Accurate wind speed forecasting is of great significance to ensure the safe utilization of wind power. However, the randomness and volatility nature of wind speed give rise to an enormous challenge to the precision of wind speed forecasting. Combining the data preprocess technology, feature selection method, forecasting model, optimization algorithm and data postprocessing technology, the complete ensemble empirical mode decomposition with adaptive noise-least absolute shrinkage and selection operator-quantile regression neural network (CEEMDAN-LASSO-QRNN) model is developed to preform multistep wind speed probabilistic forecasting. Within the proposed model, CEEMDAN technology is firstly employed to decompose original wind speed timeseries into several subsequences. For each subsequence, the explanatory variables constructed by a hybrid multistep forecasting strategy are selected by LASSO regression. Subsequently, QRNN forecasting models are established to obtain multistep conditional quantiles predictions for entire subsequences. Ultimately, the aggregated quantiles are served as the samples to fit approximate distribution through kernel density estimation (KDE), thus obtaining the probability density function, further achieving probabilistic predictions, interval predictions and point predictions. The case studies including four real datasets are provided to validate the dependability and feasibility of the proposed model. Experimental results indicate higher accuracy and robustness of the proposed model occur in multistep wind speed probabilistic forecasting. © 2022 Elsevier Ltd
Bibliographical noteThe authors would like to thank the National Natural Science Foundation of China (Nos. 71771073 and 72171068) and the Anhui Provincial Natural Science Foundation for Distinguished Young Scholars (No. 2108085J36).
- CEEMDAN decomposition
- Cooperative ensemble method
- Multistep probabilistic forecasting
- Wind speed forecasting