Acknowledgement
This work is supported by Korea Science and Engineering Foundation (KOSEF) grant funded by the Korea government (MOST) (R01-2007-000-10926-0).
Proceedings of the Korea Information Processing Society Conference (한국정보처리학회:학술대회논문집)
- 2008.11a
- /
- Pages.325-327
- /
- 2008
- /
- 2005-0011(pISSN)
- /
- 2671-7298(eISSN)
DOI QR Code
Emerging Patterns Mining for Classifying Non-Safe Electrical Sections in Power Distribution System
전력배전 시스템에서의 취약 선로 분류를 위한 출현 패턴 마이닝
- Khalid E.K. Saeed (Database/Bioinformatics Laboratory, Chungbuk National University) ;
- Minghao Piao (Database/Bioinformatics Laboratory, Chungbuk National University) ;
- Heon Gyu Lee (Database/Bioinformatics Laboratory, Chungbuk National University) ;
- Jin-Ho Shin (Power Information Technology Group, Korea Electric Power Research Institute) ;
- Keun Ho Ryu (Database/Bioinformatics Laboratory, Chungbuk National University)
- Published : 2008.11.14
Abstract
In electrical industry, classification methodology has been an important issue for analyzing power consumption patterns. It has many applications including decisions on energy purchasing, load switching as well as helping in infrastructure development. Our aim in this work is to classify the electrical section and find potentially non-safe electrical sections. For this purpose, we use Emerging Patterns based classification. The classification method uses the aggregate score of emerging patterns to build classifier. The proposed methodology was applied to a set of electrical section data of the Korea power. The test data and relational electricity information and knowledge are supported by Korea Electric Power Research Institute (KEPRI).
Keywords