Aplicação de técnicas de Machine Learning na previsão de geração de energia elétrica na UFG
Nenhuma Miniatura disponível
Data
2021-11-09
Autores
Título da Revista
ISSN da Revista
Título de Volume
Editor
Universidade Federal de Goiás
Resumo
This article aims to analyze the application of machine learning techniques in predicting the energy produced by photovoltaic panel installed on Campus Colemar Natal e Silva, at the Federal University of Goiás (UFG). At first, it presents basic concepts and explanations about how photovoltaic energy is generated and what are the main factor that affect it; later, the thematic of machine learning and the SRV algorithm – chosen for the test – and the parameters that change the behavior are approached. Then, the relationships between the variables are discussed and the relationship between the metrological variables and the generation of electricity is calculated. Finally, training is presented with different approaches between the configuration of the
algorithm and the amount of variables used of training, after which the data are compared to understand which variables and settings greatly.
Descrição
Palavras-chave
Energia solar, Machine learning, Irradiância, Placas fotovoltaicas, Solar energy, Machine learning, Irradiance, Photovoltaic cell
Citação
FERRAZ, Victor Gomide. Aplicação de técnicas de Machine Learning na previsão de geração de energia elétrica na UFG. 2021. 17 f. Trabalho de Conclusão de Curso (Bacharelado em Engenharia da Computação) - Escola de Engenharia Elétrica, Mecânica e de Computação, Universidade Federal de Goiás, Goiânia, 2021.