基于设备运行状态挖掘的非侵入式负荷分解方法

doi:10.12204/j.issn.1000-7229.2020.08.002

电力建设 ›› 2020, Vol. 41 ›› Issue (8): 9-16.doi: 10.12204/j.issn.1000-7229.2020.08.002

• 非侵入式负荷监测技术及其应用 ·栏目主持高山副教授、刘宇讲师· • 上一篇下一篇

基于设备运行状态挖掘的非侵入式负荷分解方法

庄卫金¹, 张鸿¹，方国权²，陈中²

1.中国电力科学研究院有限公司，南京市 210003；2.东南大学电气工程学院，南京市 210096

出版日期:2020-08-07 发布日期:2020-08-07
作者简介:庄卫金（1978），男，高级工程师，主要研究方向为电力系统自动化；张鸿（1980），男，高级工程师，主要研究方向为电力系统自动化；方国权（1994），男，硕士研究生，通信作者，主要研究方向为非侵入式负荷监测；陈中（1975），男，博士，研究员，主要研究方向为电力系统稳定运行与控制、FACTS 的应用、新能源并网。
基金资助:
国家重点研发计划项目（2017YFB0902600）；国家电网公司科技项目“大电网智能调度与安全预警关键技术研究及应用”（SGJS0000DKJS1700840）

Non-intrusive Load Disaggregation Method Based on the Mining of Equipment Operating States

ZHUANG Weijin¹, ZHANG Hong¹,FANG Guoquan²,CHEN Zhong²

1.China Electric Power Research Institute, Nanjing 210003, China； 2.School of Electrical Engineering, Southeast University, Nanjing 210096, China

Online:2020-08-07 Published:2020-08-07
Supported by:
This work is supported by National Key Research and Development Program of China（No. 2017YFB0902600） and research program “Research and Application of Key Technology for Intelligent Dispatching and Security Early-warning of Large Power Grid” of State Grid Corporation of China （No. SGJS0000DKJS1700840）.

摘要/Abstract

摘要： 随着非侵入式负荷监测与用户侧智能电表的结合，基于低频电力数据实现负荷分解成为了最新的研究趋势。考虑到低频电力数据的特征，文章提出一种基于设备运行状态挖掘的非侵入式负荷分解方法。该方法首先进行负荷事件检测，并在负荷事件处提取功率特征；接着在特征平面内通过聚类算法获取表征不同类型负荷事件的聚类簇；最终采用图信号处理算法在聚类簇间挖掘设备运行状态并与数据库中的模板进行匹配实现负荷分解。算例验证了该方法事件检测和负荷分解的准确率，同时验证了在状态挖掘过程中引入设备运行周期能耗对额定功率相似设备的负荷分解具有优化效果。因此，为基于低频电力数据的非侵入式负荷分解技术研究提供了新思路。

关键词: 非侵入式负荷分解, 事件检测, 事件聚类, 运行状态挖掘, 家庭负荷

Abstract: With the combination of users smart meter and non-intrusive load monitoring, research on load disaggregation based on low-rate power data has become the latest trend. On the basis of this, a non-intrusive load disaggregation method based on the mining of operating states is proposed in this paper. Firstly, this method detects load events and extracts power characteristic around load events. In the characteristic plane, a clustering algorithm is used to obtain clusters that represent different types of load events. Finally, among clusters, the GSP algorithm is used to mine equipment operation states that are matched with load templates stored in database to realize load disaggregation. The results of example in this paper verifies the accuracy of event detection and load disaggregation, and also verifies that the introduction of circle operation energy consumption in state mining process has an optimized effect on load disaggregation of devices with similar rated power. Accordingly, it provides a novel idea for the research of non-intrusive load disaggregation technology based on low-rate power data.

Key words: , non-intrusive load disaggregation, event detection, event clustering, operation states mining, household load

中图分类号:

TM 714

庄卫金, 张鸿, 方国权, 陈中. 基于设备运行状态挖掘的非侵入式负荷分解方法[J]. 电力建设, 2020, 41(8): 9-16.

ZHUANG Weijin, ZHANG Hong, FANG Guoquan, CHEN Zhong . Non-intrusive Load Disaggregation Method Based on the Mining of Equipment Operating States[J]. ELECTRIC POWER CONSTRUCTION, 2020, 41(8): 9-16.

参考文献［20］

［1］	李俊雄, 黎灿兵, 曹一家, 等. 面向智能电网的互动式节能调度初探［J］. 电力系统自动化, 2013, 37（8）: 20-25.
	LI Junxiong, LI Canbing, CAO Yijia, et al. Preliminary investigation on interactive energy-saving dispatch oriented to smart grid［J］. Automation of Electric Power Systems, 2013, 37（8）: 20-25.
［2］	HART G W. Nonintrusive appliance load monitoring［J］. Proceedings of the IEEE, 1992, 80（12）: 1870-1891.
［3］	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.
［4］	涂京，周明，宋旭帆，等.基于监督学习的非侵入式负荷监测算法比较［J］.电力自动化设备，2018，38（12）：134-140.
	TU Jing，ZHOU Ming，SONG Xufan，et al. Comparison of supervised learning-based non-intrusive load monitoring algorithms ［J］. Electric Power Automation Equipment，2018，38（12）：134-140.
［5］	孙毅, 崔灿, 陆俊, 等. 基于遗传优化的非侵入式家居负荷分解方法［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］. Power System Technology, 2016, 40（12）: 3912-3917.
［6］	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.
［7］	KONG W C, DONG Z Y, MA J, et al. An extensible approach for non-intrusive load disaggregation with smart meter data［J］. IEEE Transactions on Smart Grid, 2018, 9（4）: 3362-3372.
［8］	陈思运, 高峰, 刘烃, 等. 基于因子隐马尔可夫模型的负荷分解方法及灵敏度分析［J］. 电力系统自动化, 2016, 40（21）: 128-136.
	CHEN Siyun, GAO Feng, LIU Ting, et al. Load disaggregation method based on factorial hidden Markov model and its sensitivity analysis［J］. Automation of Electric Power Systems, 2016, 40（21）: 128-136.
［9］	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.
［10］	GIRI S, BERGS M. An error correction framework for sequences resulting from known state-transition models in non-intrusive load monitoring［J］. Advanced Engineering Informatics, 2017, 32: 152-162.
［11］	LIAO J, ELAFOUDI G, STANKOVIC L, et al. Non-intrusive appliance load monitoring using low-resolution smart meter data［C］//2014 IEEE International Conference on Smart Grid Communications （SmartGridComm）, 3-6 Nov. 2014, Venice, Italy. IEEE, 2014: 535-540.
［12］	ZHAO B C, STANKOVIC L, STANKOVIC V. On a training-less solution for non-intrusive appliance load monitoring using graph signal processing［J］. IEEE Access, 2016,4：1784-1799.
［13］	WILSON R C, NASSAR M R, GOLD J I. Bayesian online learning of the hazard rate in change-point problems［J］. Neural Computation, 2010, 22（9）: 2452-2476.
［14］	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.
［15］	COMANICIU D, MEER P. Mean shift: A robust approach toward feature space analysis［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24（5）: 603-619.
［16］	文亚凤，崔亮节，孙毅，等.考虑状态概率因子和状态修正的非侵入式负荷分解方法［J］.电网技术，2019，43（11）：4178-4184.
	WEN Yafeng， CUI Liangjie， SUN Yi， et al. Non-intrusive load decomposition method considering state probability factor and state correction ［J］. Power System Technology，2019，43 （11）：4178-4184.
［17］	ORTEGA A, FROSSARD P, KOVACEVIC J, et al. Graph signal processing: Overview, challenges, and applications［J］. Proceedings of the IEEE, 2018, 106（5）: 808-828.
［18］	STANKOVIC V, LIAO J, STANKOVIC L. A graph-based signal processing approach for low-rate energy disaggregation［C］//2014 IEEE Symposium on Computational Intelligence for Engineering Solutions （CIES）, 9-12 Dec. 2014, Orlando, FL, USA. IEEE, 2014: 81-87.
［19］	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 Xufeng, ZHAI Shaopeng, WANG Zhihua, et al. Application of deep neural network in non-intrusive load disaggregation［J］. Automation of Electric Power Systems, 2019, 43（1）: 126-132, 167.
［20］	KOLTER J Z, JOHNSON M J. REDD: A public data set for energy disaggregation research ［EB/OL］.（2011-08-01）［2019-10-10］.http://redd.csail.mit.edu./.

[1]	刘赛, 刘宇, 高山, 郭昊旻, 宋天成, 蒋伟毅, 李正, 王俊成, 徐逸民. 基于多特征目标函数PCA-ILP的非侵入式负荷分解方法[J]. 电力建设, 2020, 41(8): 1-8.
[2]	程江洲，谢诗雨，张赟宁，王劲峰，熊双菊. 预算限制下考虑综合舒适度的智能用电优化模型[J]. 电力建设, 2020, 41(1): 88-96.
[3]	曹昉，李赛，张姚. 基于前景理论量化充电效用的浮动充电服务费优化[J]. 电力建设, 2019, 40(9): 107-115.
[4]	刘志谱，李欣然，冷华，刘小龙，黄珂琪，孙瑞. 考虑非计划脱网重要负荷独立供能的综合能源系统优化调度[J]. 电力建设, 2019, 40(8): 112-120.
[5]	杨懿男，齐林海，王红，苏林萍. 基于生成对抗网络的小样本数据生成技术研究[J]. 电力建设, 2019, 40(5): 71-77.
[6]	明煦，陈艳，刘源，邹芹，李玮，胡文博，王宣，杨军. 适应于光伏接入与商圈通勤需求的电动汽车充换电能量管理策略[J]. 电力建设, 2019, 40(1): 49-59.
[7]	蔡鹏飞，杨秀，李泰杰，方陈，张勇. 基于改进聚类融合的办公型建筑用电行为分析[J]. 电力建设, 2019, 40(1): 60-67.
[8]	周冰钰，刘博，王丹，兰宇，马喜然，孙冬冬，霍秋屹. 基于自组织中心K-means算法的用户互动用电行为聚类分析[J]. 电力建设, 2019, 40(1): 68-76.
[9]	刘源，杨军，杨丙权，朱旭，陈艳，王宣. 考虑"风-光-荷-储"联合运行的配电网双层规划方法[J]. 电力建设, 2017, 38(11): 87-.
[10]	杜蜻蜓,刘继春,王冬,杨常. 计入柔性负荷的售电公司参与市场竞价两阶段优化模型 [J]. 电力建设, 2017, 38(6): 142-.
[11]	赵会茹，赵名锐，王玉玮 . 售电侧开放下日前电力市场动态博弈模型[J]. 电力建设, 2017, 38(4): 144-.
[12]	和敬涵，卢育梓，陆金耀，胡波，杨方，何博. 基于“进化”主成分分析法的用户分类及其应用[J]. 电力建设, 2017, 38(3): 101-.
[13]	雷景生,郝珈玮,朱国康. 基于“分层-汇集”模型的短期电力负荷预测[J]. 电力建设, 2017, 38(1): 68-.
[14]	张强，王毅，李鼎睿，朱文俊. 基于X-12-ARIMA季节分解与年度电量校正的月度电量预测[J]. 电力建设, 2017, 38(1): 76-.
[15]	陈玮，梁博淼，蒙文川，陈政，文福拴. 计及负荷和电价不确定性的电力零售公司购电组合优化[J]. 电力建设, 2016, 37(7): 54-63.

基于设备运行状态挖掘的非侵入式负荷分解方法

Non-intrusive Load Disaggregation Method Based on the Mining of Equipment Operating States

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献［20］

相关文章 15

编辑推荐

Metrics

本文评价

基于设备运行状态挖掘的非侵入式负荷分解方法

Non-intrusive Load Disaggregation Method Based on the Mining of Equipment Operating States

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 ［20］

相关文章 15

编辑推荐

Metrics

本文评价

参考文献［20］