一种适用于单/多光伏电站的迁移超短期光伏预测建模框架
TRANSFER ULTRA-SHORT TERM PHOTOVOLTAIC PREDICTION MODELING FRAMEWORK FOR SINGLE/MULTIPLE PHOTOVOLTAIC POWER STATIONS
任密蜂 1王家辉 1叶泽甫 2朱竹军 2阎高伟1
作者信息
- 1. 太原理工大学电气与动力工程学院,太原 030024
- 2. 山西格盟中美清洁能源研发中心有限公司,太原 030000
- 折叠
摘要
针对新建电站的历史数据量有限,且不同时段光伏数据的分布存在较大差异的问题,构建一种适用于单/多光伏电站的迁移超短期光伏预测建模框架.首先,为充分考量光伏序列的不确定性及数值天气预报的固有偏差,提出一种基于加权滚动时间窗聚类方法,同时为避免维度过高问题并强化天气类型与光伏发电功率之间的映射关系,提出类内外特征加权结构保持降维算法;其次,通过采用测地线流式核积分完成数据分布对齐,减小样本分布差异对单/多电站模型鲁棒性的影响;最后,采用梯度增强决策树建立光伏功率预测模型,实现光伏功率预测精度的提升.采用公开数据集PVOD验证了所提算法的有效性.
Abstract
To solve the problem that the historical data of new photovoltaic power stations are limited and the distribution of photovoltaic data in different periods of time is quite different,a transfer ultra-short-term photovoltaic prediction modeling framework for single/multiple photovoltaic power stations is presented.First,a weighted rolling time window clustering method based on a weighted structure preserving dimensionality reduction algorithm with inside and outside features is presented to fully consider the uncertainty of photovoltaic series and the inherent bias of numerical weather prediction.Secondly,geodesic flow kernel is used to integrate infinite subspaces to simulate the gradient process of the distribution of photovoltaic data,thus completing the data distribution alignment.Finally,a photovoltaic power prediction model is built using gradient boosting decision tree.The validity of the proposed algorithm is verified by using the public dataset PVOD.
关键词
光伏电站/预测/迁移学习/光伏功率超短期预测/结构保持/测地线流式核Key words
PV power station/forecasting/transfer learning/ultra-short term prediction of photovoltaic power/structure preservation/geodesic flow kernel引用本文复制引用
基金项目
国家自然科学基金(61973226)
山西省自然科学基金(201901D21108320210302123189)
格盟集团科技创新基金(2021-07)
出版年
2024
NETL
NSTL
万方数据