Probabilistic modelling of wind turbine power curves with application of heteroscedastic Gaussian Process regression

TLDR

Accurate wind turbine power curve models are sought to improve performance assessment, operational insight, and fault detection. This study proposes using a heteroscedastic Gaussian Process to model wind turbine power curves. The heteroscedastic GP removes the need for a parametric form, automatically quantifies prediction variance, and, within a Bayesian framework, guards against over‑fitting and handles noisy data. On operational turbine data, the model achieves <1 % normalized mean‑squared error and higher likelihoods than a homoscedastic counterpart.

Abstract

There exists continued interest in building accurate models of wind turbine power curves for better understanding of performance or assessment of the condition of the turbine or both. Better predictions of the power curve allow increased insight into the operation of the turbine, aid operational decision making, and can be a key feature of online monitoring and fault detection strategies. This work proposes the use of a heteroscedastic Gaussian Process model for this task. The model has a number of attractive properties when modelling power curves. These include, removing the need to specify a parametric functional form for the power curve and automatic quantification of the variance in the prediction. The model exists within a Bayesian framework which exhibits built-in protection against over-fitting and robustness to noisy measurements. The model is shown to be effective on data collected from an operational wind turbine, returning accurate mean predictions (<1% normalised mean-squared error) and higher likelihoods than a corresponding homoscedastic model.