Eventos Anais de eventos
ENCIT 2018
Brazilian Congress of Thermal Sciences and Engineering
IMPERIALIST COMPETITIVE ALGORITHM APPLIED TO WINDENERGY FOR A BRAZILIAN SITE AT PARAÍBA
Submission Author:
MARCUS VINICIUS SILVEIRA MACEDO , CE , Brazil
Co-Authors:
MARCUS VINICIUS SILVEIRA MACEDO, LINDEMBERG FERREIRA DOS SANTOS, Felipe Ferreira Gomes, Carla Freitas de Andrade, Paulo Alexandre Costa Rocha
Presenter: MARCUS VINICIUS SILVEIRA MACEDO
doi://10.26678/ABCM.ENCIT2018.CIT18-0733
Abstract
Due to factors such as the lack of rainfall and the high energy value from thermoelectric plants, Brazil has presented great growth in the electricity generation from wind farms. One of the main points analyzed in the wind farm implementation is the wind regime described by a probability distribution. This paper aims to estimate by heuristic method known as the Imperialist Competitive Algorithm (ICA), the Weibull distribution parameters. The ICA was implemented by the R language for the city of São João do Cariri located in Paraíba state, Brazil, and the results were compared using the statistical tests RMSE, MAE and R2, in addition to the Wind Production Deviation (WPD) value between the curve obtained and the histogram generated from the Wind speed data. The results presented by deterministic methods usually used for this purpose. In spite of the good performance in the statistical tests, the ICA did not prove to be efficient to estimate the weibull parameters curve for the analyzed region, since it obtained WPD equal to 11.86\%, higher than the acceptable maximum for the wind production deviation.
Keywords
wind energy, Weibull Distribution, Imperialist Competitive Algorithm, Heuristic, Deterministic
