Open AccessLow-voltage distribution network topology verification method based on Revised Pearson correlation coefficient
Author(s) -
Bing Lou,
Cailong Li,
Jian Deng,
Ling Zhu,
Changhong Yang,
Wujun Chen
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1633/1/012084
Subject(s) - pearson product moment correlation coefficient , correctness , computer science , correlation coefficient , data mining , reliability (semiconductor) , k nearest neighbors algorithm , similarity (geometry) , algorithm , mathematics , statistics , artificial intelligence , machine learning , power (physics) , physics , quantum mechanics , image (mathematics)
Due to the high cost and low real-time reliability of low-voltage distribution network topology checking by manual field verification, an online verification method based on revised Pearson correlation coefficient with error expectation values and KNN algorithm is proposed. Firstly, the Pearson correlation coefficient with error expectation values is used to judge the similarity between the user’s voltage curve and the transformer substation voltage curve, then the user with incorrect household relationship is found to perform re-verification. For performing re-verification, the user sample set is generated based on the data of GIS system and the Technical Guidelines for Distribution Network Planning and Design, and the K-Nearest Neighbor (KNN) algorithm is used to find out the correct station to which area the user belongs. Finally, based on the results of the manual field verification, the correctness of the algorithm verification is judged.