Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Transformer-based Hybrid Beamforming with Dynamic Subarray for Near-Space Airship-Borne Communications

Ruiqi Wang, Zhen Gao, Keke Ying, Ziwei Wan, Symeon Chatzinotas, Mohamed-Slim Alouini

TL;DR

This work tackles energy-efficient, high-capacity downlink communications for near-space airship-borne HAD MIMO with dynamic subarrays. It introduces DyHBFNet, a Transformer-based, three-module framework (ABFNet, ASNet, DBFNet) that jointly optimizes analog beamforming, antenna-to-RFC connections, and digital beamforming, with a model-driven WMMSE component for the last stage. The network is trained end-to-end to maximize spectral efficiency and demonstrates strong performance gains and robustness under imperfect CSI, along with favorable energy efficiency compared to baselines. The approach offers a scalable, practical pathway for high-throughput, energy-constrained airship links in 6G contexts.

Abstract

This paper proposes a hybrid beamforming framework for massive multiple-input multiple-output (MIMO) in near-space airship-borne communications. To achieve high energy efficiency (EE) in energy-constraint airships, a dynamic subarray structure is introduced, where each radio frequency chain (RFC) is connected to a disjoint subset of the antennas according to channel state information (CSI). The proposed joint dynamic hybrid beamforming network (DyHBFNet) comprises three key components: 1) An analog beamforming network (ABFNet) that optimizes the analog beamforming matrices and provides auxiliary information for the antenna selection network (ASNet) design, 2) an ASNet that dynamically optimizes the connections between antennas and RFCs, and 3) a digital beamforming network (DBFNet) that optimizes digital beamforming matrices by employing a model-driven weighted minimum mean square error algorithm for improving beamforming performance and convergence speed. The proposed ABFNet, ASNet, and DBFNet are all designed based on advanced Transformer encoders. Simulation results demonstrate that the proposed framework significantly enhances spectral efficiency and EE compared to baseline schemes. Additionally, its robust performance under imperfect CSI makes it a scalable solution for practical implementations.

Transformer-based Hybrid Beamforming with Dynamic Subarray for Near-Space Airship-Borne Communications

TL;DR

This work tackles energy-efficient, high-capacity downlink communications for near-space airship-borne HAD MIMO with dynamic subarrays. It introduces DyHBFNet, a Transformer-based, three-module framework (ABFNet, ASNet, DBFNet) that jointly optimizes analog beamforming, antenna-to-RFC connections, and digital beamforming, with a model-driven WMMSE component for the last stage. The network is trained end-to-end to maximize spectral efficiency and demonstrates strong performance gains and robustness under imperfect CSI, along with favorable energy efficiency compared to baselines. The approach offers a scalable, practical pathway for high-throughput, energy-constrained airship links in 6G contexts.

Abstract

This paper proposes a hybrid beamforming framework for massive multiple-input multiple-output (MIMO) in near-space airship-borne communications. To achieve high energy efficiency (EE) in energy-constraint airships, a dynamic subarray structure is introduced, where each radio frequency chain (RFC) is connected to a disjoint subset of the antennas according to channel state information (CSI). The proposed joint dynamic hybrid beamforming network (DyHBFNet) comprises three key components: 1) An analog beamforming network (ABFNet) that optimizes the analog beamforming matrices and provides auxiliary information for the antenna selection network (ASNet) design, 2) an ASNet that dynamically optimizes the connections between antennas and RFCs, and 3) a digital beamforming network (DBFNet) that optimizes digital beamforming matrices by employing a model-driven weighted minimum mean square error algorithm for improving beamforming performance and convergence speed. The proposed ABFNet, ASNet, and DBFNet are all designed based on advanced Transformer encoders. Simulation results demonstrate that the proposed framework significantly enhances spectral efficiency and EE compared to baseline schemes. Additionally, its robust performance under imperfect CSI makes it a scalable solution for practical implementations.
Paper Structure (11 sections, 8 equations, 5 figures, 2 tables)

This paper contains 11 sections, 8 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. System Model
  3. Proposed Joint DyHBFNet
  4. Problem Formulation
  5. Proposed ABFNet for Analog Beamforming
  6. Proposed ASNet for Antenna Selection
  7. Proposed DBFNet for Digital Beamforming
  8. Simulation Results
  9. Simulation Settings
  10. Performance Comparison
  11. Conclusion

Figures (5)

  • Figure 1: Near-space airship-borne communication system assisted by HAD massive MIMO with dynamic subarray structure.
  • Figure 2: Structure of the proposed joint DyHBFNet.
  • Figure 3: SE performance comparison versus $P_t$. (a) Different dynamic subarray schemes with TransHBFNet. (b) ASNet with different beamforming schemes.
  • Figure 4: EE performance comparison versus $P_t$.
  • Figure 5: SE performance comparison under imperfect CSI scenario.