Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep learning based Channel Estimation and Beamforming in Movable Antenna Systems

Kaijun Feng, Ziwei Wan, Anwen Liao, Wenyan Ma, Lipeng Zhu, Zhenyu Xiao, Zhen Gao, Rui Zhang

TL;DR

This paper tackles the challenge of integrating channel estimation, movable antenna position optimization, and beamforming in wideband multiuser MA systems. The authors propose a three-part approach: a two-stage CE combining CS-based reconstruction and Swin-Transformer denoising (MA-CENet), a Transformer-based MA position selection (MA-PSN), and a model-driven WMMSE-inspired beamforming network (MA-BFNet). The results show that MA-CENet reduces CSI error and MA-BFNet improves sum-rate, outperforming baselines under varied conditions and pilots. The framework demonstrates a path to enhanced spectral efficiency in 6G-like dense, mobility-rich scenarios with movable antennas, highlighting the synergy between DL-based denoising, spatial optimization, and model-driven optimization.

Abstract

Movable antenna (MA) has emerged as a promising technology for future wireless systems. Compared with traditional fixed-position antennas, MA improves system performance by antenna movement to optimize channel conditions. For multiuser wideband MA systems, this paper proposes deep learning-based framework integrating channel estimation (CE), antenna position optimization, and beamforming, with a clear workflow and enhanced efficiency. Specifically, to obtain accurate channel state information (CSI), we design a two-stage CE mechanism: first reconstructing the channel matrix from limited measurements via compressive sensing, then introducing a Swin-Transformer-based denoising network to refine CE accuracy for subsequent optimization. Building on this, we address the joint optimization challenge by proposing a Transformer-based network that intelligently maps CSI sequences of candidate positions to optimal MA positions while combining a model-driven weighted minimum mean square error (WMMSE) beamforming approach to achieve better performance. Simulation results demonstrate that the proposed methods achieve superior performance compared with existing counterparts under various conditions. The codes about this work are available at https://github.com/ZiweiWan/Code-4-DL-MA-CE-BF.

Deep learning based Channel Estimation and Beamforming in Movable Antenna Systems

TL;DR

This paper tackles the challenge of integrating channel estimation, movable antenna position optimization, and beamforming in wideband multiuser MA systems. The authors propose a three-part approach: a two-stage CE combining CS-based reconstruction and Swin-Transformer denoising (MA-CENet), a Transformer-based MA position selection (MA-PSN), and a model-driven WMMSE-inspired beamforming network (MA-BFNet). The results show that MA-CENet reduces CSI error and MA-BFNet improves sum-rate, outperforming baselines under varied conditions and pilots. The framework demonstrates a path to enhanced spectral efficiency in 6G-like dense, mobility-rich scenarios with movable antennas, highlighting the synergy between DL-based denoising, spatial optimization, and model-driven optimization.

Abstract

Movable antenna (MA) has emerged as a promising technology for future wireless systems. Compared with traditional fixed-position antennas, MA improves system performance by antenna movement to optimize channel conditions. For multiuser wideband MA systems, this paper proposes deep learning-based framework integrating channel estimation (CE), antenna position optimization, and beamforming, with a clear workflow and enhanced efficiency. Specifically, to obtain accurate channel state information (CSI), we design a two-stage CE mechanism: first reconstructing the channel matrix from limited measurements via compressive sensing, then introducing a Swin-Transformer-based denoising network to refine CE accuracy for subsequent optimization. Building on this, we address the joint optimization challenge by proposing a Transformer-based network that intelligently maps CSI sequences of candidate positions to optimal MA positions while combining a model-driven weighted minimum mean square error (WMMSE) beamforming approach to achieve better performance. Simulation results demonstrate that the proposed methods achieve superior performance compared with existing counterparts under various conditions. The codes about this work are available at https://github.com/ZiweiWan/Code-4-DL-MA-CE-BF.
Paper Structure (11 sections, 16 equations, 6 figures, 1 table, 1 algorithm)

This paper contains 11 sections, 16 equations, 6 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Channel Model
  4. CE and Denoising
  5. CS-based Initial CE
  6. Swin-Transformer Based Denoising Network
  7. MA Position And Beamforming Optimization
  8. MA-PSN Design
  9. MA-DBN Design
  10. Simulation Results
  11. Conclusion

Figures (6)

  • Figure 1: MA-based multiuser communication system.
  • Figure 2: The proposed MA-CENet conducts denoising to the initial estimate of channel to improve estimation performance.
  • Figure 3: The proposed MA-BFNet integrating antenna position optimization and beamforming.
  • Figure 4: The performance comparison of NMSE versus SNR for various MA positioning setups.
  • Figure 5: NMSE performance for CE: (a) NMSE versus Pilot-SNR under different CE algorithms; (b) NMSE versus Pilot-SNR under different deep learning-based denoising networks.
  • ...and 1 more figures