计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231000191-6.doi: 10.11896/jsjkx.231000191

• 网络&通信 • 上一篇    下一篇

一种基于深度自编码器的大规模MIMO系统室外CSI反馈方法

陈锰, 钱蓉蓉, 朱雨佳, 黄振国   

  1. 云南大学信息学院 昆明 650500
  • 出版日期:2024-11-16 发布日期:2024-11-13
  • 通讯作者: 钱蓉蓉(r.qiang@ynu.edu.cn)
  • 作者简介:(chairman_cm@163.com)
  • 基金资助:
    国家自然科学基金青年科学基金(61701433);云南省科技厅面上项目(2018FB099)

Method of Outdoor CSI Feedback for Massive MIMO Systems Based on Deep Autoencoder

CHEN Meng, QIAN Rongrong, ZHU Yujia, HUANG Zhenguo   

  1. School of Information,Yunnan University,Kunming 650500,China
  • Online:2024-11-16 Published:2024-11-13
  • About author:CHEN Meng,born in 1998,postgra-duate.His main research interests include deep learning and channel state information feedback.
    QIAN Rongrong,born in 1985,Ph.D.Her main research interests include wireless communication,signal proces-sing and so on.
  • Supported by:
    Young Scientists Fund of the National Natural Science Foundation of China(61701433) and Yunnan Provincial Department of Science and Technology General Project(2018FB099).

PDF (PC)

139

摘要： 在室外场景高倍压缩下,针对大规模多输入多输出(Multiple-Input Multiple-Output,MIMO)系统中大多数现有信道状态信息(Channel State Information,CSI)反馈方法重建精度低、复杂度较高的问题,提出了一种基于深度自编码器的CSI压缩反馈方法。该方法首先在编码器采用卷积神经网络提取原始CSI的特征信息;然后将全连接网络压缩为低维码字反馈回解码器;最后考虑到室外环境的CSI空间模式复杂、高倍压缩下信息损失较多,在解码器的残差网络中使用并行多分辨率卷积网络与具有丰富神经元的全连接网络对接收到的特征码字进行重建,以此增强所提方法的重建能力与泛化能力。实验结果表明,所提方法的重建质量在不同压缩比下均有显著提升。

关键词: 大规模MIMO, CSI反馈, 深度自编码器, 室外场景, 高倍压缩

Abstract: In outdoor scenarios with high compression,aiming at the problems of low accuracy and high complexity of reconstruction of most existing channel state information(CSI)feedback methods in massive multiple-input multiple-output(MIMO)systems,a deep autoencoder-based CSI compression feedback method is proposed.The method firstly uses a convolutional neural network in the encoder to extract the feature information of the original CSI,and then uses a fully connected network to compress it into a low-dimensional codeword for feedback to the decoder.Considering that the spatial pattern of CSI in outdoor environments is more complicated,and the loss of information is more at high compression,the decoder employs parallel multi-resolution convolutional networks and fully connected networks in a residual structure to reconstruct the received feature codewords.This design enhances the reconstruction and generalization capabilities of the proposed method.Experimental results show that the reconstruction quality of the proposed method is significantly improved at different compression ratios.

Key words: Massive MIMO, CSI feedback, Deep autoencoder, Outdoor scenario, High compression

中图分类号: 

  • TN925
[1]ANDREWS J G,BUZZI S,CHOI W,et al.What will 5G be? [J].IEEE Journal on Selected Areas in Communications,2014,32(6):1065-1082.
[2]METZLER C A,MALEKI A,BARANIUK R G.From denoi-sing to compressed sensing[J].IEEE Transactions on Information Theory,2016,62(9):5117-5144.
[3]DAUBECHIES I,DEFRISE M,MOL C D.An iterative thres-holding algorithm for linear inverse problems with a sparsity constraint[J].Communications on Pure and Applied Mathematics,2004,57(11):1413-1457.
[4]WEN C K,SHIH W T,JIN S.Deep learning for massive MIMOCSI feedback[J].IEEE Wireless Communications Letters,2018,7(5):748-751.
[5]GUO J J,WEN C K,JIN S,et al.Convolutional neural network based multiple-rate compressive sensing for massive MIMO CSI feedback:Design,simulation,and analysis[J].IEEE Transactions on Wireless Communications,2020,19(4):2827-2840.
[6]LU Z L,WANG J T,SONG J.Multi-resolution CSI feedbackwith deep learning in massive MIMO system[C]// IEEE International Conference on Communications.IEEE,2020:1-6.
[7]JI S,LI M.CLNet:Complex input lightweight neural network designed for massive MIMO CSI feedback[J].IEEE Wireless Communications Letters,2021,10(10):2318-2322.
[8]WANG T,WEN C K,JIN S,et al.Deeplearning-based CSI feedback approach for time-varying massive MIMO channels[J].IEEE Wireless Communications Letters,2019,8(2):416-419.
[9]CAO B,YANG Y,RAN P,et al.ACCsiNet:Asymmetric convolution-based autoencoder framework for massive MIMO CSI feedback[J].IEEE Communications Letters,2021,25(12):3873-3877.
[10]CAO Z,SHIH W,GUO J J,et al.Lightweight convolutionalneural networks for CSI feedback in massive MIMO[J].IEEE Communications Letters,2021,25(8):2624-2628.
[11]YE H Y,GAO F F,QIAN J,et al.Deep learning-based denoise network for CSI feedback in FDD massive MIMO systems[J].IEEE Communications Letters,2020,24(8):1742-1746.
[12]CAI Q,DONG C,NIU K.Attention model for massive MIMOCSI compression feedback and recovery[C]//IEEE Wireless Communications and Networking Conference.IEEE,2019:1-5.
[13]LIU W B,YAN B,SHEN L,et al.CLPNet:CSI feedback network for massive MIMO based on deeplearning[J].Radio Engineering,2022,52(9):1660-1665.
[14]ZHANG Y,ZHANG X,LIU Y.Deep learning-based CSI compression and quantization with high compression ratios in FDD massive MIMO systems[J].IEEE Wireless Communications Letters,2021,10(10):2101-2105.
[15]GUO J J,WEN C K,JIN S,et al.Overview of deep learning-based CSI feedback in massive MIMO systems[J].IEEE Tran-sactions on Communications,2022,70(12):8017-8045.
[16]LU Z,ZHANG X,HE H,et al.Binarized aggregated networkwith quantization:Flexible deep learning deployment for CSI feedback in massive MIMO systems[J].IEEE Transactions on Wireless Communications,2022,21(7):5514-5525.
[17]LIU L F,OESTGES C,POUTANEN J,et al.The COST2100 MIMO channel model[J].IEEE Wireless Communications,2012,19(6):92-99.
[18]KOLMONEN V M,ALMERS P,SALMI J,et al.A dynamicdual-link wideband MIMO channel sounder for 5.3 GHz[J].IEEE Transactions on Instrumentation and Measurement,2010,59(4):873-883.
[19]ZHU M,ERIKSSON G,TUFVESSON F.The COST 2100channel model:Parameterization and validation based on outdoor MIMO measurements at 300 MHz[J].IEEE Transactions on Wireless Communications,2013,12(2):888-897.
[20]HU Z Y,GUO J H,LIU G Z,et al.MRFNet:A deep learning-based CSI feedback approach of massive MIMOsystems[J].IEEE Communications Letters,2021,25(10):3310-3314.
[21]HE K M,CHEN X L,XIE S N,et al.Maskedautoencoders arescalable vision learners[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans,LA,USA,2022:15979-15988.
[22]CHEN M H,GUO J J,LI X,et al.An overview of the CSI feedback based on deep learning for massive MIMO systems[J].Internet Things,2020,4(10):33-44.
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