Skip to main content
ADVANCED TOPICS IN ELECTRICAL ENGINEERING – ATEE 2017

Papers Proceedings »

Outliers Discovery from Smart Meters Data Using a Statistical Based Data Mining Approach

The paper presents a statistical approach used for detection of outliers from load curves recorded on the electric substation of distribution networks. The load curves provided by smart meters were processed and their main indicators were calculated. By outliers eliminating, the remaining data have led to the discovery of accurate patterns that characterized very well the load curves characteristics through indicators. The proposed approach was tested using a real database with 60 substations from a rural area. With the help of these patterns, the operation and planning of electric distribution systems could be made more efficient.

Author(s):

Bogdan Constantin NEAGU    
Gheorghe Asachi Technical University of Iasi
Romania

Gheorghe GRIGORAS    
Gheorghe Asachi Technical University of Iasi
Romania

Florina SCARLATACHE    
Gheorghe Asachi Technical University of Iasi
Romania

 

Powered by OpenConf®
Copyright ©2002-2016 Zakon Group LLC