Multi-step wind speed prediction by combining a WRF simulation and an error correction strategy. (January 2021)

• Record Type: Journal Article
• Authors: Xu, Weifeng; Liu, Pan; Cheng, Lei; Zhou, Yong; Xia, Qian; Gong, Yu; Liu, Yini
• Is Part Of: Renewable energy. Volume 163(2021)
• Page Start: 772
• Page End: 782
• Publication Date: 2021-01
• Subjects: Wind speed prediction -- Weather research and forecasting simulation -- Error correction -- Variational mode decomposition -- Long short-term memory; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.renene.2020.09.032
• Languages: English
• ISSNs: 0960-1481

Abstract

Abstract: The accurate prediction of wind speed is important in satisfying the demands of power grids. However, the prediction of wind speed is challenging because of its randomness and volatility, especially in multi-step cases. This study proposes a novel multi-step wind speed prediction model combining a Weather Research and Forecasting (WRF) simulation and an error correction strategy. First, the WRF model is adopted to predict the wind speed. Variational Mode Decomposition (VMD) is then employed to mine features of the predicted wind speed using the WRF model. The Principal Component Analysis (PCA) method is next used to extract the main components and remove illusive components. Using these principal components and prediction error as the training dataset, Long Short-Term Memory (LSTM) is applied for error correction. The WRF-VMD-PCA-LSTM model is thus developed for the multi-step prediction of wind speed. In a case study of a wind farm located in Sichuan Province, China, the proposed WRF-VMD-PCA-LSTM model outperforms models to which it is compared. The results reveal that the VMD-PCA method effectively extracts features hidden in the numerical WRF output. The proposed model effectively improves the accuracy of multi-step wind speed prediction. Highlights: Features hidden in the numerical weather prediction output are extracted by a hybrid VMD-PCA method. Propose an error correction strategy to improve the prediction accuracy of numerical weather prediction. The proposed model is effective in multi-step wind speed prediction.