Algoritmo de Previsão de Velocidade do Vento - HW+NARX

Abstract

This document describes a computer program registered under number BR512023001329-3, which presents an algorithm for forecasting wind speed using a combination of exponential smoothing methods (Holt-Winters, HW) and autoregressive neural networks with exogenous inputs (NARX) . The goal of the program is to improve the accuracy of wind speed predictions, which is crucial for diverse applications such as wind energy and climate monitoring. The combination of HW+NARX methods provides a robust approach, capable of dealing with the variability and complexity of meteorological data. Program registration is valid for 50 years from January 1, 2022.