基于敏感气象特征因子筛选与优化组合的短期风电功率预测  

Short-term Wind Power Prediction Based on Combination of Screening and Optimizing Sensitive Meteorological Characteristics

作　　者：马伟 乔颖[1] 鲁宗相[1] 李佳明[1] 孙书鑫 周强 MA Wei;QIAO Ying;LU Zongxiang;LI Jiaming;SUN Shuxing;ZHOU Qiang(State Key Laboratory of Power System and Generation Equipment(Tsinghua University),Haidian District,Beijing 100084,China;Engineering Research Center for Renewable Energy Power Generation and Grid Technology(Xinjiang University),Ministry of Education,Urumqi 830047,Xinjiang Uygur Autonomous Region,China;State Grid Gansu Electric Power Research Institute,Lanzhou 730050,Gansu Province,China)

机构地区：[1]电力系统及发电设备控制和仿真国家重点实验室(清华大学),北京市海淀区100084 [2]可再生能源发电与并网技术教育部工程研究中心(新疆大学),新疆维吾尔自治区乌鲁木齐市830047 [3]国网甘肃省电力公司电力科学研究院,甘肃省兰州市730050

出　　处：《电网技术》2023年第7期2897-2904,共8页Power System Technology

基　　金：国家电网有限公司总部科技项目“应用于新能源场群调度辅助决策的数字孪生关键技术研究资助”(4000-202033049A-0-0-00)。

摘　　要：为有效利用数值天气预报数据提供的多类型气象信息来提升预测精度,提出了一种基于敏感气象特征因子筛选与优化组合的短期风电功率预测方法。首先,采用斯皮尔曼、信息熵、皮尔逊相关性指数分析气象特征与功率的相关性,利用证据理论计算优化组合后的相关性系数。然后,将同等属性的特征与风电场实测气象数据做误差分析组合,以此提升数值天气预报预测精度。最后,根据每个预测模型的邻近历史时段训练误差确定最佳权重,最终得到组合预测结果。算例分析表明,所提预测方法将预测精度提高了3%~8%,所构建的预测系统性能优越。In order to effectively improve the prediction accuracy with the multi-type meteorological information provided by the NWP,this paper presents a short-term wind power prediction based on the combination of the selection and optimization of the sensitive meteorological characteristics.Firstly,the Spearman,the information entropy and the Pearson correlation index are used to analyze the correlation between the meteorological features and the power,and the correlation coefficient after fusion is calculated by using the evidence theory.Then,the characteristics with the same attributes are combined with the measured meteorological data of the wind farm for error analysis so as to improve the accuracy of the NWP prediction.Finally,the optimal weight is determined according to the training errors of the adjacent historical periods of each prediction model,and the combined prediction result is finally obtained.Example analysis shows that the prediction accuracy of the proposed method is improved by 3%~8%,showing that the constructed prediction system has a superior performance.

关 键 词：证据理论 敏感气象特征因子筛选 风电功率预测 优化组合权重 

分 类 号：TM614[电气工程—电力系统及自动化]