Skip to main navigation Skip to search Skip to main content

Deep Learning Method for Movable Antenna-Enabled Multiuser Downlink System

  • Dogon Kim*
  • , Seok Hwan Park
  • *Corresponding author for this work
  • Jeonbuk National University

Research output: Contribution to conferenceConference paperpeer-review

Abstract

We investigate a movable antenna (MA)-enabled multiuser multiple-input single-output (MU-MISO) downlink system. In particular, we propose a deep learning-based algorithm comprising two deep neural networks (DNNs), where each DNN determines either the MA positions or key features of beamforming vectors. These DNNs are jointly trained to maximize the sum-rate performance. The effectiveness of the proposed method is demonstrated through numerical results.

Original languageEnglish
Title of host publication2025 30th Asia-Pacific Conference on Communications, APCC 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9784885523595
DOIs
StatePublished - 2025
Event30th Asia-Pacific Conference on Communications, APCC 2025 - Osaka, Japan
Duration: 2025.11.262025.11.28

Publication series

Name2025 30th Asia-Pacific Conference on Communications, APCC 2025

Conference

Conference30th Asia-Pacific Conference on Communications, APCC 2025
Country/TerritoryJapan
CityOsaka
Period25.11.2625.11.28

Keywords

  • deep learning
  • Movable antenna
  • multiuser beamforming

Fingerprint

Dive into the research topics of 'Deep Learning Method for Movable Antenna-Enabled Multiuser Downlink System'. Together they form a unique fingerprint.

Cite this