考虑气象特征与波动过程关联的短期风电功率组合预测  

Combined Prediction of Short-term Wind Power Considering Correlation of Meteorological Features and Fluctuation Process

作　　者：叶林[1] 赵金龙 路朋 裴铭 陈梅 王勃 车建峰 YE Lin;ZHAO Jinlong;LU Peng;PEI Ming;CHEN Mei;WANG Bo;CHE Jianfeng(College of Information and Electrical Engineering,China Agricultural University,Beijing 100083,China;State Grid Corporation of China,Beijing 100032,China;China Electric Power Research Institute,Beijing 100192,China)

机构地区：[1]中国农业大学信息与电气工程学院,北京市100083 [2]国家电网有限公司,北京市100032 [3]中国电力科学研究院有限公司,北京市100192

出　　处：《电力系统自动化》2021年第4期54-62,共9页Automation of Electric Power Systems

基　　金：国家重点研发计划资助项目(2018YFB0904200);国家电网有限公司科技项目(SGLNDKOOKJJS1800266)。

摘　　要：为解决短期风电功率预测关键气象因素提取难、天气波动过程与功率波动过程匹配性差的问题,提出了一种考虑气象特征与波动过程关联的短期风电功率组合预测方法。首先,通过最大相关-最小冗余原则得到数值天气预报的气象特征因素来划分天气波动过程。其次,考虑天气波动过程与功率波动过程的关联关系,建立了以气象特征因素为输入、以风电功率为输出的波动过程关联的短期组合预测模型。最后,将不同天气波动过程下的风电功率预测值在时序上进行重新组合,以得到波动过程为输出的短期风电功率预测结果。实际算例表明,采用气象特征因素作为输入以及面向波动过程关联的组合预测方法能够明显地提高短期风电功率的预测精度。To cope with the problems of difficulties in extraction of the critical meteorological factors and the weak relevance between the weather and power fluctuation processes,a combined prediction method of short-term wind power considering correlation of meteorological features and fluctuation processes is proposed.At first,the meteorological characteristic factors of numerical weather prediction(NWP)are obtained by the rule of minimal redundancy maximal relevance(mRMR)to classify the weather fluctuation processes.Further,considering the relationship between weather and power fluctuation processes,a short-term combined prediction model is constrcuted,which takes meteorological characteristic factors as inputs and wind power as output.Finally,the prediction values of wind power associated with different weather processes are combined in time series to get the prediction results of short-term wind power,which takes fluctuation processes as the output.Case study shows that the combined prediction method with correlations of fluctuation processes which takes meteorological characteristic factors as inputs can significantly improve the prediction accuracy of the short-term wind power.

关 键 词：短期风电功率预测 气象特征因素 天气波动过程 波动过程关联 组合预测 

分 类 号：P425.63[天文地球—大气科学及气象学] TM614[电气工程—电力系统及自动化]