Short-Term Wind Power Prediction Based on Wavelet Feature Arrangement and Convolutional Neural Networks Deep Learning

• Published in: IEEE transactions on industry applications Vol. 57; no. 6; pp. 6375 - 6384
• Main Authors: Peng, Xiaosheng, Li, Yinhuan, Dong, Lie, Cheng, Kai, Wang, Hongyu, Xu, QiyouXU, Wang, Bo, Liu, Chun, Che, Jianfeng, Yang, Fan, Li, Wenze
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: And feature arrangement; Artificial neural networks; Convolution; Convolutional neural networks; convolutional neural networks (CNN); Deep learning; Feature extraction; Frequencies; Neural networks; Numerical prediction; Numerical weather forecasting; parameter selection; Prediction models; Predictive models; Time-frequency analysis; Transforms; wavelet transform; Wavelet transforms; Wind power; Wind power generation; wind power prediction
• ISSN: 0093-9994; 1939-9367
• DOI: 10.1109/TIA.2021.3106887

Wind power prediction (WPP) has an important impact on the security and reliability operation of power grid after a large amount of wind power integration into the system. There are two main challenges in WPP: 1) Both numerical weather prediction (NWP) and wind power contain abundant frequency information. If these data are directly input to the prediction model, the connection between different frequency bands is difficult to be mined. 2) Wind power has strong randomness and volatility, so the nonlinear relationship between input and output is difficult to be reflected by traditional prediction models. To overcome the challenge, a novel short-term WPP model based on wavelet feature arrangement and convolutional neural networks (CNN) is proposed in the article. First, wavelet transform is applied to split the original NWP data and historical power data into multiple sets of different frequency components. Then, the features of different frequencies are arranged in various ways, named feature arrangement (FA), which are input into the CNN model for WPP, and finally, the prediction results are obtained. Two case studies demonstrated the effectiveness of the proposed novel WT-FA-CNN deep learning model for short-term WPP.