基于贝叶斯准则的非侵入式负荷监测方法Non-Intrusive Load Monitoring Based on Bayes Criterion
周晨轶,闫娇娇,刘晨阳
ZHOU Chenyi,YAN Jiaojiao,LIU Chenyang
摘要(Abstract)：
利用非侵入式负荷监测技术,既可以使居民了解家中电器详细的能耗信息,也有助于电力公司制定科学的需求响应政策。针对现有负荷分解方法采样频率要求高、无法有效处理多工作模式负载投入使用的问题,提出基于贝叶斯准则的负荷分解方法。首先介绍了一套用电信息采集系统;然后提出了负载电流概率密度函数的概念,并在此基础上建立了基于贝叶斯准则的负荷分解模型;最后给出了一种全新的非侵入式能耗估算方法。使用实测数据进行算法验证,结果表明所提方法可以精确估算出各家用电器的能耗。
Non-intrusive load monitoring(NILM) techniques can not only inform residents of energy consumption of household appliances but help electric enterprises formulate scientific demand response(DR) policy. In line with strict requirement on sampling frequency of the existing load decomposition method an failure of load operation with multiple running modes, this paper a load decomposition method based on Bayes criterion.Firstly, a power consumption information collection system is put forward. Then, probability density function of load current is introduced, and a Bayes criterion based load decomposition model is presented. Finally, a novel non-intrusive energy consumption calculation method is proposed. The proposed method is validated by the actually measured data that the proposed method can accurately figure out energy consumption of household appliances.
关键词(KeyWords)：
非侵入式;负荷分解;需求响应;贝叶斯准则
non-intrusive;load decomposition;demand response;Bayes criterion
基金项目(Foundation):
作者(Author):
周晨轶,闫娇娇,刘晨阳
ZHOU Chenyi,YAN Jiaojiao,LIU Chenyang
DOI: 10.19585/j.zjdl.201805002
参考文献(References)：
- [1]林弘宇,田世明.智能电网条件下的智能小区关键技术[J].电网技术,2011,35(12):1-7.
- [2]王蓓蓓,李杨.面向智能电网的电力需求侧管理规划及实施机制[J].电力自动化设备,2010,30(12):19-24.
- [3]张文亮,刘壮志,王明俊,等.智能电网的研究进展及发展趋势[J].电网技术,2009,33(13):1-11.
- [4]宋亚奇,周国亮,朱永利.智能电网大数据处理技术现状与挑战[J].电网技术,2013,37(4):927-935.
- [5]周晨轶,刘松,钟潇,等.基于差分进化算法的居民用电负荷分解方法[J].南方电网技术,2016,10(6):62-69.
- [6]余贻鑫,刘博,栾文鹏.非侵入式居民电力负荷监测与分解技术[J].南方电网技术,2013,7(4):1-5.
- [7]HART G W.Nonintrusive appliance load monitoring[J].IEEE Proceeding,1992,80(12):1870-1891.
- [8]HASSAN T,JAVED F,ARSHAD N.An empirical investigation of V-I trajectory based load signatures for non-intrusive load monitoring[J].IEEE Transactions on Smart Grid,2014,5(2):870-878.
- [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(S1):358-364.
- [10]CHANG H H,LIAN K,SU Y,et al.Power-spectrumbased wavelet transform for non-intrusive demand monitoring and load identification[J].IEEE Transactions on Industry and Application,2014,50(3):2081-2089.
- [11]SRINIVASAN D,NG W S,LIEW A C.Neural-networkbased signature recognition for harmonic source identification[J].IEEE Transactions on Power Delivery,2006,21(1):398-405.
- [12]ZEIFMAN M.Disaggregation of home energy display data using probabilistic approach[J].IEEE Transactions on Consumer Electronics,2012,58(1):23-31.
- [13]娄建楼,于华涛,曲朝阳.面向家庭用户的用电负荷分解方法[J].吉林大学学报(理学版).2015,53(4):744-753.
- [14]DINESH C,NETTASINGHE B W,GODALIYADDA R I,et al.Residential appliance identification based on spectral information of low frequency smart meter measure ments[J].IEEE Transactions on Smart Grid,2016,7(6):2781-2792.
- [15]KOLTER J Z,JOHNSON M J.REDD:A Public Data Set for Energy Disaggregation Research[C].Sustkdd,San Diego,CA,USA,2011.
- [16]颜庆国,阮文骏,陈楚,等.基于并行预测策略的公共楼宇日前空调负荷预测[J].电网与清洁能源,2016,32(11):80-86.