Short-term wind speed syntheses correcting forecasting model and its application

• Published in: International journal of electrical power & energy systems Vol. 49; pp. 264 - 268
• Main Authors: Nan, Xiaoqiang, Li, Qunzhan, Qiu, Daqiang, Zhao, Yuanzhe, Guo, Xinxin
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.07.2013; Elsevier
• Subjects: Applied sciences; Bias; Bias correction; Direct energy conversion and energy accumulation; Electrical engineering. Electrical power engineering; Electrical power engineering; Empirical orthogonal function; Energy; Errors; Exact sciences and technology; Forecasting; Mathematical models; Miscellaneous; Natural energy; Neural networks; Orthogonal functions; Prediction bias; Syntheses correcting forecasting model; Time series; Wind energy; Wind speed; Wind speed forecasting; Bias correction; Empirical orthogonal function; Syntheses correcting forecasting model; Prediction bias; Wind speed forecasting; Short term; Time series; Wind velocity; Regression analysis; Neural network; Backpropagation algorithm; Wind energy; Orthogonal function; Error correction
• ISSN: 0142-0615; 1879-3517
• DOI: 10.1016/j.ijepes.2013.01.014

► Wind speed combination forecasting model is proposed. ► Empirical orthogonal function, forecasting bias correction method, is proposed. ► Syntheses correcting forecasting model is proposed. ► The feasibility, proposed method, is verified. Wind speed prediction is important to cope with problem that large scale wind power is integrated into grid. A kind of combination forecasting model composed of time series and BP neural network prediction model for short-term wind speed forecasting is proposed. Then, the main causes of speed prediction error is analyzed in this paper. A wind speed forecasting bias correction method on Empirical Orthogonal Function (EOF) is proposed. Wind speed prediction error can be decomposed by EOF, by which the main components of error are got. Then, bias correction mode can be built by regression analysis. Then, syntheses correcting forecasting model is proposed, which consists of combination forecasting model and prediction bias correcting model. The model can be more accurately used in the short-time wind speed forecasting.