基于分布式光伏网格化负荷预测的弹性调度新模式探索实践

Exploration and Practice of a New Elastic Scheduling Model Based on Distributed Photovoltaic Grid Load Prediction

提出一种基于空间相关性和改进天气标签的分布式光伏出力预测方法,对分布式光伏线路进行梳理,建立与集中式光伏站的空间相关性分组,结合预测日的天气和改进后的天气映射,依托集中式光伏站自身预测模型,预测多天气标签下出力曲线,通过欧式距离算法选择最优曲线,最后根据经验公式,得到待预测分布式光伏出力。采用改进天气标签的出力预测模型,实现特殊情况下分布式光伏微调节能力的测算和检修计划的优化,促进基于分布式光伏网格化负荷预测的弹性调度新模式探索实践。

This paper proposes a distributed photovoltaic output prediction method based on spatial correlation and improved weather label.The distributed photovoltaic lines were sorted out,and the spatial correlation groups with the centralized photovoltaic stations were established.Combined with the weather of the forecast day and the improved weather mapping,the output curve under the multi-weather label was predicted by relying on the forecast model of the centralized photovoltaic stations.The optimal curve was selected by the Euclidean-distance algorithm,and finally the distributed photovoltaic output to be predicted was obtained by empirical formula.The output prediction model with improved weather label was adopted to calculate the distributed photovoltaic fine-tuning node capacity and optimize the maintenance plan under special circumstances,so as to explore and practice a new elastic scheduling model based on distributed photovoltaic grid load prediction.