An Ensemble Model of Wind Speed Forecasting Based on Variational Mode Decomposition and Bare-Bones Fireworks Algorithm

Wind energy is one of the fastest growing renewable energy sources. Wind speed forecasting is essential to enhance the utilization of wind energy. Various prediction models have been developed to improve the prediction accuracy of wind speed. However, wind speed time series has nonlinearity, fluctuation, and intermittence, which makes the prediction difficult. Existing prediction models ignore data decomposition and feature reduction and suffer from the deficiency of individual models. This paper proposes a novel ensemble prediction model, which integrates data preprocessing, feature selection, parameter optimization, three intelligent prediction models, and an ensemble strategy. To improve prediction performance, a highly efficient optimization algorithm is applied to determine the individual models' optimal parameters. Furthermore, partial least square regression is used to calculate combination weight. Additionally, two 10min datasets from the National Renewable Energy Laboratory (NREL) are employed for one-step-ahead prediction. Among the involved models, the proposed model can obtain the best prediction accuracy. The experimental results indicate that the mean absolute percent errors of the proposed model are 7.97% and 9.99%, which are lower than the comparison methods. Pearson's test reveals that the proposed approach can have the strongest association between the actual data and the prediction results.