《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (5): 1613-1618.DOI: 10.11772/j.issn.1001-9081.2024050587

• 网络与通信 • 上一篇    

基于深度学习的智能反射面辅助通信系统信道估计

王丹1,2, 张文豪1,2(), 彭丽娟1,2   

  1. 1.重庆邮电大学 通信与信息工程学院,重庆 400065
    2.移动通信技术重庆市重点实验室(重庆邮电大学),重庆 400065
  • 收稿日期:2024-05-11 修回日期:2024-07-18 接受日期:2024-07-22 发布日期:2024-07-25 出版日期:2025-05-10
  • 通讯作者: 张文豪
  • 作者简介:王丹(1982—),女,重庆人,正高级工程师,博士,主要研究方向:移动通信物理层算法、信号处理
    张文豪(2000—),男,河南郑州人,硕士研究生,主要研究方向:移动通信物理层算法、深度学习
    彭丽娟(1999—),女,江西赣州人,硕士研究生,主要研究方向:移动通信物理层算法、信号处理。
  • 基金资助:
    重庆市自然科学基金创新发展联合基金(中国星网)资助项目(CSTB2023NSCQ-LZX0114)

Channel estimation of reconfigurable intelligent surface assisted communication system based on deep learning

Dan WANG1,2, Wenhao ZHANG1,2(), Lijuan PENG1,2   

  1. 1.School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China
    2.Chongqing Key Laboratory of Mobile Communication Technology (Chongqing University of Posts and Telecommunications),Chongqing 400065,China
  • Received:2024-05-11 Revised:2024-07-18 Accepted:2024-07-22 Online:2024-07-25 Published:2025-05-10
  • Contact: Wenhao ZHANG
  • About author:WANG Dan, born in 1982, Ph. D., professorate senior engineer. Her research interests include physical layer algorithms for mobile communication, signal processing.
    ZHANG Wenhao, born in 2000, M. S. candidate. His research interests include physical layer algorithms for mobile communication, deep learning.
    PENG Lijuan, born in 1999, M. S. candidate. Her research interests include physical layer algorithms for mobile communication, signal processing.
  • Supported by:
    Innovation and Development Joint Fund of Chongqing Natural Science Foundation (China Satellite Network)(CSTB2023NSCQ-LZX0114)

摘要:

针对智能反射面(RIS)辅助通信系统中信道估计精度低的问题,提出一种基于信道去噪网络(CDN)的信道估计方案,将信道估计问题建模为信道噪声消除的问题。首先使用传统算法对接收到的导频信号进行初步预估计,随后将该预估计信号输入信道估计网络以学习噪声特征并进行去噪处理,从而恢复出精确的信道系数。为了提高网络的去噪能力,设计了加权注意力块(WAB)和膨胀卷积块(DCB)以增强网络对噪声主体特征的提取,同时设计多尺度特征融合模块以防止浅层特征的丢失。仿真结果表明,与经典的DnCNN (Denoising Convolutional Neural Network)和CDRN (Convolutional neural network-based Deep Residual Network)方案相比,所提方案的归一化均方误差(NMSE)在不同信噪比(SNR)下平均降低了2.89 dB和2.01 dB。

关键词: 深度学习, 智能反射面, 信道估计, 注意力机制, 卷积神经网络

Abstract:

To address the issue of low channel estimation accuracy in Reconfigurable Intelligent Surface (RIS) assisted communication systems, a channel estimation scheme based on Channel Denoising Network (CDN) was proposed, which modeled the channel estimation problem as a channel noise elimination problem. Firstly, traditional algorithms were employed to estimate the received pilot signal preliminarily. Then, the estimated signals were input into the channel estimation network to learn noise features and execute denoising, thereby recovering accurate channel coefficients. Finally, to improve the denoising capability of the network, a Weighted Attention Block (WAB) and a Dilated Convolution Block (DCB) were designed to enhance the network's extraction of dominant noise features, and a multi-scale feature fusion module was designed to prevent the loss of shallow features. Simulation results demonstrate that compared with classical DnCNN (Denoising Convolutional Neural Network) and CDRN (Convolutional neural network-based Deep Residual Network) schemes, the proposed scheme reduces the Normalized Mean Square Error (NMSE) by 2.89 dB and 2.01 dB averagely at different Signal-to-Noise Ratios (SNRs).

Key words: deep learning, Reconfigurable Intelligent Surface (RIS), channel estimation, attention mechanism, Convolutional Neural Network (CNN)

中图分类号: