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

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.

[1]  Fredrik Tufvesson,et al.  On the directional reciprocity of uplink and downlink channels in Frequency Division Duplex systems , 2014, 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication (PIMRC).

[2]  Geoffrey Ye Li,et al.  Beam Training and Allocation for Multiuser Millimeter Wave Massive MIMO Systems , 2019, IEEE Transactions on Wireless Communications.

[3]  Jing Gao,et al.  Beamforming Codebook Design and Performance Evaluation for 60GHz Wideband WPANs , 2009, 2009 IEEE 70th Vehicular Technology Conference Fall.

[4]  Zhisheng Niu,et al.  TIME-SEQUENCE CHANNEL INFERENCE FOR BEAM ALIGNMENT IN VEHICULAR NETWORKS , 2018, 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[5]  Peiyao Zhao,et al.  Deep Learning Assisted Beam Prediction Using Out-of-Band Information , 2020, 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring).

[6]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[7]  Efficient broadcasting in ad hoc wireless networks using directional antennas , 2006, IEEE Transactions on Parallel and Distributed Systems.

[8]  Rui Zhang,et al.  Wireless communications with unmanned aerial vehicles: opportunities and challenges , 2016, IEEE Communications Magazine.

[9]  Joongheon Kim,et al.  Fast millimeter-wave beam training with receive beamforming , 2014, Journal of Communications and Networks.

[10]  Thomas L. Marzetta,et al.  Inter-Cell Interference in Noncooperative TDD Large Scale Antenna Systems , 2013, IEEE Journal on Selected Areas in Communications.

[11]  Desmond P. Taylor,et al.  A Statistical Model for Indoor Multipath Propagation , 2007 .

[12]  Ian F. Akyildiz,et al.  A New Wireless Communication Paradigm through Software-Controlled Metasurfaces , 2018, IEEE Communications Magazine.

[13]  Ying Li,et al.  Deep Learning Coordinated Beamforming for Highly-Mobile Millimeter Wave Systems , 2018, IEEE Access.

[14]  Geoffrey Ye Li,et al.  Two-Step Codeword Design for Millimeter Wave Massive MIMO Systems With Quantized Phase Shifters , 2020, IEEE Transactions on Signal Processing.

[15]  Jeongho Park,et al.  Random access in millimeter-wave beamforming cellular networks: issues and approaches , 2015, IEEE Communications Magazine.

[16]  Lajos Hanzo,et al.  Graph Theory Based Beam Scheduling for Inter-Cell Interference Avoidance in MmWave Cellular Networks , 2020, IEEE Transactions on Vehicular Technology.

[17]  Nicolo Michelusi,et al.  Energy-Efficient Interactive Beam Alignment for Millimeter-Wave Networks , 2018, IEEE Transactions on Wireless Communications.

[18]  Theodore S. Rappaport,et al.  Millimeter Wave Mobile Communications for 5G Cellular: It Will Work! , 2013, IEEE Access.

[19]  A. Lee Swindlehurst,et al.  Millimeter-wave massive MIMO: the next wireless revolution? , 2014, IEEE Communications Magazine.

[20]  Robert W. Heath,et al.  Channel Estimation and Hybrid Precoding for Millimeter Wave Cellular Systems , 2014, IEEE Journal of Selected Topics in Signal Processing.

[21]  Derrick Wing Kwan Ng,et al.  On the Power Leakage Problem in Millimeter-Wave Massive MIMO With Lens Antenna Arrays , 2019, IEEE Transactions on Signal Processing.

[22]  Zhaocheng Wang,et al.  Calibrated Beam Training for Millimeter-Wave Massive MIMO Systems , 2019, 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall).

[23]  Fredrik Tufvesson,et al.  Deep convolutional neural networks for massive MIMO fingerprint-based positioning , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[24]  Ahmed Alkhateeb,et al.  Deep Reinforcement Learning for 5G Networks: Joint Beamforming, Power Control, and Interference Coordination , 2019, IEEE Transactions on Communications.

[25]  Kai-Ten Feng,et al.  Learning-Based Beam Training Algorithms for IEEE802.11ad/ay Networks , 2019, 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring).

[26]  Chin-Sean Sum,et al.  Beam Codebook Based Beamforming Protocol for Multi-Gbps Millimeter-Wave WPAN Systems , 2009, GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference.

[27]  Geoffrey Ye Li,et al.  Deep Learning-Based CSI Feedback Approach for Time-Varying Massive MIMO Channels , 2018, IEEE Wireless Communications Letters.

[28]  Sung-En Chiu,et al.  Active Learning and CSI Acquisition for mmWave Initial Alignment , 2018, IEEE Journal on Selected Areas in Communications.

[29]  Maria Scalabrin,et al.  Mobility and Blockage-Aware Communications in Millimeter-Wave Vehicular Networks , 2020, IEEE Transactions on Vehicular Technology.

[30]  Muhammad Alrabeiah,et al.  ViWi: A Deep Learning Dataset Framework for Vision-Aided Wireless Communications , 2020, 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring).

[31]  Robert W. Heath,et al.  Coverage and Rate Analysis for Millimeter-Wave Cellular Networks , 2014, IEEE Transactions on Wireless Communications.

[32]  Muhammad Alrabeiah,et al.  Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6 GHz Channels , 2019, IEEE Transactions on Communications.

[33]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[34]  Zaichen Zhang,et al.  Sparse Channel Estimation and Hybrid Precoding Using Deep Learning for Millimeter Wave Massive MIMO , 2020, IEEE Transactions on Communications.

[35]  Ming Xiao,et al.  Millimeter Wave Communications for Future Mobile Networks , 2017, IEEE Journal on Selected Areas in Communications.

[36]  Sunwoo Kim,et al.  Robust Beam-Tracking for mmWave Mobile Communications , 2017, IEEE Communications Letters.

[37]  J. Andrew Zhang,et al.  Estimation of Multiple Angle-of-Arrivals With Localized Hybrid Subarrays for Millimeter Wave Systems , 2020, IEEE Transactions on Communications.

[38]  Xiang-Gen Xia,et al.  Hierarchical Codebook Design for Beamforming Training in Millimeter-Wave Communication , 2015, IEEE Transactions on Wireless Communications.

[39]  Yujie Wang,et al.  Deep Learning for Beam Training in Millimeter Wave Massive MIMO Systems , 2020 .

[40]  Symeon Chatzinotas,et al.  Dynamic Spectrum Sharing in 5G Wireless Networks With Full-Duplex Technology: Recent Advances and Research Challenges , 2018, IEEE Communications Surveys & Tutorials.

[41]  Iain B. Collings,et al.  Robust Adaptive Beam Tracking for Mobile Millimetre Wave Communications , 2020, IEEE Transactions on Wireless Communications.

[42]  Muhammad Alrabeiah,et al.  Millimeter Wave Base Stations with Cameras: Vision-Aided Beam and Blockage Prediction , 2019, 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring).

[43]  Iain B. Collings,et al.  Explore and Eliminate: Optimized Two-Stage Search for Millimeter-Wave Beam Alignment , 2018, IEEE Transactions on Wireless Communications.

[44]  Jaechan Lim,et al.  Beam Tracking Under Highly Nonlinear Mobile Millimeter-Wave Channel , 2019, IEEE Communications Letters.

[45]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[46]  Branka Vucetic,et al.  Codebook-Based Training Beam Sequence Design for Millimeter-Wave Tracking Systems , 2019, IEEE Transactions on Wireless Communications.

[47]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[48]  Shugong Xu,et al.  Deep Reinforcement Learning-Based Beam Tracking for Low-Latency Services in Vehicular Networks , 2020, ICC 2020 - 2020 IEEE International Conference on Communications (ICC).

[49]  Lajos Hanzo,et al.  Joint Transmit Precoding and Reconfigurable Intelligent Surface Phase Adjustment: A Decomposition-Aided Channel Estimation Approach , 2020, IEEE Transactions on Communications.

[50]  Robert W. Heath,et al.  Beam tracking for mobile millimeter wave communication systems , 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[51]  Arnab Roy,et al.  A Tutorial on Beam Management for 3GPP NR at mmWave Frequencies , 2018, IEEE Communications Surveys & Tutorials.

[52]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[53]  Branka Vucetic,et al.  Beam Allocation for Millimeter-Wave MIMO Tracking Systems , 2019, IEEE Transactions on Vehicular Technology.

[54]  Claude Oestges,et al.  The COST 2100 MIMO channel model , 2011, IEEE Wirel. Commun..

[55]  Kyungwhoon Cheun,et al.  Millimeter-wave beamforming as an enabling technology for 5G cellular communications: theoretical feasibility and prototype results , 2014, IEEE Communications Magazine.

[56]  Theodore S. Rappaport,et al.  Overview of Millimeter Wave Communications for Fifth-Generation (5G) Wireless Networks—With a Focus on Propagation Models , 2017, IEEE Transactions on Antennas and Propagation.