摘要 建立了一种计及数值天气预报中气象因素和风速空间相关性的组合加权风电功率预测模型。首先,考虑到数值天气预报数据中的风速精确度不高,建立了基于高斯过程的数值天气预报风速修正模型,计入其他气象因素,如风向、温度、湿度、气压等,进行风电预测。同时,基于目标风电场与相邻风电场区域的风速空间相关性分析,求得其最大相关系数点的延迟时间,建立风速空间相关性预测模型。然后,基于数值天气预报偏差修正的风电功率预测模型和空间相关性预测模型,建立组合加权预测模型,并利用拉格朗日乘子法求得组合模型中各个单一模型的加权值。算例结果表明,所提模型及方法能够有效提高风电功率预测的精度。 A combined weighted wind power prediction model is established,which takes meteorological factors and the spatial correlation of the wind speed in numerical weather prediction(NWP)into account.First,considering that the data accuracy of the NWP is not high enough,a wind speed correction model for NWP based on Gaussian process is built,and other meteorological factors,such as wind direction,temperature,humidity,and air pressure,are taken into account for wind power prediction.At the same time,based on the analysis of the spatial correlation of the wind speed between the target wind farm and the adjacent wind farm area,the delay time of the maximum correlation coefficient point is obtained,and the prediction model of spatial correlation for the wind speed is established.Then,based on the wind power prediction model and the spatial correlation prediction model using the deviation correction of the NWP,a combined weighted prediction model is established,and the Lagrangian multiplier method is used to obtain the weighted value of each single model in the combined model.The case results show that the proposed model and method can effectively improve the accuracy of wind power prediction.
机构地区 四川大学电气工程学院
出处 《电力系统自动化》 EI CSCD 北大核心 2021年第7期28-36,共9页 Automation of Electric Power Systems
基金 中央高校基本科研业务费专项资金资助项目(YJ201654)。
关键词 风力发电 预测模型 数值天气预报 风速修正 风速相关性 气象因素 wind power generation prediction model numerical weather prediction(NWP) wind speed correction wind speed correlation meteorological factor
分类号 G63 [文化科学—教育学]
