将光伏预测拆分为气象与电站特性两阶段，提升精度与误差可解释性。
Two-Stage Photovoltaic Forecasting: Separating Weather Prediction from Plant-Characteristics
- 分两阶段建模：先预测气象参数，再结合电站特征修正输出。
- 用卫星数据替代天气预报，使误差降低11%至68%。
- 误差分布符合广义双曲与t分布，适合随机优化场景。
多个能源管理应用依赖准确的光伏发电预测。常用指标如平均绝对误差或均方根误差忽略了误差分布细节，不利于随机优化。现有方法多直接使用天气预报作为输入，未分析误差来源。为此，本文将预测过程分解为两个部分：一是基于卫星观测的气象预报模型，用于预测太阳辐照度、温度等环境参数；二是基于历史发电数据训练的神经网络集成模型，捕捉面板朝向、温升影响、遮挡等站点特异性因素。研究采用覆盖美国的高分辨率快速更新数值天气预报模型作为黑箱气象预测工具，并在历史功率数据上训练植物特征模型。结果表明，当使用天气预报而非基于卫星的地面真实气象数据作为理想预报时，两个选定光伏系统的平均绝对误差分别增加11%和68%。跨预报时长的预测误差分布可通过广义双曲分布和Student's t分布良好拟合。
原文摘要 · Abstract (English)
Several energy management applications rely on accurate photovoltaic generation forecasts. Common metrics like mean absolute error or root-mean-square error, omit error-distribution details needed for stochastic optimization. In addition, several approaches use weather forecasts as inputs without analyzing the source of the prediction error. To overcome this gap, we decompose forecasting into a weather forecast model for environmental parameters such as solar irradiance and temperature and a plant characteristic model that captures site-specific parameters like panel orientation, temperature influence, or regular shading. Satellite-based weather observation serves as an intermediate layer. We analyze the error distribution of the high-resolution rapid-refresh numerical weather prediction model that covers the United States as a black-box model for weather forecasting and train an ensemble of neural networks on historical power output data for the plant characteristic model. Results show mean absolute error increases by 11% and 68% for two selected photovoltaic systems when using weather forecasts instead of satellite-based ground-truth weather observations as a perfect forecast. The generalized hyperbolic and Student's t distributions adequately fit the forecast errors across lead times.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。