A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards

Detalhes bibliográficos
Autor(a) principal: Santana, P.
Data de Publicação: 2023
Outros Autores: Moura, J.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10071/28693
Resumo: To handle the exponential growth of data-intensive network edge services and automatically solve new challenges in routing management, machine learning is steadily being incorporated into software-defined networking solutions. In this line, the article presents the design of a piecewise-stationary Bayesian multi-armed bandit approach for the online optimum end-to-end dynamic routing of data flows in the context of programmable networking systems. This learning-based approach has been analyzed with simulated and emulated data, showing the proposal’s ability to sequentially and proactively self-discover the end-to-end routing path with minimal delay among a considerable number of alternatives, even when facing abrupt changes in transmission delay distributions due to both variable congestion levels on path network devices and dynamic delays to transmission links.
id RCAP_712847fa715320db7302a940cf31873e
oai_identifier_str oai:repositorio.iscte-iul.pt:10071/28693
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewardsNetworksRoutingCongestionVariable link delaySDNAlgorithm designMulti-armed banditsTo handle the exponential growth of data-intensive network edge services and automatically solve new challenges in routing management, machine learning is steadily being incorporated into software-defined networking solutions. In this line, the article presents the design of a piecewise-stationary Bayesian multi-armed bandit approach for the online optimum end-to-end dynamic routing of data flows in the context of programmable networking systems. This learning-based approach has been analyzed with simulated and emulated data, showing the proposal’s ability to sequentially and proactively self-discover the end-to-end routing path with minimal delay among a considerable number of alternatives, even when facing abrupt changes in transmission delay distributions due to both variable congestion levels on path network devices and dynamic delays to transmission links.MDPI2023-05-24T13:29:58Z2023-01-01T00:00:00Z20232023-05-24T14:29:36Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10071/28693eng1999-489310.3390/a16050233Santana, P.Moura, J.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-09T17:31:39Zoai:repositorio.iscte-iul.pt:10071/28693Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:14:15.191553Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards
title A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards
spellingShingle A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards
Santana, P.
Networks
Routing
Congestion
Variable link delay
SDN
Algorithm design
Multi-armed bandits
title_short A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards
title_full A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards
title_fullStr A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards
title_full_unstemmed A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards
title_sort A Bayesian multi-armed bandit algorithm for dynamic end-to-end routing in SDN-based networks with piecewise-stationary rewards
author Santana, P.
author_facet Santana, P.
Moura, J.
author_role author
author2 Moura, J.
author2_role author
dc.contributor.author.fl_str_mv Santana, P.
Moura, J.
dc.subject.por.fl_str_mv Networks
Routing
Congestion
Variable link delay
SDN
Algorithm design
Multi-armed bandits
topic Networks
Routing
Congestion
Variable link delay
SDN
Algorithm design
Multi-armed bandits
description To handle the exponential growth of data-intensive network edge services and automatically solve new challenges in routing management, machine learning is steadily being incorporated into software-defined networking solutions. In this line, the article presents the design of a piecewise-stationary Bayesian multi-armed bandit approach for the online optimum end-to-end dynamic routing of data flows in the context of programmable networking systems. This learning-based approach has been analyzed with simulated and emulated data, showing the proposal’s ability to sequentially and proactively self-discover the end-to-end routing path with minimal delay among a considerable number of alternatives, even when facing abrupt changes in transmission delay distributions due to both variable congestion levels on path network devices and dynamic delays to transmission links.
publishDate 2023
dc.date.none.fl_str_mv 2023-05-24T13:29:58Z
2023-01-01T00:00:00Z
2023
2023-05-24T14:29:36Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10071/28693
url http://hdl.handle.net/10071/28693
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 1999-4893
10.3390/a16050233
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134699355897856

Registros relacionados