Bayesian Modelling of Multivalued Power Curves from an Operational Wind Farm

TL;DR

This paper introduces a probabilistic mixture model approach to accurately capture multivalued power curves caused by curtailments in wind turbine data, improving analysis and monitoring of wind farm performance.

Contribution

It proposes a novel population-based mixture regression model to infer multivalued power relationships, addressing limitations of traditional regression methods in curtailment scenarios.

Findings

Model accurately represents multivalued power data.

Effective in capturing curtailment effects across turbines.

Improves monitoring and planning for wind farms.

Abstract

Power curves capture the relationship between wind speed and output power for a specific wind turbine. Accurate regression models of this function prove useful in monitoring, maintenance, design, and planning. In practice, however, the measurements do not always correspond to the ideal curve: power curtailments will appear as (additional) functional components. Such multivalued relationships cannot be modelled by conventional regression, and the associated data are usually removed during pre-processing. The current work suggests an alternative method to infer multivalued relationships in curtailed power data. Using a population-based approach, an overlapping mixture of probabilistic regression models is applied to signals recorded from turbines within an operational wind farm. The model is shown to provide an accurate representation of practical power data across the population.