Non-Intrusive Home-Load Identification Based on Improved Hidden Markov Model

doi:10.3969/j.issn.1000-7229.2020.04.009

Abstract

Abstract: Aiming at the low accuracy of low-frequency sampling and the poor stability of the system， a non-intrusive load monitoring （NILM） method based on improved hidden Markov model （HMM） is proposed. The model introduces artificial immune algorithm and incremental learning to optimize the traditional HMM model， solves the problem that the initial parameters of HMM model are easy to fall into local optimum， realizes the independent updating of model parameters by incremental learning， and makes the model adapt to the new environment. The recognition accuracy and robustness of the model are improved. Finally， the improved HMM model is analyzed by a low frequency data set. The results show that the model has certain advantages in recognition accuracy and robustness.

Key words: non-intrusive load monitoring（NILM）, hidden Markov model（HMM）, artificial immune algorithm, incremental learning

CLC Number:

TM 73

SUN Yi， LI Haoyang， LIU Yaoxian， QI Bing， LI Bin， ZHANG Xudong， LI Fei. Non-Intrusive Home-Load Identification Based on Improved Hidden Markov Model[J]. Electric Power Construction, 2020, 41(4): 73-80.

References

［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.
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.
［2］BASU K， DEBUSSCHERE V， BACHA S， et al. Nonintrusive load monitoring： A temporal multilabel classification approach［J］. IEEE Transactions on Industrial Informatics， 2015， 11（1）： 262-270.
［3］杨旭英，周明，李庚银. 智能电网下需求响应机理分析与建模综述［J］. 电网技术， 2016， 40（1）： 220-226.
YANG Xuying， ZHOU Ming， LI Gengyin. Survey on demand response mechanism and modeling in smart grid［J］. Power System Technology， 2016， 40（1）： 220-226.
［4］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.
［5］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.
［6］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 Power Systems， 2017， 41（4）： 86-91.
［7］武昕，祁兵，韩璐，等. 基于模板滤波的居民负荷非侵入式快速辨识算法［J］. 电力系统自动化， 2017， 41（2）： 135-141.
WU Xin， QI Bing， HAN Lu， et al. Fast non-intrusive load identification algorithm for resident load based on template filtering［J］. Automation of Electric Power Systems， 2017， 41（2）： 135-141.
［8］燕续峰，翟少鹏，王治华，等．深度神经网络在非侵入式负荷分解中的应用［J］．电力系统自动化，2019，43（1）：126-132，167．
YAN Xüfeng， ZHAI Shaopeng， WANG　Zhihua， et al. Application of deep neural network in noninvasive load decomposition［J］.Automation of Electric Power Systems，2019，43（1）：126-132， 167.
［9］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 LMD and model matching［J］. Automation of Electric Power Systems， 2017， 41（22）： 74-80.
［10］MAKONIN S， POPOWICH F， BAJIC I V， et al. Exploiting HMM sparsity to perform online real-time nonintrusive load monitoring［J］. IEEE Transactions on Smart Grid， 2016， 7（6）： 2575-2585.
［11］TRIGEORGIS G， BOUSMALIS K， ZAFEIRIOU S， et al. A deep matrix factorization method for learning attribute representations［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 39（3）： 417-429.
［12］刘博，栾文鹏. 基于负荷分解的用电数据云架构方案及应用场景［J］. 电网技术， 2016， 40（3）： 791-796.
LIU Bo， LUAN Wenpeng. Conceptual cloud solution architecture and application scenarios of power consumption data based on load disaggregation［J］. Power System Technology， 2016， 40（3）： 791-796.
［13］LIN Y H， TSAI M S. Non-intrusive load monitoring by novel neuro-fuzzy classification considering uncertainties［J］. IEEE Transactions on Smart Grid， 2014， 5（5）： 2376-2384.
［14］宋旭帆，周明，涂京，等. 基于k-NN结合核Fisher判别的非侵入式负荷监测方法［J］. 电力系统自动化， 2018， 42（6）： 73-80.
SONG Xufan， ZHOU Ming， TU Jing， et al. Non-intrusive load monitoring method based on k-NN and kernel fisher discriminant［J］. Automation of Electric Power Systems， 2018， 42（6）： 73-80.
［15］张群洪. 基于集成智能方法的电力短期负荷预测［J］. 系统工程理论与实践， 2013， 33（2）： 354-362.
ZHANG Qunhong. A model for short-term load forecasting in power system based on multi-AI methods［J］. Systems Engineering-Theory & Practice， 2013， 33（2）： 354-362.
［16］ALEMDAR H， KASTEREN T L M V， NIESSEN M E， et al. A unified model for human behavior modeling using a hierarchy with a variable number of states［C］//2014 22nd International Conference on Pattern Recognition， Stockholm， Sweden： IEEE， 2014.
［17］CRANDALL A S， COOK D J. Using a hidden Markov model for resident identification［C］//2010 Sixth International Conference on Intelligent Environments. Kuala Lumpur， Malaysia： IEEE，2010.
［18］张振兴，杨任农，房育寰，等. 基于IL-HMM的目标机动动作识别［J］. 飞行力学， 2018， 36（5）： 92-96.
ZHANG Zhenxing， YANG Rennong， FANG Yuhuan， et al. Target maneuver recognition based on IL-HMM model［J］. Flight Dynamics， 2018， 36（5）： 92-96.
［19］胡小光，张太华，杨静，等. 改进的人工免疫算法特征知识推送模型［J］. 组合机床与自动化加工技术， 2018（3）： 4-7.
HU Xiaoguang， ZHANG Taihua， YANG Jing， et al. An improved artificial immune algorithm for the characteristic knowledge push model［J］. Modular Machine Tool & Automatic Manufacturing Technique， 2018（3）： 4-7.
［20］张沛超，陈琪蕾，李仲青，等. 具有增量学习能力的智能孤岛检测方法［J］. 电力自动化设备， 2018， 38（5）： 83-89.
ZHANG Peichao， CHEN Qilei， LI Zhongqing， et al. Intelligent islanding detection method with incremental learning capability［J］. Electric Power Automation Equipment， 2018， 38（5）： 83-89.
［21］CAVALIN P R， SABOURIN R， SUEN C Y， et al. Evaluation of incremental learning algorithms for HMM in the recognition of alphanumeric characters［J］. Pattern Recognition， 2009， 42（12）： 3241-3253.
［22］JOHNSON M， WILLSKY A. Bayesian nonparametric hidden semi-Markov models［J］. Journal of Machine Learning Research， 2012， 14（1）： 673-701.
［23］CAO H， LIU S B， WU L F， et al. Achieving differential privacy against non-intrusive load monitoring in smart grid： A fog computing approach［J］. Concurrency and Computation： Practice and Experience， 2019， 31（22）： e4528.
［24］徐青山，娄藕蝶，郑爱霞，等. 基于近邻传播聚类和遗传优化的非侵入式负荷分解方法［J］. 电工技术学报， 2018， 33（16）： 3868-3878.
XU Qingshan， LOU Oudie， ZHENG Aixia， et al. A non-intrusive load decomposition method based on affinity propagation and genetic algorithm optimization［J］. Transactions of China Electrotechnical Society， 2018， 33（16）： 3868-3878.
［25］TABATABAEI S M， DICK S， XU W. Toward non-intrusive load monitoring via multi-label classification［J］. IEEE Transactions on Smart Grid， 2017， 8（1）： 26-40.
［26］MAKONIN S， POPOWICH F， BARTRAM L， et al. AMPds： A public dataset for load disaggregation and eco-feedback research［C］//2013 IEEE Electrical Power & Energy Conference. Halifax， NS， Canada： IEEE， 2013.

[1]	ZHANG Weiguo, CHEN Liangliang, CHENG Haisheng, FU Rong, JI Juan. Elastic Load Scheduling Based on Awareness of Electric Vehicle Power Supply Resources [J]. ELECTRIC POWER CONSTRUCTION, 2020, 41(8): 48-56.
[2]	WANG Hanlin, LIU Yang, XU Lixiong, CHEN Xianbang, TAN Siwei. Research on Hierarchical Coordinated Optimization Model of Multi-microgrid System Considering Wind Power Consumption [J]. ELECTRIC POWER CONSTRUCTION, 2020, 41(8): 87-98.
[3]	ZHU Xu, YANG Jun, LI Gaojunjie, DONG Xuzhu, LIU Shouwen. Optimal Dispatching Strategy of Regional Integrated Energy System Considering Virtual Energy Storage System朱旭1，杨军1，李高俊杰1，董旭柱1，刘首文2 [J]. ELECTRIC POWER CONSTRUCTION, 2020, 41(8): 99-110.
[4]	SHANG Huiyu, LIN Hongji, LI Zhonghui, ZHAO Hongwei, CHEN Minghui, YANG Zeng, WEN Fushuan. Robust Optimal Scheduling of Mobile Emergency Power Sources Considering Uncertainties [J]. ELECTRIC POWER CONSTRUCTION, 2020, 41(8): 111-119.
[5]	SHANG Huiyu, LIN Hongji, LI Zhonghui, ZHAO Hongwei, CHEN Minghui, YANG Zeng, WEN Fushuan. Robust Optimal Scheduling of Mobile Emergency Power Sources Considering Uncertainties [J]. ELECTRIC POWER CONSTRUCTION, 0, (): 111-119.
[6]	SHANG Huiyu, LIN Hongji, LI Zhonghui, ZHAO Hongwei, CHEN Minghui, YANG Zeng, WEN Fushuan. Robust Optimal Scheduling of Mobile Emergency Power Sources Considering Uncertainties [J]. ELECTRIC POWER CONSTRUCTION, 0, (): 111-119.
[7]	YUAN Lüzerui, GU Jie,JIN Zhijian. User-Side Data Application Framework Based on Cloud-Edge-User Collaboration in Power Internet of Things [J]. Electric Power Construction, 2020, 41(7): 1-8.
[8]	JIANG Dajun， WU Fubao， WANG Qiyun， ZHANG Yanjun， SUN Lixia， WU Yingjun. Robust Optimal Combined Wind-Storage Scheduling Based on Regulatory Cloud [J]. Electric Power Construction, 2020, 41(7): 9-16.
[9]	PANG Chuanjun，MOU Jianan，YU Jianming，WU Li. Identification of Abnormal Operation of Large Power Grids According to Key Operating Indicators and Seq2Seq [J]. Electric Power Construction, 2020, 41(7): 17-24.
[10]	LI Hengqiang， WANG Jun， JIANG Xingran， KUANG Zhongqin， XU Shiming,YANG Yongbiao. Control Strategies of Air-Conditioning and Model of Virtual Power Plant for Power Grid Peak Clipping [J]. Electric Power Construction, 2020, 41(7): 49-57.
[11]	ZHANG Haoyu， QIU Xiaoyan， ZHOU Shengrui， ZHAO Youlin， LI Linghao，ZHANG Kai. Distributed Optimal Dispatch Based on Chance Constrained Goal Programming for Multi-Area Integrated Electricity-Natural Gas Energy Systems [J]. Electric Power Construction, 2020, 41(7): 82-91.
[12]	WEI Zhenbo， REN Xiaolin， HUANG Yuhan. Multi-Objective Optimal Dispatch for Integrated Energy System Considering Integrated Demand Response [J]. Electric Power Construction, 2020, 41(7): 92-99.
[13]	HUAN Jiajia， HONG Haifeng， SUI Yu， YU Mengze，PAN Xianxian，WANG Chaoqun. Model and Algorithm of Probabilistic Interval Constrained Power Flow Considering the Correlation Among Wind， Solar and Load [J]. Electric Power Construction, 2020, 41(7): 117-128.
[14]	AN Qi， WANG Jianxiao， LI Gengyin， WANG Xuanyuan， LIU Zhen. Scheme and Method for Market Participation of Virtual Power Plant Based on Equilibrium Theory [J]. Electric Power Construction, 2020, 41(6): 1-8.
[15]	TAN Zhongfu，TAN Caixia，PU Lei，YANG Jiacheng. Two-Layer Game Model of Virtual Power Plant Applying CIQPSO Algorithm [J]. Electric Power Construction, 2020, 41(6): 9-17.