Multi-Task Learning for mmWave Transceiver Beam Prediction

Rigorous and reliable alignment of narrow transceiver beams is a requisite for ensuring the highly directional transmission in millimeter-wave (mmWave) communications. Exhaustively testing these narrow beam pairs results in increased reference signal (RS) overhead, latency, and power consumption. In...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Qurratulain Khan, Abdo Gaber, Mohammad Parvini, Philipp Schulz, Gerhard Fettweis
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Communications Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11050966/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321307905196032
author Muhammad Qurratulain Khan
Abdo Gaber
Mohammad Parvini
Philipp Schulz
Gerhard Fettweis
author_facet Muhammad Qurratulain Khan
Abdo Gaber
Mohammad Parvini
Philipp Schulz
Gerhard Fettweis
author_sort Muhammad Qurratulain Khan
collection DOAJ
description Rigorous and reliable alignment of narrow transceiver beams is a requisite for ensuring the highly directional transmission in millimeter-wave (mmWave) communications. Exhaustively testing these narrow beam pairs results in increased reference signal (RS) overhead, latency, and power consumption. In this paper, we propose a centralized multi-task learning (MTL) based beam prediction strategy that ensures a high success rate using measurements from a few site-specific probing beams identified via the proposed uniformly distributed beam relevance and beam significance (UDBRBS) criterion, thereby obviating the need for an exhaustive scan. Performance evaluation over 3rd Generation Partnership Project (3GPP) defined performance indicators demonstrates that the proposed method outperforms existing independent task learning (ITL) and single task learning (STL) beam prediction designs. We further argue that the proposed strategy is highly practical for implementation in fifth generation (5G)-Advanced and sixth generation (6G) communication systems.
format Article
id doaj-art-3d00fa6202a8437f9db4d7262c8b5979
institution Kabale University
issn 2644-125X
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of the Communications Society
spelling doaj-art-3d00fa6202a8437f9db4d7262c8b59792025-08-20T03:49:46ZengIEEEIEEE Open Journal of the Communications Society2644-125X2025-01-0165535555110.1109/OJCOMS.2025.358307411050966Multi-Task Learning for mmWave Transceiver Beam PredictionMuhammad Qurratulain Khan0https://orcid.org/0000-0001-7075-8990Abdo Gaber1Mohammad Parvini2https://orcid.org/0000-0002-1315-7635Philipp Schulz3https://orcid.org/0000-0002-0738-556XGerhard Fettweis4https://orcid.org/0000-0003-4622-1311Vodafone Chair for Mobile Communications Systems, Technische Universität Dresden, Dresden, GermanyNI Dresden R&D Dresden, National Instruments Corporation, Dresden, GermanyVodafone Chair for Mobile Communications Systems, Technische Universität Dresden, Dresden, GermanyVodafone Chair for Mobile Communications Systems, Technische Universität Dresden, Dresden, GermanyVodafone Chair for Mobile Communications Systems, Technische Universität Dresden, Dresden, GermanyRigorous and reliable alignment of narrow transceiver beams is a requisite for ensuring the highly directional transmission in millimeter-wave (mmWave) communications. Exhaustively testing these narrow beam pairs results in increased reference signal (RS) overhead, latency, and power consumption. In this paper, we propose a centralized multi-task learning (MTL) based beam prediction strategy that ensures a high success rate using measurements from a few site-specific probing beams identified via the proposed uniformly distributed beam relevance and beam significance (UDBRBS) criterion, thereby obviating the need for an exhaustive scan. Performance evaluation over 3rd Generation Partnership Project (3GPP) defined performance indicators demonstrates that the proposed method outperforms existing independent task learning (ITL) and single task learning (STL) beam prediction designs. We further argue that the proposed strategy is highly practical for implementation in fifth generation (5G)-Advanced and sixth generation (6G) communication systems.https://ieeexplore.ieee.org/document/11050966/Fifth generation (5G)-Advancedsixth generation (6G)beam management (BM)beam predictionmachine learning (ML)millimeter-wave (mmWave)
spellingShingle Muhammad Qurratulain Khan
Abdo Gaber
Mohammad Parvini
Philipp Schulz
Gerhard Fettweis
Multi-Task Learning for mmWave Transceiver Beam Prediction
IEEE Open Journal of the Communications Society
Fifth generation (5G)-Advanced
sixth generation (6G)
beam management (BM)
beam prediction
machine learning (ML)
millimeter-wave (mmWave)
title Multi-Task Learning for mmWave Transceiver Beam Prediction
title_full Multi-Task Learning for mmWave Transceiver Beam Prediction
title_fullStr Multi-Task Learning for mmWave Transceiver Beam Prediction
title_full_unstemmed Multi-Task Learning for mmWave Transceiver Beam Prediction
title_short Multi-Task Learning for mmWave Transceiver Beam Prediction
title_sort multi task learning for mmwave transceiver beam prediction
topic Fifth generation (5G)-Advanced
sixth generation (6G)
beam management (BM)
beam prediction
machine learning (ML)
millimeter-wave (mmWave)
url https://ieeexplore.ieee.org/document/11050966/
work_keys_str_mv AT muhammadqurratulainkhan multitasklearningformmwavetransceiverbeamprediction
AT abdogaber multitasklearningformmwavetransceiverbeamprediction
AT mohammadparvini multitasklearningformmwavetransceiverbeamprediction
AT philippschulz multitasklearningformmwavetransceiverbeamprediction
AT gerhardfettweis multitasklearningformmwavetransceiverbeamprediction