A new optimal feature selection algorithm for classification of power quality disturbances using discrete wavelet transform and probabilistic neural network. (January 2017)

• Record Type: Journal Article
• Authors: Khokhar, Suhail; Mohd Zin, Abdullah Asuhaimi; Memon, Aslam Pervez; Mokhtar, Ahmad Safawi
• Is Part Of: Measurement. Volume 95(2017)
• Page Start: 246
• Page End: 259
• Publication Date: 2017-01
• Subjects: Power quality disturbances -- Feature extraction -- Optimal feature selection -- Discrete wavelet transform -- Artificial bee colony -- Probabilistic neural network; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2016.10.013
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Power quality disturbances are classified using optimal feature selection method. Discrete wavelet transform extracts the set of features successfully. Artificial bee colony has been proposed for the selection of optimal features. 16 types of single and multiple power quality disturbances are classified. Superior results are achieved as compared to the similar existing techniques. Abstract: Automatic classification of Power Quality Disturbances (PQDs) is a challenging concern for both the utility and industry. In this paper, a novel technique of automatic classification of single and hybrid PQDs is proposed. The proposed algorithm consists of the Discrete Wavelet Transform (DWT) and Probabilistic Neural Network based Artificial Bee Colony (PNN-ABC) optimal feature selection of PQDs. DWT with Multi-Resolution Analysis (MRA) is used for the feature extraction of the disturbances. The PNN classifier is used as an effective classifier for the classification of the PQDs. However, the two critical concerns such as the selection of the optimal features and the spread constant value might affect the performance of the classifier. Hence, these two issues are addressed using a novel technique PNN-ABC based optimal feature selection and parameter optimization for improving the performance of the classification system. The ABC algorithm is used to select optimal features from a large feature set and the optimal value of the PNN spread constant. The optimal feature selection method retains the useful features and discards the redundant features. The performance of the proposed algorithm is evaluated by PSCAD/EMTDC simulation of a typical 11 kV underground distribution system of Malaysia. The noise-riding PQDs have also been analysed to validate the sensitivity of the proposed algorithm. The simulation results show that the new PNN-ABC based optimal feature selection algorithm is proficient and accurate in classifying the PQDs.