Modelagem e simulação para estimativa de risco de falha em redes IOT por meio de redes Bayesianas e método Monte Carlo

• Ano de defesa: 2024
• Autor(a) principal: Kinjo, Erika Midori
• Orientador(a): Librantz, Andre Felipe Henriques
• Banca de defesa: Librantz, Andre Felipe Henriques , Martins, Fellipe Silva , Souza, Edson Melo de , Dias, Cleber Gustavo , Araújo, Sidnei Alves de
• Tipo de documento: Tese
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Nove de Julho
• Programa de Pós-Graduação: Programa de Pós-Graduação em Informática e Gestão do Conhecimento
• Departamento: Informática
• País: Brasil
• Palavras-chave em Português: internet das coisas; redes Bayesianas; Monte Carlo; risco; modelagem; simulação
• Palavras-chave em Inglês: internet of things; bayesian networks; Monte Carlo; risk; modeling; simulation
• Área do conhecimento CNPq: CIENCIA DA COMPUTACAO::SISTEMAS DE COMPUTACAO
• Link de acesso: http://bibliotecatede.uninove.br/handle/tede/3510

The advancement of Internet of Things (IoT) technology has revolutionized several areas, such as: helping to monitor elderly people, improving classrooms, smart home automation, monitoring crops, among others. However, there are market researches that report worrying numbers regarding failures in the implementation of IoT projects, including failures that even make their use unfeasible. As a result, the subject of privacy and data security was highlighted as one of the most cited subjects in works in the area. So, in this scenario this work aims to contribute, by using Bayesian Networks combined with Monte Carlo to model a system that makes possible to simulate and measure risk in the internet of things network - IoT. The methodology used was a mixed approach, when applying the chosen methods. The model developed in this work included components external to the IoT network in a model already established in the representation of systems networks and was called OSI*. The lack of standardization when representing a network combined with the non-inclusion of external components corroborates the analysis of the criticality raised in this work. The model developed allowed us to evaluate the risk of failure of the IoT network in the context of data privacy and security.