Parallel Network Assisted Calibrated Beam Training for mmWave Communication Systems

This paper proposes a new structure called CNN-PN-LSTM to improve the beam prediction performance of existing deep learning-based calibrated mmWave beam training. Unlike previous works, we utilized a parallel network to effectively extract features from high-dimensional signals for model training. Simulation results show the effectiveness of the parallel network and the superior prediction performance of our model.

[1]  B. Shim,et al.  Towards 6G Hyper-Connectivity: Vision, Challenges, and Key Enabling Technologies , 2023, J. Commun. Networks.

[2]  S. Han,et al.  A new design of channel denoiser using residual autoencoder , 2023, Electronics Letters.

[3]  L. Wolf,et al.  Denoising Diffusion Error Correction Codes , 2022, ICLR.

[4]  Shi Jin,et al.  AI for CSI Feedback Enhancement in 5G-Advanced and 6G , 2022, IEEE Wireless Communications.

[5]  Vladlen Koltun,et al.  Non-deep Networks , 2021, NeurIPS.

[6]  Zhaocheng Wang,et al.  Deep Learning Assisted Calibrated Beam Training for Millimeter-Wave Communication Systems , 2021, IEEE Transactions on Communications.

[7]  Tomoaki Ohtsuki,et al.  A Deep Learning-Based Low Overhead Beam Selection in mmWave Communications , 2021, IEEE Transactions on Vehicular Technology.

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

[9]  Sewoong Oh,et al.  Physical Layer Communication via Deep Learning , 2020, IEEE Journal on Selected Areas in Information Theory.

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

[11]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

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

[13]  Junghyun Kim,et al.  Deep Learning-Assisted Multi-Dimensional Modulation and Resource Mapping for Advanced OFDM Systems , 2018, 2018 IEEE Globecom Workshops (GC Wkshps).

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

[15]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[19]  A. Krizhevsky.  ImageNet Classification with Deep Convolutional Neural Networks , 2022 .