Keyan Liu, Tianyuan Kang, Xueshun Ye, Muke Bai, Yaqian Fan
{"title":"基于XGBoost和SVM算法的配电网故障定位方法","authors":"Keyan Liu, Tianyuan Kang, Xueshun Ye, Muke Bai, Yaqian Fan","doi":"10.1049/cps2.12022","DOIUrl":null,"url":null,"abstract":"<p>Nowadays, the reliable supply of electric power is vital in all aspects of social life. With the development and participation of distributed generations, not only does an accurate fault location lets repair of a fault line as quickly as possible, but also it is of great significance to ensure the safe and stable economic operation of the power system. This study proposes a method to determine the fault location in distribution networks, which is a combination of Extreme Gradient Boosting and Support Vector Machine. The effectiveness of the proposed method is validated on an IEEE34-bus distribution network under single-phase-to-ground faults, using voltage measurements available at each node in the distribution network. The comparison in accuracy, precision, recall, F1-score and time-cost of the method in this study with K-Nearest Neighbour and Multi-Layer Perceptron demonstrates the feasibility of applying the proposed method in distribution system fault diagnosis.</p>","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12022","citationCount":"2","resultStr":"{\"title\":\"A fault location method of distribution network based on XGBoost and SVM algorithm\",\"authors\":\"Keyan Liu, Tianyuan Kang, Xueshun Ye, Muke Bai, Yaqian Fan\",\"doi\":\"10.1049/cps2.12022\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Nowadays, the reliable supply of electric power is vital in all aspects of social life. With the development and participation of distributed generations, not only does an accurate fault location lets repair of a fault line as quickly as possible, but also it is of great significance to ensure the safe and stable economic operation of the power system. This study proposes a method to determine the fault location in distribution networks, which is a combination of Extreme Gradient Boosting and Support Vector Machine. The effectiveness of the proposed method is validated on an IEEE34-bus distribution network under single-phase-to-ground faults, using voltage measurements available at each node in the distribution network. The comparison in accuracy, precision, recall, F1-score and time-cost of the method in this study with K-Nearest Neighbour and Multi-Layer Perceptron demonstrates the feasibility of applying the proposed method in distribution system fault diagnosis.</p>\",\"PeriodicalId\":36881,\"journal\":{\"name\":\"IET Cyber-Physical Systems: Theory and Applications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2021-10-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12022\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IET Cyber-Physical Systems: Theory and Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1049/cps2.12022\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Cyber-Physical Systems: Theory and Applications","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cps2.12022","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
A fault location method of distribution network based on XGBoost and SVM algorithm
Nowadays, the reliable supply of electric power is vital in all aspects of social life. With the development and participation of distributed generations, not only does an accurate fault location lets repair of a fault line as quickly as possible, but also it is of great significance to ensure the safe and stable economic operation of the power system. This study proposes a method to determine the fault location in distribution networks, which is a combination of Extreme Gradient Boosting and Support Vector Machine. The effectiveness of the proposed method is validated on an IEEE34-bus distribution network under single-phase-to-ground faults, using voltage measurements available at each node in the distribution network. The comparison in accuracy, precision, recall, F1-score and time-cost of the method in this study with K-Nearest Neighbour and Multi-Layer Perceptron demonstrates the feasibility of applying the proposed method in distribution system fault diagnosis.