Eventos Anais de eventos
ENCIT 2020
18th Brazilian Congress of Thermal Sciences and Engineering
MACHINE LEARNING TECHNIQUES APPLIED TO ITAIPU STREAMFLOW FORECASTING
Submission Author:
Jorge Gustavo Sandoval Simão , SC
Co-Authors:
Jorge Gustavo Sandoval Simão, Gabriel Ribeiro, Viviana Mariani, Leandro dos Santos Coelho
Presenter: Jorge Gustavo Sandoval Simão
doi://10.26678/ABCM.ENCIT2020.CIT20-0785
Abstract
Time series forecasting has gained lots of attention recently. This is because many real-world phenomena can be modeled as time series. On the other hand, applications of machine learning models to the forecasting problem are gaining interest among researchers as well as the industry and energy systems. This work evaluates three machine models including Random Forest, Support Vector Regression and k-Nearest Neighbor applied to time series forecasting for the Itaipu’s streamflow case study. The results are presented in terms of different performance metrics (RMSE, RMSLE and MAE), where the Random Forest and k-Nearest Neighbor models outperform the Support Vector Regression to the Itaipu’s streamflow forecasting.
Keywords
Random Forest, support vectors regression, k-Nearest Neighbor, Time series forecasting
