A fault location method applied in power distribution systems based on k-NN classifiers parameterized using genetic algorithms and the reactance estimation

In  this  paper,  a  parameterization  strategy  of  a  k  nearest  neighbors  (k-NN) based  fault  locator  is  described.  This  technique  is  complemented  by  a  well  validated location method based on the estimation of the fault impedance. This hybrid strategy is validated in a real power dis...

Full description

Saved in:
Bibliographic Details
Published in:Revista Facultad de Ingeniería 2014-02 (70), p.220-232
Main Authors: Zapata-Tapasco, Andrés, Pérez-Londoño, Sandra, Mora-Flórez, Juan
Format: Article
Language:English
Subjects:
fault impedance
fault location
hybrid
knearest neighbors
power distribution systems
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In  this  paper,  a  parameterization  strategy  of  a  k  nearest  neighbors  (k-NN) based  fault  locator  is  described.  This  technique  is  complemented  by  a  well  validated location method based on the estimation of the fault impedance. This hybrid strategy is validated in a real power distribution feeder, having obtained acceptable results. Finally and as an important advantage of the here proponed  methodology,  it  is  remarkable  the  easy  implementation  process,  considering real distribution feeders (more than 100 nodes).
ISSN:0120-6230
2422-2844
DOI:10.17533/udea.redin.18667