DRL-Based Beam Split Alleviation for Movable Antenna-Enabled Near-Field Wideband Communications

Tingting Zhang, Rui Jiang, Haibo Dai, Changpeng Zhou, Youyun Xu · 2026

Read DRL-Based Beam Split Alleviation for Movable Antenna-Enabled Near-Field Wideband Communications by Tingting Zhang, Rui Jiang, Haibo Dai, Changpeng Zhou, Youyun Xu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13210439.txt.

Description

Tingting Zhang and co-authors use deep reinforcement learning to fix beam splitting in near field wideband radio. Their 2026 paper deals with a problem in future 6G systems. With wide bandwidths, beams aimed by simple phase shifters split across frequencies, losing gain. Past fixes add delay hardware. This work instead uses movable antennas, whose positions can shift. The system studied is an uplink with analog beamforming.

The goal is to maximize the weakest beam gain across all subcarriers. Settings for phase and antenna position are tuned jointly. The problem is highly non convex, resisting standard solvers. A soft actor critic learning method handles the continuous choices and the awkward objective. In simulations, the approach eased the split effect. It beat conventional schemes on the minimum gain measure, the authors report.

Catalog record

CREATORTingting Zhang, Rui Jiang, Haibo Dai, Changpeng Zhou, Youyun Xu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE33 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13210439

Browse the full library · About the Tower of Babel