Staff View: Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks

Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks

The evolution of 5G technology presents unique challenges and opportunities for optimizing network performance through advanced techniques such as Reinforcement Learning (RL). Effective 5G network management requires precise optimization of subcarrier spacing and uplink-downlink (UL-DL) allocation,...

Full description

Saved in:

Bibliographic Details
Main Authors:	Samidi F.S., Radzi N.A.M., Aripin N.M.
Other Authors:	57215054855
Format:	Conference paper
Published:	Institute of Electrical and Electronics Engineers Inc. 2025
Subjects:	Network performance Queueing networks Reinforcement learning Resource allocation Dynamic condition Efficient learning Learning process Networks management Optimisations Performance Real- time Reinforcement learning models Stable performance Subcarrier spacing 5G mobile communication systems
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uniten.dspace-36900
record_format	dspace
spelling	my.uniten.dspace-369002025-03-03T15:45:37Z Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks Samidi F.S. Radzi N.A.M. Aripin N.M. 57215054855 57218936786 35092180800 Network performance Queueing networks Reinforcement learning Resource allocation Dynamic condition Efficient learning Learning process Networks management Optimisations Performance Real- time Reinforcement learning models Stable performance Subcarrier spacing 5G mobile communication systems The evolution of 5G technology presents unique challenges and opportunities for optimizing network performance through advanced techniques such as Reinforcement Learning (RL). Effective 5G network management requires precise optimization of subcarrier spacing and uplink-downlink (UL-DL) allocation, yet selecting the optimal RL model for this task remains a significant challenge. This paper evaluates the performance of RL models within the RaSSo framework for optimizing 5G networks, aiming to identify the most suitable RL approach. The primary challenge addressed is determining which RL model, in our case, Proximal Policy Optimization (PPO) or Advantage Actor-Critic (A2C), performs better in managing the dynamic and complex 5G environment. The study compares these models in terms of episode reward, entropy loss, value loss, and frames per second (FPS). The results indicate that PPO's stable performance, efficient learning process, and robust adaptation to dynamic conditions make it a more suitable choice for real-time 5G network management. The results indicate that PPO's stable performance, efficient learning process, and robust adaptation to dynamic conditions make it a more suitable choice for real-time 5G network management. Overall, this paper contributes to the field by offering a thorough comparison of RL models tailored for the nuanced demands of 5G network optimization, providing valuable insights for future advancements in this area. ? 2024 IEEE. Final 2025-03-03T07:45:36Z 2025-03-03T07:45:36Z 2024 Conference paper 10.1109/ICAEE62924.2024.10667637 2-s2.0-85204779257 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204779257&doi=10.1109%2fICAEE62924.2024.10667637&partnerID=40&md5=609628a0e22f0de29dfebf4662237cff https://irepository.uniten.edu.my/handle/123456789/36900 Institute of Electrical and Electronics Engineers Inc. Scopus
institution	Universiti Tenaga Nasional
building	UNITEN Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Tenaga Nasional
content_source	UNITEN Institutional Repository
url_provider	http://dspace.uniten.edu.my/
topic	Network performance Queueing networks Reinforcement learning Resource allocation Dynamic condition Efficient learning Learning process Networks management Optimisations Performance Real- time Reinforcement learning models Stable performance Subcarrier spacing 5G mobile communication systems
spellingShingle	Network performance Queueing networks Reinforcement learning Resource allocation Dynamic condition Efficient learning Learning process Networks management Optimisations Performance Real- time Reinforcement learning models Stable performance Subcarrier spacing 5G mobile communication systems Samidi F.S. Radzi N.A.M. Aripin N.M. Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks
description	The evolution of 5G technology presents unique challenges and opportunities for optimizing network performance through advanced techniques such as Reinforcement Learning (RL). Effective 5G network management requires precise optimization of subcarrier spacing and uplink-downlink (UL-DL) allocation, yet selecting the optimal RL model for this task remains a significant challenge. This paper evaluates the performance of RL models within the RaSSo framework for optimizing 5G networks, aiming to identify the most suitable RL approach. The primary challenge addressed is determining which RL model, in our case, Proximal Policy Optimization (PPO) or Advantage Actor-Critic (A2C), performs better in managing the dynamic and complex 5G environment. The study compares these models in terms of episode reward, entropy loss, value loss, and frames per second (FPS). The results indicate that PPO's stable performance, efficient learning process, and robust adaptation to dynamic conditions make it a more suitable choice for real-time 5G network management. The results indicate that PPO's stable performance, efficient learning process, and robust adaptation to dynamic conditions make it a more suitable choice for real-time 5G network management. Overall, this paper contributes to the field by offering a thorough comparison of RL models tailored for the nuanced demands of 5G network optimization, providing valuable insights for future advancements in this area. ? 2024 IEEE.
author2	57215054855
author_facet	57215054855 Samidi F.S. Radzi N.A.M. Aripin N.M.
format	Conference paper
author	Samidi F.S. Radzi N.A.M. Aripin N.M.
author_sort	Samidi F.S.
title	Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks
title_short	Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks
title_full	Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks
title_fullStr	Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks
title_full_unstemmed	Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks
title_sort	reinforcement learning model selection for resource allocation and subcarrier spacing optimization in 5g sliced spectrum networks
publisher	Institute of Electrical and Electronics Engineers Inc.
publishDate	2025
_version_	1825816122894581760
score	13.244413

Reinforcement Learning Model Selection for Resource Allocation and Subcarrier Spacing Optimization in 5G Sliced Spectrum Networks

Similar Items