Reinforcement learning approach for centralized cognitive radio systems

Providing that licensed or Primary Users (PUs) are oblivious to the presence of unlicensed or Secondary Users (SUs),Cognitive Radio (CR) enables the SUs to use underutilized licensed spectrum (or white spaces) opportunistically and temporarily. A centralized CR system is an architectural model for...

Full description

Bibliographic Details
Main Author: Yau, Alvin Kok-Lim *
Format: Conference or Workshop Item
Published: 2012
Subjects:
Online Access:http://eprints.sunway.edu.my/227/
_version_ 1848801777755881472
author Yau, Alvin Kok-Lim *
author_facet Yau, Alvin Kok-Lim *
author_sort Yau, Alvin Kok-Lim *
building SU Institutional Repository
collection Online Access
description Providing that licensed or Primary Users (PUs) are oblivious to the presence of unlicensed or Secondary Users (SUs),Cognitive Radio (CR) enables the SUs to use underutilized licensed spectrum (or white spaces) opportunistically and temporarily. A centralized CR system is an architectural model for a wide range of applications for example wireless medical telemetry service and medical implant communications service. As an enabling technology for white space exploitation, context awareness and intelligence (or cognition cycle, CC) remains the key characteristics of CR for using the underutilized licensed spectrum in an efficient manner. In this paper, we provide investigation into the application of a stateful Reinforcement Learning (RL) approach, to realize the conceptual CC in centralized static and mobile networks in the presence of many PUs. We investigate the use of RL with respect to Dynamic Channel Selection (DCS) that helps the SU Base Station (BS) to select channels adaptively for data transmission between different SU hosts. The purpose is to enhance the Quality of Service (QoS), particularly to maximise throughput and reduce delay by means of minimizing the number of channel switches. Simulation results reveal that RL achieves good performance and that the learning and exploration characteristics should converge to a low value to optimise performance.
first_indexed 2025-11-14T21:12:51Z
format Conference or Workshop Item
id sunway-227
institution Sunway University
institution_category Local University
last_indexed 2025-11-14T21:12:51Z
publishDate 2012
recordtype eprints
repository_type Digital Repository
spelling sunway-2272020-10-12T07:42:57Z http://eprints.sunway.edu.my/227/ Reinforcement learning approach for centralized cognitive radio systems Yau, Alvin Kok-Lim * TK Electrical engineering. Electronics Nuclear engineering Providing that licensed or Primary Users (PUs) are oblivious to the presence of unlicensed or Secondary Users (SUs),Cognitive Radio (CR) enables the SUs to use underutilized licensed spectrum (or white spaces) opportunistically and temporarily. A centralized CR system is an architectural model for a wide range of applications for example wireless medical telemetry service and medical implant communications service. As an enabling technology for white space exploitation, context awareness and intelligence (or cognition cycle, CC) remains the key characteristics of CR for using the underutilized licensed spectrum in an efficient manner. In this paper, we provide investigation into the application of a stateful Reinforcement Learning (RL) approach, to realize the conceptual CC in centralized static and mobile networks in the presence of many PUs. We investigate the use of RL with respect to Dynamic Channel Selection (DCS) that helps the SU Base Station (BS) to select channels adaptively for data transmission between different SU hosts. The purpose is to enhance the Quality of Service (QoS), particularly to maximise throughput and reduce delay by means of minimizing the number of channel switches. Simulation results reveal that RL achieves good performance and that the learning and exploration characteristics should converge to a low value to optimise performance. 2012-10 Conference or Workshop Item PeerReviewed Yau, Alvin Kok-Lim * (2012) Reinforcement learning approach for centralized cognitive radio systems. In: IET International Conference on Wireless Communications and Applications (ICWCA 2012), 8-10 Oct 2012, Kuala Lumpur. http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6544342
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Yau, Alvin Kok-Lim *
Reinforcement learning approach for centralized cognitive radio systems
title Reinforcement learning approach for centralized cognitive radio systems
title_full Reinforcement learning approach for centralized cognitive radio systems
title_fullStr Reinforcement learning approach for centralized cognitive radio systems
title_full_unstemmed Reinforcement learning approach for centralized cognitive radio systems
title_short Reinforcement learning approach for centralized cognitive radio systems
title_sort reinforcement learning approach for centralized cognitive radio systems
topic TK Electrical engineering. Electronics Nuclear engineering
url http://eprints.sunway.edu.my/227/
http://eprints.sunway.edu.my/227/