The development and expansion of clean energy, such as wind energy, are important in the preservation of the environment and development of local economies and an alternative to hydroelectric and thermal energies. In this respect, the development of efficient forecasting models to support the decision-making process is necessary. However, the effect of climatic and demographic factors makes it challenging. This study evaluates bootstrap aggregation efficiency (bagging) combined with a stacking ensemble learning model for short and medium-term (one up to twelve hours ahead) forecasting wind turbine wind power generation for a wind farm located in Parazinho, Brazil. The forecasting accuracy is evaluated through the root mean squared error, mean absolute error, and Theil’s U index of inequality (type 2). The results suggest that for one-hour-ahead forecasting wind power generation, the stacking ensemble learning achieves forecasting errors lower than the combination of stacking with bagging ensemble approach according to all performance criteria and have competitive results concerning the remaining forecasting. In 85.42% of the comparisons, the stacking combined with the bagging ensemble has better accuracy than the stacking ensemble learning model regarding the adopted criteria.