Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning

Tian Lin, Yu Zhu
4/7/2019
cs.IT

Official code: TianLin0509/BF-design-with-DL (335 stars, last commit 2022-10-08).

Abstract

Beamforming (BF) design for large-scale antenna arrays with limited radio frequency chains and the phase-shifter-based analog BF architecture, has been recognized as a key issue in millimeter wave communication systems. It becomes more challenging with imperfect channel state information (CSI). In this letter, we propose a deep learning based BF design approach and develop a BF neural network (BFNN) which can be trained to learn how to optimize the beamformer for maximizing the spectral efficiency with hardware limitation and imperfect CSI. Simulation results show that the proposed BFNN achieves significant performance improvement and strong robustness to imperfect CSI over the conventional BF algorithms.

View on arXivView PDF

Code Implementations(1)

TianLin0509/BF-design-with-DLOfficial100%

Beamforming design with deep learning.

335119MATLAB, PythonJan 14, 20194 years ago

Similar Papers

Deep Learning for Hybrid Beamforming with Finite Feedback in GSM Aided mmWave MIMO Systems

86% match1 repo82023

Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6GHz Channels

84% match1 repo412019

Deep Learning and Image Super-Resolution-Guided Beam and Power Allocation for mmWave Networks

83% match2023

Robust Millimeter Beamforming via Self-Supervised Hybrid Deep Learning

82% match2023

AI-Empowered Hybrid MIMO Beamforming

82% match2 repos172023

Efficient Graph Neural Networks for Multicarrier Wideband Hybrid Beamforming Optimization

82% match2026

Cite this paper

@article{lin2019beamforming,
  title  = {Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning},
  author = {Tian Lin and Yu Zhu},
  year   = {2019},
  eprint = {1904.03657},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1904.03657}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1904.03657.svg)](https://codeofpaper.com/paper/1904.03657)

Discussion