Intelligent models for the power curves of small wind turbines

• Published in: 2016 International Conference on Cogeneration, Small Power Plants and District Energy (ICUE) pp. 1 - 5
• Main Authors: Veena, R., Femin, V., Mathew, S., Petra, I., Hazra, J.
• Format: Conference Proceeding
• Language: English
• Published: Asian Institute of Technology 01.09.2016
• Subjects: Artificial Neural network; Artificial neural networks; Computational modeling; Gradient Boosting Machine; k-Nearest Neighbors; Small wind turbines; Support Vector Machine; Support vector machines; Training; Wind speed; Wind turbines
• DOI: 10.1109/COGEN.2016.7728965

Along with the rapid expansion of the MW sized big wind turbine sector, the small wind turbine industry is also growing. Understanding the power response of these systems to the variations in wind velocity is essential for the optimal selection and efficient management of these turbines. This is defined by the power curves of wind turbines. In this paper, we propose nonparametric models for the power curves of two small wind turbines of 50 kW and 2.5 kW rated capacities, based on the manufacturer power curve. Four different machine learning methods viz. Artificial Neural Network (ANN), Support Vector Machines (SVM), k-Nearest Neighbors (KNN) and Gradient Boosting Machines (GBM) were used for the modeling. The accuracies of these models are validated by estimating the error between the model output and the field observations from these turbines. With the lowest NRMSE values of 0.16 and 0.12, ANN-based models are found to be more reliable in defining the velocity-power performances of the turbines.