Wind Turbine Modeling With Data-Driven Methods and Radially Uniform Designs

• Published in: IEEE transactions on industrial informatics Vol. 12; no. 3; pp. 1261 - 1269
• Main Authors: Tan, Matthias, Zijun Zhang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.06.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Acceleration; Algorithm design and analysis; Algorithms; Computation; Computational modeling; Data mining; Data models; data processing; Datasets; Design analysis; Mathematical models; Neural networks; Prediction algorithms; Regression; Samplers; Training; Training data; wind energy; wind power prediction; Wind turbines; neural networks (NN); wind power prediction; wind energy; Data mining; data processing

This paper proposes a radially uniform (RU) design to sample representative datasets from a large volume of wind turbine data to build accurate data-driven models. The sampling capability and computational complexity are theoretically analyzed. It is shown that the RU design is representative of the...