Research Article
Abnormal Operation Diagnosis Method of Electric Energy Metering Equipment Based on Data Mining
@INPROCEEDINGS{10.4108/eai.2-12-2022.2328715, author={Jianfeng Sun and Yang Gao and Cunyu Long and Shubei Hua}, title={Abnormal Operation Diagnosis Method of Electric Energy Metering Equipment Based on Data Mining}, proceedings={Proceedings of the 3rd International Conference on Big Data Economy and Information Management, BDEIM 2022, December 2-3, 2022, Zhengzhou, China}, publisher={EAI}, proceedings_a={BDEIM}, year={2023}, month={6}, keywords={electric energy metering equipment data anomaly diagnosis model data mining}, doi={10.4108/eai.2-12-2022.2328715} }- Jianfeng Sun
Yang Gao
Cunyu Long
Shubei Hua
Year: 2023
Abnormal Operation Diagnosis Method of Electric Energy Metering Equipment Based on Data Mining
BDEIM
EAI
DOI: 10.4108/eai.2-12-2022.2328715
Abstract
The integration of emerging technologies and power grid business in the information age has also put forward new requirements. The demand for improving the data acquisition, processing and application capabilities of power grid construction in the new era is increasing day by day. At the same time, it also puts forward higher requirements for using new technologies to improve the efficiency of production and operation. The abnormal behavior of power grid metering equipment leads to line loss, which not only causes damage to power grid facilities, but also seriously threatens the stability and safety of power grid. In view of the large range of original data of electric power equipment and the difficulties of parameter selection and low computational efficiency in the original K-means algorithm, this paper establishes an outlier detection model based on the improved K-means algorithm to preliminarily screen out the abnormal operation set of metering equipment, and further screens out the final data set through the similarity analysis of curves. Finally, the simulation and comparative experiments prove that the anomaly diagnosis detection model based on clustering analysis can achieve good results in both detection rate and the false detection rate on the data set. It provides a data basis for the operation of power equipment and also provides theoretical support for the maintenance and repair of SGCC.