Métodos lineares e não-lineares aplicados à previsão do consumo de energia elétrica no Brasil

Loading...
Thumbnail Image

Journal Title

Journal ISSN

Volume Title

Publisher

Universidade Federal de Juiz de Fora (UFJF)

DOI

Abstract

This work contributes to a comparative study of the performance of time series predictive methodologies in forecasting the monthly consumption of electricity in the Brazilian market. The models used were Exponecial Smoothing, Box & Jenkins and Artificial Neural Networks.The performance of the models was quantified through Root Mean Squared Error (RMSE) metric. The results show the prediction superiority of Artificial Neural Networks model in relation to the others.

Description

Citation

Endorsement

Review

Supplemented By

Referenced By

Creative Commons license

Except where otherwise noted, this item's license is described as Acesso Aberto