ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs

IEEE 802.11 (Wi-Fi) is one of the technologies that provides high performance with a high density of connected devices to support emerging demanding services, such as virtual and augmented reality. However, in highly dense deployments, Wi-Fi performance is severely affected by interference. This pro...

Descripción completa

Detalles Bibliográficos
Autores: Soto, Paola, Camelo, Miguel, Mets, Kevin, Wilhelmi Roca, Francesc, Góez, David, Fletscher, Luis A., Gaviria, Natalia, Hellinckx, Peter, Botero, Juan F., Latré, Steven
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:dnet:rdupf_______::c1067677a7c773ea6f46ee1bf49e47a0
Acceso en línea:https://hdl.handle.net/10230/73076
http://dx.doi.org/10.3390/s21134321
Access Level:acceso abierto
Palabra clave:Channel bonding
Graph neural network
Machine learning
Performance prediction
WLANs
id ES_c4cf384ff0a94ccc8f4a370e6d5265dd
oai_identifier_str oai:dnet:rdupf_______::c1067677a7c773ea6f46ee1bf49e47a0
network_acronym_str ES
network_name_str España
repository_id_str
spelling ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANsSoto, PaolaCamelo, MiguelMets, KevinWilhelmi Roca, FrancescGóez, DavidFletscher, Luis A.Gaviria, NataliaHellinckx, PeterBotero, Juan F.Latré, StevenChannel bondingGraph neural networkMachine learningPerformance predictionWLANsIEEE 802.11 (Wi-Fi) is one of the technologies that provides high performance with a high density of connected devices to support emerging demanding services, such as virtual and augmented reality. However, in highly dense deployments, Wi-Fi performance is severely affected by interference. This problem is even worse in new standards, such as 802.11n/ac, where new features such as Channel Bonding (CB) are introduced to increase network capacity but at the cost of using wider spectrum channels. Finding the best channel assignment in dense deployments under dynamic environments with CB is challenging, given its combinatorial nature. Therefore, the use of analytical or system models to predict Wi-Fi performance after potential changes (e.g., dynamic channel selection with CB, and the deployment of new devices) are not suitable, due to either low accuracy or high computational cost. This paper presents a novel, data-driven approach to speed up this process, using a Graph Neural Network (GNN) model that exploits the information carried in the deployment¿s topology and the intricate wireless interactions to predict Wi-Fi performance with high accuracy. The evaluation results show that preserving the graph structure in the learning process obtains a 64% increase versus a naive approach, and around 55% compared to other Machine Learning (ML) approaches when using all training features.MDPI2026202620212026info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/10230/73076http://dx.doi.org/10.3390/s21134321reponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésSensors. 2021 Jul 1;21(13):4321© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:dnet:rdupf_______::c1067677a7c773ea6f46ee1bf49e47a02026-06-12T07:21:37Z
dc.title.none.fl_str_mv ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs
title ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs
spellingShingle ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs
Soto, Paola
Channel bonding
Graph neural network
Machine learning
Performance prediction
WLANs
title_short ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs
title_full ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs
title_fullStr ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs
title_full_unstemmed ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs
title_sort ATARI: a graph convolutional neural network approach for performance prediction in next-generation WLANs
dc.creator.none.fl_str_mv Soto, Paola
Camelo, Miguel
Mets, Kevin
Wilhelmi Roca, Francesc
Góez, David
Fletscher, Luis A.
Gaviria, Natalia
Hellinckx, Peter
Botero, Juan F.
Latré, Steven
author Soto, Paola
author_facet Soto, Paola
Camelo, Miguel
Mets, Kevin
Wilhelmi Roca, Francesc
Góez, David
Fletscher, Luis A.
Gaviria, Natalia
Hellinckx, Peter
Botero, Juan F.
Latré, Steven
author_role author
author2 Camelo, Miguel
Mets, Kevin
Wilhelmi Roca, Francesc
Góez, David
Fletscher, Luis A.
Gaviria, Natalia
Hellinckx, Peter
Botero, Juan F.
Latré, Steven
author2_role author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Channel bonding
Graph neural network
Machine learning
Performance prediction
WLANs
topic Channel bonding
Graph neural network
Machine learning
Performance prediction
WLANs
description IEEE 802.11 (Wi-Fi) is one of the technologies that provides high performance with a high density of connected devices to support emerging demanding services, such as virtual and augmented reality. However, in highly dense deployments, Wi-Fi performance is severely affected by interference. This problem is even worse in new standards, such as 802.11n/ac, where new features such as Channel Bonding (CB) are introduced to increase network capacity but at the cost of using wider spectrum channels. Finding the best channel assignment in dense deployments under dynamic environments with CB is challenging, given its combinatorial nature. Therefore, the use of analytical or system models to predict Wi-Fi performance after potential changes (e.g., dynamic channel selection with CB, and the deployment of new devices) are not suitable, due to either low accuracy or high computational cost. This paper presents a novel, data-driven approach to speed up this process, using a Graph Neural Network (GNN) model that exploits the information carried in the deployment¿s topology and the intricate wireless interactions to predict Wi-Fi performance with high accuracy. The evaluation results show that preserving the graph structure in the learning process obtains a 64% increase versus a naive approach, and around 55% compared to other Machine Learning (ML) approaches when using all training features.
publishDate 2021
dc.date.none.fl_str_mv 2021
2026
2026
2026
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 https://hdl.handle.net/10230/73076
http://dx.doi.org/10.3390/s21134321
url https://hdl.handle.net/10230/73076
http://dx.doi.org/10.3390/s21134321
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Sensors. 2021 Jul 1;21(13):4321
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 MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869418934297427969
score 15,811543

Similares en LA Referencia