Detection and Identification of Abnormalities in Customer Consumptions in Power Distribution Systems

被引:215
作者
dos Angelos, Eduardo Werley S. [1 ]
Saavedra, Osvaldo R. [1 ]
Carmona Cortes, Omar A. [2 ]
de Souza, Andre Nunes [3 ]
机构
[1] Univ Fed Maranhao, Power Syst Grp, BR-65085580 Sao Luis, Maranhao, Brazil
[2] Tech Fed Inst, BR-65030005 Sao Luis, Maranhao, Brazil
[3] State Univ Sao Paulo, BR-17033360 Bauru, Brazil
关键词
Data mining; electricity theft; fuzzy clustering; nontechnical losses;
D O I
10.1109/TPWRD.2011.2161621
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
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.
引用
收藏
页码:2436 / 2442
页数:7
相关论文
共 24 条
  • [1] ABRADEE, 2004, 5 SEM LEG ISS GOIAN
  • [2] [Anonymous], 2005, Discovering Knowledge in Data: An Introduction to Data Mining
  • [3] [Anonymous], 2011, Pei. data mining concepts and techniques
  • [4] Barbosa C, 2006, 17 NAT S ELECTR EN D
  • [5] BOLTON RJ, 2002, STAT SCI, V17
  • [6] Bonchi F., 1999, Proc. of SIGKDD99, P175
  • [7] Fraud detection in electrical energy consumers using rough sets
    Cabral, JE
    Pinto, JOP
    Gontijo, EM
    Reis, J
    [J]. 2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7, 2004, : 3625 - 3629
  • [8] Cabral JE, 2009, IEEE POW ENER SOC GE, P2283
  • [9] Dos-Angelos E. W., 2007, 7 BRAZ S INT AUT FLO
  • [10] Fabris F, 2009, NSS: 2009 3RD INTERNATIONAL CONFERENCE ON NETWORK AND SYSTEM SECURITY, P546, DOI 10.1109/NSS.2009.17