CSI feedback algorithm for massive MIMO systems based on SFNet

ZHANG Yun; HUANG Jingwei; XU Sunwu; GAO Gui; YU Shujuan; ZHAO Shengmei

doi:10.11959/j.issn.1000-436x.2025097

您当前的位置：

首页 >

文章列表页 >

CSI feedback algorithm for massive MIMO systems based on SFNet

Papers | 更新时间：2025-07-04

- CSI feedback algorithm for massive MIMO systems based on SFNet
- Journal on Communications Vol. 46, Issue 6, Pages: 196-208(2025)
- 作者机构：
  
  1.南京邮电大学电子与光学工程学院、柔性电子（未来技术）学院，江苏南京 210023
  2.南京邮电大学通信与信息工程学院，江苏南京 210003
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(62375140);Postgraduate Research & Practice Innovation Program of Jiangsu Province(KYCX23_0994)
- DOI：10.11959/j.issn.1000-436x.2025097
  CLC： TN92
- Received：20 March 2025，
  
  Revised：2025-05-19，
  
  Published：25 June 2025
- 稿件说明：
移动端阅览
张昀,黄经纬,徐孙武等.基于SFNet的大规模MIMO系统的CSI反馈算法[J].通信学报,2025,46(06):196-208.

ZHANG Yun,HUANG Jingwei,XU Sunwu,et al.CSI feedback algorithm for massive MIMO systems based on SFNet[J].Journal on Communications,2025,46(06):196-208.
张昀,黄经纬,徐孙武等.基于SFNet的大规模MIMO系统的CSI反馈算法[J].通信学报,2025,46(06):196-208. DOI： 10.11959/j.issn.1000-436x.2025097.

ZHANG Yun,HUANG Jingwei,XU Sunwu,et al.CSI feedback algorithm for massive MIMO systems based on SFNet[J].Journal on Communications,2025,46(06):196-208. DOI： 10.11959/j.issn.1000-436x.2025097.

摘要

在频分双工大规模多输入多输出（MIMO）系统中，为解决现有的基于深度学习的信道状态信息（CSI）反馈方法复杂度高、反馈精度低以及未考虑量化损失的问题，基于传统CNN和Transformer架构，结合一种利用全局信息而设计的空间频率模块（SFB）以及一种融合局部和全局特征的特征多尺度自适应空间注意力门（MASAG），提出了用于CSI反馈的深度学习算法SFNet。通过使用快速傅里叶卷积以及特征融合网络动态来激活更多的输入信息，同时调整接受野，以确保有选择地突出空间相关的特征，最大限度地减少干扰，使网络以非常低的计算复杂度实现了先进的性能。实验结果表明，所提算法在低复杂度情况下具有较好的估计性能，并且在不同环境下表现出较好的鲁棒性。

Abstract

To address the issues of high computational complexity

low feedback accuracy

and neglect of quantization loss in existing deep learning-based channel state information (CSI) feedback methods for frequency-division duplex massive multiple-input multiple-output (MIMO) systems

the deep learning algorithm SFNet for CSI feedback was proposed. SFNet integrated a traditional convolutional neural network (CNN) and Transformer architecture

incorporating a spatial-frequency block designed to leverage global information and a multi-scale adaptive spatial attention gate for fusing local and global features. Fast Fourier convolution and a dynamic feature fusion mechanism were utilized to activate more input information

adjust the receptive field

selectively highlight spatially correlated features

suppress interference

and allow the network to achieve advanced performance with extremely low computational complexity. The experimental results show that the proposed algorithm achieves advanced estimation performance with significantly low computational complexity. Furthermore

the trained model exhibits strong robustness across various environments.

关键词

Keywords

references

MARZETTA T L . Noncooperative cellular wireless with unlimited numbers of base station antennas [J ] . IEEE Transactions on Wireless Communications , 2010 , 9 ( 11 ): 3590 - 3600 .

ZHANG J , WEN C K , JIN S , et al . On capacity of large-scale MIMO multiple access channels with distributed sets of correlated antennas [J ] . arXiv Preprint , arXiv: 1209.5513 , 2012 .

DAUBECHIES I , DEFRISE M , MOL C D . An iterative thresholding algorithm for linear inverse problems with a sparsity constraint [J ] . Communications on Pure and Applied Mathematics , 2004 , 57 ( 11 ): 1413 - 1457 .

DONOHO D L , MALEKI A , MONTANARI A . Message-passing algorithms for compressed sensing [J ] . Proceedings of the National Academy of Sciences of the United States of America , 2009 , 106 ( 45 ): 18914 - 18919 .

LI C B , YIN W T , ZHANG Y . User’s guide for TVAL3: TV minimization by augmented lagrangian and alternating direction algorithms [J ] . Department of CAAM , 2009 , 20 : 46 - 47 .

WEN C K , SHIH W T , JIN S . Deep learning for massive MIMO CSI feedback [J ] . IEEE Wireless Communications Letters , 2018 , 7 ( 5 ): 748 - 751 .

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 .

LU Z L , WANG J T , SONG J . Multi-resolution CSI feedback with deep learning in massive MIMO system [C ] // Proceedings of the ICC 2020-2020 IEEE International Conference on Communications (ICC) . Piscataway : IEEE Press , 2020 : 1 - 6 .

JI S J , LI M . CLNet: complex input lightweight neural network designed for massive MIMO CSI feedback [J ] . IEEE Wireless Communications Letters , 2021 , 10 ( 10 ): 2318 - 2322 .

XU Y , YUAN M Q , PUN M O . Transformer empowered CSI feedback for massive MIMO systems [C ] // Proceedings of the 2021 30th Wireless and Optical Communications Conference (WOCC) . IEEE , 2021 : 157 - 161 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [J ] . arXiv Preprint , arXiv: 1706.03762 , 2017 .

CUI Y D , GUO A H , SONG C L . TransNet: full attention network for CSI feedback in FDD massive MIMO system [J ] . IEEE Wireless Communications Letters , 2022 , 11 ( 5 ): 903 - 907 .

BI X J , LI S , YU C D , et al . A novel approach using convolutional transformer for massive MIMO CSI feedback [J ] . IEEE Wireless Communications Letters , 2022 , 11 ( 5 ): 1017 - 1021 .

MOURYA S , AMURU S , KUCHI K K . A spatially separable attention mechanism for massive MIMO CSI feedback [J ] . IEEE Wireless Communications Letters , 2023 , 12 ( 1 ): 40 - 44 .

ZHANG D F , HUANG F Y , LIU S Z , et al . SwinFIR: revisiting the SwinIR with fast Fourier convolution and improved training for image super-resolution [J ] . arXiv Preprint , arXiv: 2208.11247 , 2022 .

KOLAHI S G , CHAHARSOOGHI S K , KHATIBI T , et al . MSA2Net: multi-scale adaptive attention-guided network for medical image segmentation [J ] . arXiv Preprint , arXiv: 2407.21640 , 2024 .

CHI L , JIANG B R , MU Y D . Fast Fourier convolution [J ] . Advances in Neural Information Processing Systems , 2020 , 33 : 4479 - 4488 .

ZHANG X D , LU Z L , ZENG R , et al . Quantization adaptor for bit-level deep learning-based massive MIMO CSI feedback [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 4 ): 5443 - 5453 .

Views

1181

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

CSI feedback algorithm based on RM-Net for massive MIMO systems in high-speed mobile environment

CSI feedback algorithm based on deep unfolding for massive MIMO systems

Review of unsupervised anomaly detection techniques for medical imaging

Target visibility prediction method based on cost-sensitive CNN-BiLSTM network

Multi-modal semantics aided mmWave beam prediction method in industrial haze environment

Related Author

Yong LIAO

Shiyi WANG

Gang CHENG

Yujie LI

Zhao Yingcheng

Song Xiaogang

Shi Zhenghao

You Zhenzhen

Related Institution

School of Microelectronics and Communication Engineering, Chongqing University

School of Computer Science and Engineering, Xi’an University of Technology

Shaanxi Key Laboratory for Network Computing and Security Technology

Human Machine Integration Intelligent Robot Shaanxi Provincial University Engineering Research Center

School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications

AI脑图

AI问答

⁰