193.
[13]ALKHATEEB A,ALEX S,VARKEY P,et al.Deep Learning Coordinated Beamforming for Highly-Mobile Millimeter Wave Systems[J].IEEE Access,2018,6:37328-37348.
[14]SUN H,CHEN X,SHI Q,et al.Learning to Optimize:Training Deep Neural Networks for Wireless Resource Management[C]//2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications(SPAWC).2017:1-6.
[15]LIANG F,SHEN C,YU W.Towards Optimal Power Control via Ensembling Deep Neural Networks[J].IEEE Transactions on Communications,2020,68(3):1760-1776.
[16]XIA W,ZHENG G,ZHU Y,et al.A Deep Learning Framework for Optimization of MISO Downlink Beamforming[J].IEEE Transactions on Communications,2020,68(3):1866-1880.
[17]BJÖRNSON E,BENGTSSON M,OTTERSTEN B.OptimalMultiuser Transmit Beamforming:A Difficult Problem with a Simple Solution Structure[J].IEEE Signal Processing Magazine,2014,31(4):142-148.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发