
Modeling Wind Speed with a Long-Term Horizon and High-Time Interval with a Hybrid Fourier-Neural Network Model
Author(s) -
Juan Gabriel Rueda-Bayona,
Juan José Cabello Eras,
Alexis Sagastume Gutiérrez
Publication year - 2021
Publication title -
mathematical modelling and engineering problems/mathematical modelling of engineering problems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.26
H-Index - 11
eISSN - 2369-0747
pISSN - 2369-0739
DOI - 10.18280/mmep.080313
Subject(s) - autoregressive model , moment (physics) , interval (graph theory) , term (time) , time horizon , fourier transform , horizon , wind speed , computer science , nonlinear system , fourier series , artificial neural network , fourier analysis , scale (ratio) , meteorology , econometrics , mathematics , mathematical optimization , artificial intelligence , geography , physics , mathematical analysis , geometry , classical mechanics , combinatorics , quantum mechanics , cartography
The limited availability of local climatological stations and the limitations to predict the wind speed (WS) accurately are significant barriers to the expansion of wind energy (WE) projects worldwide. A methodology to forecast accurately the WS at the local scale can be used to overcome these barriers. This study proposes a methodology to forecast the WS with high-resolution and long-term horizons, which combines a Fourier model and a nonlinear autoregressive network (NAR). Given the nonlinearities of the WS variations, a NAR model is used to forecast the WS based on the variability identified with the Fourier analysis. The NAR modelled successfully 1.7 years of wind-speed with 3 hours of the time interval, what may be considered the longest forecasting horizon with high resolution at the moment.