Deep Learning Assisted Calibrated Beam Training for Millimeter-Wave Communication Systems

被引:50
作者
Ma, Ke [1 ]
He, Dongxuan [1 ]
Sun, Hancun [1 ]
Wang, Zhaocheng [1 ,2 ]
Chen, Sheng [3 ]
机构
[1] Tsinghua Univ, Beijing Natl Res Ctr Informat Sci & Technol, Dept Elect Engn, Beijing, Peoples R China
[2] Tsinghua Shenzhen Int Grad Sch, Shenzhen 518055, Peoples R China
[3] Univ Southampton, Sch Elect & Comp Sci, Southampton SO17 1BJ, Hants, England
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Training; Deep learning; Array signal processing; Tracking; Channel models; Wireless communication; Simulation; Millimeter-wave communications; beam training; beam prediction; deep learning; 5G WIRELESS NETWORKS; CHANNEL ESTIMATION; MASSIVE MIMO; INTERCELL INTERFERENCE; TECHNOLOGY; TRACKING; DESIGN;
D O I
10.1109/TCOMM.2021.3098683
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Huge overhead of beam training imposes a significant challenge in millimeter-wave (mmWave) wireless communications. To address this issue, in this paper, we propose a wide beam based training approach to calibrate the narrow beam direction according to the channel power leakage. To handle the complex nonlinear properties of the channel power leakage, deep learning is utilized to predict the optimal narrow beam directly. Specifically, three deep learning assisted calibrated beam training schemes are proposed. The first scheme adopts convolution neural network to implement the prediction based on the instantaneous received signals of wide beam training. We also perform the additional narrow beam training based on the predicted probabilities for further beam direction calibrations. However, the first scheme only depends on one wide beam training, which lacks the robustness to noise. To tackle this problem, the second scheme adopts long-short term memory (LSTM) network for tracking the movement of users and calibrating the beam direction according to the received signals of prior beam training, in order to enhance the robustness to noise. To further reduce the overhead of wide beam training, our third scheme, an adaptive beam training strategy, selects partial wide beams to be trained based on the prior received signals. Two criteria, namely, optimal neighboring criterion and maximum probability criterion, are designed for the selection. Furthermore, to handle mobile scenarios, auxiliary LSTM is introduced to calibrate the directions of the selected wide beams more precisely. Simulation results demonstrate that our proposed schemes achieve significantly higher beamforming gain with smaller beam training overhead compared with the conventional and existing deep-learning based counterparts.
引用
收藏
页码:6706 / 6721
页数:16
相关论文
共 50 条
[41]   Adaptive Filters Versus Machine Learning Based Beam Tracking Techniques for Millimeter-Wave Wireless Communications Systems [J].
Anooz, Ruaa Shallal Abbas ;
Pourrostam, Jafar ;
Al-Ibadi, Mohanad .
IEEE ACCESS, 2024, 12 :165878-165888
[42]   GaitCube: Deep Data Cube Learning for Human Recognition With Millimeter-Wave Radio [J].
Ozturk, Muhammed Zahid ;
Wu, Chenshu ;
Wang, Beibei ;
Liu, K. J. Ray .
IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (01) :546-557
[43]   Deep Learning Coordinated Beamforming for Highly-Mobile Millimeter Wave Systems [J].
Alkhateeb, Ahmed ;
Alex, Sam ;
Varkey, Paul ;
Li, Ying ;
Qu, Qi ;
Tujkovic, Djordje .
IEEE ACCESS, 2018, 6 :37328-37348
[44]   Model-Driven Deep Learning Based Channel Estimation for Millimeter-Wave Massive Hybrid MIMO Systems [J].
Ma, Xisuo ;
Gao, Zhen ;
Wu, Di .
2021 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA, ICCC, 2021, :676-681
[45]   Deep Learning and Compressed Sensing Based Fast Beam Training for Cell-Free Millimeter Wave System [J].
Sheng, Yangye ;
He, Weiliang ;
Zhang, Cheng ;
Huang, Yongming .
2024 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC 2024, 2024,
[46]   Ergodic Achievable Rate Analysis and Optimization of RIS-Assisted Millimeter-Wave MIMO Communication Systems [J].
Li, Renwang ;
Sun, Shu ;
Chen, Yuhang ;
Han, Chong ;
Tao, Meixia .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2023, 22 (02) :972-985
[47]   Federated Learning-Aided Beam Prediction for Multi-User Millimeter Wave Communications [J].
Chuang, Cheng-Jui ;
Liu, Kuang-Hao .
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2025, 11 (03) :1818-1829
[48]   Deep Reinforcement Learning-Based Beam Training for Spatially Consistent Millimeter Wave Channels [J].
Narengerile ;
Thompson, John ;
Patras, Paul ;
Ratnarajah, Tharmalingam .
2021 IEEE 32ND ANNUAL INTERNATIONAL SYMPOSIUM ON PERSONAL, INDOOR AND MOBILE RADIO COMMUNICATIONS (PIMRC), 2021,
[49]   Deep Learning-Based Millimeter Wave Beam Recommendation via Channel Knowledge Map [J].
Shao, Chenyang ;
Liu, Chunshan ;
Zhao, Lou ;
Li, Min ;
Zhang, Xiaoshuai ;
Sun, Minhong .
IEEE WIRELESS COMMUNICATIONS LETTERS, 2025, 14 (06) :1648-1652
[50]   Failure Prediction for Proactive Beam Recovery in Millimeter-Wave Communication [J].
Abusaral, Ayah ;
Hassanein, Hossam S. ;
Noureldin, Aboelmagd ;
Bin Sediq, Akram .
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, :3617-3622