基于加权相似气象搜索的无地表辐照度光伏出力预测  

Photovoltaic Output Prediction Without Surface Irradiance Based on Weighted Similarity Meteorological Search

作　　者：杨家豪 张莲 王士彬 李蘅 肖远强 YANG Jiahao;ZHANG Lian;WANG Shibin;LI Heng;XIAO Yuanqiang(College of Electrical and Electronic Engineering,Chongqing University of Technology,Chongqing 400054,China;State Grid Chongqing Electric Power Company Shinan Power Supply Branch,Chongqing 401336,China)

机构地区：[1]重庆理工大学电气与电子工程学院,重庆400054 [2]国网重庆市电力公司市南供电分公司,重庆401336

出　　处：《湖南电力》2024年第5期87-94,共8页Hunan Electric Power

基　　金：重庆市教委科技项目(KJQN202001150)。

摘　　要：为解决光伏出力预测中地表辐照度数据缺失的问题,提出一种无地表辐照度的光伏出力预测方法。首先,在原有数据基础上增添天文辐射特征,考虑到该特征可能仍无法满足预测精度需求,进而引入相似气象数据下的出力数据作为另一增广特征。其次,提出对相似度算法进行特征加权的方法,通过D-S证据理论对斯皮尔曼相关系数、最大信息系数及随机森林特征重要性三种评分方式进行综合评分,得到各特征的权重系数,以进一步提高相似度算法的气象提取能力和准确性。最后,对欧氏距离和余弦相似度方法下的相似日搜索结果和相似时刻搜索结果进行了对比。宁夏某光伏电站的实例分析表明,加权的欧氏距离相似时刻搜索结果得到的预测效果最优,四季的平均准确率和合格率分别达到了0.889、0.944,实现了无地表辐照度光伏出力较为精准的预测。Aiming at the problem lacking of surface solar radiation(SSR)data when forecasting the photovoltaic(PV)power generation,a PV power generation forecast method without SSR information is proposed.First,the astronomical radiation feature is added on the original data.Considering that this feature may still not meet the prediction accuracy requirements,output data under similar meteorological data is introduced as another augmented feature.Second,the method of feature weighting is proposed for the similarity algorithm,and the weight coefficients of each feature are obtained by the synthetic scoring of three scoring methods of Spearman,maximum information coefficient,and the importance of random forest features through the D-S evidence theory,so as to extract the meteorological data and further improve the accuracy of the similarity algorithm.Finally,the similar day search results and similar hour search results under Euclidean distance and cosine similarity methods are compared.The study of a PV power plant in Ningxia shows that the weighted Euclidean distance similar hour search results obtain the optimal forecast performance,that the average accuracy rate and qualification rate of the four seasons reaches 0.889 and 0.944 respectively,promising a relatively good forecast result of PV output without the SSR information.

关 键 词：地表太阳辐射 光伏发电 预测 D-S证据理论 相似度算法 加权相似度算法 

分 类 号：TM714[电气工程—电力系统及自动化]