Performance comparison of classification methods for line outage detection
Authors:
- 2 February 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 26-32
Abstract
The Performance of three classification methods; Support Vector Machine (SVM), Naive Bayes (NB) and k-Nearest Neighbor (k-NN) is investigated by a detailed comparison for detection of line outage. This paper presents an application of Phasor Measurement Units (PMUs) in the protection of electrical power systems that is the single line outage detection in a transmission network. Also, a detection of the out of service line is accomplished through a proposed approach based mainly on the variations of voltage levels at the PMU's locations. The transient voltage signals measured by PMUs are processed by Discrete Wavelet Transform (DWT) to extract the distinctive features of these signals. To demonstrate the effectiveness of the proposed classifiers, the algorithms are trained and tested by using the computer simulation studies for a typical 14-bus network model implemented in PSCAD/EMTDC package.Keywords
This publication has 18 references indexed in Scilit:
- The Application of Phasor Measurement Units in Transmission Line Outage Detection Using Support Vector MachineInternational Journal of Intelligent Systems and Applications, 2013
- Bayesian-Inference-Based Recommendation in Online Social NetworksIEEE Transactions on Parallel and Distributed Systems, 2012
- Optimal Placement of Phasor Measurement Units for Power System ObservabilityIEEE Transactions on Power Systems, 2008
- An extension of the naive Bayesian classifierInformation Sciences, 2006
- A New PMU-Based Fault Detection/Location Technique for Transmission Lines With Consideration of Arcing Fault Discrimination—Part I: Theory and AlgorithmsIEEE Transactions on Power Delivery, 2004
- Comparing naive Bayes, decision trees, and SVM with AUC and accuracy2004
- A comparative analysis of structural risk minimization by support vector machines and nearest neighbor rulePattern Recognition Letters, 2004
- A comparative study of K-Nearest Neighbour, Support Vector Machine and Multi-Layer Perceptron for Thalassemia screeningChemometrics and Intelligent Laboratory Systems, 2003
- A composite index to adaptively perform fault detection, classification, and direction discrimination for transmission lines2003
- An adaptive out-of-step relay [for power system protection]IEEE Transactions on Power Delivery, 1997