基于改进隐马尔可夫模型的非侵入式负荷监测*

doi:10.11985/2023.02.015

电气工程学报 ›› 2023, Vol. 18 ›› Issue (2): 157-163.doi: 10.11985/2023.02.015

扫码分享

基于改进隐马尔可夫模型的非侵入式负荷监测^*

郭嘉¹^,²(), 谢景海¹^,², 袁敬中¹^,², 姜宇¹^,², 孙密¹^,², 毕忠勤³()

1.国网冀北电力有限公司经济技术研究院北京 100038
2.北京京研电力工程设计有限公司北京 100038
3.上海电力大学计算机科学与技术学院上海 200090

收稿日期:2021-11-10 修回日期:2022-01-06 出版日期:2023-06-25 发布日期:2023-07-12
通讯作者: 毕忠勤，男，1977年生，博士，教授。主要研究方向为电力大数据分析、人工智能。E-mail：zqbi@shiep.edu.cn
作者简介:郭嘉，男，1989年生，博士。主要研究方向为输电线路电气新技术、电力系统风险评估。E-mail：silenceqin@163.com
基金资助:
国网冀北经研院技术创新成本类资助项目(B3018F20000J)

Non-intrusive Load Monitoring Based on Improved Hidden Markov Model

GUO Jia¹^,²(), XIE Jinghai¹^,², YUAN Jingzhong¹^,², JIANG Yu¹^,², SUN Mi¹^,², BI Zhongqin³()

1. State Grid Jibei Economic Research Institute, Beijing 100038
2. Beijing Jingyan Electric Power Engineering Design Co., Ltd., Beijing 100038
3. College of Computer Science and Technology, Shanghai University of Electric Power, Shanghai 200090

Received:2021-11-10 Revised:2022-01-06 Online:2023-06-25 Published:2023-07-12

摘要/Abstract

摘要：

细粒度的能源消耗监测是智能电网建设的重要环节之一。非侵入式负荷监测作为一种能源消耗监测方法，能够深入分析用户细粒度的负荷成分，对用户端的电力优化具有非常重大的意义，同时还具有实施快捷、成本低的特点。首先通过放宽模型的假设条件，对隐马尔可夫模型进行改进，然后基于改进的隐马尔可夫模型对家庭电力负荷进行建模，最后用改进的Viterbi算法求解负荷设备的最佳状态转移序列，进而求解出每种设备的所消耗的功率。试验结果显示所提改进算法不仅具有较高的精度，还具备较好的稳定性，同时分解出的功率曲线与实际的功率曲线更加贴合，具有很好的效果。

关键词: 非侵入式负荷监测, 隐马可夫模型, 能源消耗监测, 智能电网

Abstract:

The fine-grained energy consumption monitoring is one of the important links of smart grid construction. As an energy consumption monitoring method, non-intrusive load monitoring can deeply analyze the fine-grained load components of users, which is of great significance to the power optimization of users, and also has the characteristics of fast implementation and low cost. Firstly, the hidden Markov model is improved by relaxing the assumptions of the model, and then the household power load is modeled based on the improved hidden Markov model. Finally, the improved Viterbi algorithm is used to solve the optimal state transition sequence of the load equipment, and then the power consumed by each equipment is calculated. The experimental results show that the proposed improved algorithm not only has high accuracy, but also has good stability. At the same time, the decomposed power curve is more consistent with the actual power curve, and has good effect.

Key words: Non-intrusive load monitoring, hidden Markov model, energy consumption monitoring, smart grid

中图分类号:

TM561

郭嘉, 谢景海, 袁敬中, 姜宇, 孙密, 毕忠勤. 基于改进隐马尔可夫模型的非侵入式负荷监测^*[J]. 电气工程学报, 2023, 18(2): 157-163.

GUO Jia, XIE Jinghai, YUAN Jingzhong, JIANG Yu, SUN Mi, BI Zhongqin. Non-intrusive Load Monitoring Based on Improved Hidden Markov Model[J]. Journal of Electrical Engineering, 2023, 18(2): 157-163.

图/表 9

图1

图2

图3

图4

表1

表2

图5

图6

图7

参考文献 21

[1]	HART G W. Nonintrusive appliance load monitoring[J]. IEEE Proc., 1992, 80:1870-1891. doi: 10.1109/5.192069
[2]	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. doi: 10.1109/TPWRD.2005.852370
[3]	KAMAT S P. Fuzzy logic based pattern recognition technique for non-intrusive load monitoring[C]// TENCON 2004. 2004 IEEE Region 10 Conference, 2004, 3:528-530.
[4]	SUZUKI K, INAGAKI S, SUZUKI T, et al. Non-intrusive appliance load monitoring based on integer programming[C]// Int. Conference on Instrumentation,Control and Information Technology,Tokyo,Japan, 2008:2742-2747.
[5]	MARCHIORI A, HAKKARINEN D, HAN Q, et al. Circuit-level load monitoring for household energy management[J]. IEEE Pervasive Computing, 2011(10):40-48.
[6]	KATO T, CHO H S, LEE D. Appliance recognition from electric current signals for information-energy integrated network in home environments[C]// In Proceedings of the 7th International Conference on Smart Homes and Health Telematics, July 1-3,2009,Tours,France. Heidelberg:Springer, 2009, 5597:150-157.
[7]	王志超. 住宅用电负荷的非侵入式监测方法研究[D]. 重庆: 重庆大学, 2015.
	WANG Zhichao. The research on algorithm of the NIALM of residential appliances[D]. Chongqing: Chongqing University, 2015.
[8]	何健明, 李梦诗, 张禄亮, 等. 基于知识蒸馏和半监督学习的非侵入式负荷分解[J]. 广东电力, 2021, 34(9):60-70.
	HE Jianming, LI Mengshi, ZHANG Luliang, et al. Non-intrusive load decomposition algorithm based on knowledge distillation and semi-supervised learning[J]. Guangdong Electric Power, 2021, 34(9):60-70.
[9]	刘影, 彭鑫霞, 王童, 等. 基于PCA-LSTM算法的非侵入式负荷辨识方法[J]. 电测与仪表, 2023, 60(3):53-58.
	LIU Ying, PENG Xinxia, WANG Tong, et al. Non-intrusive load monitoring method based on PCA-LSTM algorithm[J]. Electrical Measurement and Instrumentation, 2023, 60(3):53-58.
[10]	延菲, 张瑞祥, 孙耀杰, 等. 基于改进kNN算法的非侵入式负荷识别方法[J]. 复旦学报, 2021, 60(2):182-188.
	YAN Fei, ZHANG Ruixiang, SUN Yaojie, et al. Non-intrusive load identification method based on improved kNN algorithm[J]. Journal of Fudan University, 2021, 60(2):182-188.
[11]	汪颖, 杨维, 肖先勇, 等. 基于U-I轨迹曲线精细化识别的非侵入式居民负荷监测方法[J]. 电网技术, 2021, 45(10):4104-4113.
	WANG Ying, YANG Wei, XIAO Xianyong, et al. Non-intrusive residential load monitoring method based on refined identification of U-I trajectory curve[J]. Power System Technology, 2021, 45(10):4104-4113.
[12]	KIM H S. Unsupervised disaggregation of low frequency power measurements[C]// Eleventh Siam International Conference on Data Mining,SDM, 2011:747-758.
[13]	KOLTER J Z, JAAKKOLA T. Approximate inference in additive factorial hmms with application to energy disaggregation[C]// AISTATS, 2012:1-11.
[14]	MARTINS J F, LOPES R, LIMA C, et al. A novel nonintrusive load monitoring system based on the S-transform[C]// 13th International Conference on Optimization of Electrical and Electronic Equipment, 2012:973-978.
[15]	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 power load disaggregation and monitoring[D]. Tianjin: Tianjin University, 2009.
[16]	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. Transient event detection algorithm for non-intrusive load monitoring[J]. Automation of Electric Power Systems, 2011, 35(9):30-35.
[17]	崔灿. 面向智能用电的非侵入式居民负荷监测关键技术研究[D]. 北京: 华北电力大学, 2017.
	CUI Can. Student on key technologies in non-intrusive residential load monitoring for intelligent power utilization[D]. Beijing: North China Electric Power University, 2017.
[18]	ZEIFMAN M. Disaggregation of home energy display data using probabilistic approach[J]. IEEE Transactions on Consumer Electronics, 2012, 58(1):23-31. doi: 10.1109/TCE.30
[19]	刘博. 非侵入式电力负荷监测与分解技术[D]. 天津: 天津大学, 2013.
	LIU Bo. Non-intrusive power load monitoring and disaggregation technique[D]. Tianjin: Tianjin University, 2013.
[20]	杨秀, 李安, 孙改平, 等. 基于改进GMM-CNN-GRU混合的非侵入式负荷监测方法研究[J]. 电力系统保护与控制, 2022, 50(14):65-75.
	YANG Xiu, LI An, SUN Gaiping, et al. Non-invasive load monitoring based on an improved GMM-CNN-GRU combination[J]. Power System Protection and Control, 2022, 50(14):65-75.
[21]	王琪凯, 熊永康, 陈瑛, 等. 基于Attention机制优化CNN-seq2seq模型的非侵入式负荷监测[J]. 电力系统及其自动化学报, 2022, 34(12):27-34,42.
	WANG Qikai, XIONG Yongkang, CHEN Ying, et al. Non-intrusive load monitoring based on CNN-seq2seq model optimized by Attention mechanism[J]. Proceedings of the CSU-EPSA, 2022, 34(12):27-34,42.

模型	T_error
模型	家庭1	家庭2	家庭3	家庭4	家庭5	家庭6
HMM	0.48	0.24	0.12	0.12	0.30	0.10
HMM2	0.10	0.20	0.04	0.04	0.08	0.07

家庭	设备1		设备2		设备3		设备4
家庭	HMM	HMM2	HMM	HMM2	HMM	HMM2	HMM	HMM2
家庭1	0.214	0.082	0.264	0.076	0.182	0.080	0.345	0.184
家庭2	0.128	0.106	0.368	0.063	0.302	0.012 9	0.292	0.321
家庭3	0.096	0.108	0.121	0.083	0.288	0.065	0.332	0.214
家庭4	0.258	0.087	0.167	0.054	0.378	0.152	0.312	0.089
家庭5	0.154	0.176	0.146	0.064	0.244	0.048	0.216	0.157
家庭6	0.410	0.138	0.319	0.255	0.317	0.099	0.277	0.086

基于改进隐马尔可夫模型的非侵入式负荷监测^*

Non-intrusive Load Monitoring Based on Improved Hidden Markov Model

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 21

相关文章 4

编辑推荐

Metrics

本文评价

[1]	张明月, 王新宇. 基于残差观测器的智能电网虚假数据攻击检测研究^*[J]. 电气工程学报, 2023, 18(1): 111-117.
[2]	王建新, 李铁军, 朱军, 杜一锦. 低压开关柜运行在线监测和诊断系统设计[J]. 电气工程学报, 2021, 16(4): 189-195.
[3]	夏立萌,郭飞,顾颖,王翀,樊淑丽. 基于模拟子站的智能电网调度控制系统集成调试方法[J]. 电气工程学报, 2018, 13(6): 42-48.
[4]	张旭东, 李中平, 高志建, 张敬平. 基于EPON的配电自动化通信技术研究[J]. 电气工程学报, 2015, 10(11): 68-72.