Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AI-Empowered Hybrid MIMO Beamforming

Nir Shlezinger, Mengyuan Ma, Ortal Lavi, Nhan Thanh Nguyen, Yonina C. Eldar, Markku Juntti

TL;DR

This article reviews candidate strategies to leverage data to improve real-time hybrid beamforming design and provides a systematic comparative study between existing approaches including both numerical evaluations and qualitative measures.

Abstract

Hybrid multiple-input multiple-output (MIMO) is an attractive technology for realizing extreme massive MIMO systems envisioned for future wireless communications in a scalable and power-efficient manner. However, the fact that hybrid MIMO systems implement part of their beamforming in analog and part in digital makes the optimization of their beampattern notably more challenging compared with conventional fully digital MIMO. Consequently, recent years have witnessed a growing interest in using data-aided artificial intelligence (AI) tools for hybrid beamforming design. This article reviews candidate strategies to leverage data to improve real-time hybrid beamforming design. We discuss the architectural constraints and characterize the core challenges associated with hybrid beamforming optimization. We then present how these challenges are treated via conventional optimization, and identify different AI-aided design approaches. These can be roughly divided into purely data-driven deep learning models and different forms of deep unfolding techniques for combining AI with classical optimization.We provide a systematic comparative study between existing approaches including both numerical evaluations and qualitative measures. We conclude by presenting future research opportunities associated with the incorporation of AI in hybrid MIMO systems.

AI-Empowered Hybrid MIMO Beamforming

TL;DR

This article reviews candidate strategies to leverage data to improve real-time hybrid beamforming design and provides a systematic comparative study between existing approaches including both numerical evaluations and qualitative measures.

Abstract

Hybrid multiple-input multiple-output (MIMO) is an attractive technology for realizing extreme massive MIMO systems envisioned for future wireless communications in a scalable and power-efficient manner. However, the fact that hybrid MIMO systems implement part of their beamforming in analog and part in digital makes the optimization of their beampattern notably more challenging compared with conventional fully digital MIMO. Consequently, recent years have witnessed a growing interest in using data-aided artificial intelligence (AI) tools for hybrid beamforming design. This article reviews candidate strategies to leverage data to improve real-time hybrid beamforming design. We discuss the architectural constraints and characterize the core challenges associated with hybrid beamforming optimization. We then present how these challenges are treated via conventional optimization, and identify different AI-aided design approaches. These can be roughly divided into purely data-driven deep learning models and different forms of deep unfolding techniques for combining AI with classical optimization.We provide a systematic comparative study between existing approaches including both numerical evaluations and qualitative measures. We conclude by presenting future research opportunities associated with the incorporation of AI in hybrid MIMO systems.
Paper Structure (25 sections, 5 figures, 1 table)

This paper contains 25 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Hybrid Beamforming
  3. Hybrid mimo Transceivers
  4. Architectural Constraints
  5. Phase Shifter Networks
  6. Discrete Vector Modulators
  7. Dynamic Metasurface Antennas
  8. Hybrid Beamforming Design Challenges
  9. ai-Aided Hybrid Beamforming Design
  10. Optimization-Based Hybrid Beamforming
  11. dnn-Based Hybrid Beamforming
  12. Deep Unfolded Hybrid Beamforming
  13. Comparative Study
  14. Numerical Evaluation
  15. Qualitative Comparison
  16. ...and 10 more sections

Figures (5)

  • Figure 1: Schematic illustration of different hybrid mimo transceiver architectures and their corresponding analog processing model, including partially and fully connected phase shifter networks, vector modulators, and dma.
  • Figure 2: Illustration of different approaches for hybrid beamforming design.
  • Figure 3: Sum-rate vs. snr, $4$ RF chains.
  • Figure 4: Sum-rate per iteration.
  • Figure 5: Sum-rate vs. snr, $2$ RF chains.