Abstract
In this work, the training of a set of Mixture Density Networks (MDNs) type of Neural Networks (NNs) is presented. This set of networks is used to forecast the power generated by a wind farm in Uruguay. The advantages and challenges of using a MDN per hour-month against a single MDN are discussed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have