Deep learning for fast channel estimation in millimeter-wave MIMO systems

doi:10.23919/JSEE.2022.000126

Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (6): 1088-1095.doi: 10.23919/JSEE.2022.000126

• • 上一篇

收稿日期:2021-10-15 接受日期:2022-06-07 出版日期:2022-12-18 发布日期:2022-12-24

Deep learning for fast channel estimation in millimeter-wave MIMO systems

Siting LYU¹^,²(), Xiaohui LI¹^,²^,*(), Tao FAN¹^,²(), Jiawen LIU¹^,²(), Mingli SHI¹^,²()

¹ School of Telecommunication Engineering, Xidian University, Xi’an 710071, China
² State Key Laboratory of Integrated Service Networks, Xidian University, Xi’an 710071, China

Received:2021-10-15 Accepted:2022-06-07 Online:2022-12-18 Published:2022-12-24
Contact: Xiaohui LI E-mail:stlv_0202@stu.xidian.edu.cn;xhli@mail.xidian.edu.cn;601391627@qq.com;316631694@qq.com;1392571846@qq.com
About author:
LYU Siting was born in 1998. She received her B.S. degree in communication engineering from Yunnan University, Kunming, Yunnan, China, in 2019. She is currently pursuing her Ph.D. degree with the State Key Laboratory on Integrated Services Network, Xidian University. Her research interests include wireless communication, deep learning, and millimeter wave beamforming. E-mail: stlv_0202@stu.xidian.edu.cn

LI Xiaohui was born in 1972. In 1994, she graduated from Xidian University with her B.S. degree in communication engineering. In 1994, she stayed at school to work and has been engaged in scientific research in the field of wireless communication. She received her M.S. degree in engineering in 2000 from Xidian University. She received her Ph.D. degree in engineering in 2007. She is a professor in Xidian University. Her research interests are broadband wireless communication and wireless resource management. E-mail: xhli@mail.xidian.edu.cn

FAN Tao was born in 1994. He received his B.S. degree in Xidian University, Xi ’an, Shaanxi, China, in 2016. He is currently pursuing his Ph.D. degree with the State Key Laboratory on Integrated Services Network, Xidian University. His research interests include wireless communication, non-orthogonal multiple access and millimeter wave channel estimation. E-mail: 601391627@qq.com

LIU Jiawen was born in 1995. He received his B.S. degree in Harbin Engineering University, Harbin, Heilongjiang, China, in 2018. He is currently pursuing his Ph.D. degree in communication engineering with the State Key Laboratory on Integrated Services Network in Xidian University, Xi’an, Shaanxi, China. His research interests include wireless communication, surface wave communication, and millimeter wave beamforming. E-mail: 316631694@qq.com

SHI Mingli was born in 1997. He received his B.S. degree in Xidian University, Xi’an, Shaanxi, China, in 2019. He is currently pursuing his Ph.D. degree with the State Key Laboratory on Integrated Services Network, Xidian University. His research interests include wireless communication, millimeter wave communication, and intelligent reconfigurable surface. E-mail: 1392571846@qq.com
Supported by:
This work was supported by the National Key R&D Program of China (2018YFB1802004) and 111 Project (B08038)

摘要/Abstract

Abstract:

Channel estimation has been considered as a key issue in the millimeter-wave (mmWave) massive multi-input multi-output (MIMO) communication systems, which becomes more challenging with a large number of antennas. In this paper, we propose a deep learning (DL)-based fast channel estimation method for mmWave massive MIMO systems. The proposed method can directly and effectively estimate channel state information (CSI) from received data without performing pilot signals estimate in advance, which simplifies the estimation process. Specifically, we develop a convolutional neural network (CNN)-based channel estimation network for the case of dimensional mismatch of input and output data, subsequently denoted as channel (H) neural network (HNN). It can quickly estimate the channel information by learning the inherent characteristics of the received data and the relationship between the received data and the channel, while the dimension of the received data is much smaller than the channel matrix. Simulation results show that the proposed HNN can gain better channel estimation accuracy compared with existing schemes.

Key words: millimeter-wave (mmWave), channel estimation, deep learning (DL), dimensional mismatch, channel state information (CSI)

. [J]. Journal of Systems Engineering and Electronics, 2022, 33(6): 1088-1095.

Siting LYU, Xiaohui LI, Tao FAN, Jiawen LIU, Mingli SHI. Deep learning for fast channel estimation in millimeter-wave MIMO systems[J]. Journal of Systems Engineering and Electronics, 2022, 33(6): 1088-1095.

图/表 6

参考文献 31

1	BUSARI S A, HUQ K M S, MUMTAZ S, et al Millimeter-wave massive MIMO communication for future wireless systems: a survey. IEEE Communications Surveys & Tutorials, 2018, 20 (2): 836- 869.
2	ZHAI X F, CAI Y L, SHI Q J, et al Joint transceiver design with antenna selection for large-scale MU-MIMO mmWave systems. IEEE Journal on Selected Areas in Communications, 2017, 35 (9): 2085- 2096. doi: 10.1109/JSAC.2017.2720197
3	WEI X X, JIANG Y, LIU Q, et al Calibration of phase shifter network for hybrid beamforming in mmWave massive MIMO systems. IEEE Trans. on Signal Processing, 2020, 68, 2302- 2315. doi: 10.1109/TSP.2020.2984884
4	WANG Y, ZOU W X Low complexity hybrid precoder design for millimeter wave MIMO systems. IEEE Communications Letters, 2019, 23 (7): 1259- 1262. doi: 10.1109/LCOMM.2019.2917090
5	QIAO Y, YU S Y, SU P C, et al Research on an iterative algorithm of LS channel estimation in MIMO OFDM systems. IEEE Trans. on Broadcasting, 2005, 51 (1): 149- 153. doi: 10.1109/TBC.2004.842524
6	MA J, YU H, LIU S Y. The MMSE channel estimation based on DFT for OFDM system. Proc. of the 5th International Conference on Wireless Communications, Networking and Mobile Computing, 2009. DOI: 10.1109/WICOM.2009.5305570.
7	ANSARI N, GUPTA A S, GUPTA A. Underwater acoustic channel estimation via CS with prior information. Proc. of OCEANS, 2017. DOI: 10.1109/OCEANSE.2017.8084965.
8	WAN L, QIANG X Z, MA L, et al Accurate and efficient path delay estimation in OMP based sparse channel estimation for OFDM with equispaced pilots. IEEE Wireless Communications Letters, 2019, 8 (1): 117- 120. doi: 10.1109/LWC.2018.2860996
9	FAN D, GAO F F, LIU Y F, et al Angle domain channel estimation in hybrid millimeter wave massive MIMO systems. IEEE Trans. on Wireless Communications, 2018, 17 (12): 8165- 8179. doi: 10.1109/TWC.2018.2874640
10	CHU H Y, ZHENG L, WANG X D Super-resolution mmWave channel estimation for generalized spatial modulation systems. IEEE Journal of Selected Topics in Signal Processing, 2019, 13 (6): 1336- 1347. doi: 10.1109/JSTSP.2019.2918481
11	LIU J W, LI X H, FANG K, et al. Millimeter wave channel estimation based on clustering block sparse Bayesian learning. Proc. of the 11th International Conference on Wireless Communications and Signal Processing, 2019. DOI: 10.1109/WCSP.2019.8928086.
12	MEI K W, LIU J H, ZHANG X C, et al Performance analysis on machine learning-based channel estimation. IEEE Trans. on Communications, 2021, 69 (8): 5183- 5193. doi: 10.1109/TCOMM.2021.3083597
13	CHUN C J, KANG J M, KIM I M Deep learning-based channel estimation for massive MIMO systems. IEEE Wireless Communications Letters, 2019, 8 (4): 1228- 1231. doi: 10.1109/LWC.2019.2912378
14	SOLTANI M, POURAHMADI V, MIRZAEI A, et al Deep learning-based channel estimation. IEEE Communications Letters, 2019, 23 (4): 652- 655. doi: 10.1109/LCOMM.2019.2898944
15	BALEVI E, DOSHI A, ANDREWS J G Massive MIMO channel estimation with an untrained deep neural network. IEEE Trans. on Wireless Communications, 2020, 20 (3): 2079- 2090.
16	HIROSE H, OHTSUKI T, GUI G Deep learning-based channel estimation for massive MIMO systems with pilot contamination. IEEE Open Journal of Vehicular Technology, 2021, 2, 67- 77. doi: 10.1109/OJVT.2020.3045470
17	QIANG H, GAO F F, HAO Z, et al Deep learning for MIMO channel estimation: interpretation, performance, and comparison. IEEE Trans. on Wireless Communications, 2021, 20 (4): 2398- 2412. doi: 10.1109/TWC.2020.3042074
18	LI X F, ALKHATEEB A, TEPEDELENLIOGLU C. Generative adversarial estimation of channel covariance in vehicular millimeter wave systems. Proc. of the 52nd Asilomar Conference on Signals, Systems, and Computers, 2018: 1572–1576.
19	AYACH O E, RAJAGOPAL S, ABU-SURRA S, et al Spatially sparse precoding in millimeter wave MIMO systems. IEEE Trans. on Wireless Communications, 2014, 14 (3): 1499- 1513.
20	ALI A, GONZALEZ-PRELCIC N, HEATH R W Spatial covariance estimation for millimeter wave hybrid systems using out-of-band information. IEEE Trans. on Wireless Communications, 2019, 18 (12): 5471- 5485. doi: 10.1109/TWC.2019.2932404
21	DONG P, ZHANG H, LI G Y, et al Deep CNN-based channel estimation for mmWave massive MIMO systems. IEEE Journal of Selected Topics in Signal Processing, 2019, 13 (5): 989- 1000. doi: 10.1109/JSTSP.2019.2925975
22	GLOROT X, BENGIO Y. Understanding the difficulty of training deep feedforward neural networks. Proc. of the 13th International Conference on Artificial Intelligence and Statistics, 2010: 249–256.
23	HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. Proc. of the IEEE International Conference on Computer Vision, 2015: 1026–1034.
24	ALKHATEEB A, AYACH O E, LEUS G, et al. Hybrid precoding for millimeter wave cellular systems with partial channel knowledge. Proc. of the Information Theory and Applications Workshop, 2013. DOI: 10.1109/ITA.2013.6522603.
25	KINGMA D P, BA J. Adam: a method for stochastic optimization. https://arxiv.org/abs/1412.6980.
26	XU H, KUKSHYA V, RAPPAPORT T S Spatial and temporal characteristics of 60-GHz indoor channels. IEEE Journal on Selected Areas in Communications, 2002, 20 (3): 620- 630. doi: 10.1109/49.995521
27	SAYEED A M. Deconstructing multiantenna fading channels. IEEE Trans. on Signal Processing, 2002, 50(10): 2563–2579.
28	MOLCHANOV P, TYREE S, KARRAS T, et al. Pruning convolutional neural networks for resource efficient inference. https://arxiv.org/abs/1611.06440.
29	LDPE2G. Calculate FLOPs for CNN. https://my.oschina.net/Ldpe2G/blog/2208123.
30	YANG Y W, GAO F F, ZHONG Z M, et al Deep transfer learning-based downlink channel prediction for FDD massive MIMO systems. IEEE Trans. on Communications, 2020, 68 (12): 7485- 7497. doi: 10.1109/TCOMM.2020.3019077
31	MAO H X, LU H C, LU Y J, et al. RoemNet: robust meta learning based channel estimation in OFDM systems. Proc. of the IEEE International Conference on Communications, 2019. DOI: 10.1109/ICC.2019.8761319.

$l$	Conv1	Conv2	Conv3	DeConv1	DeConv2	DeConv3	FC1	FC2
$K_l^{(h)},K_l^{(w)}$	3, 3	3, 3	3, 3	1, 1	1, 1	1, 1	−	−
$M_l^{(h)},M_l^{(w)}$	64, 4	64, 4	64, 4	64, 4	64, 4	64, 4	−	−
${C_{l - 1} } , {C_l}$	1, 8	8, 32	32, 64	64, 64	64, 32	32, 8	−	−
${N_{l - 1} } , {N_l}$	−	−	−	−	−	−	2048, 4096	4096, 8192

Deep learning for fast channel estimation in millimeter-wave MIMO systems

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 31

相关文章 0

编辑推荐

Metrics

本文评价