Measurement-Driven Learning-Based Beam Selection for Hybrid Beamforming at 26.5 GHz
2026-06-29 • Information Theory
Information Theory
AI summaryⓘ
The authors studied how to quickly find the best direction to send signals in indoor millimeter-wave wireless systems by using machine learning. They set up real experiments in an office hallway to collect data at 26.5 GHz and used this data to teach computers to choose the best beam without trying them all. They tested two methods: one that uses information about the environment's shape and another that guesses from a few quick signal checks. Their results show that these learning methods can pick good beams accurately and much faster than searching every possibility.
millimeter-wavebeamformingsupervised learningdeep neural networkchannel measurementssignal-to-noise ratiobeam selectionpilot signalshybrid beamformingjoint transmission
Authors
Kristian Drizari, Konstantinos Maliatsos, Vasileios Tsoulos, Lefteris Tsipis, Harris K. Armeniakos, Athanasios G. Kanatas
Abstract
This paper investigates learning-assisted transmit beam selection for indoor millimeter-wave (mmWave) systems operating with hybrid beamforming and joint transmission. A synchronized SDR-based testbed at 26.5 GHz band is deployed to collect wideband channel measurements in a realistic office corridor environment. Using the measurement dataset, beam selection is formulated as a supervised learning problem aiming to approximate the SNR-optimal beam obtained through exhaustive sweeping. Two complementary approaches are examined: a geometry-driven Deep Neural Network (DNN) that predicts the optimal beam from spatial features, and a pilots-only method that infers suitable beams using a limited number of sounded pilot beams without positional information. Experimental results demonstrate high prediction accuracy and significant reduction in beam search overhead compared to exhaustive sweeping, highlighting the effectiveness of measurement-driven learning for practical indoor mmWave beam management.