On Additive Gaussian Processes for Wind Farm Power Prediction
🤖 AI Summary
This work proposes a joint modeling approach based on additive Gaussian processes to address the challenge of simultaneously capturing both individual heterogeneity and collective patterns among wind turbines within a wind farm. Within a Bayesian nonparametric framework, the method explicitly disentangles turbine-specific personalized effects from farm-wide shared characteristics, thereby revealing power generation dynamics consistent with underlying physical mechanisms. By coherently integrating individual and group-level contributions, the model not only enhances predictive accuracy but also provides more reliable decision support for wind farm control and dispatch operations.
Application Category
📝 Abstract
Population-based Structural Health Monitoring (PBSHM) aims to share information between similar machines or structures. This paper takes a population-level perspective, exploring the use of additive Gaussian processes to reveal variations in turbine-specific and farm-level power models over a collected wind farm dataset. The predictions illustrate patterns in wind farm power generation, which follow intuition and should enable more informed control and decision-making.
Problem
Research questions and friction points this paper is trying to address.
Additive Gaussian Processes
Wind Farm Power Prediction
Population-based Structural Health Monitoring
Turbine-specific Modeling
Power Generation Patterns
Innovation
Methods, ideas, or system contributions that make the work stand out.
additive Gaussian processes
population-based modeling
wind farm power prediction
turbine-specific variation
structural health monitoring
🔎 Similar Papers
No similar papers found.
