Simposio Internacional sobre la Calidad de la Energía Eléctrica - SICEL

This paper proposes kmeans clustering algorithm to identify voltage sags patterns and group fault zones with similar impact in high and medium voltage networks. The proposed methodology consists in four stages. Network modelling and faults simulation were performed in order to get information about voltage sags due faults. Voltage sags patterns were identified by kmeans clustering algorithm and fault zones for these patterns were determined. Real voltage sags were classified and real faults zones were identified using clusters of simulated voltage sags as a classifier. The proposed methodology was performed in the 115kV and 220kV distribution networks of Bogotá city.