Attention-based model and deep reinforcement learning for distribution of event processing tasks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.1/18589 |
Resumo: | Event processing is the cornerstone of the dynamic and responsive Internet of Things (IoT). Recent approaches in this area are based on representational state transfer (REST) principles, which allow event processing tasks to be placed at any device that follows the same principles. However, the tasks should be properly distributed among edge devices to ensure fair resources utilization and guarantee seamless execution. This article investigates the use of deep learning to fairly distribute the tasks. An attention-based neural network model is proposed to generate efficient load balancing solutions under different scenarios. The proposed model is based on the Transformer and Pointer Network architectures, and is trained by an advantage actorcritic reinforcement learning algorithm. The model is designed to scale to the number of event processing tasks and the number of edge devices, with no need for hyperparameters re-tuning or even retraining. Extensive experimental results show that the proposed model outperforms conventional heuristics in many key performance indicators. The generic design and the obtained results show that the proposed model can potentially be applied to several other load balancing problem variations, which makes the proposal an attractive option to be used in real-world scenarios due to its scalability and efficiency. |
id |
RCAP_ea3db88602203394e121b4048ba7ca6d |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/18589 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Attention-based model and deep reinforcement learning for distribution of event processing tasksWeb of Things (WoT)Representational state transfer (REST)Application programming interface (APIs)Edge computingLoad balancingResource placementDeep reinforcement leaningTransformer modelPointer networksActor criticEvent processing is the cornerstone of the dynamic and responsive Internet of Things (IoT). Recent approaches in this area are based on representational state transfer (REST) principles, which allow event processing tasks to be placed at any device that follows the same principles. However, the tasks should be properly distributed among edge devices to ensure fair resources utilization and guarantee seamless execution. This article investigates the use of deep learning to fairly distribute the tasks. An attention-based neural network model is proposed to generate efficient load balancing solutions under different scenarios. The proposed model is based on the Transformer and Pointer Network architectures, and is trained by an advantage actorcritic reinforcement learning algorithm. The model is designed to scale to the number of event processing tasks and the number of edge devices, with no need for hyperparameters re-tuning or even retraining. Extensive experimental results show that the proposed model outperforms conventional heuristics in many key performance indicators. The generic design and the obtained results show that the proposed model can potentially be applied to several other load balancing problem variations, which makes the proposal an attractive option to be used in real-world scenarios due to its scalability and efficiency.ElsevierSapientiaMazayev, AndriyAl-Tam, FaroqCorreia, Noélia2022-12-06T14:30:18Z2022-072022-07-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.1/18589eng10.1016/j.iot.2022.1005632542-6605info: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:RCAAP2024-03-06T02:03:43Zoai:sapientia.ualg.pt:10400.1/18589Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:08:19.209349Repositório 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 |
Attention-based model and deep reinforcement learning for distribution of event processing tasks |
title |
Attention-based model and deep reinforcement learning for distribution of event processing tasks |
spellingShingle |
Attention-based model and deep reinforcement learning for distribution of event processing tasks Mazayev, Andriy Web of Things (WoT) Representational state transfer (REST) Application programming interface (APIs) Edge computing Load balancing Resource placement Deep reinforcement leaning Transformer model Pointer networks Actor critic |
title_short |
Attention-based model and deep reinforcement learning for distribution of event processing tasks |
title_full |
Attention-based model and deep reinforcement learning for distribution of event processing tasks |
title_fullStr |
Attention-based model and deep reinforcement learning for distribution of event processing tasks |
title_full_unstemmed |
Attention-based model and deep reinforcement learning for distribution of event processing tasks |
title_sort |
Attention-based model and deep reinforcement learning for distribution of event processing tasks |
author |
Mazayev, Andriy |
author_facet |
Mazayev, Andriy Al-Tam, Faroq Correia, Noélia |
author_role |
author |
author2 |
Al-Tam, Faroq Correia, Noélia |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Sapientia |
dc.contributor.author.fl_str_mv |
Mazayev, Andriy Al-Tam, Faroq Correia, Noélia |
dc.subject.por.fl_str_mv |
Web of Things (WoT) Representational state transfer (REST) Application programming interface (APIs) Edge computing Load balancing Resource placement Deep reinforcement leaning Transformer model Pointer networks Actor critic |
topic |
Web of Things (WoT) Representational state transfer (REST) Application programming interface (APIs) Edge computing Load balancing Resource placement Deep reinforcement leaning Transformer model Pointer networks Actor critic |
description |
Event processing is the cornerstone of the dynamic and responsive Internet of Things (IoT). Recent approaches in this area are based on representational state transfer (REST) principles, which allow event processing tasks to be placed at any device that follows the same principles. However, the tasks should be properly distributed among edge devices to ensure fair resources utilization and guarantee seamless execution. This article investigates the use of deep learning to fairly distribute the tasks. An attention-based neural network model is proposed to generate efficient load balancing solutions under different scenarios. The proposed model is based on the Transformer and Pointer Network architectures, and is trained by an advantage actorcritic reinforcement learning algorithm. The model is designed to scale to the number of event processing tasks and the number of edge devices, with no need for hyperparameters re-tuning or even retraining. Extensive experimental results show that the proposed model outperforms conventional heuristics in many key performance indicators. The generic design and the obtained results show that the proposed model can potentially be applied to several other load balancing problem variations, which makes the proposal an attractive option to be used in real-world scenarios due to its scalability and efficiency. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-12-06T14:30:18Z 2022-07 2022-07-01T00:00:00Z |
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/10400.1/18589 |
url |
http://hdl.handle.net/10400.1/18589 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1016/j.iot.2022.100563 2542-6605 |
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 |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
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_ |
1799133329350459392 |