考虑风速波动特性的VMD-GRU短期风电功率预测  

VMD-GRU based short-term wind power forecast considering wind speed fluctuation characteristics

作　　者：王鑫[1] 李慧[1] 叶林[2] 范新桥[1] 刘思嘉 WANG Xin;LI Hui;YE Lin;FAN Xinqiao;LIU Sijia(School of Automation,Beijing Information Science and Technology University,Beijing 100192,China;College of Information and Electrical Engineering,China Agricultural University,Beijing 100083,China)

机构地区：[1]北京信息科技大学自动化学院,北京100192 [2]中国农业大学信息与电气工程学院,北京100083

出　　处：《电力科学与技术学报》2021年第4期20-28,共9页Journal of Electric Power Science And Technology

基　　金：国家重点研发计划(2018YFB0904200);北京市自然科学基金(3172015);国家电网有限公司科技项目(SGLNDKOOKJJS1800266);北京市教委科技计划面上项目(KM201911232016)。

摘　　要：提高风电功率预测的精准度能为大规模风电并网提供安全保障,为此提出一种考虑风速波动特性的短期风电功率组合预测方法。首先,定义5种风速波动类型,对数值天气预报中的历史风速序列进行波动类型划分,得到不同风速波动类型的天气时段;其次,将这些天气时段对应的历史风电功率序列进行分类,采用变分模态分解算法对各类风电功率序列进行分频计算,得到特征、频段互异的多个子模态;然后,利用门控循环单元神经网络建立每个子模态预测模型,将各个子模态预测结果进行叠加,得到风电功率预测值;最后,对待测时段的风速序列进行波动类型划分和识别,选取相匹配的功率预测模型计算出最终预测值。利用某实际风电场的数值天气预报风速数据和功率数据进行仿真分析,验证所提组合预测方法的有效性。The accuracy of wind power prediction can improve the security environment of large-scale wind power integration.Under the background,a combined approach considering wind speed fluctuation characteristics for short-term wind power forecasting is proposed in this paper.Firstly,five types of wind speed fluctuations are defined,and the fluctuation type of historical wind speed series in numerical weather prediction is divided to get the time period of different wind speed fluctuation types.Secondly,the historical wind power series corresponding to these time periods are classified,and the variational mode decomposition algorithm is used to deal with various types of wind power series for obtaining multiple sub-modalities with different characteristics and frequency bands.Thirdly,a prediction model based on the gated recurrent unit neural network is constructed for each sub-mode,and the prediction results of each sub-mode are added to obtain the predicted value of the wind power.Finally,the wind speed series of the forecasted day is identified from the types of fluctuation,and the matching power prediction model is selected to calculate the final prediction value.The wind speed data in the numerical weather prediction and power data of an actual wind farm are used for simulation analysis to verify the effectiveness of the proposed combined forecasting method.

关 键 词：风电功率预测 数值天气预报 风速波动特性 变分模态分解 门控循环单元神经网络 

分 类 号：TM614[电气工程—电力系统及自动化]