面向日前光伏功率预测的基于人工智能的决策支持流程
An AI-Based Decision-Support Pipeline for Day-Ahead Photovoltaic Forecasting
查看机构详情
- University of Southampton（南安普顿大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究针对新部署站点数据不足导致的日前光伏预测难题，开发了防数据泄露的环境AI堆叠流程，在英国充电站站点验证了其优于基准模型的预测性能。
中文摘要 AI 辅助
低碳能源系统需要可靠的光伏（PV）预测，但新部署的站点通常拥有短期且不完善的记录，这使得标准日前预测变得困难：持续性基准和物理基准可能对校准和时间戳对齐敏感，而单一机器学习模型可能仅捕获数据中的一种结构，并在非时间验证下夸大性能。我们在英国的一个充电站站点研究该问题，此处的PV预测误差会影响充电可用性、存储调度和下游控制。利用实测逆变器输出和公开的气象输入，我们开发了一种面向部署的环境人工智能（AI）流程，用于日前小时级PV预测。该流程校正时间戳约定，构建防数据泄露的太阳几何和晴空指数特征，添加短期大气上下文，并通过经验证学习的堆叠方法组合互补预测器。相较于智能持续性基准（一种利用预期晴空辐照度调整近期PV输出的晴空基准），最优集成模型在随机日块评估下将昼间归一化均方根误差（RMSE）降低约32%，在更严格的滚动原点评估协议下降低9%；相较于最强的单一机器学习基准，其昼间RMSE分别降低6.6%和6.4%。结果表明，结合物理知识的堆叠方法可利用有限站点数据支持PV预测，但其价值取决于模型类别、评估协议和部署场景。
英文摘要
Reliable photovoltaic (PV) forecasts can support low-carbon energy systems, but deployed sites may have only short and incomplete records. Physical and hybrid methods can be sensitive to weather inputs, calibration, and timestamp-alignment, while individual machine learning models may capture different parts of the forecasting problem. We study hourly day-ahead PV forecasting at a United Kingdom charging station using one year of inverter measurements, with 9.25% of hours missing. The pipeline checks timestamp-alignment, derives solar and clearness features, adds short-term weather context, and combines five complementary models using non-negative least squares stacking, with the combination fitted only on validation observations. We compare against smart persistence, a weather-scaled baseline that carries the previous day's PV behaviour forward using target-day irradiance. With retrospective weather, the combined model reduces daylight normalised root mean square error (RMSE) by 31.2% under random day-fold evaluation and by 2.9% under rolling-origin evaluation, although the latter improvement is not robust across days. It also improves by 3.0% over the single model selected from validation performance. Replacing retrospective weather with a public product sampled at a constant 24-hour lead increases daylight RMSE by 13.1% and 4.2% under the two protocols, while retaining positive skill over smart persistence.
