基于监督学习的非侵入式负荷监测算法比较
|
摘要
非侵入式负荷监测(NILM)能够在不干扰用户正常用电的情况下,低成本地实现用户用电设备类型的识别和用电负荷的分解,因此非常适用于家庭用户用电监测。大量智能电表在家庭用户中的安装为居民NILM提供了数据支撑,也使得居民NILM研究成为热点。基于家庭负荷稳态电流样本,采用负荷电流谐波系数作为负荷分类特征,建立了基于多层感知器(MLP)神经网络、k-近邻算法、逻辑回归、支持向量机的4种NILM分类模型,利用BLUED数据库对4种分类器进行训练和测试,对比分析其在识别精度、训练时间、识别速度和抗噪能力方面的表现,并对其在家庭负荷识别中的应用效果进行对比研究。结果表明,4种分类器中MLP神经网络具有总体最优的分类效果和计算性能,更适用于家庭用户负荷监测。
NILM( Non-Intrusive Load Monitoring) can realize the type identification of the user's electrical equipment and the load decomposition with low costs and without disturbing the users' normal electricity consumption,which is especially suitable for residential load monitoring. The installations of massive smart meters for domestic consumers provide data support for residential NILM,which makes the residential NILM become a hot research topic.Based on the samples of residential load steady-state current,the harmonic coefficients of the load steady-state current are used as the load classification characteristics,and four NILM classification models based on MLP( MultiLayer Perceptions) neural network,k-nearest neighbor algorithm,logistic regression and SVM( Support Vector Machine) are established. The four types of classifiers are trained and tested with the BLUED database,their performances of identification accuracy,training time,identification speed and anti-noise property are compared,and their application effects in residential load identification are contrasted. Results show that,among the four classifiers,the MLP neural network has the optimal classification effect and computational performance,which is more suitable for monitoring the residential load.
NILM( Non-Intrusive Load Monitoring) can realize the type identification of the user's electrical equipment and the load decomposition with low costs and without disturbing the users' normal electricity consumption,which is especially suitable for residential load monitoring. The installations of massive smart meters for domestic consumers provide data support for residential NILM,which makes the residential NILM become a hot research topic.Based on the samples of residential load steady-state current,the harmonic coefficients of the load steady-state current are used as the load classification characteristics,and four NILM classification models based on MLP( MultiLayer Perceptions) neural network,k-nearest neighbor algorithm,logistic regression and SVM( Support Vector Machine) are established. The four types of classifiers are trained and tested with the BLUED database,their performances of identification accuracy,training time,identification speed and anti-noise property are compared,and their application effects in residential load identification are contrasted. Results show that,among the four classifiers,the MLP neural network has the optimal classification effect and computational performance,which is more suitable for monitoring the residential load.
引文
[1]王守相,葛磊蛟,王凯.智能配电系统的内涵及其关键技术[J].电力自动化设备,2016,36(6):1-6.WANG Shouxiang,GE Leijiao,WANG Kai. Main contents and key technologies of smart distribution system[J]. Electric Power Automation Equipment,2016,36(6):1-6.
[2]程祥,李林芝,吴浩,等.非侵入式负荷监测与分解研究综述[J].电网技术,2016,40(10):3108-3117.CHENG Xiang,LI Linzhi,WU Hao,et al. A survey of the research on non-intrusive load monitoring and disaggregation[J]. Power System Technology,2016,40(10):3108-3117.
[3]刘博.非侵入式电力负荷监测与分解技术[D].天津:天津大学,2014.LIU Bo. Non-intrusive power load monitoring and disaggregation technique[D]. Tianjin:Tianjin University,2014.
[4]AZAZA M,WALLIN F. Supervised household's loads pattern recognition[C]∥Electrical Power and Energy Conference(EPEC).[S.l.]:IEEE,2016:1-5.
[5]祁兵,程媛,武昕.基于Fisher有监督判别的非侵入式居民负荷辨识方法[J].电网技术,2016,40(8):2484-2491.QI Bing,CHENG Yuan,WU Xin. Non-intrusive household appliance load identification method based on Fisher supervised discriminant[J]. Power System Technology,2016,40(8):2484-2491.
[6]CHANG H H,LIN L S,CHEN N,et al. Particle swarm optimization based nonintrusive demand monitoring and load identification in smart meters[J]. IEEE Transactions on Industry Applications,2013,49(5):2229-2236.
[7]李如意,王晓换,胡美璇,等. RPROP神经网络在非侵入式负荷分解中的应用[J].电力系统保护与控制,2016,44(7):55-61.LI Ruyi,WANG Xiaohuan,HU Meixuan,et al. Application of RPROP neural network in nonintrusive load decomposition[J]. Power System Protection and Control,2016,44(7):55-61.
[8]DUFOUR L,GENOUD D,JARA A,et al. A non-intrusive model to predict the exible energy in a residential building[C]∥Wireless Communications and Networking Conference Workshops(WCNCW).[S.l.]:IEEE,2015:69-74.
[9]孙毅,崔灿,陆俊,等.基于遗传优化的非侵入式家居负荷分解方法[J].电网技术,2016,40(12):3912-3917.SUN Yi,CUI Can,LU Jun,et al. A non-intrusive household load monitoring method based on genetic optimization[J]. Power System Technology,2016,40(12):3912-3917.
[10]刘兴杰,曹美晗,许月娟.基于改进鸡群算法的非侵入式负荷监测[J].电力自动化设备,2018,38(5):235-240.LIU Xingjie,CAO Meihan,XU Yuejuan. Non-intrusive load monitoring based on improved chicken swarm optimization algorithm[J].Electric Power Automation Equipment,2018,38(5):235-240.
[11]牛卢璐,贾宏杰.一种适用于非侵入式负荷监测的暂态事件检测算法[J].电力系统自动化,2011,35(9):30-35.NIU Lulu,JIA Hongjie. A transient event detection algorithm for nonintrusive load monitoring[J]. Automation of Electric Power Systems,2011,35(9):30-35.
[12]DONG M,MEIRA P C M,XU W,et al. Non-intrusive signature extraction for major residential loads[J]. IEEE Transactions on Smart Grid,2013,4(3):1421-1430.
[13]ANDERSON K,OCNEANU A,BENITEZ D,et al. BLUED:a fully labeled public dataset for event-based non-intrusive load monitoring research[C]∥Proceedings of the 2nd KDD Workshop on Data Mining Applications in Sustainability(Sust KDD). Beijing,China:IEEE,2012:1-5.
[14]HART G W. Nonintrusive appliance load monitoring[J]. Proceedings of the IEEE,1992,80(12):1870-1891.
[15]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2005:10-37.
[16]KREINOVICH V Y. Arbitrary nonlinearity is sufficient to represent all functions by neural networks:a theorem[J]. Neural Networks,1991,4(3):381-383.
[17]BISHOP C M. Pattern recognition and machine learning[M]. New York,USA:Springer-Verlag,2006:181-192.
[18]王彬,郭文鑫,向德军,等.基于改进支持向量机和两步式聚类分析的电网关键断面辨识和精细规则生成方法[J].电力自动化设备,2017,37(9):166-170,177.WANG Bin,GUO Wenxin,XIANG Dejun,et al. Grid critical section detection and fine operational rule generation based on improved support vector machine and two-step clustering analysis[J].Electric Power Automation Equipment,2017,37(9):166-170,177.
[19]MOUNTRAKIS G,IM J,OGOLE C. Support vector machines in remote sensing:a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2011,66(3):247-259.
[2]程祥,李林芝,吴浩,等.非侵入式负荷监测与分解研究综述[J].电网技术,2016,40(10):3108-3117.CHENG Xiang,LI Linzhi,WU Hao,et al. A survey of the research on non-intrusive load monitoring and disaggregation[J]. Power System Technology,2016,40(10):3108-3117.
[3]刘博.非侵入式电力负荷监测与分解技术[D].天津:天津大学,2014.LIU Bo. Non-intrusive power load monitoring and disaggregation technique[D]. Tianjin:Tianjin University,2014.
[4]AZAZA M,WALLIN F. Supervised household's loads pattern recognition[C]∥Electrical Power and Energy Conference(EPEC).[S.l.]:IEEE,2016:1-5.
[5]祁兵,程媛,武昕.基于Fisher有监督判别的非侵入式居民负荷辨识方法[J].电网技术,2016,40(8):2484-2491.QI Bing,CHENG Yuan,WU Xin. Non-intrusive household appliance load identification method based on Fisher supervised discriminant[J]. Power System Technology,2016,40(8):2484-2491.
[6]CHANG H H,LIN L S,CHEN N,et al. Particle swarm optimization based nonintrusive demand monitoring and load identification in smart meters[J]. IEEE Transactions on Industry Applications,2013,49(5):2229-2236.
[7]李如意,王晓换,胡美璇,等. RPROP神经网络在非侵入式负荷分解中的应用[J].电力系统保护与控制,2016,44(7):55-61.LI Ruyi,WANG Xiaohuan,HU Meixuan,et al. Application of RPROP neural network in nonintrusive load decomposition[J]. Power System Protection and Control,2016,44(7):55-61.
[8]DUFOUR L,GENOUD D,JARA A,et al. A non-intrusive model to predict the exible energy in a residential building[C]∥Wireless Communications and Networking Conference Workshops(WCNCW).[S.l.]:IEEE,2015:69-74.
[9]孙毅,崔灿,陆俊,等.基于遗传优化的非侵入式家居负荷分解方法[J].电网技术,2016,40(12):3912-3917.SUN Yi,CUI Can,LU Jun,et al. A non-intrusive household load monitoring method based on genetic optimization[J]. Power System Technology,2016,40(12):3912-3917.
[10]刘兴杰,曹美晗,许月娟.基于改进鸡群算法的非侵入式负荷监测[J].电力自动化设备,2018,38(5):235-240.LIU Xingjie,CAO Meihan,XU Yuejuan. Non-intrusive load monitoring based on improved chicken swarm optimization algorithm[J].Electric Power Automation Equipment,2018,38(5):235-240.
[11]牛卢璐,贾宏杰.一种适用于非侵入式负荷监测的暂态事件检测算法[J].电力系统自动化,2011,35(9):30-35.NIU Lulu,JIA Hongjie. A transient event detection algorithm for nonintrusive load monitoring[J]. Automation of Electric Power Systems,2011,35(9):30-35.
[12]DONG M,MEIRA P C M,XU W,et al. Non-intrusive signature extraction for major residential loads[J]. IEEE Transactions on Smart Grid,2013,4(3):1421-1430.
[13]ANDERSON K,OCNEANU A,BENITEZ D,et al. BLUED:a fully labeled public dataset for event-based non-intrusive load monitoring research[C]∥Proceedings of the 2nd KDD Workshop on Data Mining Applications in Sustainability(Sust KDD). Beijing,China:IEEE,2012:1-5.
[14]HART G W. Nonintrusive appliance load monitoring[J]. Proceedings of the IEEE,1992,80(12):1870-1891.
[15]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2005:10-37.
[16]KREINOVICH V Y. Arbitrary nonlinearity is sufficient to represent all functions by neural networks:a theorem[J]. Neural Networks,1991,4(3):381-383.
[17]BISHOP C M. Pattern recognition and machine learning[M]. New York,USA:Springer-Verlag,2006:181-192.
[18]王彬,郭文鑫,向德军,等.基于改进支持向量机和两步式聚类分析的电网关键断面辨识和精细规则生成方法[J].电力自动化设备,2017,37(9):166-170,177.WANG Bin,GUO Wenxin,XIANG Dejun,et al. Grid critical section detection and fine operational rule generation based on improved support vector machine and two-step clustering analysis[J].Electric Power Automation Equipment,2017,37(9):166-170,177.
[19]MOUNTRAKIS G,IM J,OGOLE C. Support vector machines in remote sensing:a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2011,66(3):247-259.