Real-time data analytics for Non-Functional Requirements satisfaction

Detalhes bibliográficos
Autor(a) principal: Sousa, Rita Rocha de
Data de Publicação: 2021
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.22/20199
Resumo: Smart systems, more than ever, demands processing a massive amount of data generated by heterogeneous and distributed data sources. This dissertation presents the contribution made to a software architecture that processes big-data analytics from the edge to the cloud. The software architecture integrates both responsive data-in-motion (edge computing) and latent data-at-rest analytics (cloud computing) into a single solution, satisfying extremescale analytics performance requirements. This dissertation focused on fulfilling the nonfunctional properties inherited from smart systems, such as real-time and energy-efficiency, to ensure the performance of the software architecture first referred. The Non-Functional Requirements (NRF) Tool manages computing resources and detects Quality of Service (QoS) violations. The Global Resource Manager (GRM) helps the scheduler/orchestrator redeploy the applications through the NFR Tools’ feedback. In addition, it can act reactively or proactively (recurring to Machine Learning techniques) to improve the system’s health.
id RCAP_9cac3d32b03ff2036e35972e7281c76c
oai_identifier_str oai:recipp.ipp.pt:10400.22/20199
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Real-time data analytics for Non-Functional Requirements satisfactionNon-Functional RequirementsQuality of ServiceReal TimeMachine LearningRequisitos não funcionaisQualidade de Serviço,Tempo RealAprendizagem de MáquinaSmart systems, more than ever, demands processing a massive amount of data generated by heterogeneous and distributed data sources. This dissertation presents the contribution made to a software architecture that processes big-data analytics from the edge to the cloud. The software architecture integrates both responsive data-in-motion (edge computing) and latent data-at-rest analytics (cloud computing) into a single solution, satisfying extremescale analytics performance requirements. This dissertation focused on fulfilling the nonfunctional properties inherited from smart systems, such as real-time and energy-efficiency, to ensure the performance of the software architecture first referred. The Non-Functional Requirements (NRF) Tool manages computing resources and detects Quality of Service (QoS) violations. The Global Resource Manager (GRM) helps the scheduler/orchestrator redeploy the applications through the NFR Tools’ feedback. In addition, it can act reactively or proactively (recurring to Machine Learning techniques) to improve the system’s health.Os sistemas inteligentes, mais do que nunca, exigem processamento de grandes quantidades de dados gerados por fontes de dados heterogéneos e distribuídos. Esta tese apresenta a contribuição para uma arquitetura de software que processa análises de big-data desde a Edge até à Cloud. A arquitetura de software integra, numa única solução, dados em movimento responsivos (Edge computing) e dados analíticos em repouso latentes (Cloud computing), atendendo aos requisitos de desempenho de análises em escala extrema. O foco desta tese incide no cumprimento das propriedades não funcionais herdadas de sistemas inteligentes, como tempo real (Real Time) e eficiência energética, para garantir o desempenho da arquitetura de software inicialmente referida. A ferramenta de requisitos não funcionais (Non-Functional Requirements (NFR)) faz a gestão de recursos computacionais e deteta violações de Qualidade de Serviço (Quality of Service (QoS)). O gestor de recursos global ajuda o escalonador/orquestrador a reescalonar as aplicações através do feedback da NFR e pode agir de forma reativa ou proativa (recorrendo a técnicas de Aprendizagem de Máquina (Machine Learning (ML)) para melhorar a integridade do sistema.Nogueira, Luís Miguel PinhoRepositório Científico do Instituto Politécnico do PortoSousa, Rita Rocha de2022-11-11T01:31:22Z20212021-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.22/20199TID:202797368enginfo: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:RCAAP2023-03-13T13:15:08Zoai:recipp.ipp.pt:10400.22/20199Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:40:15.514336Repositório 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 Real-time data analytics for Non-Functional Requirements satisfaction
title Real-time data analytics for Non-Functional Requirements satisfaction
spellingShingle Real-time data analytics for Non-Functional Requirements satisfaction
Sousa, Rita Rocha de
Non-Functional Requirements
Quality of Service
Real Time
Machine Learning
Requisitos não funcionais
Qualidade de Serviço,
Tempo Real
Aprendizagem de Máquina
title_short Real-time data analytics for Non-Functional Requirements satisfaction
title_full Real-time data analytics for Non-Functional Requirements satisfaction
title_fullStr Real-time data analytics for Non-Functional Requirements satisfaction
title_full_unstemmed Real-time data analytics for Non-Functional Requirements satisfaction
title_sort Real-time data analytics for Non-Functional Requirements satisfaction
author Sousa, Rita Rocha de
author_facet Sousa, Rita Rocha de
author_role author
dc.contributor.none.fl_str_mv Nogueira, Luís Miguel Pinho
Repositório Científico do Instituto Politécnico do Porto
dc.contributor.author.fl_str_mv Sousa, Rita Rocha de
dc.subject.por.fl_str_mv Non-Functional Requirements
Quality of Service
Real Time
Machine Learning
Requisitos não funcionais
Qualidade de Serviço,
Tempo Real
Aprendizagem de Máquina
topic Non-Functional Requirements
Quality of Service
Real Time
Machine Learning
Requisitos não funcionais
Qualidade de Serviço,
Tempo Real
Aprendizagem de Máquina
description Smart systems, more than ever, demands processing a massive amount of data generated by heterogeneous and distributed data sources. This dissertation presents the contribution made to a software architecture that processes big-data analytics from the edge to the cloud. The software architecture integrates both responsive data-in-motion (edge computing) and latent data-at-rest analytics (cloud computing) into a single solution, satisfying extremescale analytics performance requirements. This dissertation focused on fulfilling the nonfunctional properties inherited from smart systems, such as real-time and energy-efficiency, to ensure the performance of the software architecture first referred. The Non-Functional Requirements (NRF) Tool manages computing resources and detects Quality of Service (QoS) violations. The Global Resource Manager (GRM) helps the scheduler/orchestrator redeploy the applications through the NFR Tools’ feedback. In addition, it can act reactively or proactively (recurring to Machine Learning techniques) to improve the system’s health.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-01-01T00:00:00Z
2022-11-11T01:31:22Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.22/20199
TID:202797368
url http://hdl.handle.net/10400.22/20199
identifier_str_mv TID:202797368
dc.language.iso.fl_str_mv eng
language eng
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.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_ 1799131490967093248

Registros relacionados