A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances

The increasing trend towards renewable energy sources requires higher power quality (PQ) at the generation, transmission and distribution systems. The PQ disturbances are produced due to the nonlinear loads, power electronic converters, system faults and switching events. The utilities and consumers of electric power are expected to acquire ideal voltage and current waveforms at rated power frequency. The development of new techniques for the automatic classification of PQ events is at present a major concern. This paper presents a comprehensive literature review on the applications of digital signal processing, artificial intelligence and optimization techniques in the classification of PQ disturbances. Various signal processing techniques used for the feature extraction such as Fourier transform, wavelet transform, S-transform, Hilbert transform, Gabor transform and their hybrids have been reviewed. The artificial intelligent techniques used for the pattern recognition such as artificial neural network, fuzzy logic, support vector machine are reviewed in detail. The optimization techniques used for the optimal feature selection such as genetic algorithm, particle swarm optimization and ant colony optimization are also reviewed. A comparison of various classification systems is presented in tabular form which highlights the important techniques used in the field of PQ disturbance monitoring. The comparison of research works carried out on the classification of PQ disturbances points out that many researchers have focussed on the feature extraction and classification techniques. Only few authors have used the feature selection techniques for selecting the best suitable features. This review may be considered a valuable source for researchers as a reference point to explore the opportunities for further improvement in the field of PQ classification.