An improved automated PQD classification method for distributed generators with hybrid SVM-based approach using un-decimated wavelet transform. (March 2022)

• Record Type: Journal Article
• Authors: Yılmaz, Alper; Küçüker, Ahmet; Bayrak, Gökay; Ertekin, Davut; Shafie-Khah, Miadreza; Guerrero, Josep M.
• Is Part Of: International journal of electrical power & energy systems. Volume 136(2022)
• Publication Date: 2022-03
• Subjects: Power quality disturbances -- Un-decimated wavelet transform -- Machine learning -- Distributed generation; CB Circuit Breaker -- CWT Continuous Wavelet Transform -- DbN Daubechies-N -- DCNN Deep Convolutional Neural Network -- DFIG Double-fed Induction Generator -- DGs Distributed Generators -- DT Decision Tree -- DWT Discrete Wavelet Transform -- EWT Empirical Wavelet Transform -- FT Fourier Transform -- GBDT Gradient Boosting Decision Tree -- kNN K-Nearest Neighbors -- ML Machine Learning -- PCC Point of Common Coupling -- pu Per-unit -- PQ Power Quality -- PQD Power Quality Disturbances -- RF Random Forest -- SNR Signal-to-noise Ratio -- ST S-transform -- STFT Short-Term Fourier Transform -- SVM Support Vector Machine -- UWT Un-Decimated Wavelet-Transform -- VMD Variational Mode Decomposition -- WPT Wavelet Packet Transform -- WT Wavelet Transform -- WTS Wind Turbine System -- WVD Wigner-Ville Distribution; Electrical engineering -- Periodicals; Electric power systems -- Periodicals; Électrotechnique -- Périodiques; Réseaux électriques (Énergie) -- Périodiques; Electric power systems; Electrical engineering; Periodicals; 621.3
• DOI: 10.1016/j.ijepes.2021.107763
• Languages: English
• ISSNs: 0142-0615

Abstract

Highlights: UWT&SVM-based method is proposed for classification of PQDs in DG-based microgrid. UWT technique with á trous is used to extract features from PQDs of microgrid. UWT-based decomposition improved the resolution of time–frequency analysis. Low performance under noise in WTs is dramatically improved with UWT. It provides better performance than state-of-the-art PQD classification methods. Abstract: Artificial intelligence (AI) approaches are usually coupled with the wavelet transform (WT) for feature extraction to classify the power quality disturbances (PQDs). Therefore, selecting a useful WT-based signal processing approach is required for a reliable classification, especially in real-time applications. In this study, a new hybrid, un-decimated wavelet-transform (UWT)-based feature extraction method using a support vector machine (SVM) with a "á trous" algorithm is proposed to classify PQDs in distributed generators (DGs). The proposed method was performed in a real-time application of a DG system to classify PQDs. The derived features were tested on five different machine learning (ML) models by determining the most appropriate classification technique for the proposed UWT-based feature extraction method. An experimental DG system is constituted in the laboratory using a LabVIEW environment, and the proposed method is tested under different grid conditions. Besides, other well-known and studied conventional ML methods were also tested under 25 dB, 30 dB, and 40 dB noise and compared to the developed method. The experimental and simulation results show that the features extracted with the proposed UWT-based method provide much more successful results in classification than the existing wavelet methods in the literature. Furthermore, the proposed method's noise sensitivity performance is much better than other conventional wavelet algorithms, especially in real-time applications.