计及风力资源的风电场出力研究  

Research on Output of a Wind Farm Considering Wind Resources

作　　者：曹建伟 陈文进 沈诚亮 张若伊 张认 刘皓明[3] CAO Jianwei;CHEN Wenjin;SHEN Chengliang;ZHANG Ruoyi;ZHANG Ren;LIU Haoming(State Grid Huzhou Power Supply Company,Huzhou Zhejiang 313000,China;State Grid Zhejiang Electric Power Co.,Ltd.,Hangzhou 310007,China;Hohai University,Nanjing 211100,China)

机构地区：[1]国网浙江省电力有限公司湖州供电公司,浙江湖州313000 [2]国网浙江省电力有限公司,杭州310007 [3]河海大学,南京211100

出　　处：《浙江电力》2022年第6期45-53,共9页Zhejiang Electric Power

基　　金：国网浙江省电力有限公司科技项目(5211UZ2000K4)。

摘　　要：新能源出力与其资源环境在时间和空间上具有复杂关联特性。对此,分析了不同资源环境条件下新能源发电的时空相关性,构建新能源差异化出力模型。首先,采用主成分分析法确定新能源场站的资源主成分,并与表征新能源场站运行特性的自然出力特性指标相结合,生成新能源场站特征数据;通过改进K-means算法对新能源场站进行聚类,获得资源时空相关的新能源发电集群。然后,根据集群内各新能源场站历史出力数据,通过聚类分析构建不同环境条件的新能源差异化出力模型。最后,利用中国东南某地区的风电场实际环境与出力监测数据进行仿真分析,结果证明所提方法提升了新能源发电集群出力特性的相关性,且构建的差异化出力模型的误差水平优于典型日法。The output of renewable power generation and its resources and environment are characterized by complex correlation in respect to time and space. The paper analyzes the spatiotemporal correlation of renewable energy under different resources and environmental conditions and builds differentiated output models of renewable energy power generation. Firstly,principal component analysis(PCA)is used to determine the principal components of the renewable energy sources in new energy stations. It combines with the natural output characteristic indexes that characterize the operating characteristics of new energy stations to generate their characteristics data. The improved Kmeans algorithm clusters the new energy stations to obtain the new energy generation clusters with the spatiotemporal correlation of resources. Secondly,based on the historical output data of each new energy station in the cluster,a new energy differential output model for different environmental conditions is constructed by cluster analysis. Finally,a simulation analysis is conducted using wind farms’ actual environmental and output monitoring data in southeast China. The results demonstrate that the proposed method has improved the correlation between the output characteristics of new energy generation clusters and the error level of the constructed differentiated output model is higher than that of the typical daily method.

关 键 词：新能源发电 资源相关 主成分分析 聚类算法 出力特性 

分 类 号：TM614[电气工程—电力系统及自动化]