Produção Nacional
Methodology Based on Artificial Neural Networks for Hourly Forecasting of PV Plants Generation
2022; Institute of Electrical and Electronics Engineers; Volume: 20; Issue: 4 Linguagem: Inglês
10.1109/tla.2022.9675472
ISSN1548-0992
AutoresANNE GABRIELLE DOS SANTOS SILVA, Breno Bezerra Freitas, César Lédio de Alencar Filho, Claudivan Domingos de Freitas, Elder Alves de Sousa, Erasmo Saraiva de Castro, Esdras Miranda de Araújo, Francisco Correia, Francisco Renato Ponte da Silva, José Janiere Silva de Souza, Luís L'Aiglon Pinto Martins, Luis Rodolfo Rebouças Coutinho, Natalia Pimentel Lado Ces, Ricardo Castelo, Paulo César Marques de Carvalho, Tatiane Carolyne Carneiro,
Tópico(s)Photovoltaic System Optimization Techniques
ResumoWe propose a methodology for the hourly forecast of the photovoltaic (PV) power of two plants (6.03 kWp and 7.37 kWp) installed in the metropolitan region of Fortaleza - CE. The methodology uses two Artificial Neural Networks (ANN) to predict time series: Perceptron type with Multiple Layers (MLP) and radial base functions (RBF), trained with historical data of hourly PV power collected during the year 2020 in the locations under study. System performance meters are applied (correlation coefficient - R, Nash-Sutcliffe efficiency - NSE and relative trend - VR). The data evaluated in each plant are treated using MLP and RBF networks, as well as the Persistence method, seeking to increase the study reliability. ANN results indicate potential to learn the behavior of the plants, with R above 80%, VR close to zero and NSE above 0.50 in two of the applications. In this specific case, despite being similar networks, MLP shows a higher accuracy than RBF.
Referência(s)