Probabilistic Prediction of Regional Wind Power Based on Spatiotemporal Quantile Regression

• Published in: IEEE transactions on industry applications Vol. 56; no. 6; pp. 6117 - 6127
• Main Authors: Yu, Yixiao, Han, Xueshan, Yang, Ming, Yang, Jiajun
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Convolutional neural network (CNN); Correlation; Feature extraction; hybrid neural network (HNN); long short-term memory (LSTM) network; Neural networks; Nonlinearity; Power systems; Prediction models; Predictive models; Probabilistic logic; probabilistic prediction; QR algorithms; Quantiles; regional wind power prediction; Regression models; spatiotemporal quantile regression (SQR); Statistical analysis; Wind farms; Wind power; Wind power generation
• ISSN: 0093-9994; 1939-9367
• DOI: 10.1109/TIA.2020.2992945

Different from power prediction for a single wind farm, the regional wind power prediction is to predict the total power of multiple wind farms located in the specific region. The regional wind power prediction involves more data that implicate abundant information on spatiotemporal correlations and nonlinearity. So that addressing the massive data and extracting the representative features became the crucial issues to construct an effective regional wind power prediction model. This article proposes a spatiotemporal quantile regression (QR) algorithm to perform the short-term nonparametric probabilistic prediction of regional wind power, incorporating the advantages of the hybrid neural network (HNN) and QR. In the approach, the high-dimensional input data are reorganized into a feature graph that is ready for feature extraction by the HNN. Therefore, the advantages of HNN can be utilized to extract the representative features and construct nonlinear regression models. Meanwhile, by following the QR rules, the model obtains quantiles and perform probabilistic prediction. By properly addressing the explanatory variable selection issue, the approach provides a specific solution for regional wind power probabilistic prediction with the massive input data. The test results in a region with ten wind farms demonstrate the effectiveness of the proposed approach.