Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Tecnura
Print version ISSN 0123-921X
Abstract
GIL GONZALEZ, Walter Julián; MORA FLOREZ, Juan José and PEREZ LONDONO, Sandra Milena. Analysis of the input data processing for fault location in power distribution systems. Tecnura [online]. 2014, vol.18, n.41, pp.64-75. ISSN 0123-921X.
Aimed to determine the effect of data normalization on the accuracy and the computational effort of a fault locator based on support vector machines (SVM), a comparison of five different data preprocessing strategies are analyzed in this paper. The proposed methodology is tested on an IEEE 34-bus test feeder, which is subdivided in eleven zones, by using a database of 6442 single-phase to ground faults obtained under different load conditions. Considering the testing scenarios, the comparison of the proposed preprocessing methods shows that Min-Max method has the best performance mainly considering computational effort and average accuracy on the fault locator.
Keywords : Accuracy and power distribution systems; attribute; normalization methods; support vector machines.