QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning Approach

Modern wireless communication systems face increasingly complex challenges due to rapidly changing channel conditions and the growing diversity of application-specific Quality of Service (QoS) requirements. Traditional link adaptation mechanisms primarily aim to maximize throughput and often lack th...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Parsa, Neda Moghim, Sachin Shetty
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/11104833/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849228544280887296
author Ali Parsa
Neda Moghim
Sachin Shetty
author_facet Ali Parsa
Neda Moghim
Sachin Shetty
author_sort Ali Parsa
collection DOAJ
description Modern wireless communication systems face increasingly complex challenges due to rapidly changing channel conditions and the growing diversity of application-specific Quality of Service (QoS) requirements. Traditional link adaptation mechanisms primarily aim to maximize throughput and often lack the flexibility to support emerging applications, such as Extended Reality (XR) and Virtual Reality (VR), which demand simultaneous guarantees for high data rates, ultra low latency, and high reliability. These stringent and multidimensional QoS needs call for more intelligent and adaptive solutions. In this paper, we propose QDRLLA (QoS-aware Deep Reinforcement Learning-based Link Adaptation), a novel framework that employs deep reinforcement learning to dynamically adjust key link parameters, including modulation and coding schemes, transmission power, and subcarrier spacing, based on the QoS requirements of each application. QDRLLA learns from the environment and past observations to make informed decisions that go beyond conventional heuristic-based methods. Through extensive simulations, we demonstrate that QDRLLA significantly improves compliance with QoS targets across a range of network conditions and application types. It also improves energy efficiency by avoiding unnecessary retransmissions and optimizing resource usage. These results underscore the effectiveness of QDRLLA in supporting the complex service requirements of next-generation wireless networks.
format Article
id doaj-art-d67e87f3c2f642c7b2a79f6aebe79f00
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-d67e87f3c2f642c7b2a79f6aebe79f002025-08-22T23:17:23ZengIEEEIEEE Open Journal of the Communications Society2644-125X2025-01-0166368638210.1109/OJCOMS.2025.359383611104833QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning ApproachAli Parsa0https://orcid.org/0009-0005-0038-3843Neda Moghim1https://orcid.org/0000-0002-6338-5505Sachin Shetty2Department of Computer Engineering, University of Isfahan, Isfahan, IranDepartment of Computer Engineering, University of Isfahan, Isfahan, IranCenter for Secure and Intelligent Critical Systems, Office of Enterprise Research and Innovation, Old Dominion University, Norfolk, VA, USAModern wireless communication systems face increasingly complex challenges due to rapidly changing channel conditions and the growing diversity of application-specific Quality of Service (QoS) requirements. Traditional link adaptation mechanisms primarily aim to maximize throughput and often lack the flexibility to support emerging applications, such as Extended Reality (XR) and Virtual Reality (VR), which demand simultaneous guarantees for high data rates, ultra low latency, and high reliability. These stringent and multidimensional QoS needs call for more intelligent and adaptive solutions. In this paper, we propose QDRLLA (QoS-aware Deep Reinforcement Learning-based Link Adaptation), a novel framework that employs deep reinforcement learning to dynamically adjust key link parameters, including modulation and coding schemes, transmission power, and subcarrier spacing, based on the QoS requirements of each application. QDRLLA learns from the environment and past observations to make informed decisions that go beyond conventional heuristic-based methods. Through extensive simulations, we demonstrate that QDRLLA significantly improves compliance with QoS targets across a range of network conditions and application types. It also improves energy efficiency by avoiding unnecessary retransmissions and optimizing resource usage. These results underscore the effectiveness of QDRLLA in supporting the complex service requirements of next-generation wireless networks.https://ieeexplore.ieee.org/document/11104833/B5Gdeep Q-networkdeep reinforcement learninglink adaptationmachine learningmodulation and coding schemes
spellingShingle Ali Parsa
Neda Moghim
Sachin Shetty
QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning Approach
IEEE Open Journal of the Communications Society
B5G
deep Q-network
deep reinforcement learning
link adaptation
machine learning
modulation and coding schemes
title QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning Approach
title_full QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning Approach
title_fullStr QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning Approach
title_full_unstemmed QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning Approach
title_short QoS-Aware Link Adaptation for Beyond 5G Networks: A Deep Reinforcement Learning Approach
title_sort qos aware link adaptation for beyond 5g networks a deep reinforcement learning approach
topic B5G
deep Q-network
deep reinforcement learning
link adaptation
machine learning
modulation and coding schemes
url https://ieeexplore.ieee.org/document/11104833/
work_keys_str_mv AT aliparsa qosawarelinkadaptationforbeyond5gnetworksadeepreinforcementlearningapproach
AT nedamoghim qosawarelinkadaptationforbeyond5gnetworksadeepreinforcementlearningapproach
AT sachinshetty qosawarelinkadaptationforbeyond5gnetworksadeepreinforcementlearningapproach