基于生成对抗网络的MIMO信道估计方法

doi:10.11959/j.issn.1000-0801.2021135

电信科学 ›› 2021, Vol. 37 ›› Issue (6): 14-22.doi: 10.11959/j.issn.1000-0801.2021135

基于生成对抗网络的MIMO信道估计方法

华郁秀¹, 李荣鹏¹, 赵志峰¹^,², 吴建军³, 张宏纲¹

¹ 浙江大学信息与电子工程学院，浙江杭州 310027
² 之江实验室，浙江杭州 311121
³ 华为技术有限公司，上海 200120

修回日期:2021-06-10 出版日期:2021-06-20 发布日期:2021-06-01
作者简介:华郁秀（1993- ），男，浙江大学信息与电子工程学院博士生，主要研究方向为无线资源管理、网络切片、深度学习、强化学习
李荣鹏（1989- ），男，浙江大学信息与电子工程学院副教授，主要研究方向为智能通信网络、网络智能、网络切片
赵志峰（1975- ），男，浙江大学信息与电子工程学院教授，之江实验室科研发展部主任，主要研究方向为认知无线电、无线mesh 网络和SDN 在无线通信中的应用
吴建军（1977- ），男，华为技术有限公司未来网络架构实验室主任，主要研究方向为6G网络架构、5G端到端切片、下一代移动通信标准及产业发展
张宏纲（1967- ），男，浙江大学电子与信息工程学院教授，主要研究方向为认知无线电、绿色通信和下一代异构蜂窝网络架构
基金资助:
国家重点研发计划项目(2020YFB1804804SCI);国家自然科学基金资助项目(61731002);国家自然科学基金资助项目(62071425);浙江省重点研发计划项目(2019C01002);浙江省重点研发计划项目(2019C03131);华为合作项目：之江实验室资助项目(2019LC0AB01);浙江省自然科学基金资助项目(LY20F010016)

GAN-based channel estimation for massive MIMO system

Yuxiu HUA¹, Rongpeng LI¹, Zhifeng ZHAO¹^,², Jianjun WU³, Honggang ZHANG¹

¹ College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
² Zhejiang Lab, Hangzhou 311121, China
³ Huawei Technologies Co., Ltd., Shanghai 200120, China

Revised:2021-06-10 Online:2021-06-20 Published:2021-06-01
Supported by:
The National Key Research and Development Program of China(2020YFB1804804SCI);The National Natural Science Foundation of China(61731002);The National Natural Science Foundation of China(62071425);Zhejiang Key Research and Development Plan(2019C01002);Zhejiang Key Research and Development Plan(2019C03131);Huawei Cooperation Project, The Project sponsored by Zhejiang Lab(2019LC0AB01);The Natural Science Foundation of Zhejiang Provincial of China(LY20F010016)

摘要/Abstract

摘要：

作为 5G 的一项关键技术，大规模多输入多输出（MIMO）系统通过在基站配备大量天线可以显著提高频谱效率和能效。然而，在大规模MIMO 系统中，精确的信道估计面临严峻挑战。为了在导频序列长度小于发射天线数量以及信道噪声强烈的情况下进行精确的估计信道，提出了一种基于生成对抗网络的大规模MIMO 信道估计方法N2N-GAN。N2N-GAN首先对接收端的导频信号进行去噪，然后使用条件生成对抗网络根据去噪后的导频信号估计信道矩阵。仿真实验证明，与传统的信道估计算法和基于深度学习的算法相比， N2N-GAN 对环境噪声具有更高的鲁棒性，而且可以适应更少导频符号和更多天线数量的场景。

关键词: 信道估计, 大规模MIMO, 信号降噪, 生成对抗网络

Abstract:

As a key technology of 5G, massive MIMO system can significantly improve spectrum efficiency and energy efficiency by equipping a large number of antennas in base stations.However, in massive MIMO system, accurate channel estimation faces severe challenges.In order to estimate the channel accurately when the pilot sequence length is smaller than the number of transmitting antennas and the channel noise is strong, the estimation method N2N-GAN was proposed.N2N-GAN firstly denoised the pilot channel at the receiving end, and then used the conditional generative adversarial network to estimate the channel matrix according to the denoised pilot signal.Simulation experiments show that N2N-GAN achieves better robustness against noise compared with traditional channel estimation algorithms and deep learning-based methods.Meanwhile, it can adapt to scenarios with fewer pilot symbols and more antennas.

Key words: channel estimation, massive MIMO, signaldenoising, generative adversarial network

中图分类号:

TP393

华郁秀, 李荣鹏, 赵志峰, 吴建军, 张宏纲. 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.

Yuxiu HUA, Rongpeng LI, Zhifeng ZHAO, Jianjun WU, Honggang ZHANG. GAN-based channel estimation for massive MIMO system[J]. Telecommunications Science, 2021, 37(6): 14-22.

图/表 6

图1

图2

图3

表1

图4

图5

参考文献 25

[1]	YANG P , XIAO Y , XIAO M ,et al. 6G wireless communications:Vision and potential techniques[J]. IEEE Network, 2019,33(4): 70-75.
[2]	AKYILDIZ I F , HAN C , NIE S . Combating the distance problem in the millimeter wave and terahertz frequency bands[J]. IEEE Communications Magazine, 2018,56(6): 102-108.
[3]	HASSIBI B , HOCHWALD B M . How much training is needed in multiple-antenna wireless links?[J]. IEEE Transactions on Information Theory, 2003,49(4): 951-963.
[4]	MA J , PING L . Data-aided channel estimation in large antenna systems[J]. IEEE Transactions on Signal Processing, 2014,62(12): 3111-3124.
[5]	LI Y , TAO C , SECO-GRANADOS G ,et al. Channel estimation and performance analysis of one-bit massive MIMO systems[J]. IEEE Transactions on Signal Processing, 2017,65(15): 4075-4089.
[6]	HUANG C , ALEXANDEROPOULOS G C , ZAPPONE A ,et al. Deep learning for UL/DL channel calibration in generic massive MIMO systems[C]// Proceedings of IEEE International Conference on Communications(ICC). Piscataway:IEEE Press, 2019: 1-6.
[7]	DONG P , ZHANG H , LI G Y ,et al. Deep CNN-based channel estimation for mmWave massive MIMO systems[J]. IEEE Journal of Selected Topics in Signal Processing, 2019,13(5): 989--1000.
[8]	HE H , WEN C K , JIN S ,et al. Deep learning-based channel estimation for beam space mmWave massive MIMO systems[J]. IEEE Wireless Communications Letters, 2018,7(5): 852-855.
[9]	SOLTANI M , POURAHMADI V , MIRZAEI A ,et al. Deep learning-based channel estimation[J]. IEEE Communications Letters, 2019,23(4): 652-655.
[10]	SHEA T O , HOYDIS J . An introduction to deep learning for the physical layer[J]. IEEE Transactions on Cognitive Communications and Networking, 2017,3(4): 563-575.
[11]	DORNER S , CAMMERER S , HOYDIS J ,et al. Deep learning based communication over the air[J]. IEEE Journal of Selected Topics in Signal Processing, 2017,12(1): 132-143.
[12]	GAO S , DONG P , PAN Z ,et al. Deep learning based channel estimation for massive MIMO with mixed-resolution ADCs[J]. IEEE Communications Letters, 2019,23(11): 1989-1993.
[13]	KANG J M , CHUN C J , KIM I M . Deep-learning-based channel estimation for wireless energy transfer[J]. IEEE Communications Letters, 2018,22(11): 2310-2313.
[14]	DONG Y , WANG H , YAO Y D . Channel estimation for one-bit multiuser massive MIMO using conditional GAN[J]. IEEE Communications Letters, 2020.
[15]	ZHANG K , ZUO W , CHEN Y ,et al. Beyond a gaussian denoiser:residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017,26(7): 3142-3155.
[16]	BALEVI E , DOSHI A , ANDREWS J G . Massive MIMO channel estimation with an untrained deep neural network[J]. IEEE Transactions on Wireless Communications, 2020,19(3): 2079-2090.
[17]	ULYANOV D , VEDALDI A , LEMPITSKY V . Deep image prior[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2018: 9446-9454.
[18]	ALKHATEEB A . DeepMIMO:A generic deep learning dataset for millimeter wave and massive MIMO applications[J]. arXiv preprint arXiv:1902.06435, 2019.
[19]	REMCOM. Wireless insite[Z]. 2021.
[20]	LEHTINEN J , MUNKBERG J , HASSELGREN J ,et al. Noise2noise:learning image restoration without clean data[J]. arXiv preprint arXiv:1803.04189, 2018.
[21]	GOODFELLOW I J , POUGET-ABADIE J ,, MIRZA M ,et al. Generative adversarial networks[J]. arXiv preprint arXiv:1406.2661, 2014.
[22]	MIRZA M , OSINDERO S . Conditional generative adversarial nets[J]. arXiv preprint arXiv:1411.1784, 2014.
[23]	RONNEBERGER O , FISCHER P , BROX T . U-net:convolutional networks for biomedical image segmentation[C]// Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention. Piscataway:IEEE Press, 2015: 234-241.
[24]	KINGMA D P , BA J . Adam:a method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014.
[25]	ISOLA P , ZHU J Y , ZHOU T ,et al. Image-to-image translation with conditional adversarial networks[Z]. 2017.

参数	值
工作频率	2.5 GHz
天线间隔	半波长
带宽	10 MHz
多径数量/个	10
天线数量/根	64、128、192、256
用户数量/个	32
导频序列长度	4、8、16

基于生成对抗网络的MIMO信道估计方法

GAN-based channel estimation for massive MIMO system

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 25

相关文章 15

Metrics

推荐阅读 0

[1]	马辉, 王瑞琴, 杨帅. 一种渐进式增长条件生成对抗网络模型[J]. 电信科学, 2023, 39(6): 105-113.
[2]	卢敏, 秦泽豪, 陈志辉, 张敏, 乐光学. 基于1D-Concatenate的信道估计DNN模型优化方法[J]. 电信科学, 2023, 39(4): 71-86.
[3]	阿克弘, 胡晓东. 基于GAN数据重构的电信用户流失预测方法[J]. 电信科学, 2023, 39(3): 135-142.
[4]	王晖, 邰其心, 刘镠, 王鸿, 宋荣方. 基于GSIC的上行链路毫米波大规模MIMO-NOMA系统低功耗传输方法[J]. 电信科学, 2023, 39(1): 51-59.
[5]	邓丹昊, 王朝炜, 江帆, 王卫东. 无人机辅助无蜂窝大规模MIMO中的空地协同调度[J]. 电信科学, 2022, 38(8): 37-44.
[6]	曹海燕, 汪忠亮, 徐好, 陈千鸿, 许方敏. 基于混合精度ADC量化的大规模MIMO系统能效联合优化算法[J]. 电信科学, 2022, 38(8): 65-74.
[7]	高子路, 孙韶辉, 李丽. 面向新一代移动通信的智能超表面技术综述[J]. 电信科学, 2022, 38(10): 20-35.
[8]	孙金杨, 刘柏嵩, 任豪, 钱江波. TAGAN：一种融合细粒度语义特征的学术论文对抗推荐算法[J]. 电信科学, 2021, 37(8): 57-65.
[9]	张沛昌, 安万年, 钟世达, 黄磊, 庄春生, 张伟. 一种新型低复杂度双层分组天线选择算法[J]. 电信科学, 2021, 37(7): 67-76.
[10]	章坚武, 王路鑫, 孙玲芬, 章谦骅, 单杭冠. 人工智能在5G系统中的应用综述[J]. 电信科学, 2021, 37(5): 14-31.
[11]	于玄, 耿烜. 一种降低复杂度的压缩感知水声信道估计方法[J]. 电信科学, 2021, 37(3): 114-124.
[12]	郑声晟, 殷海兵, 黄晓峰, 章天杰. 基于GAN的无监督域自适应行人重识别[J]. 电信科学, 2021, 37(2): 99-106.
[13]	曹海燕, 马智尧, 智应娟, 刘仁清, 许方敏, 方昕. 毫米波大规模MIMO系统基于等效信道的全连接混合预编码设计[J]. 电信科学, 2021, 37(1): 85-93.
[14]	程露,杨丽花,王增浩,张捷,梁彦. 基于历史信息的软卡尔曼滤波迭代时变信道估计方法[J]. 电信科学, 2020, 36(9): 23-31.
[15]	邱佳锋. 基于优化BM3D的毫米波大规模MIMO信道估计[J]. 电信科学, 2020, 36(9): 44-50.