Metodologia para avaliação de projetos com ênfase na qualidade do serviço utilizando técnicas de inteligência artificial

• Ano de defesa: 2022
• Autor(a) principal: Sousa, Bruno José Sampaio de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal da Paraíba; Brasil; Engenharia Elétrica; Programa de Pós-Graduação em Engenharia Elétrica; UFPB
• Palavras-chave em Português: Qualidade do serviço; Indicadores de continuidade; Redes neurais artificiais; Algoritmos evolutivos; Projetos de investimento; Benefício dos projetos; Quality of service; Continuity indicators; Artificial neural networks; Genetic Algorithms; Investment projects; Benefit of projects; CNPQ::ENGENHARIAS::ENGENHARIA ELETRICA
• Link de acesso: https://repositorio.ufpb.br/jspui/handle/123456789/23544

The quality of the electricity distribution service has a great impact on consumer satisfaction and on guaranteeing the concession right for distribution companies. For the concessionaire under study, the main indicators of continuity of service are at levels below the regulatory limits, but due to budget restrictions, the forecast of benefit that the improvement or expansion projects bring to the continuity indicators must be assertive, for a targeting appropriate investment and decision making. In view of this scenario, a methodology was proposed for evaluating projects aimed at improving the quality of service, with the estimate of the benefit associated with the reduction in continuity indicators, using concepts of Artificial Neural Networks (ANN) and Genetic Algorithms (AG). The data used were extracted from the distributor's databases and analyzed to identify the input variables and propose models to predict the outputs of interest. The historical values of interruptions due to causes were considered as input and the results of the continuity indicators associated with the types of projects studied form the outputs of the model. The model was developed using the RNA Multi Layer Perceptron (MLP) topology and the results obtained by the simulation of the new methodology showed absolute relative errors almost 100 times smaller for estimating the benefits of the projects compared to the current method used by the distributor.