On the efficacy of fingerprint-based mmWave beamforming in NLOS environments: experimental validation

Warning The system is temporarily closed to updates for reporting purpose.

Chraiti, Mohaned and Ghrayeb, Ali (2024) On the efficacy of fingerprint-based mmWave beamforming in NLOS environments: experimental validation. In: Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit), Antwerp, Belgium

Full text not available from this repository. (Request a copy)

Abstract

Fingerprint-based millimeter-wave (mmWave) beamforming is attracting growing attention due to its efficacy in reducing beam search/alignment time and subsequently decreasing channel estimation overhead to a negligible rate. This technique entails offline measurement collection to construct a dataset comprising potential high-gain beam directions, with location serving as a feature (fingerprint). The fingerprint-based mmWave beamforming is the inverse process of the localization. Assuming that the User Equipment (UE) possesses its position estimate, a machinery determines a set of candidate beams (beamforming codebook) based on the measurements within the dataset that are collected at proximate locations to the UE. The results in existing works, however, are often based on abstract models (often, the two-ray model), simulation results (typically based rays tracing simulator), and, in many cases, the outdoor environment with high probable Line-Of-Sight (LOS) link. In an effort to understand the extent and potential of such a technique, we have carried out a real-world experiment in an indoor office environment with high Non-LOS (NLOS) probability. We have trained a neural network model that provides the candidates' beams given a UE location. Although the results show an average beamforming gain of 17 dB, there is a considerable gap with respect to the highest possible beamforming gain obtained through exhaustive search.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: beamforming; experimental validation; fingerprint; machine learning; mmWave
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Mohaned Chraiti
Date Deposited: 27 Aug 2024 11:30
Last Modified: 27 Aug 2024 11:30
URI: https://research.sabanciuniv.edu/id/eprint/49787

Actions (login required)

View Item
View Item