Power load abnormal data recognition and modification method based on nonparametric regression analysis

Abstract

The invention discloses a power load abnormal data recognition and modification method based on nonparametric regression analysis. The method comprises the steps of 1, performing power utilization mode classification on power load data to obtain a common power utilization mode data set and a special power utilization mode data set; 2, extracting a load feature value at each moment from the obtained common power utilization mode data set by adopting a nonparametric regression analysis method; 3, forming an abnormal data field by using the extracted load feature values according to the selected confidence level; 4, performing load abnormal data recognition on load data in the common power utilization mode data set and the special power utilization mode data set by using the abnormal data field formed in step 3; and 5, modifying the recognized load abnormal value by using an improved introduced load level mapping relation and a weighted mean method considering the influence of feature values. The method can recognize and modify power load abnormal data including big industrial power load data, and simultaneously can overcome the defect of the load abnormal data recognition and modification theory on the aspect of power load data processing.

Description

technical field [0001] The invention relates to a processing method of electric load data, in particular to a method for identifying and correcting abnormal electric load data based on non-parametric regression analysis. Background technique [0002] With the continuous expansion of the installation of smart meters in my country, a large amount of power load data is collected and uploaded to the centralized control center. However, data loss due to failure of installed smart meters and other measuring devices or communication failures, unplanned power outages or maintenance, temporary weather changes, shutdown of production lines of large industrial users and other reasons can cause the recorded power load data to deviate from its original value. Regular value. [0003] Nowadays, the power load data collected by smart meters comes from residential power consumption, general industrial and commercial power consumption and large industrial power consumption. The research obj...

AI Technical Summary

Problems solved by technology

[0004] Conventional load anomaly data identification and correction methods include: identification and adjustment method based on improved ART2 network, identification and correction method combining system clustering and traditional t test method, combination of improved Knhonen neural network and radial basis function (RBF) network The cleaning method of abnormal power load data, the identification and correction method of abnormal power load data based on kernel density estimation, and the method based on T 2 Abnormal data identification of ellipse graph and missing data filling method of least squares support vector machine, complex uncertainty detection of bus load abnormal data and correction method based on comprehensive cloud, improved data horizontal comparison method to identify and correct data, according to wavelet The method of singularity detection to determine the location and type of errors in the load data and the method of combining the dynamic multi-source processing technology and the grid terminal load one by one scanning identification, but the common feature of the existing methods is that the method model is complex, and sometimes other data to aid identification and correction

Images