On Additive Gaussian Processes for Wind Farm Power Prediction

TL;DR

This paper explores additive Gaussian processes to model and predict wind farm power generation, revealing patterns that can improve control and decision-making in wind energy management.

Contribution

It introduces the use of additive Gaussian processes for population-level wind farm power prediction, capturing turbine-specific and farm-level variations.

Findings

Patterns in wind power generation are identified.

Additive Gaussian processes improve understanding of turbine and farm variations.

Predictions align with intuitive expectations of wind farm behavior.

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.