RSSI-Based Hybrid Beamforming Design with Deep Learning

@article{Hojatian2020RSSIBasedHB,
  title={RSSI-Based Hybrid Beamforming Design with Deep Learning},
  author={Hamed Hojatian and Vu Nguyen Ha and J{\'e}r{\'e}my Nadal and Jean-François Frigon and François Leduc-Primeau},
  journal={ICC 2020 - 2020 IEEE International Conference on Communications (ICC)},
  year={2020},
  pages={1-6}
}
Hybrid beamforming is a promising technology for 5G millimetre-wave communications. However, its implementation is challenging in practical multiple-input multiple-output (MIMO) systems because non-convex optimization problems have to be solved, introducing additional latency and energy consumption. In addition, the channel-state information (CSI) must be either estimated from pilot signals or fed back through dedicated channels, introducing a large signaling overhead. In this paper, a hybrid… 

Figures and Tables from this paper

Limited-Fronthaul Cell-Free Hybrid Beamforming with Distributed Deep Neural Network
TLDR
This letter proposes two unsupervised deep neural networks (DNN) architectures, fully and partially distributed, that can perform coordinated hybrid beamforming with zero or limited communication overhead between APs and NC, while achieving near-optimal sum-rate with a reduced computational complexity compared to conventional near-Optimal solutions.
Decentralized Beamforming for Cell-Free Massive MIMO With Unsupervised Learning
TLDR
This letter proposes two unsupervised deep neural networks (DNN) architectures, fully and partially distributed, that can perform decentralized coordinated beamforming with zero or limited communication overhead between APs and NC, for both fully digital and hybrid precoding.
DNN-Based Decentralized Hybrid Beamforming for Cell-Free Massive MIMO
TLDR
This letter proposes two unsupervised deep neural networks (DNN) architectures, fully and partially distributed, that can perform decentralized coordinated hybrid beamforming with zero or limited communication overhead between APs and NC, while achieving near-optimal sum-rate with a reduced computational complexity compared to conventionalNearoptimal solutions.
Unsupervised Deep Learning for Massive MIMO Hybrid Beamforming
TLDR
It is shown that the proposed RSSI-based unsupervised deep learning method to design the hybrid beamforming in massive MIMO systems not only greatly increases the spectral efficiency, but also has near-optimal sum-rate and outperforms other state-of-the-art full-CSI solutions.

References

SHOWING 1-10 OF 21 REFERENCES
A Deep Learning Framework for Optimization of MISO Downlink Beamforming
TLDR
A deep learning framework for the optimization of downlink beamforming is proposed based on convolutional neural networks and exploitation of expert knowledge, such as the uplink-downlink duality and the known structure of optimal solutions, paving the way for fast realization of optimal beamforming in multiuser MISO systems.
Deep Learning for Massive MIMO CSI Feedback
TLDR
CsiNet is developed, a novel CSI sensing and recovery mechanism that learns to effectively use channel structure from training samples that can recover CSI with significantly improved reconstruction quality compared with existing compressive sensing (CS)-based methods.
Deep-Learning-Based Millimeter-Wave Massive MIMO for Hybrid Precoding
TLDR
A deep-learning-enabled mmWave massive MIMO framework for effective hybrid precoding is proposed, in which each selection of the precoders for obtaining the optimized decoder is regarded as a mapping relation in the deep neural network (DNN).
Machine learning inspired energy-efficient hybrid precoding for mmWave massive MIMO systems
TLDR
An adaptive CE (ACE)-based hybrid precoding scheme that aims to adaptively update the probability distributions of the elements in hybrid precoder by minimizing the CE, which can generate a solution close to the optimal one with a sufficiently high probability.
Limited Feedback Hybrid Precoding for Multi-User Millimeter Wave Systems
TLDR
Analytical and simulation results show that the proposed techniques offer higher sum rates compared with analog-only beamforming solutions, and approach the performance of the unconstrained digital beamforming with relatively small codebooks.
Channel estimation and precoder design for millimeter-wave communications: The sparse way
We propose strategies for mmWave communications that exploit the inherent sparsity of mmWave channels in the angle and delay domains. In particular, we propose the use of aperture shaping to ensure a
Subchannel Allocation and Hybrid Precoding in Millimeter-Wave OFDMA Systems
TLDR
Two novel analog precoding designs, namely semi-definite-relaxation-based and projected-gradient-descent-based, are proposed to optimize the analog part of the obtained HP’s and show superior performances over joint SA and HP benchmark algorithms.
Alternating Minimization Algorithms for Hybrid Precoding in Millimeter Wave MIMO Systems
TLDR
Treating the hybrid precoder design as a matrix factorization problem, effective alternating minimization (AltMin) algorithms will be proposed for two different hybrid precoding structures, i.e., the fully-connected and partially-connected structures, and simulation comparisons between the two hybrid precode structures will provide valuable design insights.
Channel Estimation and Hybrid Precoding for Millimeter Wave Cellular Systems
TLDR
An adaptive algorithm to estimate the mmWave channel parameters that exploits the poor scattering nature of the channel is developed and a new hybrid analog/digital precoding algorithm is proposed that overcomes the hardware constraints on the analog-only beamforming, and approaches the performance of digital solutions.
Large-scale antenna systems with hybrid analog and digital beamforming for millimeter wave 5G
TLDR
A reference signal design for the hybrid beamform structure is presented, which achieves better channel estimation performance than the method solely based on analog beamforming, and can be conveniently utilized to guide practical LSAS design for optimal energy/ spectrum efficiency trade-off.
...
1
2
3
...