Wenpeng Luan, Da Xu, Bo Liu, Wenqian Jiang, Li Feng, Wenbin Liu
{"title":"Improved topology identification for distribution network with relatively balanced power supplies","authors":"Wenpeng Luan, Da Xu, Bo Liu, Wenqian Jiang, Li Feng, Wenbin Liu","doi":"10.1049/esi2.12142","DOIUrl":null,"url":null,"abstract":"<p>Having correct distribution network topology information is essential for system state estimation, line loss analysis, electricity theft detection and fault location. At present, with continuous deployment of smart sensors, a large amount of monitoring data is collected, which enables refined management for distribution network. A data-driven low voltage (LV) distribution network topology identification method is proposed, which realises transformer-customer pairing and customer phase identification for distribution network with relatively balanced power supplies. Firstly, an integrated similarity coefficient of voltage curve is proposed, which can reflect the neighbourhood relationship within stations while increase the distinction between stations; the K-Nearest Neighbour (KNN) algorithm is used to propagate the service transformer labels to complete transformer-customer association. Then, the influence of power fluctuation on voltage curve is analysed and a dynamic sliding window model is adopted to search for voltage segments with significantly difference among three phase feeders to formulate a voltage time series to identify customer phase. Finally, the results are corrected and verified based on the principle of network power balance. The proposed algorithm is tested in two different real substations in China and Europe and shows high accuracy and robustness especially in distribution network with relatively balanced power supplies.</p>","PeriodicalId":33288,"journal":{"name":"IET Energy Systems Integration","volume":"6 2","pages":"162-173"},"PeriodicalIF":1.6000,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/esi2.12142","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Energy Systems Integration","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/esi2.12142","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
Abstract
Having correct distribution network topology information is essential for system state estimation, line loss analysis, electricity theft detection and fault location. At present, with continuous deployment of smart sensors, a large amount of monitoring data is collected, which enables refined management for distribution network. A data-driven low voltage (LV) distribution network topology identification method is proposed, which realises transformer-customer pairing and customer phase identification for distribution network with relatively balanced power supplies. Firstly, an integrated similarity coefficient of voltage curve is proposed, which can reflect the neighbourhood relationship within stations while increase the distinction between stations; the K-Nearest Neighbour (KNN) algorithm is used to propagate the service transformer labels to complete transformer-customer association. Then, the influence of power fluctuation on voltage curve is analysed and a dynamic sliding window model is adopted to search for voltage segments with significantly difference among three phase feeders to formulate a voltage time series to identify customer phase. Finally, the results are corrected and verified based on the principle of network power balance. The proposed algorithm is tested in two different real substations in China and Europe and shows high accuracy and robustness especially in distribution network with relatively balanced power supplies.