Highlights
- •
-
A model of wind power curve is developed from industrial data.
- •
-
Wind power and speed data is clustered.
- •
-
Support vector machine algorithm is applied to construct the model.
- •
-
The model captures dynamic behavior of the wind turbine.
- •
-
Computational results demonstrate effectiveness of the proposed approach.
Abstract
Model of a power curve allows to analyze performance of a wind turbine and compare it with other turbines. An approach based on centers of data partitions and data mining is proposed to construct such a model. Wind speed range is partitioned into intervals for which centers are computed. The centers are regarded as representative samples in modeling. A support vector machine algorithm is used to build a power curve model. Computational results have demonstrated that the model reflects dynamic properties of a power curve. In addition it is accurate and efficient to generate. The model accuracy has been tested with industrial wind energy data.
Keywords
- Wind turbine power curve;
- Partition centers;
- Data mining;
- Support vector machine
© 2016 Elsevier Ltd. All rights reserved.
Be the first to comment