Data driven 3D channel estimation for massive MIMO

Massive MIMO is considered as promising technology enabling 5G and beyond 5G cellular communication networks. High-resolution gain and angle estimation of the channel are significant challenges in the design of massive MIMO. The existing signal subspace-based estimation techniques lack the resolution for the detection of slight angles. The severity increases when both azimuth and elevation angle are jointly estimating for the 3D channel. The existing techniques rely on the combination of signal subspace-based approaches to estimate both azimuth and elevation angles. The resulting estimate’s accuracy is less due to its low resolution and angular coupling. Data-driven techniques can address this issue. This work is the first-ever attempt to apply data-driven techniques for 3D channel estimation of massive MIMO to the best of our knowledge. This paper considers two approaches for the same, one based on K nearest neighbour (KNN) and the other based on deep neural network (DNN) with restricted Boltzmann machine (RBM). We also investigated data generation and feature extraction for data-driven communication technologies in three ways. An intensive performance analysis of both architectures using these three feature vectors is carried out. The simulation reveals deep learning (DL) model’s superiority compared to the machine learning (ML)-based counterpart and other signal subspace-based estimation techniques. SNR of 10 dB lesser than other signal subspace estimation is required for ML-based approach, whereas the DL-based estimator needs 20 dB lesser SNR for the received signal to achieve the same BER value. In the comparative study on the feature vectors for data-driven estimation techniques, the data processing based on the Pearson correlation feature vector (PCFV) performs the best. Performance comparison of the DNN model with the KNN model is based on tenfold cross-validation showing an average AUC of 0.915 for DL based estimation and a coefficient of 0.904 for ML-based counterpart.

[1]  Ismayil Siyad C,et al.  Frequency Domain Learning Scheme for Massive MIMO Using Deep Neural Network , 2020, 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS).

[2]  Emil Björnson,et al.  Sum Spectral Efficiency Maximization in Massive MIMO Systems: Benefits from Deep Learning , 2019, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[3]  Mohamed-Slim Alouini,et al.  3D Massive MIMO Systems: Modeling and Performance Analysis , 2015, IEEE Transactions on Wireless Communications.

[4]  Lassi Hentila,et al.  WINNER II Channel Models , 2009 .

[5]  Guan Gui,et al.  Deep Learning for Super-Resolution Channel Estimation and DOA Estimation Based Massive MIMO System , 2018, IEEE Transactions on Vehicular Technology.

[6]  Xianbin Wang,et al.  Hybrid Analog-Digital Channel Estimation and Beamforming: Training-Throughput Tradeoff , 2015, IEEE Transactions on Communications.

[7]  Ranjay Hazra,et al.  An efficient Deep reinforcement learning with extended Kalman filter for device‐to‐device communication underlaying cellular network , 2019, Trans. Emerg. Telecommun. Technol..

[8]  Firdous A. Shah,et al.  Wavelet neural network model for network intrusion detection system , 2019 .

[9]  Sangmi Moon,et al.  Deep learning-based channel estimation and tracking for millimeter-wave vehicular communications , 2020, Journal of Communications and Networks.

[10]  S. Tamilselvan,et al.  Deep Learning Enabled Physical Layer Security to Combat Eavesdropping in Massive MIMO Networks , 2019, ICCNCT - 2019.

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

[12]  Yan Li,et al.  Angle and Delay Estimation for 3-D Massive MIMO/FD-MIMO Systems Based on Parametric Channel Modeling , 2017, IEEE Transactions on Wireless Communications.

[13]  Yong Liang Guan,et al.  Adaptive Spatial Modulation MIMO Based on Machine Learning , 2019, IEEE Journal on Selected Areas in Communications.

[14]  Yejun He,et al.  Geometrical Model for Massive MIMO Systems , 2017, 2017 IEEE 85th Vehicular Technology Conference (VTC Spring).

[15]  Yunlong Cai,et al.  Reduced-Rank DOA Estimation Algorithms Based on Alternating Low-Rank Decomposition , 2016, IEEE Signal Processing Letters.

[16]  R. Samworth.  Optimal weighted nearest neighbour classifiers , 2011, 1101.5783.

[17]  Emil Björnson,et al.  Massive MIMO Networks: Spectral, Energy, and Hardware Efficiency , 2018, Found. Trends Signal Process..

[18]  Lam Thanh Tu,et al.  A Statistical Estimation of 5G Massive MIMO Networks’ Exposure Using Stochastic Geometry in mmWave Bands , 2020, Applied Sciences.

[19]  Mohamed Hassan Essai Ali,et al.  Deep learning-based pilot-assisted channel state estimator for OFDM systems , 2021, IET Commun..

[20]  Navrati Saxena,et al.  Deep‐DRX: A framework for deep learning–based discontinuous reception in 5G wireless networks , 2019, Trans. Emerg. Telecommun. Technol..

[21]  Bhekisizwe Mzimkhulu Mthethwa,et al.  Deep Learning-Based Wireless Channel Estimation for MIMO Uncoded Space-Time Labeling Diversity , 2020, IEEE Access.

[22]  Zhi Zheng,et al.  Direction-of-Arrival Estimation of Coherent Signals Under Direction-Dependent Mutual Coupling , 2021, IEEE Communications Letters.

[23]  Wen-Qin Wang,et al.  Efficient Beamspace-Based Algorithm for Two-Dimensional DOA Estimation of Incoherently Distributed Sources in Massive MIMO Systems , 2018, IEEE Transactions on Vehicular Technology.

[24]  Tzu-Tsung Wong,et al.  Reliable Accuracy Estimates from k-Fold Cross Validation , 2020, IEEE Transactions on Knowledge and Data Engineering.

[25]  Jun Wu,et al.  Low-Complexity Deep-Learning-Based DOA Estimation for Hybrid Massive MIMO Systems With Uniform Circular Arrays , 2020, IEEE Wireless Communications Letters.

[26]  H. Vincent Poor,et al.  Neyman-Pearson Detection of Gauss-Markov Signals in Noise: Closed-Form Error Exponent and Properties , 2005, ISIT.

[27]  T. Srinivas,et al.  Highly sensitive lab-on-chip with deep learning AI for detection of bacteria in water , 2019, International Journal of Information Technology.

[28]  Emil Björnson,et al.  Massive MIMO: ten myths and one critical question , 2015, IEEE Communications Magazine.

[29]  Dong-Seong Kim,et al.  Deep Q-learning based resource allocation in industrial wireless networks for URLLC , 2020, IET Commun..

[30]  H. Vincent Poor,et al.  Neyman-pearson detection of gauss-Markov signals in noise: closed-form error exponentand properties , 2005, IEEE Transactions on Information Theory.

[31]  Geoffrey Ye Li,et al.  Deep Learning-Based Denoise Network for CSI Feedback in FDD Massive MIMO Systems , 2020, IEEE Communications Letters.

[32]  Emil Björnson,et al.  Channel Estimation in Massive MIMO Under Hardware Non-Linearities: Bayesian Methods Versus Deep Learning , 2020, IEEE Open Journal of the Communications Society.

[33]  Mehmet Kemal Özdemir,et al.  Extended reduced-rank joint estimation of direction of arrival with mutual coupling for coherent signals , 2019, Trans. Emerg. Telecommun. Technol..

[34]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[35]  Aleena Swetapadma,et al.  A machine learning based method to detect epilepsy , 2018, International Journal of Information Technology.

[36]  Y. Xu,et al.  IMPROVED ARTIFICIAL NEURAL NETWORK BASED ON INTELLIGENT OPTIMIZATION ALGORITHM , 2018 .

[37]  Tareq Y. Al-Naffouri,et al.  Distributed Channel Estimation and Pilot Contamination Analysis for Massive MIMO-OFDM Systems , 2015, IEEE Transactions on Communications.

[38]  Ahmad Nimr,et al.  Deep Learning Based Channel Estimation Schemes for IEEE 802.11p Standard , 2020, IEEE Access.