Achieving Skilled and Reliable Daily Probabilistic Forecasts of Wind Power at Subseasonal-to-Seasonal Timescales over France

2025-11-20

AI Summary

This study addresses the need for daily probabilistic forecasting of French wind power generation at subseasonal-to-seasonal (S2S) timescales (1–46 days), supporting grid stability, supply-demand balancing, and market risk management. We propose an end-to-end forecasting framework that integrates ECMWF S2S meteorological forecasts, employs a physically constrained wind power conversion model, and applies ensemble-based bias correction and dispersion adjustment for post-processing. Crucially, our method operates without spatial or temporal aggregation. Within the 15–46-day forecast horizon, it achieves a 50% improvement in the Continuous Ranked Probability Skill Score (CRPSS) over climatological benchmarks, while reducing calibration error—measured by the CRPS decomposition—to near zero. This represents the first S2S wind power forecasting framework to simultaneously attain high forecast skill and near-perfect probabilistic calibration. The approach establishes a generalizable technical paradigm for medium- to long-range probabilistic renewable energy forecasting.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Accurate and reliable wind power forecasts are crucial for grid stability, balancing supply and demand, and market risk management. Even though short-term weather forecasts have been thoroughly used to provide short-term renewable power predictions, forecasts involving longer prediction horizons still need investigations. Despite the recent progress in subseasonal-to-seasonal weather probabilistic forecasting, their use for wind power prediction usually involves both temporal and spatial aggregation achieve reasonable skill. In this study, we present a forecasting pipeline enabling to transform ECMWF subseasonal-to-seasonal weather forecasts into wind power forecasts for lead times ranging from 1 day to 46 days at daily resolution. This framework also include post-processing of the resulting power ensembles to account for the biases and lack of dispersion of the weather forecasts. We show that our method is able to outperform a climatological baseline by 50 % in terms of both Continuous Ranked Probability Skill Score and Ensemble Mean Squared Error while also providing near perfect calibration of the forecasts for lead times ranging from 15 to 46 days.

Problem

• Developing skilled probabilistic wind power forecasts at subseasonal-to-seasonal timescales
• Overcoming limitations of temporal and spatial aggregation in long-term forecasting
• Addressing biases and dispersion issues in weather-to-power conversion models

Innovation

• Transforms ECMWF weather forecasts into wind power predictions
• Post-processes power ensembles to correct forecast biases
• Achieves 50% improvement over climatological baseline accuracy