基于复数生成对抗网络的5G OFDM信道估计方法

陆元智; 魏祥麟; 于龙; 姚昌华

doi:10.11959/j.issn.1000-0801.2024069

您当前的位置：

首页 >

文章列表页 >

基于复数生成对抗网络的5G OFDM信道估计方法

研究与开发 | 更新时间：2024-06-05

- 基于复数生成对抗网络的5G OFDM信道估计方法
- 5G OFDM channel estimation method based on complex-valued generative adversarial network
- 电信科学 2024年40卷第3期页码：39-52
- 作者机构：
  
  1.南京信息工程大学电子与信息工程学院，江苏南京 210044
  2.国防科技大学第六十三研究所，江苏南京 210007
- 作者简介：
  
  [ "陆元智（1997- ），男，南京信息工程大学硕士生，主要研究方向为深度学习、信道估计。" ]
  魏祥麟（1985- ），男，博士，国防科技大学第六十三研究所副研究员，主要研究方向为频谱智能计算。
  于龙（1981- ），男，博士，国防科技大学第六十三研究所高级工程师，主要研究方向为通信抗干扰、智能通信博弈。
  姚昌华（1982- ），男，博士，南京信息工程大学教授，主要研究方向为智能无人集群、智能无线通信。
- 基金信息：
  
  国家自然科学基金资助项目(61971439;U22B2002);江苏省自然科学基金资助项目(BK20191329);通信抗干扰全国重点实验室基础科研创新基金（稳定支持）项目(IFN20230207)
- DOI：10.11959/j.issn.1000-0801.2024069
  中图分类号： TN911
- 收稿日期：2023-10-20，
  
  修回日期：2023-12-22，
  
  纸质出版日期：2024-03-20
- 稿件说明：
移动端阅览
陆元智,魏祥麟,于龙等.基于复数生成对抗网络的5G OFDM信道估计方法[J].电信科学,2024,40(03):39-52.

LU Yuanzhi,WEI Xianglin,YU Long,et al.5G OFDM channel estimation method based on complex-valued generative adversarial network[J].Telecommunications Science,2024,40(03):39-52.
陆元智,魏祥麟,于龙等.基于复数生成对抗网络的5G OFDM信道估计方法[J].电信科学,2024,40(03):39-52. DOI： 10.11959/j.issn.1000-0801.2024069.

LU Yuanzhi,WEI Xianglin,YU Long,et al.5G OFDM channel estimation method based on complex-valued generative adversarial network[J].Telecommunications Science,2024,40(03):39-52. DOI： 10.11959/j.issn.1000-0801.2024069.

摘要

准确的信道估计能够显著地降低误码率（bit error rate，BER），提高无线通信效率和质量，是5G OFDM通信系统接收机设计的关键环节之一。基于最小二乘（least square，LS）法和基于最小均方差（minimum mean square error，MMSE）的信道估计方法利用系统稀疏性计算信道响应矩阵，但LS算法计算精度较低，而MMSE算法计算量过大。为提升估计精度，业界设计了基于深度学习的信道估计方法。然而，现有的深度学习方法将复数矩阵拆分成实部和虚部，没有充分提取信道中的复数特征，造成估计的信道响应矩阵出现失真。为此，设计了一种基于复数的生成对抗网络模型，充分提取信号的复数特征，从而更准确地估计5G新空口（new radio，NR）标准的物理下行链路共享信道（physical downlink shared channel，PDSCH）的信道响应矩阵。为了验证所提方法的有效性，将所提方法分别与LS算法、实际信道估计、超分辨率神经网络、残差神经网络信道估计算法进行了对比分析。结果表明，当估计的信道响应矩阵与真实矩阵之间的均方差达到0.01时，采用所提方法实现的无线通信系统的信噪比高于现有方法5 dB左右。

Abstract

Accurate channel estimation is a critical component in the design of 5G OFDM communication system receivers

since it can significantly reduce the bit error rate (BER)

thus improving wireless communication efficiency and quality. Channel estimation methods based on least square (LS) and minimum mean square error (MMSE) effectively utilize the system’s sparsity

but LS algorithms face low computational precision

while MMSE algorithms suffer from high computational complexity. To promote the estimation accuracy

practitioners have presented several deep learning-based channel estimation methods. However

existing methods often split complex matrices into real and imaginary parts

failing to adequately capture the complex characteristics of the channel

leading to distortion in the estimated channel matrix. A complex-valued generative adversarial network (GAN) model that could fully extract the complex features of the signals was proposed

enabling accurate estimation of the channel matrix for the physical downlink shared channel (PDSCH) in the 5G new radio (NR) standard. To validate the effectiveness of the proposed method

the proposed method was compared with LS algorithms

actual channel estimation

super-resolution neural networks

and residual neural network channel estimation methods. Results show that when the mean square error between the estimated channel matrix and the true channel matrix is 0.01

the proposed method-based communication system has a signal-to-noise ratio (SNR) that is 5 dB higher than existing ones.

关键词

Keywords

references

NOH G , HUI B , KIM J , et al . DMRS design and evaluation for 3GPP 5G new radio in a high speed train scenario [C ] // Proceedings of the GLOBECOM 2017-2017 IEEE Global Communications Conference . Piscataway : IEEE Press , 2017 : 1 - 6 .

高尚蕾 , 张治中 , 段浴 , 等 . 5G系统中基于解调参考信号的信道估计方法 [J ] . 电讯技术 , 2021 , 61 ( 2 ): 191 - 196 .

GAO S L , ZHANG Z Z , DUAN Y , et al . A channel estimation method based on demodulation reference signal in 5G system [J ] . Telecommunication Engineering , 2021 , 61 ( 2 ): 191 - 196 .

SOLTANI M , POURAHMADI V , MIRZAEI A , et al . Deep learning-based channel estimation [J ] . IEEE Communications Letters , 2019 , 23 ( 4 ): 652 - 655 .

LIN B , WANG X D , YUAN W H , et al . A novel OFDM autoencoder featuring CNN-based channel estimation for Internet of vessels [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 8 ): 7601 - 7611 .

KAPULA P R , SRIDEVI P V . Channel estimation in 5G multi input multi output wireless communication using optimized deep neural framework [J ] . Cluster Computing , 2022 , 25 ( 5 ): 3517 - 3530 .

KALPHANA I , KESAVAMURTHY T . Convolutional neural network auto encoder channel estimation algorithm in MIMO-OFDM system [J ] . Computer Systems Science and Engineering , 2022 , 41 ( 1 ): 171 - 185 .

王义元 , 常俊 , 卢中奎 , 等 . 深度学习辅助的5G OFDM系统的信道估计 [J ] . 电讯技术 , 2024 , 64 ( 1 ): 36 - 42 .

WANG Y Y , CHANG J , LU Z K , et al . Channel estimation of deep learning-assisted 5G OFDM system [J ] . Telecommunication Engineering , 2024 , 64 ( 1 ): 36 - 42 .

YE H , LI G Y , JUANG B H . Power of deep learning for channel estimation and signal detection in OFDM systems [J ] . IEEE Wireless Communications Letters , 2018 , 7 ( 1 ): 114 - 117 .

卢敏 , 秦泽豪 , 陈志辉 , 等 . 基于1D-Concatenate的信道估计DNN模型优化方法 [J ] . 电信科学 , 2023 , 40 ( 4 ): 72 - 86 .

LU M , QIN Z H , CHEN Z H , et al . 1D-Concatenate based channel estimation DNN model optimization method [J ] . Telecommunications Science , 2023 , 40 ( 4 ): 72 - 86 .

GE L J , GUO Y C , ZHANG Y , et al . Deep neural network based channel estimation for massive MIMO-OFDM systems with imperfect channel state information [J ] . IEEE Systems Journal , 2022 , 16 ( 3 ): 4675 - 4685 .

LIAO Y , HUA Y X , DAI X W , et al . ChanEstNet: a deep learning based channel estimation for high-speed scenarios [C ] // Proceedings of the ICC 2019-2019 IEEE International Conference on Communications (ICC) . Piscataway : IEEE Press , 2019 : 1 - 6 .

华郁秀 , 李荣鹏 , 赵志峰 , 等 . 基于生成对抗网络的MIMO信道估计方法 [J ] . 电信科学 , 2021 , 37 ( 6 ): 14 - 22 .

HUA Y X , LI R P , ZHAO Z F , et al . GAN-based channel estimation for massive MIMO system [J ] . Telecommunications Science , 2021 , 37 ( 6 ): 14 - 22 .

DONG Y , WANG H , YAO Y D . Channel estimation for one-bit multiuser massive MIMO using conditional GAN [J ] . IEEE Communications Letters , 2020 , 25 ( 3 ): 854 - 858 .

张昀 , 周婧 , 黄经纬 , 等 . 基于深度学习的正交频分复用系统信道估计 [J ] . 通信学报 , 2023 , 44 ( 12 ): 125 - 133 .

ZHANG Y , ZHOU J , HUANG J W , et al . Channel estimation for OFDM system based on deep learning [J ] . Journal on Communications , 2023 , 44 ( 12 ): 125 - 133 .

MELGAR A , DE LA FUENTE A , CARRO-CALVO L , et al . Deep neural network: an alternative to traditional channel estimators in massive MIMO systems [J ] . IEEE Transactions on Cognitive Communications and Networking , 2022 , 8 ( 2 ): 657 - 671 .

JIANG P W , WEN C K , JIN S , et al . Dual CNN-based channel estimation for MIMO-OFDM systems [J ] . IEEE Transactions on Communications , 2021 , 69 ( 9 ): 5859 - 5872 .

LIU C , LIU X , NG D W K , et al . Deep residual learning for channel estimation in intelligent reflecting surface-assisted multi-user communications [J ] . IEEE Transactions on Wireless Communications , 2021 , 21 ( 2 ): 898 - 912 .

GUO J , WANG L , LI F , et al . CSI feedback with model-driven deep learning of massive MIMO systems [J ] . IEEE Communications Letters , 2021 , 26 ( 3 ): 547 - 551 .

LIU Q , ZHANG Z , YANG G , et al . CSI feedback based on complex neural network for massive MIMO systems [J ] . IEEE Access , 2022 ( 10 ): 78414 - 78422 .

ARJOVSKY M , SHAH A , BENGIO Y . Unitary evolution recurrent neural networks [J ] . JMLR.org , 2015 . doi: 10.48550/arXiv.1511.06464 http://dx.doi.org/10.48550/arXiv.1511.06464 .

TRABELSI C , BILANIUK O , ZHANG Y , et al . Deep complex networks [J ] . arXiv preprint , 2017 , arXiv: 1705.09792 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于生成对抗网络的MIMO信道估计方法

基于时间卷积网络的无监督入侵检测模型

一种基于ADMM的多用户联合的RIS信道估计方案

基于生成对抗网络的超宽带数字信道建模

基于近似消息传递的NOMA系统信道和脉冲噪声联合估计方法