**5. Conclusions**

The present chapter aimed to define the most efficient RNN configuration to predict the wind speed for 1 h and, after that, to apply it for 6 h ahead, using as reference observational data collected from two anemometric towers, with anemometers installed at 100.0 and 101.8 m height, located, respectively, in a tropical region in Mucuri, Bahia, northeastern Brazil, and in a subtropical region in Colonia Eulacio, Soriano Department, Uruguay. It has been shown graphically and verified through numerical simulations that the RNN was better than MLP in Mucuri and worst in Colonia Eulacio.

In the light of the statistical results recorded in this work, the application of computational intelligence is a viable alternative for the predictability of wind speed and, in this way, wind power generation, mainly due to the low computational cost; however, one must choose the ANN architecture that best suits the project, as well as quantitatively and qualitatively analyzes the available data that will feed the network, since these variables directly impact the results of the forecast.

The results of the short-term wind speed forecasting showed good accuracy at all the anemometer heights tested. Therefore, the proposed short-term wind speed forecasting method is an important scientific contribution for reliable large-scale wind power forecasting and integration in tropical and subtropical regions, like in Brazil and Uruguay.

#### *Aerodynamics*

The suggestion for improving the accuracy of ANN for higher lead time is wavelet packet decomposition because the empirical wavelet transform can effectively identify and extract a finite number of intrinsic modes of a wind speed time series and thus improving the accuracy of the supervised machine learning; other suggestion is to apply the wind speed x-axis component and wind speed y-axis component ANN's input.

We can suggest as future work to use the Mucuri, Colonia Eulacio, and other observational data collected in different heights in Brazil and Uruguay to perform the prediction of the wind speed more accurately in the short-term and in the medium-term using computational intelligence by long short-term memory (LSTM) and gated recurrent unit (GRU) and to compare these results with the output produced by numerical and meteorological modeling using the weather research and forecasting (WRF) model, for example. Wind ramp and greater forecasting horizons are also a great subject of research.
