Short-Horizon Prediction of Wind Power: A Data-Driven Approach

• Published in: IEEE transactions on energy conversion Vol. 25; no. 4; pp. 1112 - 1122
• Main Authors: Kusiak, A, Zijun Zhang
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2010; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computation; Data mining; Direct power generation; evolutionary strategy (ES) algorithm; exponential smoothing; Mathematical models; Neural networks; neural networks (NNs); Power generation; power prediction; Power system modeling; Predictive models; Smoothing; Smoothing methods; time-series model; Wind energy; Wind energy generation; Wind forecasting; Wind power; Wind power generation; Wind speed; wind speed prediction; Wind turbines
• ISSN: 0885-8969; 1558-0059
• DOI: 10.1109/TEC.2010.2043436

This paper discusses short-horizon prediction of wind speed and power using wind turbine data collected at 10 s intervals. A time-series model approach to examine wind behavior is studied. Both exponential smoothing and data-driven models are developed for wind prediction. Power prediction models are established, which are based on the most effective wind prediction model. Comparative analysis of the power predicting models is discussed. Computational results demonstrate performance advantages provided by the data-driven approach. All computations reported in the paper are based on the data collected at a large wind farm.