CSI Classification for 5G via Deep Learning

5G communication requires continuous exchanges of channel state information (CSI) between the base station and user equipment (UE) to adjust the physical layer parameters. CSI classification in a noisy environment is challenging, since CSI can get corrupted. To address this problem, we apply a convolutional neural network (CNN) to classify several key CSI parameters. In a simulation study, our CNN method classifies the CSI parameters with accuracy ranging between 84-98\%, which is approximately 24-38\% higher than the 3GPP recommendations for UEs.

[1]  François Chollet,et al.  Deep Learning with Python , 2017 .

[2]  Shi Jin,et al.  A low-complexity adaptive transmission scheme based on the dual-codebook of 3GPP LTE-advanced , 2011, 2011 International Conference on Wireless Communications and Signal Processing (WCSP).

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

[4]  Jocelyn Fiorina,et al.  muMAB: A Multi-Armed Bandit Model for Wireless Network Selection , 2018, Algorithms.

[5]  Shahrokh Valaee,et al.  A Survey on Behaviour Recognition Using WiFi Channel State Information , 2017 .

[6]  Chih-Wei Huang,et al.  A study of deep learning networks on mobile traffic forecasting , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[7]  Walid Saad,et al.  Machine Learning for Wireless Networks with Artificial Intelligence: A Tutorial on Neural Networks , 2017, ArXiv.

[8]  Takashi Dateki,et al.  A Low Complexity PMI/RI Selection Scheme in LTE-A Systems , 2013, 2013 IEEE 77th Vehicular Technology Conference (VTC Spring).

[9]  Fotis Foukalas,et al.  Low-Complexity and Low-Feedback-Rate Channel Allocation in CA MIMO Systems With Heterogeneous Channel Feedback , 2017, IEEE Transactions on Vehicular Technology.

[10]  Houman Zarrinkoub,et al.  Understanding LTE with MATLAB: From Mathematical Modeling to Simulation and Prototyping , 2014 .

[11]  Biing-Hwang Juang,et al.  Deep Learning in Physical Layer Communications , 2018, IEEE Wireless Communications.

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

[13]  Sirui Duan,et al.  Automatic Multicarrier Waveform Classification via PCA and Convolutional Neural Networks , 2018, IEEE Access.

[14]  Félix J. García Clemente,et al.  A Self-Adaptive Deep Learning-Based System for Anomaly Detection in 5G Networks , 2018, IEEE Access.

[15]  Pan Li,et al.  Channel State Information Prediction for 5G Wireless Communications: A Deep Learning Approach , 2020, IEEE Transactions on Network Science and Engineering.

[16]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[17]  Yan Chen,et al.  Intelligent 5G: When Cellular Networks Meet Artificial Intelligence , 2017, IEEE Wireless Communications.

[18]  Zhi Chen,et al.  Supervised and Semi-Supervised Deep Neural Networks for CSI-Based Authentication , 2018, ArXiv.

[19]  Sudeep Pasricha,et al.  Adapting Convolutional Neural Networks for Indoor Localization with Smart Mobile Devices , 2018, ACM Great Lakes Symposium on VLSI.

[20]  Reza Bosagh Zadeh,et al.  TensorFlow for Deep Learning: From Linear Regression to Reinforcement Learning , 2018 .

[21]  Shi Jin,et al.  A PMI Feedback Scheme for Downlink Multi-User MIMO Based on Dual-Codebook of LTE-Advanced , 2012, 2012 IEEE Vehicular Technology Conference (VTC Fall).

[22]  Jing Wang,et al.  A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs , 2017, 2017 IEEE International Conference on Communications (ICC).