Desenvolvimento de uma rede neuro-fuzzy para a previsão da carga

• Ano de defesa: 2015
• Autor(a) principal: Amorim, Aline Jardim [UNESP]
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Estadual Paulista (Unesp)
• Palavras-chave em Português: Sistemas de energia eletrica; Carga e distribuição elétrica; Redes neurais (Computação); Lógica difusa; Electric power systems
• Link de acesso: http://hdl.handle.net/11449/126567; http://www.athena.biblioteca.unesp.br/exlibris/bd/cathedra/12-08-2015/000844134.pdf

The prediction process study is a very important task for the operation of the electrical power systems. Therefore, it is necessary to predict the future behavior to provide energy with security, efficiency and economy to the users. This work presents a methodology based on neural networks to solve the problem of load forecasting. The proposal is to improve the neural network using the backpropagation algorithm adapting the inclination and translation parameters of the sigmoid function (activation function of the neural network). Besides, it is developed a fuzzy controller to adjust the training during the convergence process. To test the proposed methodology, it is presented a load forecasting study considering a database from an electrical energy company