Combined Forecast Model for Wind Generation in Brazilian Monthly Dispatch Scheduling

The fast growing of wind generation in Brazil has brought benefits to the country's energy supply, especially under critical hydrological conditions, as observed between 2014 and 2017. However, deviations in wind generation predictions may lead to the depletion of reservoirs and expensive thermal generation. In order to improve the accuracy of wind generation forecasts for the monthly dispatch scheduling, different models based on Holt-Winters and SARIMA approach were proposed for Rio do Fogo wind farm, located in the Northeast of Brazil. The results show that the variance-weighted combination of a SARIMA (1,0,0) x (1,1,1)12 and a multiplicative Holt-Winters model provides 13.54% lower mean absolute percentage errors (MAPE) than the current forecast model (moving averages). Thus, it is possible to apply the SARIMA/Holt-Winters variance-weighted combination model with greater accuracy for forecasting the monthly generation of Rio do Fogo wind farm, during the dispatch planning carried out by the Brazilian independent system operator.