ARIMA vs. Neural networks for wind speed forecasting

Autor:	J. J. G. de la Rosa, J. Melgar, A. Aguera, Antonio Francisco Romero Moreno, José Carlos Palomares-Salas, J. G. Ramiro
Rok vydání:	2009
Předmět:	Wind power Computer science business.industry Weather forecasting Regression analysis computer.software_genre Backpropagation Wind speed Statistics Autoregressive integrated moving average Time series Energy source business computer Simulation
Zdroj:	2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.
DOI:	10.1109/cimsa.2009.5069932
Popis:	In this paper an ARIMA model is used for time-series forecast involving wind speed measurements. Results are compared with the performance of a back propagation type NNT. Results show that ARIMA model is better than NNT for short time-intervals to forecast (10 minutes, 1 hour, 2 hours and 4 hours). Data was acquired from a unit located in Southern Andalusia (Penaflor, Sevilla), with a soft orography (10 minutes between measurements). This feature is which makes performance of the ARIMA model and the NNT very similar, so a simple forecasting model could be used in order to administrate energy sources. The paper presents the process of model validation, along with a regression analysis, based in real-life data.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::944e55f3b817f44ae02a2fc7818dc5c6 https://doi.org/10.1109/cimsa.2009.5069932 Zobrazit plný text záznamu