摘要
针对低压配电网拓扑结构人工校验成本高、实时性不强的问题,提出了一种基于皮尔逊相关系数和KNN算法的低压配电网拓扑结构纯软件在线校验方法。首先用皮尔逊相关系数判断用户电压序列曲线的相似性,通过相关系数算法校验台区户变关系的正确性,找出户变关系不正确的用户,进行再校验。对于需再校验的用户,基于GIS系统的数据和《配电网规划设计技术导则》剪辑生成用户样本集,运用KNN算法分析剪辑生成用户样本集,然后找出校验用户所属的正确台区。最后根据人工现场校验结果,判断算法校验的正确性。
In view of the high cost and low real-time performance of the low voltage distribution network topology structure, a new online check method for low voltage distribution network topology based on Pearson correlation coefficient and KNN algorithm is proposed. First, the similarity of the user voltage sequence curve is judged by the correlation coefficient of Pearson. The correlation coefficient algorithm is used to verify the correctness of the relationship between the transformer and the user in the platform area, then find out the users with incorrect relationship and check again. For the users who need to be checked again, based on the data of GIS system and Technical Guidelines for Distribution Network Planning and Design, the user sample set is generated. The KNN algorithm is used to analyze the clips to generate the user sample set, and then the correct platform area is checked by the user. Finally, the correctness of the algorithm is judged according to the results of the artificial field check.
引文
[1]郑杰,赵敬凤,王海江,等.一种基于载波通信的电力相位识别方法[J].电测与仪表,2015,52(增刊1):85-87.ZHENG Jie,ZHAO Jingfeng,WANG Haijiang,et al.Apower phase recognition method based on carrier communication[J].Electrical Measurement and Instrumentation,2015,52(S1):85-87.
[2]孙乐乐,杨鹏举,童仁莉,等.电力相位识别技术研究与实现[J].机电信息,2017,47(30):90-91.SUN Lele,YANG Pengju,TONG Renli,et al.Research and implementation of power phase identification technology[J].Electromechanical Information,2017,47(30):90-91.
[3]LUAN W,PENG J,MARAS M,et al.Distribution network topology error correction using smart meter data analytics[C]//IEEE Power Engineering Society general meeting,2013,Vancouver,Canada:21-25.
[4]林景栋,曹长修,张帮礼.基于分层模型的配电网拓扑辨识[J].重庆大学学报(自然科学版),2002,25(2):71-74.LIN Jingdong,CAO Changxiu,ZHANG Bangli.Topology identification of distribution network based on hierarchical model[J].Journal of Chongqing University(Natural Science),2002,25(2):71-74.
[5]徐大青,栾文鹏,王鹏,等.智能电表数据分析方法及应用[J].供用电,2015,32(8):25-30.XU Daqing,LUAN Wenpeng,WANG Peng,et al.Analysis and applications of smart meter data[J].Utilization&Distribution,2015,32(8):25-30.
[6]王汪兵,王先培,尤泽樟,等.电力通信网关键节点辨识方法研究[J].电力系统保护与控制,2018,46(1):44-49.WANG Wangbing,WANG Xianpei,YU Zezhang,et al.Key node identification method of power communication network[J].Power System Protection and Control,2018,46(1):44-49.
[7]应俊,梅军,王勇,等.配电主站馈线拓扑模型校核方法研究[J].电力系统保护与控制,2018,46(7):83-89.YING Jun,MEI Jun,WANG Yong,et al.Research on the topology model of the feeder line model of distribution main station[J].Power System Protection and Control,2018,46(7):83-89.
[8]郎燕生,李静,罗雅迪,等.基于图划分的大电网拓扑分析[J].电力系统保护与控制,2017,45(23):108-115.LANG Yansheng,LI Jing,LUO Yadi,et al.The topology analysis of large grid based on graph division[J].Power System Protection and Control,2017,45(23):108-115.
[9]李昂,刘亚东,孙鹏,等.基于μPMU相位数据的配电网拓扑识别方法[J].智慧电力,2017,45(11):31-36.LI Ang,LIU Yadong,SUN Peng,et al.Distribution network topology identification method based on phase data ofμPMU[J].Smart Power,2017,45(11):31-36.
[10]耿俊成,吴博,万迪明,等.基于离群点检测的低压配电网拓扑结构校验[J].电力信息与通信技术,2017,15(5):61-65.GENG Juncheng,WU Bo,WAN Diming,et al.Topology verification of low voltage distribution network based on outlier detection[J].Power Information and Communication Technology,2017,15(5):61-65.
[11]梅睿,余昆,陈星莺.基于节点注入功率的配电网运行拓扑辨识[J].电力建设,2017,38(11):41-47.MEI Rui,YU Kun,CHEN Xingying.Topology identification of power distribution network based on node injection power[J].Electric Power Construction,2017,38(11):41-47.
[12]王涓,吴旭鸣,王爱凤.应用皮尔逊相关系数算法查找异常电能表用户[J].电力需求侧管理,2014,16(2):52-54.WANG Juan,WU Xuming,WANG Aifeng.The application of Pearson correlation coefficient algorithm in searching for the users with abnormal watt-hour meters[J].Power Demand Side Management,2014,16(2):52-54.
[13]栾文鹏,余贻鑫,工兵.AMI数据分析方法[J].中国电机工程学报,2015,35(1):29-36.LUAN Wenpeng,YU Yixin,GONG Bing.AMI data analytics[J].Proceedings of the CSEE,2015,35(1):29-36.
[14]LUAN W,PENG J,MARAS M,et al.Smart meter data analytics for distribution network connectivity verification[J].IEEE Transactions on Smart Grid,2015,6(4):1964-1971.
[15]张世强,吕杰能,蒋峥,等.关于相关系数的探讨[J].数学的实践与认识,2009,39(19):102-107.ZHANG Shiqiang,LüJieneng,JIANG Zheng,et al.Study of the correlation coefficients in mathematical statistics[J].Mathematics in Practice and Theory,2009,39(19):102-107.
[16]陈永秀.相关系数含义的理解[J].中国考试,2011(7):15-19.CHEN Yongxiu.Understanding of the meaning of correlation coefficient[J].Chinese Examination,2011(7):15-19.
[17]邵凡,陈辰,葛淼佳,等.基于电网线损的皮尔逊算法分析[J].科技创新与应用,2017(14):54-55.SHAO Fan,CHEN Chen,GE Miaojia,et al.Analysis of technology innovation and application based on the power line loss Pearson algorithm[J].Scientific and Technological Innovation,2017(14):54-55.
[18]闭小梅,闭瑞华.KNN算法综述[J].科技创新导报,2009(14):31.BI Xiaomei,BI Ruihua.KNN algorithm summary[J].Science and Technology Innovation Guide,2009(14):31.
[19]配电网规划设计技术导则:Q/GDW1738-2012[S].Technical guidelines for distribution network planning and design:Q/GDW1738-2012[S].
[20]耿俊成,张小斐,郭志民,等.基于离散Frechet距离和剪辑近邻法的低压配电网拓扑结构校验方法[J].电测与仪表,2017,54(5):50-55.GENG Juncheng,ZHANG Xiaofei,GUO Zhimin,et al.Low voltage distribution network topology verification method based on discrete Frechet distance and clipping near neighbor method[J].Electrical Measurement and Instrumentation,2017,54(5):50-55.