R$^2$Energy: A Large-Scale Benchmark for Robust Renewable Energy Forecasting under Diverse and Extreme Conditions

2026-02-17

AI Summary

This study addresses the insufficient robustness of existing renewable energy forecasting models under extreme weather conditions, which poses a threat to power grid stability. The authors construct a high-fidelity wind and solar power forecasting benchmark encompassing 902 sites across four Chinese provinces and over 10.7 million hours of data. They propose a standardized input mechanism based on numerical weather prediction (NWP) and an evaluation paradigm that prevents information leakage. Additionally, they introduce expert-annotated extreme weather event labels and a region- and scenario-specific evaluation framework. Their analysis reveals, for the first time, a systematic “robustness gap” in model performance under extreme conditions, demonstrating that meteorological information fusion strategies are more critical to reliability than model complexity. This work establishes a reproducible and fair evaluation standard for safety-critical power systems.

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The rapid expansion of renewable energy, particularly wind and solar power, has made reliable forecasting critical for power system operations. While recent deep learning models have achieved strong average accuracy, the increasing frequency and intensity of climate-driven extreme weather events pose severe threats to grid stability and operational security. Consequently, developing robust forecasting models that can withstand volatile conditions has become a paramount challenge. In this paper, we present R$^2$Energy, a large-scale benchmark for NWP-assisted renewable energy forecasting. It comprises over 10.7 million high-fidelity hourly records from 902 wind and solar stations across four provinces in China, providing the diverse meteorological conditions necessary to capture the wide-ranging variability of renewable generation. We further establish a standardized, leakage-free forecasting paradigm that grants all models identical access to future Numerical Weather Prediction (NWP) signals, enabling fair and reproducible comparison across state-of-the-art representative forecasting architectures. Beyond aggregate accuracy, we incorporate regime-wise evaluation with expert-aligned extreme weather annotations, uncovering a critical ``robustness gap'' typically obscured by average metrics. This gap reveals a stark robustness-complexity trade-off: under extreme conditions, a model's reliability is driven by its meteorological integration strategy rather than its architectural complexity. R$^2$Energy provides a principled foundation for evaluating and developing forecasting models for safety-critical power system applications.

Problem

• renewable energy forecasting
• extreme weather
• robustness
• grid stability
• NWP-assisted forecasting

Innovation

• robust forecasting
• renewable energy
• extreme weather
• NWP-assisted prediction
• benchmark dataset