基于高维随机矩阵的异常用电行为识别方法
|
摘要
基于高维随机矩阵理论,提出一种用户异常用电行为识别方法。该方法利用电网用户侧大数据构建高维随机矩阵,得出其矩阵特征值的谱分布和谱密度函数,通过M-P定律和单环定律判断样本数据有无异常;并通过平均谱半径确定用户用电异常时间区段。通过对某电网公司某台区近一年半的日用电量和有功功率数据进行分析,验证该方法的准确性和有效性。结果表明该方法能解决传统异常用电行为识别方法耗费人力大、时效性差及识别不精准等问题。
Based on the high dimensional random matrix theory, this paper proposes a kind of recognition method for users' abnormal electricity consumption behavior. By using big data of power grid user side, this method constructs a high dimensional random matrix and obtains spectral distribution and spectral density functions of matrix eigenvalues. According to M-P's law and single loop law, the method is used to decide whether sample data is abnormal or not. Meanwhile, it determines abnormal time section of electricity consumption according to mean spectral radius. On the basis of analyzing data of daily electricity consumption and reactive power in recent a year and half of a certain area of a power grid, correctness and effectiveness of this method is verified. The results indicate the method can solve problems of traditional recognition methods for abnormal electricity consumption behavior such as large manpower, poor timeliness, inaccurate recognition, and so on.
Based on the high dimensional random matrix theory, this paper proposes a kind of recognition method for users' abnormal electricity consumption behavior. By using big data of power grid user side, this method constructs a high dimensional random matrix and obtains spectral distribution and spectral density functions of matrix eigenvalues. According to M-P's law and single loop law, the method is used to decide whether sample data is abnormal or not. Meanwhile, it determines abnormal time section of electricity consumption according to mean spectral radius. On the basis of analyzing data of daily electricity consumption and reactive power in recent a year and half of a certain area of a power grid, correctness and effectiveness of this method is verified. The results indicate the method can solve problems of traditional recognition methods for abnormal electricity consumption behavior such as large manpower, poor timeliness, inaccurate recognition, and so on.
引文
[1]YAP K S,TIONG S K,NAGI J,et al.Comparison of supervised learning techniques for non-technical loss detection in power utility[J].International Review on Computers&Software,2012,7(2):626-636.
[2]NAGI J,YAP K S,TIONG S K,et al.Nontechnical loss detection for metered customers in power utility using support vector machines[J].IEEE Transactions on Power Delivery,2010,25(2):1162-1171.
[3]刘杰,侯跃斌,刘念.针对非技术性损失的智能用电异常识别方法[J].华东电力,2014,42(4):650-656.LIU Jie,HOU Yuebin,LIU Nian.Abnormity detection method of intelligent electricity consumption for nontechnical loss[J].Ease China Electric Power,2014,42(4):650-656.
[4]刘仕宁,陈从坦.电力设备异常运行及事故处理[J].工业,2017,10(3):00239-00239.LIU Shining,CHEN Congtan.Abnormal operation of power equipment and accident handling[J].Industry,2017,10(3):00239-00239.
[5]胡江溢,祝恩国,杜新纲,等.用电信息采集系统应用现状及发展趋势[J].电力系统自动化,2014(2):131-135.HU Jiangyi,ZHU Enguo,DU Xingang,et al.Application status and development trend of power consumption information collection system[J].Automation of Electric Power Systems,2014(2):131-135.
[6]中国电机工程学会电力信息化专业委员会.中国电力大数据发展白皮书(2013)[M].北京:中国电力出版社,2013.
[7]李占英.智能配电网大数据应用技术与前景分析[J].电力大数据,2017,20(11):18-20.LI Zhanying.Intelligent power distribution network and prospect analysis technology of data applications[J].Power Systems and Big Data,2017,20(11):18-20.
[8]王立斌,李振东,等.一种用电信息采集系统异常电量数据的识别与修复方法[J].电力大数据,2018,20(3):74-78.WANG Libin,LI Zhendong,et al.A method of identifying and repairing abnormal electric energy data in electric information acquisition system[J].Power Systems and Big Data,2018,20(3):74-78.
[9]陈冬沣,肖建华,周志琴,等.基于组合模型的负荷预测在地区电网反窃电中的应用[J].内蒙古电力技术,2017,35(2):67-70,74.CHEN Dongfeng,XIAO Jianhua,ZHOU Zhiqin,et al.Application of load forecasting based on combined models in regional power grid anti-stealing[J].Inner Mongolia Electric Power,2017,35(2):67-70,74.
[10]NAGI J,YAP K S,TIONG S K,et al.Detection of abnormalities and electricity theft using genetic support vector machines[C]//TENCON2008-2008 IEEE Region10Conference.Piscataway:IEEE,2009:1-6.
[11]林幕群,彭显刚,林利祥,等.基于数据挖掘技术的电价执行在线稽查模型[J].广东电力,2016(1):108-112.LIN Muqun,PENG Xiangang,LIN Lixiang,et al.Online Inspection model for electricity price implementation based on data mining technology[J].Guangdong Electric Power,2016(1):108-112.
[12]田力,向敏.基于密度聚类技术的电力系统用电量异常分析算法[J].电力系统自动化,2017(5):64-70.TIAN Li,XIANG Min.Abnormal power consumption analysis based on density based spatial ciustering of applications with noise in power systems[J].Automation of Electric Power Systems,2017(5):64-70.
[13]MONEDERO I,BISCARRI F,LEN C,et al.Detection of frauds and other non-technical-losses in a power utility using Pearson coefficient,Bayesian networks and decision trees[J].International Journal of Electrical Power&Energy Systems,2012,34(1):90-98.
[14]庄池杰,张斌,胡军,等.基于无监督学习的电力用户异常用电行为识别[J].中国电机工程学报,2016,36(2):379-387.ZHUANG Chijie,ZHANG Bin,HU Jun,et al.Anomaly detection for power consumption patterns based on unsupervised learning[J].Proceedings of the CSEE,2016,36(2):379-387.
[15]程超,张汉敬,景志敏,等.基于离群点算法和用电信息采集系统的反窃电研究[J].电力系统保护与控制,2015(17):69-74.CHENG Chao,ZHANG Hanjing,JING Zhimin,et al.Study on the anti-electricity stealing based on outlier algorithm and the electricity information acquisition system[J].Power System Protection and Control,2015(17):69-74.
[16]曹峥,杨镜非,刘晓娜.BP神经网络在反窃电系统中的研究与应用[J].水电能源科学,2011,29(9):199-202.CAO Zheng,YANG Jingfei,LIU Xiaona.Study and application of preventing system from stealing power based on BP neural network[J].Water Resources and Power,2011,29(9):199-202.
[17]严英杰,盛戈皞,陈玉峰,等.基于时间序列分析的输变电设备状态大数据清洗方法[J].电力系统自动化,2015(7):138-144.YAN Yingjie,SHENG Gehao,CHEN Yufeng,et al.Cleaning method for big data of power transmission and transformation equipment state based on time sequence analysis[J].Automation of Electric Power Systems,2015(7):138-144.
[18]王德文,杨力平.智能电网大数据流式处理方法与状态监测异常识别[J].电力系统自动化,2016,40(14):122-128.WANG Dewen,YANG Liping.Stream processing method and condition monitoring anomaly detection for big data in smart grid[J].Automation of Electric Power Systems,2016,40(14):122-128.
[19]HU W,GAO J,WANG Y,et al.Online adaboost-based parameterized methods for dynamic distributed network intrusion detection.[J].IEEE Transactions on Cybernetics,2013,44(1):66-82.
[20]BAI Zhidong,SILVERSTEIN J W.Spectral analysis of large dimensional random matrices[M].New York:Springer,2010.
[21]李子龙,刘亚东,王耀东,等.基于大维随机矩阵的电网异常快速识别方法[J].陕西电力,2017,45(3):77-81.LI Zilong,LIU Yadong,WANG Yaodong,et al.Abnormal situation detection in power grid with large-dimensional random matrix spectral distribution[J].Shaanxi Electric Power,2017,45(3):77-81.
[22]姜丹丹.大维随机矩阵谱理论在多元统计分析中的应用[D].吉林:东北师范大学,2010.
[23]魏大千,王波,刘涤尘,等.高维随机矩阵描述下的量测大数据建模与异常数据识别方法[J].中国电机工程学报,2015,35(增刊1):59-66.WEI Daqian,WANG Bo,LIU Dichen,et al.A method for WAMS big data modeling and abnormal data detection with large random matrices[J].Proceedings of the CSEE,2015,35(S1):59-66.
[24]杨婧,辛明勇.基于拉依达准则的计量自动化系统数据准确性判断方法[J].电力大数据,2017,20(11):74-78.YANG Jing,XIN Mingyong.Data accuracy judgment method of metrology automation system based on La Yida criterion[J].Power Systems and Big Data,2017,20(11):74-78.
[2]NAGI J,YAP K S,TIONG S K,et al.Nontechnical loss detection for metered customers in power utility using support vector machines[J].IEEE Transactions on Power Delivery,2010,25(2):1162-1171.
[3]刘杰,侯跃斌,刘念.针对非技术性损失的智能用电异常识别方法[J].华东电力,2014,42(4):650-656.LIU Jie,HOU Yuebin,LIU Nian.Abnormity detection method of intelligent electricity consumption for nontechnical loss[J].Ease China Electric Power,2014,42(4):650-656.
[4]刘仕宁,陈从坦.电力设备异常运行及事故处理[J].工业,2017,10(3):00239-00239.LIU Shining,CHEN Congtan.Abnormal operation of power equipment and accident handling[J].Industry,2017,10(3):00239-00239.
[5]胡江溢,祝恩国,杜新纲,等.用电信息采集系统应用现状及发展趋势[J].电力系统自动化,2014(2):131-135.HU Jiangyi,ZHU Enguo,DU Xingang,et al.Application status and development trend of power consumption information collection system[J].Automation of Electric Power Systems,2014(2):131-135.
[6]中国电机工程学会电力信息化专业委员会.中国电力大数据发展白皮书(2013)[M].北京:中国电力出版社,2013.
[7]李占英.智能配电网大数据应用技术与前景分析[J].电力大数据,2017,20(11):18-20.LI Zhanying.Intelligent power distribution network and prospect analysis technology of data applications[J].Power Systems and Big Data,2017,20(11):18-20.
[8]王立斌,李振东,等.一种用电信息采集系统异常电量数据的识别与修复方法[J].电力大数据,2018,20(3):74-78.WANG Libin,LI Zhendong,et al.A method of identifying and repairing abnormal electric energy data in electric information acquisition system[J].Power Systems and Big Data,2018,20(3):74-78.
[9]陈冬沣,肖建华,周志琴,等.基于组合模型的负荷预测在地区电网反窃电中的应用[J].内蒙古电力技术,2017,35(2):67-70,74.CHEN Dongfeng,XIAO Jianhua,ZHOU Zhiqin,et al.Application of load forecasting based on combined models in regional power grid anti-stealing[J].Inner Mongolia Electric Power,2017,35(2):67-70,74.
[10]NAGI J,YAP K S,TIONG S K,et al.Detection of abnormalities and electricity theft using genetic support vector machines[C]//TENCON2008-2008 IEEE Region10Conference.Piscataway:IEEE,2009:1-6.
[11]林幕群,彭显刚,林利祥,等.基于数据挖掘技术的电价执行在线稽查模型[J].广东电力,2016(1):108-112.LIN Muqun,PENG Xiangang,LIN Lixiang,et al.Online Inspection model for electricity price implementation based on data mining technology[J].Guangdong Electric Power,2016(1):108-112.
[12]田力,向敏.基于密度聚类技术的电力系统用电量异常分析算法[J].电力系统自动化,2017(5):64-70.TIAN Li,XIANG Min.Abnormal power consumption analysis based on density based spatial ciustering of applications with noise in power systems[J].Automation of Electric Power Systems,2017(5):64-70.
[13]MONEDERO I,BISCARRI F,LEN C,et al.Detection of frauds and other non-technical-losses in a power utility using Pearson coefficient,Bayesian networks and decision trees[J].International Journal of Electrical Power&Energy Systems,2012,34(1):90-98.
[14]庄池杰,张斌,胡军,等.基于无监督学习的电力用户异常用电行为识别[J].中国电机工程学报,2016,36(2):379-387.ZHUANG Chijie,ZHANG Bin,HU Jun,et al.Anomaly detection for power consumption patterns based on unsupervised learning[J].Proceedings of the CSEE,2016,36(2):379-387.
[15]程超,张汉敬,景志敏,等.基于离群点算法和用电信息采集系统的反窃电研究[J].电力系统保护与控制,2015(17):69-74.CHENG Chao,ZHANG Hanjing,JING Zhimin,et al.Study on the anti-electricity stealing based on outlier algorithm and the electricity information acquisition system[J].Power System Protection and Control,2015(17):69-74.
[16]曹峥,杨镜非,刘晓娜.BP神经网络在反窃电系统中的研究与应用[J].水电能源科学,2011,29(9):199-202.CAO Zheng,YANG Jingfei,LIU Xiaona.Study and application of preventing system from stealing power based on BP neural network[J].Water Resources and Power,2011,29(9):199-202.
[17]严英杰,盛戈皞,陈玉峰,等.基于时间序列分析的输变电设备状态大数据清洗方法[J].电力系统自动化,2015(7):138-144.YAN Yingjie,SHENG Gehao,CHEN Yufeng,et al.Cleaning method for big data of power transmission and transformation equipment state based on time sequence analysis[J].Automation of Electric Power Systems,2015(7):138-144.
[18]王德文,杨力平.智能电网大数据流式处理方法与状态监测异常识别[J].电力系统自动化,2016,40(14):122-128.WANG Dewen,YANG Liping.Stream processing method and condition monitoring anomaly detection for big data in smart grid[J].Automation of Electric Power Systems,2016,40(14):122-128.
[19]HU W,GAO J,WANG Y,et al.Online adaboost-based parameterized methods for dynamic distributed network intrusion detection.[J].IEEE Transactions on Cybernetics,2013,44(1):66-82.
[20]BAI Zhidong,SILVERSTEIN J W.Spectral analysis of large dimensional random matrices[M].New York:Springer,2010.
[21]李子龙,刘亚东,王耀东,等.基于大维随机矩阵的电网异常快速识别方法[J].陕西电力,2017,45(3):77-81.LI Zilong,LIU Yadong,WANG Yaodong,et al.Abnormal situation detection in power grid with large-dimensional random matrix spectral distribution[J].Shaanxi Electric Power,2017,45(3):77-81.
[22]姜丹丹.大维随机矩阵谱理论在多元统计分析中的应用[D].吉林:东北师范大学,2010.
[23]魏大千,王波,刘涤尘,等.高维随机矩阵描述下的量测大数据建模与异常数据识别方法[J].中国电机工程学报,2015,35(增刊1):59-66.WEI Daqian,WANG Bo,LIU Dichen,et al.A method for WAMS big data modeling and abnormal data detection with large random matrices[J].Proceedings of the CSEE,2015,35(S1):59-66.
[24]杨婧,辛明勇.基于拉依达准则的计量自动化系统数据准确性判断方法[J].电力大数据,2017,20(11):74-78.YANG Jing,XIN Mingyong.Data accuracy judgment method of metrology automation system based on La Yida criterion[J].Power Systems and Big Data,2017,20(11):74-78.