基于贝叶斯的非侵入式负荷监测冲击波形分类方法

Abstract
Figure/Table
References
Related Citation (0)

Download: PDF (1505 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Aiming at the problem of impact load type identification in non-intrusive load monitoring, an impact waveform classification method based on Bayesian classifier is proposed. Firstly, the characteristic parameters of an impulse current waveform such as impulse amplitude, rising time, dropping amplitude, and falling time are defined to establish a multi-feature Bayesian classification model. Secondly, the current impulse waveform samples of different appliances are divided into several groups, and the mean values of the characteristic values of the samples are used as the parameters of the classification model. Finally, the classification algorithm is implemented on the hardware platform of single-phase watt hour meter. The classification tests of fixed frequency air conditioner and variable frequency air conditioner are carried out in the laboratory scene. The results show that the proposed method can effectively identify two types of impulse waveforms, which verifies the feasibility of the proposed method.

Key words： non-intrusive load monitoring Bayesian classifier load impulse current smart electricity meter

Received: 29 October 2021

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHANG Bo
	LIANG Kai

Cite this article:

ZHANG Bo,LIANG Kai. A Bayesian-based classification method of impulse waveforms for non-intrusive load monitoring application[J]. Electrical Engineering, 2022, 23(7): 64-68.

URL:

http://dqjs.cesmedia.cn/EN/Y2022/V23/I7/64

[1] 王宏飞, 周鑫, 徐哲壮, 等. 基于云平台的工业用电分析与预测[J]. 电气技术, 2020, 21(12): 6-11.
[2] 郝朝, 张浩然, 张晓崎, 等. 北京郊区电网冬季典型日“煤改电”负荷特性分析[J]. 电气技术, 2021, 22(10): 17-21, 33.
[3] 张敏, 钱霜秋, 吴仲麒, 等. 基于数据挖掘技术的中长期负荷预测方法[J]. 电气技术, 2021, 22(6): 43-48.
[4] HART G W.Non-instructive appliance load moni-toring[J]. Proceedings of the IEEE, 1992, 80(12): 1870-1891.
[5] LUO Dong, NORFORD L K, SHAW S R, et al.Monitoring HVAC equipment electrical loads from a centralized location-methods and field test results[J]. ASHRAE Transactions, 2002, 108(1): 841-857.
[6] 周东国, 张恒, 周洪, 等. 基于状态特征聚类的非侵入式负荷事件检测方法[J]. 电工技术学报, 2020, 35(21): 4565-4575.
[7] ZHANG Shuai, ZHU Zhicheng, YIN Bo, et al.Event detection methods for nonintrusive load monitoring in smart metering using the improved CUSUM algo-rithm[C]//2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, Xi’an, China, 2018.
[8] ZHU Zhicheng, WEI Zhiqiang, YIN Bo, et al.A novel approach for event detection in non-intrusive load monitoring[C]//2017 IEEE Conference on Energy Internet and Energy System Integration, Beijing, China, 2017.
[9] 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): 35-40.
[10] BOUHOURAS A S, MILIOUDIS A N, ANDREOU G T, et al.Load signatures improvement through the determination of a spectral distribution coefficient for load identification[C]//9th International Conference on the European Energy Market, Florance, Italy, 2012.
[11] LIN Yu-Hsiu, TSAI Men-Shen.A novel feature extra-ction method for the development of nonintrusive load monitoring system based on BP-ANN[C]//3CA Inter-national Symposium, Taiwan, China, 2010: 215-218.
[12] YANG Hong-Tzer, CHANG Hsueh-Hsien, LIN Ching-Lung.Design a neural network for features selection in non-intrusive monitoring of industrial monitoring electrical loads[C]//2007 11th International Con-ference on Computer Supported Cooperative Work in Design, Melbourne, VIC, Australia, 2007: 1022-1027.
[13] NG S K K, LIANG Jian, CHENG J W M. Automatic appliance load signature identification by statistical clustering[C]//8th International Conference on Advances in Power System Control, Operation and Management (APSCOM 2009), Hong Kong, China, 2009.
[14] HONG Yingyi, CHOU Jinghan.Non-intrusive energy monitoring for micro-grids using hybrid self-organizing feature-mapping networks[J]. Energies, 2012, 5(7): 2578-2593.
[15] 陈鸿川, 刘博, 栾文鹏, 等. 用于非侵入式电力负荷监测的改进Viterbi算法[J]. 电力系统及其自动化学报, 2017, 29(2): 84-88.
[16] 徐春华, 陈克绪, 马建, 等. 基于深度置信网络的电力负荷识别[J]. 电工技术学报, 2019, 34(19): 4135-4142.
[17] 王孝慈, 董树锋, 王莉, 等. 基于电器状态关联分析的民可平移负荷辨识[J]. 电工技术学报, 2020, 35(23): 4961-4970.
[18] 雷怡琴, 孙兆龙, 叶志浩, 等. 电力系统负荷非侵入式监测方法研究[J]. 电工技术学报, 2021, 36(11): 2288-2297.
[19] 李永昆. 非侵入式多户居民负荷辨识装置开发及应用研究[D]. 南京: 东南大学, 2017.
[20] 廉永乐. 空管供配电系统可靠性分析[J]. 电气技术, 2021, 22(5): 89-96.
[21] 路军, 王梓耀, 余涛. 基于朴素贝叶斯和D-S证据理论的多时空数据融合[J]. 电气技术, 2019, 20(11): 27-32, 45.