Obtaining clean energy through wind farms is considered viable because of its low operating cost. However, the wind speed behavior is not constant, it has a chaotic behavior, and it is highly data-dependent. The present work aims to carry out a comparison of several short-term wind forecasts using Artificial Intelligence models such as Artificial Neural Networks (ANN), Multilayer Perceptron (MLP), Convolutional Neural Networks (CNN), and Large Short-Term Memory Networks (LSTM). We discuss several scenarios where the models are contrasted, analyzing the advantages and disadvantages of using these strategies to decide the viability of building a wind farm in the analyzed place.