Power Quality Management and Classification for Smart Grid Application using Machine Learning

The Efficient Wavelet-based Convolutional Transformer network (EWT-ConvT) is proposed to detect power quality disturbances in time-frequency domain using attention mechanism. The support of machine learning further improves the network accuracy with synthetic signal generation and less system comple...

Full description

Bibliographic Details
Main Author: Chiam, Dar Hung
Format: Thesis
Published: Curtin University 2023
Online Access:http://hdl.handle.net/20.500.11937/92726
_version_ 1848765657327337472
author Chiam, Dar Hung
author_facet Chiam, Dar Hung
author_sort Chiam, Dar Hung
building Curtin Institutional Repository
collection Online Access
description The Efficient Wavelet-based Convolutional Transformer network (EWT-ConvT) is proposed to detect power quality disturbances in time-frequency domain using attention mechanism. The support of machine learning further improves the network accuracy with synthetic signal generation and less system complexity under practical environment. The proposed EWT-ConvT can achieve 94.42% accuracy which is superior than other deep learning models. The detection of disturbances using EWT-ConvT can also be implemented into smart grid applications for real-time embedded system development.
first_indexed 2025-11-14T11:38:44Z
format Thesis
id curtin-20.500.11937-92726
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:38:44Z
publishDate 2023
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-927262023-07-10T03:29:30Z Power Quality Management and Classification for Smart Grid Application using Machine Learning Chiam, Dar Hung The Efficient Wavelet-based Convolutional Transformer network (EWT-ConvT) is proposed to detect power quality disturbances in time-frequency domain using attention mechanism. The support of machine learning further improves the network accuracy with synthetic signal generation and less system complexity under practical environment. The proposed EWT-ConvT can achieve 94.42% accuracy which is superior than other deep learning models. The detection of disturbances using EWT-ConvT can also be implemented into smart grid applications for real-time embedded system development. 2023 Thesis http://hdl.handle.net/20.500.11937/92726 Curtin University fulltext
spellingShingle Chiam, Dar Hung
Power Quality Management and Classification for Smart Grid Application using Machine Learning
title Power Quality Management and Classification for Smart Grid Application using Machine Learning
title_full Power Quality Management and Classification for Smart Grid Application using Machine Learning
title_fullStr Power Quality Management and Classification for Smart Grid Application using Machine Learning
title_full_unstemmed Power Quality Management and Classification for Smart Grid Application using Machine Learning
title_short Power Quality Management and Classification for Smart Grid Application using Machine Learning
title_sort power quality management and classification for smart grid application using machine learning
url http://hdl.handle.net/20.500.11937/92726