基于图信号处理的智能电表功率信号分解
|
摘要
智能电表的大规模部署,使得对电表采集的低频信号进行数据分析成为一个研究热点。以非侵入式负荷监测为背景,研究基于图信号处理(GSP)的低频功率信号分解算法。首先,将功率信号分解定义为最小化求解问题,并引入基于图转移矩阵的全局变化量作为正则项。然后,分两步对该优化问题求解:第1步最小化正则项得到满足图信号全局变化量最小的近似解;第2步以该解为基础,利用模拟退火算法对目标函数和约束条件迭代寻优。最后利用开源数据库REDD进行仿真,验证了该算法在分类准确率上的优势,且与其他算法相比对训练数据的依赖性较小。
With the large-scale deployment of smart meters,data analysis based on low frequency signals collected by electric meter has become a research hotspot.Therefore,a low-rate power signal disaggregation algorithm based on graph signal processing(GSP)is studied in the background of non-intrusive load monitoring.Firstly,the power signal disaggregation problem is defined as a minimization problem,the total graph variation based on graph shift matrix is introduced as a regularization term.Then,the optimization problem is solved in two steps,which are minimizing the regularization term to find the approximate solution with minimum variation,using SA algorithm to minimize the objective function and constraint interactively based on the approximate solution.Finally,the open-access REDD dataset is used to demonstrate the advantage of the proposed algorithm in classification accuracy,especially for low power and multi-state load.Compared with other algorithms,the proposed algorithm is less dependent on training data.
With the large-scale deployment of smart meters,data analysis based on low frequency signals collected by electric meter has become a research hotspot.Therefore,a low-rate power signal disaggregation algorithm based on graph signal processing(GSP)is studied in the background of non-intrusive load monitoring.Firstly,the power signal disaggregation problem is defined as a minimization problem,the total graph variation based on graph shift matrix is introduced as a regularization term.Then,the optimization problem is solved in two steps,which are minimizing the regularization term to find the approximate solution with minimum variation,using SA algorithm to minimize the objective function and constraint interactively based on the approximate solution.Finally,the open-access REDD dataset is used to demonstrate the advantage of the proposed algorithm in classification accuracy,especially for low power and multi-state load.Compared with other algorithms,the proposed algorithm is less dependent on training data.
引文
[1]王守相,孙智卿,刘喆.面向智能用电的家庭能量协同调度策略[J].电力系统自动化,2015,39(17):108-113.DOI:10.7500/AEPS20140625016.WANG Shouxiang,SUN Zhiqing,LIU Zhe.Co-scheduling strategy of home energy for smart power utilization[J].Automation of Electric Power Systems, 2015, 39(17):108-113.DOI:10.7500/AEPS20140625016.
[2]YAN H,BIN L I,CHEN S,et al.Future evolution of automated demand response system in smart grid for low-carbon economy[J].Journal of Modern Power Systems and Clean Energy,2015,3(1):72-81.
[3]LIANG J,NG S K K,KENDALL G,et al.Load signature study:PartⅠbasic concept,structure,and methodology[J].IEEE Transactions on Power Delivery,2010,25(2):551-560.
[4]WICHAKOOL W,REMSCRIM Z,ORJI U A,et al.Smart metering of variable power loads[J].IEEE Transactions on Smart Grid,2015,6(1):189-198.
[5]祁兵,刘利亚,王丽丽.基于LMD和模型匹配的家电负荷识别算法[J].电力系统自动化,2017,41(22):74-80.DOI:10.7500/AEPS20170212001.QI Bing,LIU Liya,WANG Lili.A load identification algorithm for appliance load based on LMD and model matching[J].Automation of Electric Power Systems,2017,41(22):74-80.DOI:10.7500/AEPS20170212001.
[6]武昕,韩璐,韩笑,等.欠定分离机制下基于特征滤波的居民负荷非侵入辨识算法[J].电力系统自动化,2017,41(20):118-125.DOI:10.7500/AEPS20170319002.WU Xin,HAN Lu,HAN Xiao,et al.Feature filtering based non-intrusive identification algorithm for residential load in underdetermined separation mechanism[J].Automation of Electric Power Systems, 2017, 41(20):118-125. DOI:10.7500/AEPS20170319002.
[7]LIN Y H,TSAI M S.Development of an improved time—frequency analysis-based nonintrusive load monitor for load demandidentification[J]. IEEETransactionson Instrumentation&Measurement,2014,63(6):1470-1483.
[8]SRINIVASAN D,NG W S,LIEW A C.Neural-network-based signature recognition for harmonic source identification[J].IEEE Transactions on Power Delivery,2006,21(1):398-405.
[9]曲朝阳,于华涛,郭晓利.基于开启瞬时负荷特征的家电负荷识别[J].电工技术学报,2015,30(增刊1):358-364.QU Zhaoyang,YU Huatao,GUO Xiaoli.The recognition of appliances instantaneous load[J].Transactions of China Electrotechnical Society,2015,30(Supplement 1):358-364.
[10]高云,杨洪耕.基于暂态特征贴近度匹配的家用负荷识别[J].电力系统自动化,2013,37(9):54-59.GAO Yun,YANG Honggeng.Household load identification based on transient characteristics with closeness matching[J].Automation of Electric Power Systems,2013,37(9):54-59.
[11]GIRI S,BERGS M.An energy estimation framework for event-based methods in non-intrusive load monitoring[J].Energy Conversion&Management,2015,90:488-498.
[12]CHANG H H,CHEN K L,TSAI Y P,et al.A new measurement method for power signatures of nonintrusive demand monitoring and load identification[J].IEEE Transactions on Industry Applications,2012,48(2):764-771.
[13]LIAO J,ELAFOUDI G,STANKOVIC L,et al.Nonintrusive appliance load monitoring using low-resolution smart meter data[C]//IEEE International Conference on Smart Grid Communications,November 3-6, 2014, Venice, Italy:535-540.
[14]KIM H S.Unsupervised disaggregation of low frequency power measurements[C]//SDM 2011 Eleventh Siam International Conference on Data Mining,April 28-30,2011,Mesa,USA:747-758.
[15]PARADISO F,PAGANELLI F,GIULI D,et al.Contextbased energy disaggregation in smart homes[J].Future Internet,2016,8(1):4.
[16]AIAD M,PENG H L.Unsupervised approach for load disaggregation with devices interactions[J].Energy&Buildings,2016,116:96-103.
[17]JOHNSON M J, WILLSKY A S.Bayesian nonparametric hidden semi-Markov models[J].Journal of Machine Learning Research,2012,14(1):673-701.
[18]PARSON O,GHOSH S,WEAL M J,et al.An unsupervised training method for non-intrusive appliance load monitoring[M].USA:Elsevier Science Publishers Ltd.,2014.
[19]SANDRYHAILA A, MOURA J M F.Discrete signal processing on graphs:frequency analysis[J].IEEE Transactions on Signal Processing,2014,62(12):3042-3052.
[20]HE K,STANKOVIC L,LIAO J,et al.Non-intrusive load disaggregation using graph signal processing[J].IEEE Transactions on Smart Grid,2018,9(3):1739-1747.
[21]杨汉键.基于图信号处理的滚动轴承故障特征提取方法研究[D].长沙:湖南大学,2016.YANG Hanjian.Study on feature extraction method of rolling bearing fault based on graph signal processing[D].Changsha:Hunan University,2016.
[22]NARANG,SUNIL K,ORTEGA,et al.The emerging field of signal processing on graphs[J].IEEE Signal Processing Magazine,2013,30(3):83-98.
[23]BOYD S,VANDENBERGHE L.Convex Optimization[M].Beijing,China:World Book Inc.,2013.
[24]KOLTER J Z,JOHNSON M J.REDD:apublic data set for energy disaggregation research[EB/OL].[2011-08-01].http://redd.csail.mit.edu/.
[2]YAN H,BIN L I,CHEN S,et al.Future evolution of automated demand response system in smart grid for low-carbon economy[J].Journal of Modern Power Systems and Clean Energy,2015,3(1):72-81.
[3]LIANG J,NG S K K,KENDALL G,et al.Load signature study:PartⅠbasic concept,structure,and methodology[J].IEEE Transactions on Power Delivery,2010,25(2):551-560.
[4]WICHAKOOL W,REMSCRIM Z,ORJI U A,et al.Smart metering of variable power loads[J].IEEE Transactions on Smart Grid,2015,6(1):189-198.
[5]祁兵,刘利亚,王丽丽.基于LMD和模型匹配的家电负荷识别算法[J].电力系统自动化,2017,41(22):74-80.DOI:10.7500/AEPS20170212001.QI Bing,LIU Liya,WANG Lili.A load identification algorithm for appliance load based on LMD and model matching[J].Automation of Electric Power Systems,2017,41(22):74-80.DOI:10.7500/AEPS20170212001.
[6]武昕,韩璐,韩笑,等.欠定分离机制下基于特征滤波的居民负荷非侵入辨识算法[J].电力系统自动化,2017,41(20):118-125.DOI:10.7500/AEPS20170319002.WU Xin,HAN Lu,HAN Xiao,et al.Feature filtering based non-intrusive identification algorithm for residential load in underdetermined separation mechanism[J].Automation of Electric Power Systems, 2017, 41(20):118-125. DOI:10.7500/AEPS20170319002.
[7]LIN Y H,TSAI M S.Development of an improved time—frequency analysis-based nonintrusive load monitor for load demandidentification[J]. IEEETransactionson Instrumentation&Measurement,2014,63(6):1470-1483.
[8]SRINIVASAN D,NG W S,LIEW A C.Neural-network-based signature recognition for harmonic source identification[J].IEEE Transactions on Power Delivery,2006,21(1):398-405.
[9]曲朝阳,于华涛,郭晓利.基于开启瞬时负荷特征的家电负荷识别[J].电工技术学报,2015,30(增刊1):358-364.QU Zhaoyang,YU Huatao,GUO Xiaoli.The recognition of appliances instantaneous load[J].Transactions of China Electrotechnical Society,2015,30(Supplement 1):358-364.
[10]高云,杨洪耕.基于暂态特征贴近度匹配的家用负荷识别[J].电力系统自动化,2013,37(9):54-59.GAO Yun,YANG Honggeng.Household load identification based on transient characteristics with closeness matching[J].Automation of Electric Power Systems,2013,37(9):54-59.
[11]GIRI S,BERGS M.An energy estimation framework for event-based methods in non-intrusive load monitoring[J].Energy Conversion&Management,2015,90:488-498.
[12]CHANG H H,CHEN K L,TSAI Y P,et al.A new measurement method for power signatures of nonintrusive demand monitoring and load identification[J].IEEE Transactions on Industry Applications,2012,48(2):764-771.
[13]LIAO J,ELAFOUDI G,STANKOVIC L,et al.Nonintrusive appliance load monitoring using low-resolution smart meter data[C]//IEEE International Conference on Smart Grid Communications,November 3-6, 2014, Venice, Italy:535-540.
[14]KIM H S.Unsupervised disaggregation of low frequency power measurements[C]//SDM 2011 Eleventh Siam International Conference on Data Mining,April 28-30,2011,Mesa,USA:747-758.
[15]PARADISO F,PAGANELLI F,GIULI D,et al.Contextbased energy disaggregation in smart homes[J].Future Internet,2016,8(1):4.
[16]AIAD M,PENG H L.Unsupervised approach for load disaggregation with devices interactions[J].Energy&Buildings,2016,116:96-103.
[17]JOHNSON M J, WILLSKY A S.Bayesian nonparametric hidden semi-Markov models[J].Journal of Machine Learning Research,2012,14(1):673-701.
[18]PARSON O,GHOSH S,WEAL M J,et al.An unsupervised training method for non-intrusive appliance load monitoring[M].USA:Elsevier Science Publishers Ltd.,2014.
[19]SANDRYHAILA A, MOURA J M F.Discrete signal processing on graphs:frequency analysis[J].IEEE Transactions on Signal Processing,2014,62(12):3042-3052.
[20]HE K,STANKOVIC L,LIAO J,et al.Non-intrusive load disaggregation using graph signal processing[J].IEEE Transactions on Smart Grid,2018,9(3):1739-1747.
[21]杨汉键.基于图信号处理的滚动轴承故障特征提取方法研究[D].长沙:湖南大学,2016.YANG Hanjian.Study on feature extraction method of rolling bearing fault based on graph signal processing[D].Changsha:Hunan University,2016.
[22]NARANG,SUNIL K,ORTEGA,et al.The emerging field of signal processing on graphs[J].IEEE Signal Processing Magazine,2013,30(3):83-98.
[23]BOYD S,VANDENBERGHE L.Convex Optimization[M].Beijing,China:World Book Inc.,2013.
[24]KOLTER J Z,JOHNSON M J.REDD:apublic data set for energy disaggregation research[EB/OL].[2011-08-01].http://redd.csail.mit.edu/.