Fault location in radial distribution systems based on decision trees and optimized allocation of power quality meters

One of the reasons for not achieving satisfactory indices of Power Quality (PQ) is due to the discontinuity of power supply in Distribution Systems (DS), usually caused by the occurrence of short-circuits. In this context, to characterize these occurrences, a database was compiled by simulations in the IEEE 34-bus DS using the ATP (Alternative Transients Program) software. In these simulations, the type, location and fault impedance were used as parameters. The voltages and currents of all three phases of the power quality meters optimally allocated in the DS were considered. Based on these measurements, the J48 decision tree algorithm was used to identify in which area of the 34-bus DS the single-phase faults occurred. In order to use the J48 decision tree, the WEKA (Waikato Environment for Knowledge Analysis) software was used. Promising results demonstrated the effectiveness of the proposed algorithm to locate the single-phase short-circuit situations considered.

[1]  Ali Feliachi,et al.  Fault location and isolation using multi agent systems in power distribution systems with distributed generation sources , 2013, 2013 IEEE PES Innovative Smart Grid Technologies Conference (ISGT).

[2]  Chandima Gomes,et al.  Short Circuit Power based fault location algorithm in distribution networks , 2014, 2014 IEEE 8th International Power Engineering and Optimization Conference (PEOCO2014).

[3]  J.F. Martins,et al.  The application of neural networks and Clarke-Concordia transformation in fault location on distribution power systems , 2002, IEEE/PES Transmission and Distribution Conference and Exhibition.

[4]  Andrés Zapata-Tapasco,et al.  Fault location in power distribution systems using a learning approach based on decision trees , 2014, 2014 IEEE PES Transmission & Distribution Conference and Exposition - Latin America (PES T&D-LA).

[5]  Mohammad A. S. Masoum,et al.  Power Quality in Power Systems and Electrical Machines , 2008 .

[6]  Raed Shatnawi,et al.  Finding software metrics threshold values using ROC curves , 2010, J. Softw. Maintenance Res. Pract..

[7]  Ian H. Witten,et al.  WEKA: a machine learning workbench , 1994, Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference.

[8]  Raj K. Aggarwal,et al.  Current transients based phase selection and fault location in active distribution networks with spurs using artificial intelligence , 2013, 2013 IEEE Power & Energy Society General Meeting.

[9]  Papia Ray,et al.  Hybrid technique for fault location of a distribution line , 2015, 2015 Annual IEEE India Conference (INDICON).

[10]  Adly A. Girgis,et al.  Automated fault location and diagnosis on electric power distribution feeders , 1997 .

[11]  Jamal Moshtagh,et al.  A new approach to fault location in three-phase underground distribution system using combination of wavelet analysis with ANN and FLS , 2014 .

[12]  Tina R. Patil,et al.  Performance Analysis of Naive Bayes and J 48 Classification Algorithm for Data Classification , 2013 .

[13]  Eugeniusz Rosolowski,et al.  Fault Location on Power Networks , 2009 .

[14]  Walmir Freitas,et al.  Fault location in distribution systems based on smart feeder meters , 2014, 2014 IEEE PES General Meeting | Conference & Exposition.