Intelligent Massive MIMO Antenna Selection Using Monte Carlo Tree Search

Antenna selection is a promising technology to achieve a good balance between high transmission capacity and low hardware complexity for massive multiple-input multiple-output (MIMO) systems. However, the design of a near-optimal antenna selection algorithm with low searching complexity is still a challenge. In this paper, we describe a self-supervised learning based Monte Carlo Tree Search (MCTS) method to solve the antenna selection problem for a massive MIMO system. The search process for selecting antennas with maximal channel capacity is converted to a decision-making based problem. Based on the system model of antenna selection, we map the components of a MIMO system to the basic elements of MCTS such as action, tree state, and reward. To improve the search efficiency of the MCTS, we employ a linear regression module to extract the channel features from the channel state information (CSI) and output the prediction to MCTS as prior probability. Since the data and label are generated by the MCTS process itself, the entire process can be considered as a self-supervised learning process. According to the simulation results, the proposed self-supervised learning MCTS-based antenna search method exhibits a high searching efficiency with near-optimal performance, which archives 40% and 15% outage capacity compared with random selection and greedy search selection, respectively. The bit error rate (BER) performance of the proposed method has about 1-dB gain compared to the greedy search selection method.

[1]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[2]  Tao Jiang,et al.  Deep learning for wireless physical layer: Opportunities and challenges , 2017, China Communications.

[3]  Jianhao Hu,et al.  An Intra-Iterative Interference Cancellation Detector for Large-Scale MIMO Communications Based on Convex Optimization , 2016, IEEE Transactions on Circuits and Systems I: Regular Papers.

[4]  Antonio Criminisi,et al.  Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning , 2012, Found. Trends Comput. Graph. Vis..

[5]  Thomas Kaiser,et al.  Massive MIMO Antenna Selection: Switching Architectures, Capacity Bounds, and Optimal Antenna Selection Algorithms , 2018, IEEE Transactions on Signal Processing.

[6]  Thomas L. Marzetta,et al.  Noncooperative Cellular Wireless with Unlimited Numbers of Base Station Antennas , 2010, IEEE Transactions on Wireless Communications.

[7]  Chintha Tellambura,et al.  Receive Antenna Selection Based on Union-Bound Minimization Using Convex Optimization , 2007, IEEE Signal Processing Letters.

[8]  Furqan Jameel,et al.  Massive MIMO: A survey of recent advances, research issues and future directions , 2017, 2017 International Symposium on Recent Advances in Electrical Engineering (RAEE).

[9]  Mojtaba Soltanalian,et al.  Signal Recovery From 1-Bit Quantized Noisy Samples via Adaptive Thresholding , 2018, 2018 52nd Asilomar Conference on Signals, Systems, and Computers.

[10]  Enrique Stevens-Navarro,et al.  A Low-Complexity Antenna Selection Algorithm for Cooperative Sensor Networks , 2018, 2018 IEEE Canadian Conference on Electrical & Computer Engineering (CCECE).

[11]  Erik G. Larsson,et al.  Energy and Spectral Efficiency of Very Large Multiuser MIMO Systems , 2011, IEEE Transactions on Communications.

[12]  Fredrik Tufvesson,et al.  Achievable Rates and Training Overheads for a Measured LOS Massive MIMO Channel , 2018, IEEE Wireless Communications Letters.

[13]  E. Larsson,et al.  MIMO Detection Methods: How They Work , 2010 .

[14]  Moe Z. Win,et al.  Capacity of MIMO systems with antenna selection , 2001, IEEE Transactions on Wireless Communications.

[15]  Walid A. Al-Hussaibi,et al.  A Closed-Form Approximation of Correlated Multiuser MIMO Ergodic Capacity With Antenna Selection and Imperfect Channel Estimation , 2018, IEEE Transactions on Vehicular Technology.

[16]  Jianhao Hu,et al.  Hardware Efficient Massive MIMO Detector Based on the Monte Carlo Tree Search Method , 2017, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[17]  Simon M. Lucas,et al.  A Survey of Monte Carlo Tree Search Methods , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[18]  Yonina C. Eldar,et al.  Deep Signal Recovery with One-bit Quantization , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[19]  Sumei Sun,et al.  Two-step transmit antenna selection algorithms for massive MIMO , 2016, 2016 IEEE International Conference on Communications (ICC).

[20]  Kamil Rocki,et al.  Large-Scale Parallel Monte Carlo Tree Search on GPU , 2011, 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum.

[21]  E.G. Larsson,et al.  MIMO Detection Methods: How They Work [Lecture Notes] , 2009, IEEE Signal Processing Magazine.

[22]  Tony Q. S. Quek,et al.  Transmit Antenna Selection in MIMO Wiretap Channels: A Machine Learning Approach , 2018, IEEE Wireless Communications Letters.

[23]  Feng Zheng,et al.  Rotman Lens Based Hybrid Analog–Digital Beamforming in Massive MIMO Systems: Array Architectures, Beam Selection Algorithms and Experiments , 2017, IEEE Transactions on Vehicular Technology.

[24]  Joseph R. Cavallaro,et al.  Large-Scale MIMO Detection for 3GPP LTE: Algorithms and FPGA Implementations , 2014, IEEE Journal of Selected Topics in Signal Processing.

[25]  Yonina C. Eldar,et al.  Cognitive radar antenna selection via deep learning , 2018, IET Radar, Sonar & Navigation.

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

[27]  Namyoon Lee,et al.  Supervised-Learning-Aided Communication Framework for MIMO Systems With Low-Resolution ADCs , 2016, IEEE Transactions on Vehicular Technology.

[28]  Ami Wiesel,et al.  Deep MIMO detection , 2017, 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[29]  C. Geetha Priya,et al.  Design of efficient massive MIMO for 5G systems — Present and past: A review , 2017, 2017 International Conference on Intelligent Computing and Control (I2C2).

[30]  Nicolas Pinto,et al.  PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation , 2009, Parallel Comput..

[31]  Erik G. Larsson,et al.  Massive MIMO in Real Propagation Environments: Do All Antennas Contribute Equally? , 2015, IEEE Transactions on Communications.

[32]  Hyuncheol Park,et al.  Performance Analysis of MIMO System with Linear MMSE Receiver , 2008, IEEE Transactions on Wireless Communications.

[33]  Amine Mezghani,et al.  Blind Estimation of Sparse Broadband Massive MIMO Channels With Ideal and One-bit ADCs , 2017, IEEE Transactions on Signal Processing.

[34]  Lajos Hanzo,et al.  Fifty Years of MIMO Detection: The Road to Large-Scale MIMOs , 2015, IEEE Communications Surveys & Tutorials.

[35]  Jeffrey H. Reed,et al.  A new approach to signal classification using spectral correlation and neural networks , 2005, First IEEE International Symposium on New Frontiers in Dynamic Spectrum Access Networks, 2005. DySPAN 2005..

[36]  Erik G. Larsson,et al.  Scaling Up MIMO: Opportunities and Challenges with Very Large Arrays , 2012, IEEE Signal Process. Mag..

[37]  Mohammad Gharavi-Alkhansari,et al.  Fast antenna subset selection in MIMO systems , 2004, IEEE Transactions on Signal Processing.

[38]  Wolfgang Rave,et al.  Hybrid Beamforming Based on Implicit Channel State Information for Millimeter Wave Links , 2017, IEEE Journal of Selected Topics in Signal Processing.

[39]  Josef A. Nossek,et al.  A Comparison of Hybrid Beamforming and Digital Beamforming With Low-Resolution ADCs for Multiple Users and Imperfect CSI , 2017, IEEE Journal of Selected Topics in Signal Processing.

[40]  Jae-Mo Kang,et al.  Adaptive Rate and Energy Harvesting Interval Control Based on Reinforcement Learning for SWIPT , 2018, IEEE Communications Letters.

[41]  Jae-Mo Kang,et al.  Deep-Learning-Based Channel Estimation for Wireless Energy Transfer , 2018, IEEE Communications Letters.

[42]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[43]  Joseph R. Cavallaro,et al.  A 3.8Gb/s large-scale MIMO detector for 3GPP LTE-Advanced , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[44]  Danilo De Donno,et al.  mm-Wave channel estimation with accelerated gradient descent algorithms , 2018, EURASIP J. Wirel. Commun. Netw..

[45]  Jingon Joung,et al.  Machine Learning-Based Antenna Selection in Wireless Communications , 2016, IEEE Communications Letters.

[46]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[47]  Hao Li,et al.  Joint Antenna Selection and Power Allocation for an Energy-efficient Massive MIMO System , 2019, IEEE Wireless Communications Letters.

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

[49]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.