Eventos Anais de eventos
COBEM 2021
26th International Congress of Mechanical Engineering
Multi-Step Wind Speed Forecasting Based on Multi-Stage Decomposition Approach
Submission Author:
Ramon Gomes da Silva , PR
Co-Authors:
Ramon Gomes da Silva, Sinvaldo Rodrigues Moreno, Matheus Henrique Dal Molin Ribeiro, Viviana Mariani, Leandro dos Santos Coelho
Presenter: Sinvaldo Rodrigues Moreno
doi://10.26678/ABCM.COBEM2021.COB2021-0022
Abstract
Wind energy is one of the sources which is still in development in Brazil, however, it already represents 17% of the National Interconnected System. Due to the high level of uncertainty and fluctuations in wind speed, prediction of wind speed with high accuracy is a challenging task. The contribution of this study proposes a framework that combines Singular Spectrum Analysis (SSA) and Variational Mode Decomposition (VMD) based on Machine Learning models to forecast the wind speed of a turbine in a wind farm at Parazinho city, Brazil, using a multi-step ahead forecasting strategy (10, 30, and 60 minutes ahead). The forecasting models of the wind speed time series are k-Nearest Neighbor and Support Vector Regression. The performance of the proposed forecasting models were evaluated by using mean absolute percentage error and root mean square error criteria. The VMD-SSA models outperform the SSA, VMD, and single models in all evaluated forecasting horizons, with a performance improvement that ranges within 0.20%-55.78%. Indeed, VMD--SSA is an efficient and accurate model for wind speed forecasting.
Keywords
Wind speed, Time series forecasting, Singular spectrum analysis, Variational mode decomposition, machine learning
