Fault detection in distribution networks in presence of distributed generations using a data mining–driven wavelet transform. Issue 2 (15th February 2019)

• Record Type: Journal Article
• Authors: Mohammadnian, Youness; Amraee, Turaj; Soroudi, Alireza
• Is Part Of: IET smart grid. Volume 2:Issue 2(2019)
• Page Start: 163
• Page End: 171
• Publication Date: 2019-02-15
• Subjects: decision trees -- data mining -- genetic algorithms -- power engineering computing -- distributed power generation -- wavelet transforms -- fault diagnosis -- neural nets -- power distribution faults -- support vector machines -- discrete wavelet transforms -- probability; probabilistic neural network -- solid short‐circuit faults -- HIF faults -- distributed generations -- data mining–driven scheme -- high impedance fault detection -- phase current signal -- current wavelet -- HIF detection method -- decision tree -- input data -- utilised SVM‐based classifier -- active distribution networks -- discrete wavelet transform -- IEEE 13‐Bus systems -- IEEE 34‐Bus systems -- support vector machine; B0230 Integral transforms -- B0250 Combinatorial mathematics -- B0260 Optimisation techniques -- C1130 Integral transforms -- C1140Z Other topics in statistics -- C1160 Combinatorial mathematics -- C1180 Optimisation techniques -- C5290 Neural computing techniques -- C6170K Knowledge engineering techniques -- C7410B Power engineering computing -- B8120K Distributed power generation; Smart power grids -- Periodicals; Computer science -- Periodicals; Energy industries -- Periodicals; Broadcasting -- Periodicals; 333.79110285
• DOI: 10.1049/iet-stg.2018.0158
• Languages: English
• ISSNs: 2515-2947

Abstract

Abstract : Here, a data mining–driven scheme based on discrete wavelet transform (DWT) is proposed for high impedance fault (HIF) detection in active distribution networks. Correlation between the phase current signal and the related details of the current wavelet transform is presented as a new index for HIF detection. The proposed HIF detection method is implemented in two subsequent stages. In the first stage, the most important features for HIF detection are extracted using support vector machine (SVM) and decision tree (DT). The parameters of SVM are optimised using the genetic algorithm (GA) over the input scenarios. In second stage, SVM is utilised to classify the input data. The efficiency of the utilised SVM‐based classifier is compared with a probabilistic neural network (PNN). A comprehensive list of scenarios including load switching, inrush current, solid short‐circuit faults, HIF faults in the presence of harmonic loads is generated. The performance of the proposed algorithm is investigated for two active distribution networks including IEEE 13‐Bus and IEEE 34‐Bus systems.