A complexity-trait-driven rolling decomposition-reconstruction-ensemble model for short-term wind power forecasting

Abstract

In order to improve the accuracy of the short-term wind power forecasting, a novel complexity-trait-driven rolling decomposition-reconstruction-ensemble forecasting model is proposed to predict short-term wind power. In this model, four steps are involved, i.e., data decomposition, mode reconstruction, component prediction and ensemble prediction, which are all driven by complexity trait. In addition, rolling mechanism is applied to the decomposition-reconstruction-ensemble model to solve the problem of the misuse of future information. For verification, the proposed model is used to predict the total wind power with 5-minute interval data. The empirical result demonstrates that the proposed model has better prediction performance than the benchmark models. Compared with the benchmark models, the average improvement percentage of the proposed model is 46.819%, in terms of the mean absolute percentage error. This indicates that the proposed complexity-trait-driven rolling decomposition-reconstruction-ensemble model can be used as an effective tool for short-term wind power forecasting.