RIS辅助的OFDM系统中时变信道估计方法

doi:10.12305/j.issn.1001-506X.2025.01.33

摘要/Abstract

摘要：

为了克服在可重构智能反射面(reconfigurable intelligent surface, RIS)辅助的正交频分复用(orthogonal frequency division multiplexing, OFDM)系统中现有基于深度学习的信道估计方法计算复杂度过高的问题, 在RIS下利用基扩展模型(base extension model, BEM)对时变信道进行建模, 并提出基于残差链接超分辨率卷积神经网络的时变信道估计方法。具体来说, 所提方法首先将参数较多的信道系数估计转换为参数较少的基系数估计, 以降低所提方法计算复杂度。在线下训练中, 利用低分辨率的基系数估计对神经网络进行训练, 仅需要少量的输入即可获取高分辨率的信道估计。为了提高所提方法的实用性, 将网络训练的标签设置为具有高精度的信道估计值, 而非理想的信道信息。仿真实验验证, 所提方法在RIS辅助移动通信系统下能够准确获取时变信道信息, 且具有更高的估计精度和更低的计算复杂度。

关键词: 可重构智能反射面, 正交频分复用, 时变信道估计, 基扩展模型, 残差链接超分辨率卷积神经网络

Abstract:

To overcome the problem of high computational complexity in existing deep learning channel estimation methods in reconfigurable intelligent surface (RIS)-assisted orthogonal frequency division multiplexing (OFDM) system, the base extension model (BEM) is used to model the time-varying channel under RIS, and a time-varying channel estimation method based on residual link super-resolution convolutional neural network is proposed. Specifically, the proposed method firstly converts the channel coefficient estimation with more parameters to the base coefficient estimation with fewer parameters to reduce the computational complexity of the proposed method. In offline training process, the neural network is trained with low-resolution basis coefficient estimation, where only a small amount of input is required to obtain high-resolution channel estimation. In order to improve the practicability of the proposed method, the training network label is set to have high-precision channel estimation value instead of ideal channel information. The proposed method is verified by simulation test, which proves that it can accurately obtain time-varying channel information in RIS-assisted mobile communication system, and has higher estimation accuracy and lower computational complexity.

Key words: reconfigurable intelligent surface (RIS), orthogonal frequency division multiplexing (OFDM), time-varying channel estimation, basis extension model (BEM), residual-linked super-resolution convolutional neural network (ResSRCNN)

中图分类号:

TN929.5

邵永琪, 杨丽花, 常澳, 任露露. RIS辅助的OFDM系统中时变信道估计方法[J]. 系统工程与电子技术, 2025, 47(1): 324-331.

Yongqi SHAO, Lihua YANG, Ao CHANG, Lulu REN. Time-varying channel estimation in RIS-assisted OFDM system[J]. Systems Engineering and Electronics, 2025, 47(1): 324-331.

图/表 11

图1

图2

表1

图3

图4

图5

图6

图7

图8

表2

图9

参考文献 31

1	ELMOSSALLAMY M , ZHANG H , SONG L , et al. Reconfi-gurable intelligent surfaces for wireless communications: principles, challenges, and opportunities[J]. IEEE Trans.on Communications, 2020, 6 (3): 990- 1002.
2	ZHAO M M , LIU A , WAN Y B , et al. Two-timescale beamforming optimization for intelligent reflecting surface aided multiuser communication with qos constraints[J]. IEEE Trans.on Wireless Communications, 2021, 20 (9): 6179- 6194. doi: 10.1109/TWC.2021.3072382
3	BASAR E , RENZO M , et al. Wireless communications through reconfigurable intelligent surfaces[J]. IEEE Access, 2019, 7, 116753- 116773. doi: 10.1109/ACCESS.2019.2935192
4	RENZO M , ZAPPONE A , DEBBAH M , et al. Smart radio environments empowered by reconfigurable intelligent surfaces: how it works, state of research, and the road ahead[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (11): 2450- 2525. doi: 10.1109/JSAC.2020.3007211
5	HUANG C W , ZAPPONE A , ALEXANDROPOULOS G , et al. Reconfigurable intelligent surfaces for energy efficiency in wireless communication[J]. IEEE Trans.on Wireless Communications, 2018, 18 (8): 4157- 4170.
6	刘怡伶. 面向6G的智能反射表面技术的研究探讨[J]. 新型工业化, 2022, 12 (11): 247- 250.
	LIU Y L . Research on intelligent reflective surface technology for 6G[J]. New Industrialization, 2022, 12 (11): 247- 250.
7	ZHANG H, SHLEZINGER N, ALAMZADEH I, et al. Channel estimation with simultaneous reflecting and sensing reconfi-gurable intelligent metasurfaces[C]//Proc. of the IEEE Signal Processing Advances in Wireless Communications, 2021: 536-540.
8	HUANG C W , HU S , ALEXANDROPOULOS G , et al. Holographic MIMO surfaces for 6G wireless networks: opportunities, challenges, and trends[J]. IEEE Wireless Communications, 2020, 27 (5): 118- 125. doi: 10.1109/MWC.001.1900534
9	LIU H , YUAN X J , ZHANG Y J . Matrix-calibration-based cascaded channel estimation for reconfigurable intelligent surface assisted multiuser MIMO[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (11): 2621- 2636. doi: 10.1109/JSAC.2020.3007057
10	ZHENG B X , ZHANG R . Intelligent reflecting surface-enhanced OFDM: channel estimation and reflection optimization[J]. IEEE Wireless Communications Letters, 2020, 9 (4): 518- 522. doi: 10.1109/LWC.2019.2961357
11	YOU C S , ZHENG B X , ZHANG R . Channel estimation and passive beamforming for intelligent reflecting surface: discrete phase shift and progressive refinement[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (11): 2604- 2620. doi: 10.1109/JSAC.2020.3007056
12	WANG P L , FANG J , DUAN H P , et al. Compressed channel estimation for intelligent reflecting surface-assisted millimeter wave systems[J]. IEEE Signal Processing Letters, 2020, 27, 905- 909. doi: 10.1109/LSP.2020.2998357
13	HE J G, LEINONEN M, WYMEERSCH H, et al. Channel estimation for RIS-aided mmwave MIMO systems[C]//Proc. of the IEEE Global Communications Conference, 2020.
14	WEI X H , SHEN D , DAI L L . Channel estimation for RIS assisted wireless communications-Part Ⅱ: an improved solution based on double-structured sparsity[J]. IEEE Communications Letters, 2021, 25 (5): 1403- 1407. doi: 10.1109/LCOMM.2021.3052787
15	MISHRA D, JOHANSSON H. Channel estimation and low-complexity beamforming design for passive intelligent surface assisted MISO wireless energy transfer[C]//Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2019: 4659-4663.
16	MAO Z D , PENG M G , LIU X Q . Channel estimation for reconfigurable intelligent surface assisted wireless communication systems in mobility scenarios[J]. China Communications, 2021, 18 (3): 29- 38. doi: 10.23919/JCC.2021.03.003
17	SUN S , YAN H S . Channel estimation for reconfigurable intelligent surface-assisted wireless communications considering Doppler effect[J]. IEEE Wireless Communications Letters, 2021, 10 (4): 790- 794. doi: 10.1109/LWC.2020.3044004
18	XU M , ZHANG S , MA J P , et al. Deep learning-based time-varying channel estimation for RIS assisted communication[J]. IEEE Communications Letters, 2022, 26 (1): 94- 98. doi: 10.1109/LCOMM.2021.3127160
19	YU J D , LIU X L , GAO Y , et al. Deep learning for channel tracking in IRS-Assisted UAV communication systems[J]. IEEE Trans.on Wireless Communications, 2022, 21 (9): 7711- 7722. doi: 10.1109/TWC.2022.3160517
20	TANG Q, LONG H, YANG H J, et al. An enhanced LMMSE channel estimation under high speed railway scenarios[C]//Proc. of the IEEE International Conference on Communications Workshops, 2017: 999-1004.
21	杨丽花, 任露露, 呼博, 等. 基于元学习的时变信道估计方法[J]. 系统工程与电子技术, 2023, 45 (6): 1872- 1879. doi: 10.12305/j.issn.1001-506X.2023.06.32
	YANG L H , REN L L , HU B , et al. Time-varying channel estimation method based on meta-learning[J]. Systems Engineering and Electronics, 2023, 45 (6): 1872- 1879. doi: 10.12305/j.issn.1001-506X.2023.06.32
22	聂倩, 杨丽花, 呼博, 等. 基扩展模型下基于LSTM神经网络的时变信道预测方法[J]. 系统工程与电子技术, 2022, 44 (9): 2971- 2977. doi: 10.12305/j.issn.1001-506X.2022.09.33
	NIE Q , YANG L H , HU B , et al. Time-varying channel prediction method based on LSTM neural network under base extension model[J]. Systems Engineering and Electronics, 2022, 44 (9): 2971- 2977. doi: 10.12305/j.issn.1001-506X.2022.09.33
23	LIAO Y, SUN G D, SHEN X F, et al. BEM-based channel estimation and interpolation methods for doubly-selective OFDM channel[C]//Proc. of the IEEE International Conference, 2018: 70-75.
24	YANG H, XIONG J, LI S Y, et al. Wavelet BEM based channel estimation over rapidly time-varying channels[C]//Proc. of the IEEE Wireless Communications and Networking Conference Workshops, 2013: 71-75.
25	YANG S, WANG D D, LIU L Z, et al. BEM based fast time-varying channel estimation method for 5G integrated satellite systems[C]//Proc. of the IEEE International Conference on Communication Technology, 2022: 1020-1024.
26	XU C , AN J C , BAI T , et al. Channel estimation for reconfi-gurable intelligent surface assisted high-mobility wireless systems[J]. IEEE Trans.on Vehicular Technology, 2023, 72 (1): 718- 734. doi: 10.1109/TVT.2022.3203818
27	ZHENG X, CHENG W C, WANG J Z. Position-aided on/off states judgment for 1-bit RIS assisted V2V mmwave communication[C]//Proc. of the IEEE Global Communications Confe-rence, 2022: 3211-3216.
28	PAPAZAFEIROPOULOS A , PAN C , PANDELIS K , et al. Intelligent reflecting surface-assisted MU-MISO systems with imperfect hardware: channel estimation and beamforming design[J]. IEEE Trans.on Wireless Communications, 2022, 21 (3): 2077- 2092. doi: 10.1109/TWC.2021.3109391
29	曹春阳, 胡诚. 基于卷积神经网络的单幅图像超分辨率重建算法综述[J]. 中国高新科技, 2022, 12, 105- 110.
	CAO C Y , HU C . A review of super-resolution reconstruction of single image based on convolution neural networks[J]. China High-Tech, 2022, 12, 105- 110.
30	HUANG H J , YANG J , HUANG H , et al. Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system[J]. IEEE Trans.on Vehicular Techno-logy, 2018, 67 (9): 8549- 8560. doi: 10.1109/TVT.2018.2851783
31	WANG X Y, WANG G P, HE R S, et al. Uplink channel estimation with basis expansion model and expectation maximization for wireless communication systems on high-speed railways[C]//Proc. of the IEEE International Conference on Communication in China, 2017.

参数	数值
OFDM符号长度	128
导频数目	32
CP长度	16
载波频率/GHz	2.3
子载波间隔/kHz	15
信道模型	5径莱斯信道
基函数个数	4
RIS反射单元数目	4
优化器	Adam
损失函数	MSE
迭代轮次	50
批次大小	128
学习率	0.001

方法	阶段	复杂度
文献[18]	训练阶段	V((2NMR₁+R₂R₃₊R₃R₄₊R₄R₅₊R₅2NM)+ 2NME+15E²+E2NM)
文献[18]	估计阶段	(2NMR₁+R₂R₃₊R₃R₄₊R₄R₅₊R₅2NM)+ 2NME+15E²+E2NM
文献[19]	训练阶段	V((2NMD₁+D₁D₂+D₂D₃+D₃D₄+D₄D₅+ D₅D₆+2D₆NM)+(2NMR₁+R₁R₂+R₂2NM))
文献[19]	估计阶段	2NMD₁+D₁D₂+D₂D₃+D₃D₄+D₄D₅+ D₅D₆+2D₆NM+2NMR₁+R₁R₂+R₂2NM
所提方法	训练阶段	V(2QLMC₁+C₁C₂+C₂C₃+C₃C₄+C₄C₅+c)
所提方法	估计阶段	2QLMC₁+C₁C₂+C₂C₃+C₃C₄+C₄C₅+c

[1]	刘方正, 曾瑞琪, 龚阳, 韩振中. 一种ZC-OFDM雷达干扰一体化波形设计与处理方法[J]. 系统工程与电子技术, 2024, 46(9): 2999-3011.
[2]	谭钢, 鄢社锋, 叶子豪, 杨基睿. OFDM系统迭代脉冲噪声抑制与信道估计方法[J]. 系统工程与电子技术, 2024, 46(8): 2841-2849.
[3]	方智敬, 陈媛, 王俊杰. 改进的可见光通信系统PTS峰均比抑制方法[J]. 系统工程与电子技术, 2024, 46(7): 2509-2514.
[4]	邹涵, 张天骐, 马焜然, 杨宗方. 基于多特征融合的MIMO-OFDM系统单-混信号调制识别算法[J]. 系统工程与电子技术, 2024, 46(4): 1456-1465.
[5]	张刚, 陈茜, 蒋忠均. 高速置换索引差分混沌移位键控通信系统[J]. 系统工程与电子技术, 2024, 46(3): 1125-1133.
[6]	金志刚, 尹欢, 苏毅珊. 基于不完美CSI的水声自适应功率分配算法[J]. 系统工程与电子技术, 2023, 45(9): 2941-2948.
[7]	杨丽花, 任露露, 呼博, 邵永琪, 聂倩. 基于元学习的时变信道估计方法[J]. 系统工程与电子技术, 2023, 45(6): 1872-1879.
[8]	汪锐, 张天骐, 安泽亮, 王雪怡, 方竹. 基于联合特征参数和一维CNN的MIMO-OFDM系统调制识别算法[J]. 系统工程与电子技术, 2023, 45(3): 902-912.
[9]	季策, 宋博翰, 耿蓉, 梁敏骏. 快时变信道下基于深度学习的OFDM系统信道估计[J]. 系统工程与电子技术, 2023, 45(11): 3649-3655.
[10]	吕岩, 曹菲, 许剑锋, 冯晓伟. 基于FRFT的单基地MIMO雷达稳健波束形成算法[J]. 系统工程与电子技术, 2023, 45(1): 79-85.
[11]	聂倩, 杨丽花, 呼博, 任露露. 基扩展模型下基于LSTM神经网络的时变信道预测方法[J]. 系统工程与电子技术, 2022, 44(9): 2971-2977.
[12]	王震铎, 朱云飞, 宁晓燕, 刁鸣. FrFT-OFDM系统中联合ICI自消除方案[J]. 系统工程与电子技术, 2022, 44(8): 2645-2651.
[13]	高潭, 吕成财, 田川. 面向OFDM-MFSK水声通信的差错控制方法[J]. 系统工程与电子技术, 2022, 44(5): 1701-1708.
[14]	张捷, 杨丽花, 聂倩. 新型的基于堆栈式ELM的时变信道预测方法[J]. 系统工程与电子技术, 2022, 44(2): 662-667.
[15]	刘步花, 丁丹, 杨柳, 薛乃阳, 刘仲谦. 基于DNN的无人机数据OFDM传输技术[J]. 系统工程与电子技术, 2022, 44(2): 696-702.