期刊
IEEE TRANSACTIONS ON POWER DELIVERY
卷 26, 期 4, 页码 2436-2442出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TPWRD.2011.2161621
关键词
Data mining; electricity theft; fuzzy clustering; nontechnical losses
资金
- CNPq
- Eletrobras-Brazil [ECV 065/2005]
This paper proposes a computational technique for the classification of electricity consumption profiles. The methodology is comprised of two steps. In the first one, a C-means-based fuzzy clustering is performed in order to find consumers with similar consumption profiles. Afterwards, a fuzzy classification is performed using a fuzzy membership matrix and the Euclidean distance to the cluster centers. Then, the distance measures are normalized and ordered, yielding a unitary index score, where the potential fraudsters or users with irregular patterns of consumption have the highest scores. The approach was tested and validated on a real database, showing good performance in tasks of fraud and measurement defect detection.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据