[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121688-en":3,"doc-seo-121688-105":30,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121688,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Power Quality Management and Classification for Smart Grid Application using Machine Learning","Power Quality Management and Classification for Smart Grid Application using Machine Learning focuses on detecting and controlling power quality disturbances (PQDs) to optimize renewable energy utilization and power-flow management in smart grids. The work structures PQD classification into knowledge-based, model-based deep learning, and hybrid approaches, then proposes a hybrid pipeline using multi-level signal decomposition with wavelet transform. WT-SFA-LSTM reaches 93.79% accuracy, surpassing a Deep CNN baseline, while later models introduce transformer-based convolutional designs (WT-ConvT and EWT-ConvT). The real-time embedded implementation on Raspberry Pi 4B verifies fast PQD classification across three disturbance classes.","School of Engineering and Science Department of Electrical and Computer Engineering  \nPower Quality Management and Classification for Smart Grid Application using Machine Learning  \nChiam Dar Hung  \nID 0000-0001-8455-8658  \nThis thesis is presented for the degree of  \nDoctor of Philosophy  \nof  \nCurtin University  \nDeclaration  \nTo the best of my knowledge and belief, this thesis contains no material previously published by any other person except where due acknowledgment has been made.  \nThis thesis contains no material which has been accepted for the award of any other degree or diploma in any university.  \nSignature:  \nDate:  \nAcknowledgements  \nFirst and foremost, I would like to express my sincere gratitude towards my main supervisor Prof. Garenth Lim King Hann for the continuous support and guidance [in my Ph.D. study. Thank you](in my Ph.D. study. Thank you) for providing us with all the required hardware and research needs. Thank you for your patience in guiding me for more than seven years in my university life. The motivationsand mental supports from you are priceless. Next, i would also like to thank my research committee, Dr. Law Kah Haw and A/Prof. Ling Huo Chong in supporting my research with all the useful comments and suggestions.  \nI would also like to express special gratitude towards my research companion, Dr. Jonathan Phang Then Sien. Thank you for your companionship throughout my studies. Thank you also for all the guidance in the field of machine learning. I couldn’t imagine the research journey without your great support. Moreover, I would like to thank all the ECE department staffs in Curtin Malaysia. Thank you for all the support given during my study, especially when carrying out experiments in the lab. Thank you Curtin Malaysia for providing a safe and comfortable place for the research.  \nLast but not least, I would also like to thank my friends and family for supporting my Ph.D. journey. Thank you for your companionship throughout these years. I am truly thankful to my loving parents, Chiam Tow Jin and Pang Nyuk Ngo for providing me with such a healthy environment for my physical and mental growth, and with the opportunity to further my studies.  \nAbstract  \nThe advancement of the smart grid is crucial in optimizing renewable energy resource utilization and power flow management with better power quality disturbance (PQD) detection and control. The classification of PQD detection can be divided into three types, i.e. knowledge-based method, model-based method and hybrid method. The knowledge-based method requires expert knowledge to manually extract PQD features using the mathematical form for classification. On the other hand, model-based methods apply a deep learning approach to automatically select features based on data representation to achieve better classification performance. The hybrid method integrates the advantage of knowledge-based signal processing tools in providing semi-processed signals, and combines with model-based methods for automatic feature extraction and selections.  \nA hybrid method using multi-level signal decomposition (MSD) with wavelet transform (WT) is proposed to improve the poor magnitude sensitivity on high-frequency signals. Our proposed model WT-SFA-LSTM combines MSD with a spatial attention mechanism to achieve a classification accuracy of 93 .79% . This performance is better than the state-of-the-art Deep CNN model with 90 .56% accuracy. However, further improvement is required to address the 32% larger model size of WT-SFA-LSTM compared to the Deep CNN model. On the other hand, a transformer with a multihead attention mechanism, and faster computation via parallel processing on sequential input is introduced to replace LSTM. A compact model waveletbased convolutional transformer (WT-ConvT) is proposed to address the issue of insensitivity to small-magnitude changes. Results show that WTConvT achieves a better classification accuracy of 94 . 11% . An efficient W","cbCaimknAx4EHPoG","https://ap.wps.com/l/cbCaimknAx4EHPoG","pdf",6744172,1,147,"English","en",105,"# Abstract\n## PQD classification approaches\n## Proposed models and performance\n## Real-time hardware implementation\n## Publications","[{\"question\":\"How is real-time PQD classification validated?\",\"answer\":\"A Raspberry Pi 4B-based real-time embedded system captures PQD waveforms and classifies three disturbance classes; EWT-ConvT classifies a 200 ms signal waveform within 75.51 ms to demonstrate real-time capability.\"}]","Power Quality Management and Classification for Smart Grid Application using Machine Learning | PDF",1785806247,370,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"power-quality-management-and-classification-for-smart-grid-application-using-machine-learning","",{"@graph":36,"@context":77},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/power-quality-management-and-classification-for-smart-grid-application-using-machine-learning/121688/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How is real-time PQD classification validated?","Question",{"text":75,"@type":76},"A Raspberry Pi 4B-based real-time embedded system captures PQD waveforms and classifies three disturbance classes; EWT-ConvT classifies a 200 ms signal waveform within 75.51 ms to demonstrate real-time capability.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]