基于小波设计和数据挖掘算法协同训练的非侵入式负载识别
|
摘要
居民用电信息细化对于规划居民电器使用和降低电能消耗具有重要的意义。文章在非侵入式负载识别技术的基础上,提出了一种利用数据挖掘算法进行协同训练的方法,小波设计用于提取家庭常用电器的开、关暂态特性的特征信息,利用小波的能量系数作为特征值,使用k近邻算法和决策树算法协同训练分类出负载样本,对测试集进行了算法验证实验,在简化了计算复杂性的基础上获得了更高的识别精度,克服了一对余算法在分类真实负类事件上存在的缺陷,为用电可视化的研究工作打下基础。
The decomposed information of power consumption of household appliances is meaningful for scheduling the appliances and the reduction in home energy use. This paper validates the effectiveness of implementing co-testing in NILM.On the basis of non-intrusive load recognition technique,a co-training method is proposed through using data mining algorithm. Wavelet design is used to extract features from the switching transients of loads. The energy coefficient of wavelet is used as the eigenvalue,k-NN algorithm and DT model were used to co-train the load samples. This paper has carried on the algorithmic verification experiment,and obtained the higher identification accuracy on the basis of simplifying the computational complexity and overcomes the deficiencies of OAR algorithms in the classification of true negative class events.It concludes that the research laid the foundation for the study of electricity visualization service.
The decomposed information of power consumption of household appliances is meaningful for scheduling the appliances and the reduction in home energy use. This paper validates the effectiveness of implementing co-testing in NILM.On the basis of non-intrusive load recognition technique,a co-training method is proposed through using data mining algorithm. Wavelet design is used to extract features from the switching transients of loads. The energy coefficient of wavelet is used as the eigenvalue,k-NN algorithm and DT model were used to co-train the load samples. This paper has carried on the algorithmic verification experiment,and obtained the higher identification accuracy on the basis of simplifying the computational complexity and overcomes the deficiencies of OAR algorithms in the classification of true negative class events.It concludes that the research laid the foundation for the study of electricity visualization service.
引文
[1]赵俊华,董朝阳,文福拴,等.面向能源系统的数据科学:理论、技术与展望[J].电力系统自动化,2017,41(4):1-11,19.Zhao Junhua,Dong Zhaoyang,Wen Fushuan,et al.Data Science for Energy Systems:Theory,Techniques and Prospects[J].Automation of Electric Power Systems,2017,41(4):1-11,19.
[2]梁明,李学瑞,石永华,等.智能家居能耗管理的研究进展[J].日用电器,2012,(12):38-42.Liang Ming,Li Xuerui,Shi Yonghua,et al.Research Progress on Energy Consumption Management in Smart Home[J].Household Electrical Appliances,2012,(12):38-42.
[3]林顺富,赵伦加,刘庆强,等.基于0-1二次规划的非干预式负荷识别算法研究[J].电力系统保护与控制,2016,44(8):85-91.Lin Shunfu,Zhao Lunjia,Liu Qingqiang,et al.A nonintrusive load identification method based on quadratic0-1 programming.Power System Protection and Control,2016,44(8):85-91.
[4]郑小霞,刘庆强,林顺富,等.面向非干预式负荷监测的居民负荷微观特性研[J].电力系统保护与控制,2014,42(10):62-70.Zheng Xiaoxia,Liu Qingqiang,Lin Shunfu,et al.Research of the microscopic signatures of residential loads for NILM[J].Power System Protection and Control,2014,42(10):62-70.
[5]Hassan T,Javed F,Arshad N.An Empirical Investigation of V-I Trajectory Based Load Signatures for Non-Intrusive Load Monitoring[J].IEEE Transactionson Smart Grid,2014,5(2):870-878.
[6]C.Duarte,P.Delmar,K.W.Goossen K.Barner,and E.Gomez-Luna.“Non-intrusive load monitoring based on switching voltage transients and wavelet transforms”,in Proc.IEEE Future Instrum.Workshop(FIIW),Gatlinburg,TN,USA,Oct.2012.
[7]H.-H.Chang,K.-L.Chen,Y.-P.Tsai,and W.-J.Lee,“A new measurement method for power signatures of nonintrusive demand monitoring and load identification,”IEEE Trans.Ind.Appl.,vol.48,no.2,pp.764-771,Mar./Apr.2012
[8]KONG S,KIM Y,KO R.Home appliance load disaggregation using cepstrum-smoothing-based method[J].IEEE Trans on Instrumentation and Measurement,2015,61(1):24-30.
[9]J.M.Gillis,S.M.Alshareef and W.G.Morsi,"Nonintrusive Load Monitoring Using Wavelet Design and Machine Learning",IEEE Transactions on Smart Grid,vol.7,no.1,pp.320-328,Jan.2016.
[10]韩霄汉,沈曙明,肖涛,等.基于形态小波的畸变信号电能计量[J].电测与仪表,2016,53(10):44-51.Han Xiaohan,Shen Shuming,Xiao Tao,et al.Distortion signal energy metering based on morphological wavelet[J].Electrical Measurement and Instrumentation,2016,53(10):44-51.
[11]何正友,蔡玉梅,钱清泉.小波熵理论及其在电力系统故障检测中的应用研究[J].中国电机工程学报,2005,25(5):23-43.He Zhengyou,Cai Yumei,Qian Qingquan.Wavelet entropy theory and its application in power system fault detection[J].Proceeding of the CSEE,2005,25(5):23-43.
[12]L.Breiman,J.H.Friedman,C.J.Stone,and R.A.Olshen.Classification and Regression Trees[M].1st ed.London,U.K:Chapman and Hall,Jan.1984.
[13]罗辑,杨劲锋,肖勇,等.用电数据挖掘技术与应用[M].北京:中国电力出版社,2015.
[14]范庚,马登武,张继军,等.基于决策树和相关向量机的智能故障诊断方法[J].计算机工程与应用,2013,49(14):267-270.Fan Geng,Ma Dengwu,Zhang Jijun,et al.An intelligent fault diagnosis method based on decision tree and correlation vector machine[J].Journal of Computer Engineering and Applications,2013,49(14):267-270.
[2]梁明,李学瑞,石永华,等.智能家居能耗管理的研究进展[J].日用电器,2012,(12):38-42.Liang Ming,Li Xuerui,Shi Yonghua,et al.Research Progress on Energy Consumption Management in Smart Home[J].Household Electrical Appliances,2012,(12):38-42.
[3]林顺富,赵伦加,刘庆强,等.基于0-1二次规划的非干预式负荷识别算法研究[J].电力系统保护与控制,2016,44(8):85-91.Lin Shunfu,Zhao Lunjia,Liu Qingqiang,et al.A nonintrusive load identification method based on quadratic0-1 programming.Power System Protection and Control,2016,44(8):85-91.
[4]郑小霞,刘庆强,林顺富,等.面向非干预式负荷监测的居民负荷微观特性研[J].电力系统保护与控制,2014,42(10):62-70.Zheng Xiaoxia,Liu Qingqiang,Lin Shunfu,et al.Research of the microscopic signatures of residential loads for NILM[J].Power System Protection and Control,2014,42(10):62-70.
[5]Hassan T,Javed F,Arshad N.An Empirical Investigation of V-I Trajectory Based Load Signatures for Non-Intrusive Load Monitoring[J].IEEE Transactionson Smart Grid,2014,5(2):870-878.
[6]C.Duarte,P.Delmar,K.W.Goossen K.Barner,and E.Gomez-Luna.“Non-intrusive load monitoring based on switching voltage transients and wavelet transforms”,in Proc.IEEE Future Instrum.Workshop(FIIW),Gatlinburg,TN,USA,Oct.2012.
[7]H.-H.Chang,K.-L.Chen,Y.-P.Tsai,and W.-J.Lee,“A new measurement method for power signatures of nonintrusive demand monitoring and load identification,”IEEE Trans.Ind.Appl.,vol.48,no.2,pp.764-771,Mar./Apr.2012
[8]KONG S,KIM Y,KO R.Home appliance load disaggregation using cepstrum-smoothing-based method[J].IEEE Trans on Instrumentation and Measurement,2015,61(1):24-30.
[9]J.M.Gillis,S.M.Alshareef and W.G.Morsi,"Nonintrusive Load Monitoring Using Wavelet Design and Machine Learning",IEEE Transactions on Smart Grid,vol.7,no.1,pp.320-328,Jan.2016.
[10]韩霄汉,沈曙明,肖涛,等.基于形态小波的畸变信号电能计量[J].电测与仪表,2016,53(10):44-51.Han Xiaohan,Shen Shuming,Xiao Tao,et al.Distortion signal energy metering based on morphological wavelet[J].Electrical Measurement and Instrumentation,2016,53(10):44-51.
[11]何正友,蔡玉梅,钱清泉.小波熵理论及其在电力系统故障检测中的应用研究[J].中国电机工程学报,2005,25(5):23-43.He Zhengyou,Cai Yumei,Qian Qingquan.Wavelet entropy theory and its application in power system fault detection[J].Proceeding of the CSEE,2005,25(5):23-43.
[12]L.Breiman,J.H.Friedman,C.J.Stone,and R.A.Olshen.Classification and Regression Trees[M].1st ed.London,U.K:Chapman and Hall,Jan.1984.
[13]罗辑,杨劲锋,肖勇,等.用电数据挖掘技术与应用[M].北京:中国电力出版社,2015.
[14]范庚,马登武,张继军,等.基于决策树和相关向量机的智能故障诊断方法[J].计算机工程与应用,2013,49(14):267-270.Fan Geng,Ma Dengwu,Zhang Jijun,et al.An intelligent fault diagnosis method based on decision tree and correlation vector machine[J].Journal of Computer Engineering and Applications,2013,49(14):267-270.