Automatic identification of wind turbine models using evolutionary multiobjective optimization. (March 2016)

• Record Type: Journal Article
• Authors: La Cava, William; Danai, Kourosh; Spector, Lee; Fleming, Paul; Wright, Alan; Lackner, Matthew
• Is Part Of: Renewable energy. Volume 87:Part 2(2016)
• Page Start: 892
• Page End: 902
• Publication Date: 2016-03
• Subjects: Wind energy -- System identification -- Genetic programming -- Multiobjective optimization; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.renene.2015.09.068
• Languages: English
• ISSNs: 0960-1481

Abstract

Abstract: Modern industrial-scale wind turbines are nonlinear systems that operate in turbulent environments. As such, it is difficult to characterize their behavior accurately across a wide range of operating conditions using physically meaningful models. Customarily, the models derived from wind turbine data are in 'black box' format, lacking in both conciseness and intelligibility. To address these deficiencies, we use a recently developed symbolic regression method to identify models of a modern horizontal-axis wind turbine in symbolic form. The method uses evolutionary multiobjective optimization to produce succinct dynamic models from operational data while making minimal assumptions about the physical properties of the system. We compare the models produced by this method to models derived by other methods according to their estimation capacity and evaluate the trade-off between model intelligibility and accuracy. Several succinct models are found that predict wind turbine behavior as well as or better than more complex alternatives derived by other methods. We interpret the new models to show that they often contain intelligible estimates of real process physics. Highlights: Accurate, succinct models of wind turbine dynamics are identified from normal operating data. A novel evolutionary multi-objective optimization system is described. The proposed method produces physically meaningful models without prior knowledge of the system. The method is bench-marked against other modeling techniques.