基于GSA算法与抗差估计的抽水蓄能电站电能数据校正方法

Data Correction Method of Pumped Storage Power Station Based on GSA Algorithm and Robust Estimation

针对混合式抽水蓄能电站电能计量校正问题,本文提出了一种将抗差估计与间隙统计算法相结合的电能计量校正方法。该方法将抗差估计与加权最小二乘法相结合,形成了指数加权最小二乘抗差估计,削弱了在整体估计中坏数据产生的影响,得到估计值后将计算得到的相对估计误差值输入聚类算法,最后通过GSA聚类分析方法实现不良数据辨识,在保证校正准确度的同时,又保持了对坏数据鉴别能力的速度和准确度,有效解决了残差污染、淹没问题。

In order to solve the problem of power metering correction in hybrid pumped storage power station, this paper presents a method of power metering correction which combines robust estimation and gap statistical algorithm. This method combines robust estimation with weighted least square method to form exponential weighted least square robust estimation, which weakens the influence of bad data in the overall estimation. After getting the estimated value, the calculated relative estimation error is input into the clustering algorithm. Finally, GSA clustering analysis method is used to identify bad data, which not only ensures the accuracy of correction, but also maintains the speed and accuracy of bad data identification. The method can effectively solve the problem of residual pollution and inundation.