Open AccessAbnormal behaviour analysis algorithm for electricity consumption based on density clustering
Author(s) -
Xiang Min,
Rao Huayang,
Tan Tong,
Wang Zaiqian,
Ma Yue
Publication year - 2019
Publication title -
the journal of engineering
Language(s) - English
Resource type - Journals
ISSN - 2051-3305
DOI - 10.1049/joe.2018.5123
Subject(s) - electricity , cluster analysis , consumption (sociology) , local outlier factor , computer science , outlier , smart grid , matching (statistics) , data mining , algorithm , engineering , artificial intelligence , statistics , mathematics , electrical engineering , social science , sociology
How to effectively detect abnormal electricity consumption behaviour from a large‐scale electrical load data is very important to smart grid. An abnormal electricity consumption analysis method based on density clustering is proposed. First, the similar users located in fix area are clustered in accordance with the electricity consumption characteristics. Then, on the basis of electricity consumption data sequence, the outlier electricity consumption for the similar users are obtained with density clustering. The matching degrees of these outliers can be calculated based on the similar user electricity consumption model and historical electricity consumption model. Finally, according to the threshold value, the abnormal electricity consumption can be discriminated with the comprehensive support degree. The simulation results show that this method can effectively identify the abnormal electricity consumption behaviour.