RIS-Aided mmWave Localization Under Cross-Link Interference via Beam-Domain ML Fingerprinting
2026-08-07 • Emerging Technologies
Emerging TechnologiesMachine Learning
AI summaryⓘ
The authors present a method to locate user devices in 6G networks that use special surfaces (RIS) to help signals, even when direct connections to the base station are missing. Their approach uses patterns of signal quality measurements to predict the device’s direction and distance without needing detailed channel information. They also test how interference from nearby signals affects this method and find that angle predictions get worse than distance predictions in noisy environments. Different machine learning models were compared, with k-nearest neighbors performing best in clean and noisy conditions.
User Equipment (UE)Reconfigurable Intelligent Surface (RIS)Millimeter-wave (mmWave)6G NetworksBeam ManagementSignal-to-Noise Ratio (SNR)Signal-to-Interference-plus-Noise Ratio (SINR)Machine Learning RegressionLocalizationk-Nearest Neighbors (KNN)
Authors
Md Tarek Hassan, Dmitry Zelenchuk, Muhammad Ali Babar Abbasi
Abstract
Accurate user equipment (UE) localization is critical for beam management in reconfigurable intelligent surface (RIS)-assisted millimeter-wave (mmWave) based sixth-generation (6G) networks, especially if the direct base-station-UE links are unavailable. This paper proposes a beam-domain fingerprint framework that maps the received signal-to-noise ratio (SNR) across a small set of predefined RIS reflection states to the UE azimuth angle and range, without requiring channel state information (CSI). Crucially, we extend the framework to a realistic interference-impaired scenario in which a nearby cross-link interferer (CLI) corrupts the clean SNR fingerprint, yielding a signal-to-interference-plus-noise ratio (SINR) fingerprint; an interference-to-noise ratio (INR)-constrained calibration strategy keeps the interference level physically interpretable. Four machine-learning (ML) regressors are evaluated under both conditions. Simulation results at 28 GHz with a 20x20 RIS show that k-nearest neighbors (KNN) achieves the lowest angle MAE of 0.37 degrees and range MAE of 4 cm under clean conditions, rising to 1.4 degrees and 7.6 cm under interference. A key finding is that interference degrades angle estimation substantially more than range estimation across all models, a consequence of the asymmetric encoding of location information in the beam-domain fingerprint.