GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication

Millimeter-wave (mmWave) communication enables high data rates for cellular-connected Uncrewed Aerial Vehicles (UAVs). However, a robust beam management remains challenging due to significant path loss and the dynamic mobility of UAVs, which can destabilize the UAV-base station (BS) link. This resea...

Full description

Saved in:
Bibliographic Details
Main Authors: Vendi Ardianto Nugroho, Byung Moo Lee
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11072409/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704023715741696
author Vendi Ardianto Nugroho
Byung Moo Lee
author_facet Vendi Ardianto Nugroho
Byung Moo Lee
author_sort Vendi Ardianto Nugroho
collection DOAJ
description Millimeter-wave (mmWave) communication enables high data rates for cellular-connected Uncrewed Aerial Vehicles (UAVs). However, a robust beam management remains challenging due to significant path loss and the dynamic mobility of UAVs, which can destabilize the UAV-base station (BS) link. This research presents a GPS-aided deep learning (DL) model that simultaneously predicts current and future optimal beams for UAV mmWave communications, maintaining a Top-1 prediction accuracy exceeding 70% and an average power loss below 0.6 dB across all prediction steps. These outcomes stem from a proposed data splitting method ensuring balanced label distribution, paired with a GPS preprocessing technique that extracts key positional features, and a DL architecture that maps sequential position data to beam index predictions. The model reduces overhead by approximately 93% compared to exhaustive search methods with 95% beam prediction accuracy guarantees, and ensures 94% to 96% of predictions exhibit mean power loss not exceeding 1 dB.
format Article
id doaj-art-eae0cb6ef6cf4ec39be1bd2ec43270b4
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-eae0cb6ef6cf4ec39be1bd2ec43270b42025-08-20T03:16:56ZengIEEEIEEE Access2169-35362025-01-011311706511707710.1109/ACCESS.2025.358659411072409GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave CommunicationVendi Ardianto Nugroho0https://orcid.org/0009-0008-2329-5725Byung Moo Lee1https://orcid.org/0000-0003-3675-929XDepartment of Intelligent Mechatronics Engineering, Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul, South KoreaDepartment of Intelligent Mechatronics Engineering, Department of Convergence Engineering for Intelligent Drone, Sejong University, Seoul, South KoreaMillimeter-wave (mmWave) communication enables high data rates for cellular-connected Uncrewed Aerial Vehicles (UAVs). However, a robust beam management remains challenging due to significant path loss and the dynamic mobility of UAVs, which can destabilize the UAV-base station (BS) link. This research presents a GPS-aided deep learning (DL) model that simultaneously predicts current and future optimal beams for UAV mmWave communications, maintaining a Top-1 prediction accuracy exceeding 70% and an average power loss below 0.6 dB across all prediction steps. These outcomes stem from a proposed data splitting method ensuring balanced label distribution, paired with a GPS preprocessing technique that extracts key positional features, and a DL architecture that maps sequential position data to beam index predictions. The model reduces overhead by approximately 93% compared to exhaustive search methods with 95% beam prediction accuracy guarantees, and ensures 94% to 96% of predictions exhibit mean power loss not exceeding 1 dB.https://ieeexplore.ieee.org/document/11072409/Millimeter wave communicationGPSdroneUAVdeep learningbeam prediction
spellingShingle Vendi Ardianto Nugroho
Byung Moo Lee
GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication
IEEE Access
Millimeter wave communication
GPS
drone
UAV
deep learning
beam prediction
title GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication
title_full GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication
title_fullStr GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication
title_full_unstemmed GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication
title_short GPS-Aided Deep Learning for Beam Prediction and Tracking in UAV mmWave Communication
title_sort gps aided deep learning for beam prediction and tracking in uav mmwave communication
topic Millimeter wave communication
GPS
drone
UAV
deep learning
beam prediction
url https://ieeexplore.ieee.org/document/11072409/
work_keys_str_mv AT vendiardiantonugroho gpsaideddeeplearningforbeampredictionandtrackinginuavmmwavecommunication
AT byungmoolee gpsaideddeeplearningforbeampredictionandtrackinginuavmmwavecommunication