Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning

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.

arXiv commentThe codes are available in https://github.com/TianLin0509/BF-design-with-DL

References in corpus (7)

• Spatially Sparse Precoding in Millimeter Wave MIMO Systems
• Channel Estimation and Hybrid Precoding for Millimeter Wave Cellular Systems
• Alternating Minimization Algorithms for Hybrid Precoding in Millimeter Wave MIMO Systems
• Hybrid Digital and Analog Beamforming Design for Large-Scale Antenna Arrays
• Deep Learning-Based Communication Over the Air
• Deep-Learning-based Millimeter-Wave Massive MIMO for Hybrid Precoding
• Hybrid Beamforming for Millimeter Wave Systems Using the MMSE Criterion

Cited by in corpus (8)

• Hybrid Precoding for Multi-User Millimeter Wave Massive MIMO Systems: A Deep Learning Approach
• Robust Beamforming for RIS-aided Communications: Gradient-based Manifold Meta Learning
• Deep Unsupervised Learning for Joint Antenna Selection and Hybrid Beamforming
• Deep Learning for Channel Sensing and Hybrid Precoding in TDD Massive MIMO OFDM Systems
• Robust Millimeter Beamforming via Self-Supervised Hybrid Deep Learning
• Multi-hop RIS-Empowered Terahertz Communications: A DRL-based Hybrid Beamforming Design
• Experimental Evaluation of All-Optical Up- and Down-Conversion of 3GPP 5G NR Signals using an Optomechanical Crystal Cavity Frequency Comb
• Deep-Learning Based Linear Precoding for MIMO Channels with Finite-Alphabet Signaling