Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration

This paper studies fast downlink beamforming algorithms using deep learning in multiuser multiple-input-single-output systems where each transmit antenna at the base station has its own power constraint. We focus on the signal-to-interference-plus-noise ratio (SINR) balancing problem which is quasi-convex but there is no efficient solution available. We first design a fast subgradient algorithm that can achieve near-optimal solution with reduced complexity. We then propose a deep neural network structure to learn the optimal beamforming based on convolutional networks and exploitation of the duality of the original problem. Two strategies of learning various dual variables are investigated with different accuracies, and the corresponding recovery of the original solution is facilitated by the subgradient algorithm. We also develop a generalization method of the proposed algorithms so that they can adapt to the varying number of users and antennas without re-training. We carry out intensive numerical simulations and testbed experiments to evaluate the performance of the proposed algorithms. Results show that the proposed algorithms achieve close to optimal solution in simulations with perfect channel information and outperform the alleged theoretically optimal solution in experiments, illustrating a better performance-complexity tradeoff than existing schemes.

[1]  Stefano Cioni,et al.  DVB-S2X-enabled precoding for high throughput satellite systems , 2016, Int. J. Satell. Commun. Netw..

[2]  Andrea J. Goldsmith,et al.  Detection Algorithms for Communication Systems Using Deep Learning , 2017, ArXiv.

[3]  Robert W. Heath,et al.  Five disruptive technology directions for 5G , 2013, IEEE Communications Magazine.

[4]  Geoffrey Ye Li,et al.  Deep Learning-Based Channel Estimation for Beamspace mmWave Massive MIMO Systems , 2018, IEEE Wireless Communications Letters.

[5]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[6]  Nikos D. Sidiropoulos,et al.  Convex Optimization-Based Beamforming , 2010, IEEE Signal Processing Magazine.

[7]  Jian Xiong,et al.  Unsupervised Learning-Based Fast Beamforming Design for Downlink MIMO , 2019, IEEE Access.

[8]  Roy D. Yates,et al.  A Framework for Uplink Power Control in Cellular Radio Systems , 1995, IEEE J. Sel. Areas Commun..

[9]  Erik G. Larsson,et al.  Per-Antenna Constant Envelope Precoding for Large Multi-User MIMO Systems , 2012, IEEE Transactions on Communications.

[10]  Leandros Tassiulas,et al.  Transmit beamforming and power control for cellular wireless systems , 1998, IEEE J. Sel. Areas Commun..

[11]  Trinh Van Chien,et al.  Power Control in Cellular Massive MIMO With Varying User Activity: A Deep Learning Solution , 2019, IEEE Transactions on Wireless Communications.

[12]  Ami Wiesel,et al.  Linear precoding via conic optimization for fixed MIMO receivers , 2006, IEEE Transactions on Signal Processing.

[13]  Paul de Kerret,et al.  Robust Decentralized Joint Precoding using Team Deep Neural Network , 2018, 2018 15th International Symposium on Wireless Communication Systems (ISWCS).

[14]  Ami Wiesel,et al.  Zero-Forcing Precoding and Generalized Inverses , 2008, IEEE Transactions on Signal Processing.

[15]  Woongsup Lee,et al.  Deep Power Control: Transmit Power Control Scheme Based on Convolutional Neural Network , 2018, IEEE Communications Letters.

[16]  Athina P. Petropulu,et al.  A Deep Learning Framework for Optimization of MISO Downlink Beamforming , 2019, IEEE Transactions on Communications.

[17]  Bruno Clerckx,et al.  Recent trend of multiuser MIMO in LTE-advanced , 2013, IEEE Communications Magazine.

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

[19]  Hao Chen,et al.  Artificial Intelligence-Enabled Cellular Networks: A Critical Path to Beyond-5G and 6G , 2019, IEEE Wireless Communications.

[20]  Sreeram Kannan,et al.  Communication Algorithms via Deep Learning , 2018, ICLR.

[21]  Zhe Zhang,et al.  A HYBRID NEURAL NETWORK FRAMEWORK AND APPLICATION TO RADAR AUTOMATIC TARGET RECOGNITION , 2018, 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

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

[23]  Gerhard Fettweis,et al.  SINR Balancing for the Multi-User Downlink under General Power Constraints , 2008, IEEE GLOBECOM 2008 - 2008 IEEE Global Telecommunications Conference.

[24]  Yongming Huang,et al.  Heterogeneous Cellular Networks: Network MIMO techniques , 2011 .

[25]  Andrea J. Goldsmith,et al.  On the optimality of multiantenna broadcast scheduling using zero-forcing beamforming , 2006, IEEE Journal on Selected Areas in Communications.

[26]  Chengwen Xing,et al.  Transceiver Optimization for Multi-Hop Communications With Per-Antenna Power Constraints , 2016, IEEE Transactions on Signal Processing.

[27]  Wei Yu,et al.  Transmitter Optimization for the Multi-Antenna Downlink With Per-Antenna Power Constraints , 2007, IEEE Transactions on Signal Processing.

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

[29]  Yahong Rosa Zheng,et al.  Brain-Inspired Wireless Communications: Where Reservoir Computing Meets MIMO-OFDM , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[30]  Geoffrey Ye Li,et al.  Model-Driven Deep Learning for Physical Layer Communications , 2018, IEEE Wireless Communications.

[31]  Yuanming Shi,et al.  Transfer Learning for Mixed-Integer Resource Allocation Problems in Wireless Networks , 2018, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[32]  Ami Wiesel,et al.  Learning to Detect , 2018, IEEE Transactions on Signal Processing.

[33]  Jiaheng Wang,et al.  A General Framework for Covariance Matrix Optimization in MIMO Systems , 2017, ArXiv.

[34]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[35]  Pekka Kyosti,et al.  MATLAB implementation of the 3GPP spatial channel model (3GPP TR 25.996) , 2005 .

[36]  Athina P. Petropulu,et al.  Deep Learning Based Beamforming Neural Networks in Downlink MISO Systems , 2019, 2019 IEEE International Conference on Communications Workshops (ICC Workshops).

[37]  Cong Shen,et al.  Towards Optimal Power Control via Ensembling Deep Neural Networks , 2018, IEEE Transactions on Communications.

[38]  A. Lee Swindlehurst,et al.  A vector-perturbation technique for near-capacity multiantenna multiuser communication-part I: channel inversion and regularization , 2005, IEEE Transactions on Communications.

[39]  Erik G. Larsson,et al.  Optimal MIMO Precoding Under a Constraint on the Amplifier Power Consumption , 2019, IEEE Transactions on Communications.

[40]  Emil Björnson,et al.  Optimal Multiuser Transmit Beamforming: A Difficult Problem with a Simple Solution Structure [Lecture Notes] , 2014, IEEE Signal Processing Magazine.

[41]  Zhi-Quan Luo,et al.  SINR Constrained Beamforming for a MIMO Multi-User Downlink System: Algorithms and Convergence Analysis , 2012, IEEE Transactions on Signal Processing.

[42]  Geoffrey Ye Li,et al.  A Model-Driven Deep Learning Network for MIMO Detection , 2018, 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[43]  Zhi-Quan Luo,et al.  Semidefinite Relaxation of Quadratic Optimization Problems , 2010, IEEE Signal Processing Magazine.

[44]  Cong Shen,et al.  An Iterative BP-CNN Architecture for Channel Decoding , 2017, IEEE Journal of Selected Topics in Signal Processing.

[45]  Zhi-Quan Luo,et al.  An iteratively weighted MMSE approach to distributed sum-utility maximization for a MIMO interfering broadcast channel , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[46]  Nikos D. Sidiropoulos,et al.  Learning to optimize: Training deep neural networks for wireless resource management , 2017, 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[47]  Shi Jin,et al.  Deep Learning for Massive MIMO CSI Feedback , 2017, IEEE Wireless Communications Letters.

[48]  Zhi Chen,et al.  Intelligent Power Control for Spectrum Sharing in Cognitive Radios: A Deep Reinforcement Learning Approach , 2017, IEEE Access.

[49]  Symeon Chatzinotas,et al.  Generic Optimization of Linear Precoding in Multibeam Satellite Systems , 2011, IEEE Transactions on Wireless Communications.

[50]  Wei Xu,et al.  Transmitter Optimization for Per-Antenna Power Constrained Multi-Antenna Downlinks: An SLNR Maximization Methodology , 2016, IEEE Transactions on Signal Processing.

[51]  Boris Bellalta,et al.  IEEE 802.11ax: High-efficiency WLANS , 2015, IEEE Wireless Communications.

[52]  Xing-Peng Mao,et al.  Learning to Beamform for Minimum Outage , 2018, IEEE Transactions on Signal Processing.

[53]  Stephan ten Brink,et al.  Deep Learning Based Communication Over the Air , 2017, IEEE Journal of Selected Topics in Signal Processing.

[54]  Holger Boche,et al.  Solution of the multiuser downlink beamforming problem with individual SINR constraints , 2004, IEEE Transactions on Vehicular Technology.

[55]  Björn E. Ottersten,et al.  Beamformer Designs for MISO Broadcast Channels with Zero-Forcing Dirty Paper Coding , 2013, IEEE Transactions on Wireless Communications.

[56]  John M. Cioffi,et al.  Weighted Sum-Rate Maximization Using Weighted MMSE for MIMO-BC Beamforming Design , 2008, 2009 IEEE International Conference on Communications.