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

Zhi Sheng, Yuan Yuan+2 more|arXiv (Cornell University)|Feb 17, 2026

Energy Load and Power Forecasting被引用 0

一句话总结

R2Energy 提供一个覆盖中国 902 个风电/光伏站点的大规模、无泄漏的 NWP 辅助预测基准，并进行分 regimes 的极端事件注释以评估超出平均准确性的鲁棒性。

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.

研究动机与目标

• 在气候驱动极端事件增多的背景下，促进电网可靠性所需的鲁棒可再生能源预测。
• 提供一个大规模、多样化、来自多源的数据集，以在不同气候区域与极端事件条件下评估模型。
• 建立标准化、无泄漏的预测协议，以实现跨模型公平对比。
• 引入分 regime 的评估，结合专家对极端天气的注释，以揭示鲁棒性差距。

提出的方法

• 将可再生能源预测视为一个带有标准化未来天气信号的 NWP 辅助映射任务。
• 使用无泄漏协议，确保所有模型在不同预测区间获得相同的未来 NWP 访问权限。
• 引入 Qualification Rate（Q）来衡量预测的行业安全合规性。
• 采用带 CMA 基于极端天气注释的分 regime 评估（暴雨和热浪等级 1–3）。
• 比较覆盖统计/物理基线、自回归 RNN 与非自回归 Transformer/CNN/MLP 架构的 16 种模型。

Figure 1. Overall framework of R 2 Energy.

实验结果

研究问题

• RQ1 当在中国多样气候区域预测未来 NWP 信号下的可再生发电量时，模型的表现如何？
• RQ2 在极端天气事件下，平均准确度与可靠性之间的鲁棒性差距有多大？
• RQ3 哪些预测策略（架构与气象数据整合）对在压力下的可靠性影响最大？
• RQ4 提出的无泄漏协议如何影响自回归与非自回归模型之间的公平比较？

主要发现

• R2Energy 使用 901/902 个站点的 10.7 百万小时记录对 16 种模型进行评估，揭示鲁棒性与复杂度之间的权衡：在压力下的可靠性更多由气象数据整合策略驱动，而非架构的复杂性。
• 自回归模型（如 GRU）通过在每一步注入未来 NWP 信号来锚定轨迹，表现出稳定性。
• 基于 Transformer 的模型在嘈杂的情景下敏感性更高、稳定性较差，尤其在风场波动较大的情况下。
• 以分 regime 的极端情景评估揭示在暴雨和热浪条件下功率分布的非线性偏移，强调了平均指标的局限性。
• Qualification Rate（Q）提供了与行业 dispatch 安全相关的指标，能够补充传统的 MAE/RMSE 指标。
• 该框架强调，鲁棒性能需要正确整合未来天气背景并进行分 regime 测试，而不仅仅是提升模型容量。

Figure 2. Intra-day and seasonal variability across the wind and solar datasets. The top row (a) illustrates the average wind speed (m/s) variations between daytime (07:00–18:00, solid bars) and nighttime (dotted bars). The bottom row (b) compares solar radiation (W/m²) during peak midday hours (11: