Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs

While dynamic channel bonding (DCB) is proven to boost the capacity of wireless local area networks (WLANs) by adapting the bandwidth on a per-frame basis, its performance is tied to the primary and secondary channel selection. Unfortunately, in uncoordinated high-density deployments where multiple...

Descripción completa

Detalles Bibliográficos
Autor: Bellalta, Boris
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10230/53597
Acceso en línea:http://hdl.handle.net/10230/53597
http://doi.org/10.1109/ACCESS.2021.3114430
Access Level:acceso abierto
Palabra clave:Channel bonding
spectrum allocation
multi-agent
reinforcement learning
multi-armed bandit
id ES_9a33c23d65ffbb97a96080dcd26d5897
oai_identifier_str oai:recercat.cat:10230/53597
network_acronym_str ES
network_name_str España
repository_id_str
spelling Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANsBellalta, BorisChannel bondingspectrum allocationmulti-agentreinforcement learningmulti-armed banditWhile dynamic channel bonding (DCB) is proven to boost the capacity of wireless local area networks (WLANs) by adapting the bandwidth on a per-frame basis, its performance is tied to the primary and secondary channel selection. Unfortunately, in uncoordinated high-density deployments where multiple basic service sets (BSSs) may potentially overlap, hand-crafted spectrum management techniques perform poorly given the complex hidden/exposed nodes interactions. To cope with such challenging Wi-Fi environments, in this paper, we first identify machine learning (ML) approaches applicable to the problem at hand and justify why model-free RL suits it the most. We then design a complete RL framework and call into question whether the use of complex RL algorithms helps the quest for rapid learning in realistic scenarios. Through extensive simulations, we derive that stateless RL in the form of lightweight multi-armed-bandits (MABs) is an efficient solution for rapid adaptation avoiding the definition of broad and/or meaningless states. In contrast to most current trends, we envision lightweight MABs as an appropriate alternative to the cumbersome and slowly convergent methods such as Q-learning, and especially, deep reinforcement learning.The work of Sergio Barrachina-Muñoz and Boris Bellalta was supported in part by Cisco, Machine Learning for Wireless Networking in Highly Dynamic Scenarios (WINDMAL), under Grant PGC2018-099959-B-I00 [Ministerio de Ciencia e Innovación (MCIU)/Agencia Estatal de Innovación (AEI)/Fondo Europeo de Desarrollo Regional (FEDER), Union Europea (UE)] and Grant SGR-2017-1188. The work of Alessandro Chiumento was supported in part by the ECSEL Joint Undertaking (JU) through the Intelligent Secure Trustable Things (InSecTT) Project (https://www.insectt.eu/) under Grant 876038.The work of Sergio Barrachina-Muñoz and Boris Bellalta was supported in part by Cisco, Machine Learning for Wireless Networking in Highly Dynamic Scenarios (WINDMAL), under Grant PGC2018-099959-B-I00 [Ministerio de Ciencia e Innovación (MCIU)/Agencia Estatal de Innovación (AEI)/Fondo Europeo de Desarrollo Regional (FEDER), Union Europea (UE)] and Grant SGR-2017-1188. The work of Alessandro Chiumento was supported in part by the ECSEL Joint Undertaking (JU) through the Intelligent Secure Trustable Things (InSecTT) Project (https://www.insectt.eu/) under Grant 876038.Institute of Electrical and Electronics Engineers (IEEE)202220222021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/53597http://doi.org/10.1109/ACCESS.2021.3114430reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)InglésIEEE Access. 2021;9:133472-90.info:eu-repo/grantAgreement/ES/2PE/PGC2018-099959-B-I00This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:recercat.cat:10230/535972026-05-29T05:05:01Z
dc.title.none.fl_str_mv Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs
title Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs
spellingShingle Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs
Bellalta, Boris
Channel bonding
spectrum allocation
multi-agent
reinforcement learning
multi-armed bandit
title_short Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs
title_full Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs
title_fullStr Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs
title_full_unstemmed Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs
title_sort Multi-armed bandits for spectrum allocation in multi-agent channel bonding WLANs
dc.creator.none.fl_str_mv Bellalta, Boris
author Bellalta, Boris
author_facet Bellalta, Boris
author_role author
dc.subject.none.fl_str_mv Channel bonding
spectrum allocation
multi-agent
reinforcement learning
multi-armed bandit
topic Channel bonding
spectrum allocation
multi-agent
reinforcement learning
multi-armed bandit
description While dynamic channel bonding (DCB) is proven to boost the capacity of wireless local area networks (WLANs) by adapting the bandwidth on a per-frame basis, its performance is tied to the primary and secondary channel selection. Unfortunately, in uncoordinated high-density deployments where multiple basic service sets (BSSs) may potentially overlap, hand-crafted spectrum management techniques perform poorly given the complex hidden/exposed nodes interactions. To cope with such challenging Wi-Fi environments, in this paper, we first identify machine learning (ML) approaches applicable to the problem at hand and justify why model-free RL suits it the most. We then design a complete RL framework and call into question whether the use of complex RL algorithms helps the quest for rapid learning in realistic scenarios. Through extensive simulations, we derive that stateless RL in the form of lightweight multi-armed-bandits (MABs) is an efficient solution for rapid adaptation avoiding the definition of broad and/or meaningless states. In contrast to most current trends, we envision lightweight MABs as an appropriate alternative to the cumbersome and slowly convergent methods such as Q-learning, and especially, deep reinforcement learning.
publishDate 2021
dc.date.none.fl_str_mv 2021
2022
2022
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/53597
http://doi.org/10.1109/ACCESS.2021.3114430
url http://hdl.handle.net/10230/53597
http://doi.org/10.1109/ACCESS.2021.3114430
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv IEEE Access. 2021;9:133472-90.
info:eu-repo/grantAgreement/ES/2PE/PGC2018-099959-B-I00
dc.rights.none.fl_str_mv https://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
dc.source.none.fl_str_mv reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869414351907061760
score 15.811543

Similares en LA Referencia