基于堆叠去相关自编码器和支持向量机的窃电检测
|
摘要
已有窃电检测模型的准确率尚无法满足应用需求,是因其均将建模重点放在了分类算法的选择或改进上,而相对地忽视了特征提取过程。因此,提出一种基于深度学习的特征提取方法,即堆叠去相关自编码器。得益于深层结构和高度非线性,其能够从用户用电数据中提取到高度抽象和简明的特征。随后支持向量机将这些特征映射到指示是否窃电的标签。基于真实数据的算例测试,验证了所提窃电检测模型具有较高的检出率和较低的虚警率,同时也验证了堆叠去相关自编码器能够提取到有效的特征。
The performance of existing consumption-pattern based models is not sufficiently satisfactory for application.This is partly because most of them have focused on the selection of classification algorithms rather than the design of features,and existing feature design methods with respect to electricity nontechnical loss(NTL)detection remain inefficient and unsatisfactory.A deep-learning based feature extraction model is proposed for NTL detection,namely the stacked uncorrelating autoencoder(SUAE).Due to the deep architecture and powerful uncorrelating ability of SUAE,features are extracted from load profiles concisely and effectively,which has thus enabled a great improvement in final NTL detection performance.Support vector machines(SVM)are applied as classifiers,which use the features extracted by SUAE to output a judgment result.Case studies on real datasets have demonstrated that the proposed NTL model has high relevance ratio and low false alarm rate,as well as the powerful feature extraction ability of the SUAE.
The performance of existing consumption-pattern based models is not sufficiently satisfactory for application.This is partly because most of them have focused on the selection of classification algorithms rather than the design of features,and existing feature design methods with respect to electricity nontechnical loss(NTL)detection remain inefficient and unsatisfactory.A deep-learning based feature extraction model is proposed for NTL detection,namely the stacked uncorrelating autoencoder(SUAE).Due to the deep architecture and powerful uncorrelating ability of SUAE,features are extracted from load profiles concisely and effectively,which has thus enabled a great improvement in final NTL detection performance.Support vector machines(SVM)are applied as classifiers,which use the features extracted by SUAE to output a judgment result.Case studies on real datasets have demonstrated that the proposed NTL model has high relevance ratio and low false alarm rate,as well as the powerful feature extraction ability of the SUAE.
引文
[1]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.
[2]MILLARD R,EMMERTON M.Non-technical losses—how do other countries tackle the problem?[EB/OL].[2018-05-01].http://www.ameu.co.za/Portals/16/Conventions/Convention%202009/Papers/Non%20Technical%20Losses%20How%20do%20other%20countries%20tackle%20the%20problem%20-%20Ron%20Millard.pdf.
[3]JIANG R,LU R,WANG Y,et al.Energy-theft detection issues for advanced metering infrastructure in smart grid[J].Tsinghua Science and Technology,2014,19(2):105-120.
[4]JOKAR P,ARIANPOO N,LEUNG V C M.Electricity theft detection in AMI using customers’consumption patterns[J].IEEE Transactions on Smart Grid,2016,7(1):216-226.
[5]DEPURU S S S R,WANG L,DEVABHAKTUNI V.Support vector machine based data classification for detection of electricity theft[C]//2011 IEEE/PES Power Systems Conference and Exposition, March 20-23,2011,Phoenix,USA:1-8.
[6]JINDAL A,DUA A,KAUR K,et al.Decision tree and SVMbased data analytics for theft detection in smart grid[J].IEEE TransactionsonIndustrialInformatics, 2016, 12(3):1005-1016.
[7]NAGI J,YAP K S,TIONG S K,et al.Improving SVM-based nontechnical loss detection in power utility using the fuzzy inference system[J].IEEE Transactions on Power Delivery,2011,26(2):1284-1285.
[8]DEPURU S S S R,WANG L,DEVABHAKTUNI V,et al.A hybrid neural network model and encoding technique for enhanced classification of energy consumption data[C]//2011IEEE Power and Energy Society General Meeting,July 24-29,2011,Detroit,USA:1-8.
[9]NIZAR A H, DONG Z Y, WANG Y.Power utility nontechnical loss analysis with extreme learning machine method[J].IEEE Transactions on Power Systems,2008,23(3):946-955.
[10]GONTIJO E M,DELAIBA A C,MAZINA E,et al.Fraud identification in electricity company customers using decision tree[C]//2004IEEE International Conference on Systems,Man and Cybernetics,October 10-13,2004,The Hague,Netherlands:3730-3734.
[11]ANGELOS E W S,SAAVEDRA O R,CORTS O A C,et al.Detection and identification of abnormalities in customer consumptions in power distribution systems[J].IEEE Transactions on Power Delivery,2011,26(4):2436-2442.
[12]GOODFELLOW I,BENGIO Y,COURVILLE A,et al.Deep learning[M].Cambridge:MIT Press,2016.
[13]FABRIS F, MARGOTO L R, VAREJAO F M.Novel approaches for detecting frauds in energy consumption[C]//Third International Conference on Network and System Security, October 19-21,2009, Gold Coast, Australia:546-551.
[14]RAMOS C C O,de SOUZA A N,FALCAO A X,et al.New insights on nontechnical losses characterization through evolutionary-based feature selection[J].IEEE Transactions on Power Delivery,2012,27(1):140-146.
[15]RAMOS C C O,SOUZA A N,CHIACHIA G,et al.A novel algorithm for feature selection using harmony search and its application for non-technical losses detection[J].Computers&Electrical Engineering,2011,37(6):886-894.
[16]RAMOS C C O,RODRIGUES D,de SOUZA A N,et al.On the study of commercial losses in Brazil:a binary black hole algorithm for theft characterization[J].IEEE Transactions on Smart Grid,2018,9(2):676-683.
[17]NAGI J,MOHAMMAD A M,YAP K S,et al.Non-technical loss analysis for detection of electricity theft using support vector machines[C]//IEEE 2nd International Power and Energy Conference, December 1-3,2008,Johor Bahru,Malaysia:907-912.
[18]JIANG R,TAGARIS H,LACHSZ A,et al.Wavelet based feature extraction and multiple classifiers for electricity fraud detection[C]//IEEE/PES Transmission and Distribution Conference and Exhibition,October 6-10,2002,Yokohama,Japan:2251-2256.
[19]韩传家,张孝顺,余涛,等.风险调度中引入知识迁移的细菌觅食强化学习优化算法[J].电力系统自动化,2017,41(8):69-77.DOI:10.7500/AEPS20160619004.HAN Chuanjia, ZHANG Xiaoshun, YU Tao, et al.Optimization algorithm of reinforcement learning based knowledge transfer bacteria foraging for risk dispatch[J].Automation of Electric Power Systems,2017,41(8):69-77.DOI:10.7500/AEPS20160619004.
[20]孙润稼,刘玉田.基于深度学习和蒙特卡洛树搜索的机组恢复在线决策[J].电力系统自动化,2018,42(14):40-47.DOI:10.7500/AEPS20170930011.SUN Runjia, LIU Yutian. Online decision-making for generator start-up based on deep learning and Monte Carlo tree search[J].Automation of Electric Power Systems,2018,42(14):40-47.DOI:10.7500/AEPS20170930011.
[21]BOURLARD H,KAMP Y.Auto-association by multilayer perceptions and singular value decomposition[J].Biological Cybernetics,1988,59(4/5):291-294.
[22]LECUN Y.PhD thesis:Modeles connexionnistes de l’apprentissage(connectionist learning models)[D/OL].[2018-05-01].https://nyuscholars.nyu.edu/en/publications/phdthesis-modeles-connexionnistes-de-lapprentissage-connectionis.
[23]HINTON G E, ZEMEL R S.Autoencoders, minimum description length and Helmholtz free energy[C]//Proceedings of the 6th International Conference on Neural Information Processing Systems,November 29-December 2,1993,San Francisco,USA:3-10.
[24]SALAKHUTDINOV R,HINTON G.Semantic hashing[J].International Journal of Approximate Reasoning, 2009,50(7):969-978.
[25]HINTON G E,OSINDERO S,TEH Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[26]CHAPELLE O,HAFFNER P,VAPNIK V N.Support vector machines for histogram-based image classification[J].IEEE Transactions on Neural Networks,1999,10(5):1055-1064.
[27]JIA Y,SHELHAMER E, DONAHUE J,et al.Caffe:convolutional architecture for fast feature embedding[EB/OL].[2017-01-20].http://cn.arxiv.org/abs/1408.5093.
[28]ISSDA.Data from the commission for energy regulation[EB/OL].[2018-05-01].http://www.ucd.ie/issda/data/commis sionforenergyregulationcer/.
[29]SHIY. Particleswarmoptimization:developments,applications and resources[C]//Proceedings of the 2001Congress on Evolutionary Computation,May 27-30,2001,Seoul,South Korea:81-86.
[2]MILLARD R,EMMERTON M.Non-technical losses—how do other countries tackle the problem?[EB/OL].[2018-05-01].http://www.ameu.co.za/Portals/16/Conventions/Convention%202009/Papers/Non%20Technical%20Losses%20How%20do%20other%20countries%20tackle%20the%20problem%20-%20Ron%20Millard.pdf.
[3]JIANG R,LU R,WANG Y,et al.Energy-theft detection issues for advanced metering infrastructure in smart grid[J].Tsinghua Science and Technology,2014,19(2):105-120.
[4]JOKAR P,ARIANPOO N,LEUNG V C M.Electricity theft detection in AMI using customers’consumption patterns[J].IEEE Transactions on Smart Grid,2016,7(1):216-226.
[5]DEPURU S S S R,WANG L,DEVABHAKTUNI V.Support vector machine based data classification for detection of electricity theft[C]//2011 IEEE/PES Power Systems Conference and Exposition, March 20-23,2011,Phoenix,USA:1-8.
[6]JINDAL A,DUA A,KAUR K,et al.Decision tree and SVMbased data analytics for theft detection in smart grid[J].IEEE TransactionsonIndustrialInformatics, 2016, 12(3):1005-1016.
[7]NAGI J,YAP K S,TIONG S K,et al.Improving SVM-based nontechnical loss detection in power utility using the fuzzy inference system[J].IEEE Transactions on Power Delivery,2011,26(2):1284-1285.
[8]DEPURU S S S R,WANG L,DEVABHAKTUNI V,et al.A hybrid neural network model and encoding technique for enhanced classification of energy consumption data[C]//2011IEEE Power and Energy Society General Meeting,July 24-29,2011,Detroit,USA:1-8.
[9]NIZAR A H, DONG Z Y, WANG Y.Power utility nontechnical loss analysis with extreme learning machine method[J].IEEE Transactions on Power Systems,2008,23(3):946-955.
[10]GONTIJO E M,DELAIBA A C,MAZINA E,et al.Fraud identification in electricity company customers using decision tree[C]//2004IEEE International Conference on Systems,Man and Cybernetics,October 10-13,2004,The Hague,Netherlands:3730-3734.
[11]ANGELOS E W S,SAAVEDRA O R,CORTS O A C,et al.Detection and identification of abnormalities in customer consumptions in power distribution systems[J].IEEE Transactions on Power Delivery,2011,26(4):2436-2442.
[12]GOODFELLOW I,BENGIO Y,COURVILLE A,et al.Deep learning[M].Cambridge:MIT Press,2016.
[13]FABRIS F, MARGOTO L R, VAREJAO F M.Novel approaches for detecting frauds in energy consumption[C]//Third International Conference on Network and System Security, October 19-21,2009, Gold Coast, Australia:546-551.
[14]RAMOS C C O,de SOUZA A N,FALCAO A X,et al.New insights on nontechnical losses characterization through evolutionary-based feature selection[J].IEEE Transactions on Power Delivery,2012,27(1):140-146.
[15]RAMOS C C O,SOUZA A N,CHIACHIA G,et al.A novel algorithm for feature selection using harmony search and its application for non-technical losses detection[J].Computers&Electrical Engineering,2011,37(6):886-894.
[16]RAMOS C C O,RODRIGUES D,de SOUZA A N,et al.On the study of commercial losses in Brazil:a binary black hole algorithm for theft characterization[J].IEEE Transactions on Smart Grid,2018,9(2):676-683.
[17]NAGI J,MOHAMMAD A M,YAP K S,et al.Non-technical loss analysis for detection of electricity theft using support vector machines[C]//IEEE 2nd International Power and Energy Conference, December 1-3,2008,Johor Bahru,Malaysia:907-912.
[18]JIANG R,TAGARIS H,LACHSZ A,et al.Wavelet based feature extraction and multiple classifiers for electricity fraud detection[C]//IEEE/PES Transmission and Distribution Conference and Exhibition,October 6-10,2002,Yokohama,Japan:2251-2256.
[19]韩传家,张孝顺,余涛,等.风险调度中引入知识迁移的细菌觅食强化学习优化算法[J].电力系统自动化,2017,41(8):69-77.DOI:10.7500/AEPS20160619004.HAN Chuanjia, ZHANG Xiaoshun, YU Tao, et al.Optimization algorithm of reinforcement learning based knowledge transfer bacteria foraging for risk dispatch[J].Automation of Electric Power Systems,2017,41(8):69-77.DOI:10.7500/AEPS20160619004.
[20]孙润稼,刘玉田.基于深度学习和蒙特卡洛树搜索的机组恢复在线决策[J].电力系统自动化,2018,42(14):40-47.DOI:10.7500/AEPS20170930011.SUN Runjia, LIU Yutian. Online decision-making for generator start-up based on deep learning and Monte Carlo tree search[J].Automation of Electric Power Systems,2018,42(14):40-47.DOI:10.7500/AEPS20170930011.
[21]BOURLARD H,KAMP Y.Auto-association by multilayer perceptions and singular value decomposition[J].Biological Cybernetics,1988,59(4/5):291-294.
[22]LECUN Y.PhD thesis:Modeles connexionnistes de l’apprentissage(connectionist learning models)[D/OL].[2018-05-01].https://nyuscholars.nyu.edu/en/publications/phdthesis-modeles-connexionnistes-de-lapprentissage-connectionis.
[23]HINTON G E, ZEMEL R S.Autoencoders, minimum description length and Helmholtz free energy[C]//Proceedings of the 6th International Conference on Neural Information Processing Systems,November 29-December 2,1993,San Francisco,USA:3-10.
[24]SALAKHUTDINOV R,HINTON G.Semantic hashing[J].International Journal of Approximate Reasoning, 2009,50(7):969-978.
[25]HINTON G E,OSINDERO S,TEH Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[26]CHAPELLE O,HAFFNER P,VAPNIK V N.Support vector machines for histogram-based image classification[J].IEEE Transactions on Neural Networks,1999,10(5):1055-1064.
[27]JIA Y,SHELHAMER E, DONAHUE J,et al.Caffe:convolutional architecture for fast feature embedding[EB/OL].[2017-01-20].http://cn.arxiv.org/abs/1408.5093.
[28]ISSDA.Data from the commission for energy regulation[EB/OL].[2018-05-01].http://www.ucd.ie/issda/data/commis sionforenergyregulationcer/.
[29]SHIY. Particleswarmoptimization:developments,applications and resources[C]//Proceedings of the 2001Congress on Evolutionary Computation,May 27-30,2001,Seoul,South Korea:81-86.