Autoencoder for Position-Assisted Beam Prediction in mmWave ISAC Systems

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: El-Banna, Ahmad A. Aziz, Dobre, Octavia A.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908671012765696
author El-Banna, Ahmad A. Aziz
Dobre, Octavia A.
author_facet El-Banna, Ahmad A. Aziz
Dobre, Octavia A.
contents Integrated sensing and communication and millimeter wave (mmWave) have emerged as pivotal technologies for 6G networks. However, the narrow nature of mmWave beams requires precise alignments that typically necessitate large training overhead. This overhead can be reduced by incorporating the position information with beam adjustments. This letter proposes a lightweight autorencoder (LAE) model that addresses the position-assisted beam prediction problem while significantly reducing computational complexity compared to the conventional baseline method, i.e., deep fully connected neural network. The proposed LAE is designed as a three-layer undercomplete network to exploit its dimensionality reduction capabilities and thereby mitigate the computational requirements of the trained model. Simulation results show that the proposed model achieves a similar beam prediction accuracy to the baseline with an 83% complexity reduction.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18594
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Autoencoder for Position-Assisted Beam Prediction in mmWave ISAC Systems
El-Banna, Ahmad A. Aziz
Dobre, Octavia A.
Signal Processing
Machine Learning
Integrated sensing and communication and millimeter wave (mmWave) have emerged as pivotal technologies for 6G networks. However, the narrow nature of mmWave beams requires precise alignments that typically necessitate large training overhead. This overhead can be reduced by incorporating the position information with beam adjustments. This letter proposes a lightweight autorencoder (LAE) model that addresses the position-assisted beam prediction problem while significantly reducing computational complexity compared to the conventional baseline method, i.e., deep fully connected neural network. The proposed LAE is designed as a three-layer undercomplete network to exploit its dimensionality reduction capabilities and thereby mitigate the computational requirements of the trained model. Simulation results show that the proposed model achieves a similar beam prediction accuracy to the baseline with an 83% complexity reduction.
title Autoencoder for Position-Assisted Beam Prediction in mmWave ISAC Systems
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2511.18594