Preview

PDF Pending copyright assessment - Request a copy 6Mb

Harmonics and waveform distortion is a significant power quality problem in modern power systems with high penetration of Renewable Energy Sources (RES). This problem has attracted more attention in recent decades, owing to the increasing integration of power electronic devices and nonlinear loads into power systems. In this paper, Artificial Intelligence (AI) techniques used in different aspects of analyzing harmonics in electrical power networks are reviewed. The tasks of spectrum analysis and waveform estimation or prediction, harmonic source classification, harmonic source location and estimation, determination of harmonic source contributions, harmonic data clustering, filter-based harmonic elimination, and Distributed Generation (DG) hosting capacity in the context of harmonics are considered. The applications of AI in these tasks have been addressed within the literature and are reviewed in this paper. Different AI techniques applied in the study of harmonics such as artificial neural networks, fuzzy systems, support vector machine and decision tree are reviewed. AI techniques mostly outperformed traditional methods in harmonic analysis, particularly under varying operating condition. However, there is still room for improvement regarding the use of combinations of techniques, ensemble learning, optimal structures, training algorithms and further comprehension. This review provides researchers with an insight into research trends in harmonic analysis and outlines opportunities for further research on this increasingly important topic.

Item Type:	Refereed Article
Keywords:	Harmonic analysis Harmonic source location Harmonic source classification Artificial intelligence Neural network Active power filter Fuzzy system
Research Division:	Engineering
Research Group:	Electrical engineering
Research Field:	Electrical energy generation (incl. renewables, excl. photovoltaics)
Objective Division:	Energy
Objective Group:	Renewable energy
Objective Field:	Renewable energy not elsewhere classified
UTAS Author:	Eslami, A (Mr Ahmadreza Eslami)
UTAS Author:	Negnevitsky, M (Professor Michael Negnevitsky)
UTAS Author:	Franklin, Evan (Associate Professor Evan Franklin)
UTAS Author:	Lyden, S (Dr Sarah Lyden)
ID Code:	155271
Year Published:	2022
Web of Science® Times Cited:	9
Deposited By:	Engineering
Deposited On:	2023-02-08
Last Modified:	2023-02-08
Downloads:	0