A Low-Complexity Machine Learning Design for mmWave Beam Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khan, Muhammad Qurratulain, Gaber, Abdo, Parvini, Mohammad, Schulz, Philipp, Fettweis, Gerhard
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929205487337472
author Khan, Muhammad Qurratulain
Gaber, Abdo
Parvini, Mohammad
Schulz, Philipp
Fettweis, Gerhard
author_facet Khan, Muhammad Qurratulain
Gaber, Abdo
Parvini, Mohammad
Schulz, Philipp
Fettweis, Gerhard
contents The 3rd Generation Partnership Project (3GPP) is currently studying machine learning (ML) for the fifth generation (5G)-Advanced New Radio (NR) air interface, where spatial and temporal-domain beam prediction are important use cases. With this background, this letter presents a low-complexity ML design that expedites the spatial-domain beam prediction to reduce the power consumption and the reference signaling overhead, which are currently imperative for frequent beam measurements. Complexity analysis and evaluation results showcase that the proposed model achieves state-of-the-art accuracy with lower computational complexity, resulting in reduced power consumption and faster beam prediction. Furthermore, important observations on the generalization of the proposed model are presented in this letter.
format Preprint
id arxiv_https___arxiv_org_abs_2310_19323
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Low-Complexity Machine Learning Design for mmWave Beam Prediction
Khan, Muhammad Qurratulain
Gaber, Abdo
Parvini, Mohammad
Schulz, Philipp
Fettweis, Gerhard
Signal Processing
The 3rd Generation Partnership Project (3GPP) is currently studying machine learning (ML) for the fifth generation (5G)-Advanced New Radio (NR) air interface, where spatial and temporal-domain beam prediction are important use cases. With this background, this letter presents a low-complexity ML design that expedites the spatial-domain beam prediction to reduce the power consumption and the reference signaling overhead, which are currently imperative for frequent beam measurements. Complexity analysis and evaluation results showcase that the proposed model achieves state-of-the-art accuracy with lower computational complexity, resulting in reduced power consumption and faster beam prediction. Furthermore, important observations on the generalization of the proposed model are presented in this letter.
title A Low-Complexity Machine Learning Design for mmWave Beam Prediction
topic Signal Processing
url https://arxiv.org/abs/2310.19323