Digital relaying equipment at substations allow for large amounts of data storage that can be triggered by predetermined system conditions. Some of this information retrieved from relays at several locations in a local utility's service territory has been mined for determining trends and relationships. Data mining aims to make sense of the retrieved data by revealing meaningful relationships. This paper discusses some useful data mining techniques that are applied to data recorded by overcurrent relays at several substations. The purpose is to classify faults, verify relay settings and determine fault induced trip per substations. High accuracy is obtained.
B. H. Chowdhury and H. M. Dola, "Data Mining for Distribution System Fault Classification," Proceedings of the 37th Annual North American Power Symposium, 2005, Institute of Electrical and Electronics Engineers (IEEE), Jan 2005.
The definitive version is available at http://dx.doi.org/10.1109/NAPS.2005.1560559
37th Annual North American Power Symposium, 2005
Electrical and Computer Engineering
Keywords and Phrases
Data Mining; Data Mining Techniques; Data Storage; Distribution System Fault Classification; Fault Diagnosis; Information Retrieval; Overcurrent Protection; Overcurrent Relays; Power Distribution Faults; Predetermined System Conditions; Relay Protection; Substation Automation; Substation Protection; Substations Digital Relaying Equipment
Article - Conference proceedings
© 2005 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.