Probabilistic Wind Power Forecasting with Tree-Based Machine Learning and Weather Ensembles

TL;DR

This paper develops probabilistic wind power forecasts using tree-based machine learning and weather ensembles, demonstrating significant improvements over traditional methods and identifying the most effective probabilistic approach.

Contribution

It introduces a novel combination of gradient boosting trees with weather ensembles for probabilistic wind power forecasting, comparing three advanced probabilistic methods.

Findings

Machine learning methods reduce MAE by up to 53% and 33%.

Conditional diffusion yields the best probabilistic and point estimates.

Weather ensembles improve forecast accuracy by up to 23%.

Abstract

Accurate production forecasts are essential to continue facilitating the integration of renewable energy sources into the power grid. This paper illustrates how to obtain probabilistic day-ahead forecasts of wind power generation via gradient boosting trees using an ensemble of weather forecasts. To this end, we perform a comparative analysis across three state-of-the-art probabilistic prediction methods-conformalised quantile regression, natural gradient boosting and conditional diffusion models-all of which can be combined with tree-based machine learning. The methods are validated using four years of data for all wind farms present within the Belgian offshore zone. Additionally, the point forecasts are benchmarked against deterministic engineering methods, using either the power curve or an advanced approach incorporating a calibrated analytical wake model. The experimental results show that the machine learning methods improve the mean absolute error by up to 53% and 33% compared to the power curve and the calibrated wake model. Considering the three probabilistic prediction methods, the conditional diffusion model is found to yield the best overall probabilistic and point estimate of wind power generation. Moreover, the findings suggest that the use of an ensemble of weather forecasts can improve point forecast accuracy by up to 23%.