基于选择性贝叶斯分类的非侵入式负荷识别方法
|
摘要
非侵入式负荷识别可以提供用电信息,帮助用户改善用电习惯,是智能用电的关键技术。现有非侵入式负荷识别方法主要基于负荷的稳态特征进行识别,对稳态特征近似的负荷识别率不高。针对此问题,该文结合各类家用负荷在投切过程中的不同特点,提出了一种基于选择性贝叶斯分类的识别方法。首先,利用模拟退火算法从特征库中依据负荷特点选择出对于各类负荷最具辨识度的特征;然后,根据选择的特征和高斯核密度估计方法建立灵活贝叶斯分类器;最后,通过计算各负荷的后验概率对负荷进行识别。经实测数据检验,该方法具有良好的识别精度和计算速度。
Non-intrusive load identification can provide information of household loads and improve users' habits,and it is the key technique of smart power utilization. Current non-intrusive load identification methods mainly use steady-state characteristics of loads; usually result in inaccuracy when the loads have similar steady-state characteristics. As various household loads have different peculiarity on switching process,this paper proposes a newidentification method based on selected Bayes classifier. Firstly,simulated annealing algorithm is adopted to select the most recognizable characteristics of loads from database for characteristics. Secondly, the flexible Bayes classifier is built on the basis of the selected characteristics and Gaussian kernel density estimation methods. Finally,posterior probability is calculated to identify the load. The measured data shows that the proposed method has high identification accuracy and calculation speed.
Non-intrusive load identification can provide information of household loads and improve users' habits,and it is the key technique of smart power utilization. Current non-intrusive load identification methods mainly use steady-state characteristics of loads; usually result in inaccuracy when the loads have similar steady-state characteristics. As various household loads have different peculiarity on switching process,this paper proposes a newidentification method based on selected Bayes classifier. Firstly,simulated annealing algorithm is adopted to select the most recognizable characteristics of loads from database for characteristics. Secondly, the flexible Bayes classifier is built on the basis of the selected characteristics and Gaussian kernel density estimation methods. Finally,posterior probability is calculated to identify the load. The measured data shows that the proposed method has high identification accuracy and calculation speed.
引文
[1]李同智.灵活互动智能用电的技术内涵及发展方向[J].电力系统自动化,2012,36(2):11-17.LI Tongzhi.Technical implications and development trends of flexible and interactive utilization of intelligent pow er[J].Automation of Electric Pow er Systems,2012,36(2):11-17.
[2]宋璇坤,韩柳,鞠黄培,等.中国智能电网技术发展实践综述[J].电力建设,2016,37(7):1-11.SONG Xuankun,HAN Liu,JU Huangpei,et al.A review on development practice of smart grid technology in China[J].Electric Pow er Construction,2016,37(7):1-11.
[3]章鹿华,王思彤,易忠林,等.面向智能用电的家庭综合能源管理系统的设计与实现[J].电测与仪表,2010,47(9):35-38.ZHANG Luhua,WANG Sitong,YI Zhonglin,et al.The design and implementation of family comprehensive energy management system facing the smart pow er[J].Electrical M easurement&Instrumentation,2010,47(9):35-38.
[4]张延宇,曾鹏,臧传治.智能电网环境下家庭能源管理系统研究综述[J].电力系统保护与控制,2014,42(18):144-154.ZHANG Yanyu,ZENG Peng,ZANG Chuanzhi.Review of home energy management system in smart grid[J].Pow er System Protection and Control,2014,42(18):144-154.
[5]LI J,CHUNG J Y,XIAO J,et al.On the design and implementation of a home energy management system[C]//20116th International Symposium on Wireless and Pervasive Computing(ISWPC).Hong Kong:IEEE,2011:1-6.
[6]史常凯,张波,盛万兴,等.灵活互动智能用电的技术框架探讨[J].电网技术,2013,37(10):2868-2874.SHI Changkai,ZHANG Bo,SHENG Wanxing,et al.A discussion on technical architecture for flexible intelligent interactive pow er utilization[J].Pow er System Technology,2013,37(10):2868-2874.
[7]黎鹏.非侵入式电力负荷分解与监测[D].天津:天津大学,2009.LI Peng.Non-intrusive method for pow er load disaggregation and monitoring[D].Tianjin:Tianjin University,2009.
[8]SUZUKI K,INAGAKI S,SUZUKI T,et al.Nonintrusive appliance load monitoring based on integer programming[C]//SICE Annual Conference.Tokyo:IEEE,2008:2742-2747.
[9]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 M eixuan,et al.Application of RPROP neural netw ork in nonintrusive load decomposition[J].Pow er System Protection and Control,2016,44(7):55-61.
[10]孙毅,崔灿,陆俊,等.基于差量特征提取与模糊聚类的非侵入式负荷监测方法[J].电力系统自动化,2017,41(4):86-91.SUN Yi,CUI Can,LU Jun,et al.Non-intrusive load monitoring method based on delta feature extraction and fuzzy clustering[J].Automation of Electric Pow er Systems,2017,41(4):86-91.
[11]祁兵,董超,武昕,等.基于DTW算法与稳态电流波形的非侵入式负荷辨识方法[J].电力系统自动化,2018,42(3):70-76.QI Bing,DONG Chao,WU Xin,et al.Non-intrusive load identification method based on DTW algorithm and steady-state current w aveform[J].Automation of Electric Pow er Systems,2018,42(3):70-76.
[12]孙毅,崔灿,陆俊,等.基于遗传优化的非侵入式家居负荷分解算法[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].Pow er System Technology,2016,40(12):3912-3917.
[13]GUZEL T,USTUNEL E.Principal components null space analysis based non-intrusive load monitoring[C]//IEEE Electrical Pow er and Energy Conference.Ontario:IEEE,2015:420-423.
[14]JING L,GEORGIA E,LNA S,et al.Non-intrusive appliance load monitoring using low-resolution smart meter data[C]//International Conference on Smart Grid Communications.Venice:IEEE,2014:535-540.
[15]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.QI Bing,LIU Liya,WANG Lili.Identification algorithm for appliance load based on LM D and model matching[J].Automation of Electric Pow er Systems,2017,41(22):74-80.
[16]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 M eihan,XU Yuejuan.Non-intrusive load monitoring based on improved chicken sw arm optimization algorithm[J].Electric Pow er Automation Equipment,2018,38(5):235-240.
[17]孙毅,张璐,赵洪磊,等.基于动态自适应粒子群算法的非侵入式家居负荷分解方法[J].电网技术,2018,42(6):1819-1826.SUN Yi,ZHANG Lu,ZHAO Honglei,et al.A non-intrusive household load monitoring method based on dynamic adaptive particle sw arm optimization algorithm[J].Pow er System Technology,2018,42(6):1819-1826.
[18]庞峰.模拟退火算法的原理及算法在优化问题上的应用[D].吉林:吉林大学,2006.PANG Feng.The principle of SA algorithm and algorithm’s application on optimization problem[D].Jilin:Jilin University,2006.
[19]杜瑞杰.贝叶斯分类器及其应用研究[D].上海:上海大学,2012.DURuijie.The research of Bayesian classifier and its applications[D].Shanghai:Shanghai University,2012.
[20]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 closeness matching of transient characteristics[J].Automation of Electric Pow er Systems,2013,37(9):54-59.
[2]宋璇坤,韩柳,鞠黄培,等.中国智能电网技术发展实践综述[J].电力建设,2016,37(7):1-11.SONG Xuankun,HAN Liu,JU Huangpei,et al.A review on development practice of smart grid technology in China[J].Electric Pow er Construction,2016,37(7):1-11.
[3]章鹿华,王思彤,易忠林,等.面向智能用电的家庭综合能源管理系统的设计与实现[J].电测与仪表,2010,47(9):35-38.ZHANG Luhua,WANG Sitong,YI Zhonglin,et al.The design and implementation of family comprehensive energy management system facing the smart pow er[J].Electrical M easurement&Instrumentation,2010,47(9):35-38.
[4]张延宇,曾鹏,臧传治.智能电网环境下家庭能源管理系统研究综述[J].电力系统保护与控制,2014,42(18):144-154.ZHANG Yanyu,ZENG Peng,ZANG Chuanzhi.Review of home energy management system in smart grid[J].Pow er System Protection and Control,2014,42(18):144-154.
[5]LI J,CHUNG J Y,XIAO J,et al.On the design and implementation of a home energy management system[C]//20116th International Symposium on Wireless and Pervasive Computing(ISWPC).Hong Kong:IEEE,2011:1-6.
[6]史常凯,张波,盛万兴,等.灵活互动智能用电的技术框架探讨[J].电网技术,2013,37(10):2868-2874.SHI Changkai,ZHANG Bo,SHENG Wanxing,et al.A discussion on technical architecture for flexible intelligent interactive pow er utilization[J].Pow er System Technology,2013,37(10):2868-2874.
[7]黎鹏.非侵入式电力负荷分解与监测[D].天津:天津大学,2009.LI Peng.Non-intrusive method for pow er load disaggregation and monitoring[D].Tianjin:Tianjin University,2009.
[8]SUZUKI K,INAGAKI S,SUZUKI T,et al.Nonintrusive appliance load monitoring based on integer programming[C]//SICE Annual Conference.Tokyo:IEEE,2008:2742-2747.
[9]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 M eixuan,et al.Application of RPROP neural netw ork in nonintrusive load decomposition[J].Pow er System Protection and Control,2016,44(7):55-61.
[10]孙毅,崔灿,陆俊,等.基于差量特征提取与模糊聚类的非侵入式负荷监测方法[J].电力系统自动化,2017,41(4):86-91.SUN Yi,CUI Can,LU Jun,et al.Non-intrusive load monitoring method based on delta feature extraction and fuzzy clustering[J].Automation of Electric Pow er Systems,2017,41(4):86-91.
[11]祁兵,董超,武昕,等.基于DTW算法与稳态电流波形的非侵入式负荷辨识方法[J].电力系统自动化,2018,42(3):70-76.QI Bing,DONG Chao,WU Xin,et al.Non-intrusive load identification method based on DTW algorithm and steady-state current w aveform[J].Automation of Electric Pow er Systems,2018,42(3):70-76.
[12]孙毅,崔灿,陆俊,等.基于遗传优化的非侵入式家居负荷分解算法[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].Pow er System Technology,2016,40(12):3912-3917.
[13]GUZEL T,USTUNEL E.Principal components null space analysis based non-intrusive load monitoring[C]//IEEE Electrical Pow er and Energy Conference.Ontario:IEEE,2015:420-423.
[14]JING L,GEORGIA E,LNA S,et al.Non-intrusive appliance load monitoring using low-resolution smart meter data[C]//International Conference on Smart Grid Communications.Venice:IEEE,2014:535-540.
[15]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.QI Bing,LIU Liya,WANG Lili.Identification algorithm for appliance load based on LM D and model matching[J].Automation of Electric Pow er Systems,2017,41(22):74-80.
[16]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 M eihan,XU Yuejuan.Non-intrusive load monitoring based on improved chicken sw arm optimization algorithm[J].Electric Pow er Automation Equipment,2018,38(5):235-240.
[17]孙毅,张璐,赵洪磊,等.基于动态自适应粒子群算法的非侵入式家居负荷分解方法[J].电网技术,2018,42(6):1819-1826.SUN Yi,ZHANG Lu,ZHAO Honglei,et al.A non-intrusive household load monitoring method based on dynamic adaptive particle sw arm optimization algorithm[J].Pow er System Technology,2018,42(6):1819-1826.
[18]庞峰.模拟退火算法的原理及算法在优化问题上的应用[D].吉林:吉林大学,2006.PANG Feng.The principle of SA algorithm and algorithm’s application on optimization problem[D].Jilin:Jilin University,2006.
[19]杜瑞杰.贝叶斯分类器及其应用研究[D].上海:上海大学,2012.DURuijie.The research of Bayesian classifier and its applications[D].Shanghai:Shanghai University,2012.
[20]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 closeness matching of transient characteristics[J].Automation of Electric Pow er Systems,2013,37(9):54-59.