X. Zhao, Linhuan Luo, Guolong Ma, Z. Cai, Zhanji Gu, Qinghai Wang
{"title":"基于大数据挖掘的配电网运维管理与决策分析","authors":"X. Zhao, Linhuan Luo, Guolong Ma, Z. Cai, Zhanji Gu, Qinghai Wang","doi":"10.1109/POWERCON.2018.8601825","DOIUrl":null,"url":null,"abstract":"The operation and maintenance management of the distribution network (DN) mainly includes fault analysis, active early-warning and differentiated operation and maintenance. In the context of multi-time-scale and multi-spatial-temporal data in DN, this paper deals with the application of data mining for distribution network operation and maintenance management. In the paper, the one-dimensional fault feature is extracted from fault information by K-means clustering algorithm. Then, we employed Apriori algorithm to mine association rules of different failure modes and establish key performance matrix. The spatial-temporal characteristics are analyzed based on high-dimensional random matrix theory (RMT). Afterwards, one-dimensional and multi-dimensional fault features are combined based on D-S evidence theory so that the fault diagnosis criteria of DN is obtained. At the same time, comprehensively considering the DN operating state and the variation for power users, health index and importance index of equipment are established, which could help to significantly reduce the decision-making risk of DN operation and maintenance. The result of simulation proves the effectiveness of the proposed method.","PeriodicalId":260947,"journal":{"name":"2018 International Conference on Power System Technology (POWERCON)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Operation and Maintenance Management and Decision Analysis in Distribution Network Based on Big Data Mining\",\"authors\":\"X. Zhao, Linhuan Luo, Guolong Ma, Z. Cai, Zhanji Gu, Qinghai Wang\",\"doi\":\"10.1109/POWERCON.2018.8601825\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The operation and maintenance management of the distribution network (DN) mainly includes fault analysis, active early-warning and differentiated operation and maintenance. In the context of multi-time-scale and multi-spatial-temporal data in DN, this paper deals with the application of data mining for distribution network operation and maintenance management. In the paper, the one-dimensional fault feature is extracted from fault information by K-means clustering algorithm. Then, we employed Apriori algorithm to mine association rules of different failure modes and establish key performance matrix. The spatial-temporal characteristics are analyzed based on high-dimensional random matrix theory (RMT). Afterwards, one-dimensional and multi-dimensional fault features are combined based on D-S evidence theory so that the fault diagnosis criteria of DN is obtained. At the same time, comprehensively considering the DN operating state and the variation for power users, health index and importance index of equipment are established, which could help to significantly reduce the decision-making risk of DN operation and maintenance. The result of simulation proves the effectiveness of the proposed method.\",\"PeriodicalId\":260947,\"journal\":{\"name\":\"2018 International Conference on Power System Technology (POWERCON)\",\"volume\":\"29 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 International Conference on Power System Technology (POWERCON)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/POWERCON.2018.8601825\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Conference on Power System Technology (POWERCON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/POWERCON.2018.8601825","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Operation and Maintenance Management and Decision Analysis in Distribution Network Based on Big Data Mining
The operation and maintenance management of the distribution network (DN) mainly includes fault analysis, active early-warning and differentiated operation and maintenance. In the context of multi-time-scale and multi-spatial-temporal data in DN, this paper deals with the application of data mining for distribution network operation and maintenance management. In the paper, the one-dimensional fault feature is extracted from fault information by K-means clustering algorithm. Then, we employed Apriori algorithm to mine association rules of different failure modes and establish key performance matrix. The spatial-temporal characteristics are analyzed based on high-dimensional random matrix theory (RMT). Afterwards, one-dimensional and multi-dimensional fault features are combined based on D-S evidence theory so that the fault diagnosis criteria of DN is obtained. At the same time, comprehensively considering the DN operating state and the variation for power users, health index and importance index of equipment are established, which could help to significantly reduce the decision-making risk of DN operation and maintenance. The result of simulation proves the effectiveness of the proposed method.