摘要
针对电网电能质量数据缺失的问题,提出基于相关分析的缺失数据填充方法.该方法首先进行相关分析,通过归一化互信息计算指标间的相关性,然后选择其中最强相关性的指标进行回归分析,并采用自动分段回归的方式得到预测模型,进行缺失数据填充.实验结果表明这种方法在缺失率不高于20%的情况下,平均误差百分比与平均值填充相比提高了20%,平均误差不超过8%,准确性较好;在缺失率高于20%的情况下,不分段效果更好.
In view of the problem of missing values of power quality data in power grids,a missing value filling method based on correlation analysis is proposed.This method firstly performs correlation analysis:calculate the correlation between indicators through normalized mutual information,and then selects the index with the strongest correlation among them for regression analysis,and finally adopts automatic stagewise regression to obtain the prediction model and fills in the missing data.The experimental results show that under the condition that when the average missing data is less than 20%,the error rate is less than 8%,which proves that the method has a better accuracy.And when the average missing data is higher than 20%,the effect of no segmentation is better.
作者
雷峰津
房俊
LEI Fengjin;FANG Jun(Col.of Information,North China Univ.of Tech.,100144,Beijing,China)
出处
《北方工业大学学报》
2020年第5期77-82,共6页
Journal of North China University of Technology
基金
国家自然科学基金重点项目“大数据环境下的大服务理论与方法研究”(61832004).
关键词
数据缺失
相关分析
归一化互信息
回归分析
分段回归
missing data
correlation analysis
normalized mutual information
regression analysis
stagewise regression
