Uma arquitetura de fog computing virtualizada para prover gerenciamento de recursos, QoS e SLA em um ambiente inteligente

• Ano de defesa: 2020
• Autor(a) principal: Barreto, Bruno Nunes
• Orientador(a): Ribeiro, Admilson de Ribamar Lima
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Programa de Pós-Graduação: Pós-Graduação em Ciência da Computação
• Palavras-chave em Português: Computação em nuvem; Gerenciamento de recurso; Engenharia da computação
• Palavras-chave em Inglês: Fog computing; Cloud computing; Resource management; QoS; SLA
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://ri.ufs.br/jspui/handle/riufs/14130

Fog Computing represents a change in the use and architecture of the Internet of Things combined with Cloud Computing, where ubiquitous devices with different levels of autonomy and needs go through intelligent gateways capable of providing flexible resources and services to end-users at the edge of the network. Due to the proposed breadth and heterogeneity of technologies and “objects” in the Internet of things, their direct interconnection with the cloud becomes impractical for some types of applications, among them, some aimed at intelligent environments, making it necessary the interference of a new paradigm capable of meeting such needs. Thus, motivated by the number of open questions and because it is a current topic, this research work demonstrates the capacity of the virtualized fog computing architecture (VFCA), developed and implemented, to provide resource management, QoS, and support to contracts of service level agreement (SLA). The experiments carried out in a real environment, validate the advantages of VFCA concerning the conventional cloud through results such as efficiency in communication (where AFCV surpassed the cloud by 52.97% with the UDP protocol and 79.72% with TCP), bandwidth, among others. This research work fills gaps related to fog computing and makes it possible to guarantee and provide services capable of being implemented in smart environments (such smart home), as well as helping to develop business models aimed at it.