SciELO - Scientific Electronic Library Online

 
vol.28 issue3Studying and comparing spectrum efficiency and error probability in GMSK and DBPSK modulation schemesTopographical characteristics and evaluating water quality in watershed management author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Ingeniería e Investigación

Print version ISSN 0120-5609

Abstract

MORA-FLOREZ, Juan; MORALES-ESPANA, Gérman  and  BARRERA-CARDENAS, Rene. Evaluating a k-nearest neighbours-based classifier for locating faulty areas in power systems. Ing. Investig. [online]. 2008, vol.28, n.3, pp.81-86. ISSN 0120-5609.

This paper reports a strategy for identifying and locating faults in a power distribution system. The strategy was based on the K-nearest neighbours technique. This technique simply helps to estimate a distance from the features used for describing a particular fault being classified to the faults presented during the training stage. If new data is presented to the proposed fault locator, it is classified according to the nearest example recovered. A characterisation of the voltage and current measurements obtained at one single line end is also presented in this document for assigning the area in the case of a fault in a power system. The proposed strategy was tested in a real power distribution system, average 93% confidence indexes being obtained which gives a good indicator of the proposal’s high performance. The results showed how a fault could be located by using features obtained from voltage and current, improving utility response and thereby improving system continuity indexes in power distribution systems.

Keywords : k-nearest neighbours; fault location; power distribution system; supply continuity.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )

 

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License