基于智能用电网络的负荷状态与类型在线辨识

doi:10.12204/j.issn.1000-7229.2022.04.008

电力建设 ›› 2022, Vol. 43 ›› Issue (4): 69-80.doi: 10.12204/j.issn.1000-7229.2022.04.008

基于智能用电网络的负荷状态与类型在线辨识

郭治远¹^,²(), 李志勇³(), 邵洁³(), 黄婷⁴(), 周欢¹^,²(), 范帅¹^,²(), 何光宇¹^,²()

1.电力传输与功率变换控制教育部重点实验室(上海交通大学),上海市 200240
2.上海交通大学电子信息与电气工程学院,上海市 200240
3.国网上海浦东供电公司张江科学城能源服务中心,上海市 201210
4.国网上海市电力公司电力调度控制中心,上海市200122

收稿日期:2021-10-14 出版日期:2022-04-01 发布日期:2022-03-24
通讯作者: 周欢 E-mail:15821891687@163.com;lizy@hn.csg.cn;shaoj@hn.csg.cn;huangting@sh.sgcc.com.cn;shenarder@sjtu.edu.cn;fanshuai@sjtu.edu.cn;hhhxxjj@163.com
作者简介:郭治远(1997),男,硕士研究生,主要研究方向为智能用电网络、负荷监测,E-mail: 15821891687@163.com;
李志勇(1972),男,学士,高级讲师,主要研究方向为智慧园区建设与培训等,E-mail: lizy@hn.csg.cn;
邵洁(1972),女,硕士,讲师,主要研究方向为智智慧园区建设与培训等,E-mail: shaoj@hn.csg.cn;
黄婷(1989),女,硕士,工程师,主要研究方向为自动需求响应、综合能源系统,E-mail: huangting@sh.sgcc.com.cn;
范帅(1993),男,博士,助理研究员,主要研究方向为需求响应、虚拟电厂等,E-mail: fanshuai@sjtu.edu.cn;
何光宇(1972),男,教授,博士生导师,通信作者,主要研究方向为智能电网、状态估计、智能用电网络等,E-mail: hhhxxjj@163.com。
基金资助:
国家重点研发计划项目(2019YFE0122600);南方电网重点科技项目(HNKJXM20180209)

Online Monitoring of Load States and Types Based on Smart Electric Appliance Network

GUO Zhiyuan¹^,²(), LI Zhiyong³(), SHAO Jie³(), HUANG Ting⁴(), ZHOU Huan¹^,²(), FAN Shuai¹^,²(), HE Guangyu¹^,²()

1. Key Laboratory of Control of Power Transmission and Conversion (Shanghai Jiao Tong University), Ministry of Education, Shanghai 200240, China
2. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
3. Zhangjiang Science City Energy Service Center, State Grid Shanghai Pudong Power Supply Company, Shanghai 201210, China
4. Electric Power Dispatching and Control Center, State Grid Shanghai Municipal Electric Power Company, Shanghai 200122, China

Received:2021-10-14 Online:2022-04-01 Published:2022-03-24
Contact: ZHOU Huan E-mail:15821891687@163.com;lizy@hn.csg.cn;shaoj@hn.csg.cn;huangting@sh.sgcc.com.cn;shenarder@sjtu.edu.cn;fanshuai@sjtu.edu.cn;hhhxxjj@163.com
Supported by:
National Key Research and Development Program of China(2019YFE0122600);Key Science and Technology Project of China Southern Power Grid(HNKJXM20180209)

摘要/Abstract

摘要：

电器级负荷的实时信息辨识是实现负荷控制类需求响应以及用户侧自趋优运行的前提。为满足智能用电网络辨识后自动进行精准控制的应用需要,提出了电器级负荷状态与类型在线辨识技术,以期快速、准确且高可扩展地为智能用电网络的调控提供信息基础。智能用电网络的大量终端可提供电器级低频数据的实时测量结果。基于此,采用改进双边累积和分段算法以及隐马尔科夫模型对电器状态进行实时辨识,实现对应电器实际工况的状态序列提取;对电器类型采用基于支持向量数据描述的单分类方法进行高扩展性在线辨识。以居民和办公楼宇等应用场景搭建智能用电网络,实证结果表明所提方法具有较好的准确性、实时性和扩展性。

关键词: 智能用电网络, 负荷状态, 负荷类型, 双边累积和, 单分类

Abstract:

Perceiving state and identity of real-time electrical load is the premise of refined energy management and demand response. To meet the automatic and precise control requirements of smart electric appliance network, the on-line identification technology of appliance-level load state and type is proposed. On the basis of real-time measurement and communication of multi-appliances, the state of load is extracted by improved CUSUM segmentation and hidden Markov model, and the single classification method SVDD is used to identify the electrical appliance type extensively. The accuracy, timeliness and extensive ability of the proposed methods are verified by constructing smart electric appliance network in residential and office buildings.

Key words: smart electric appliance network, load state, load identity, cumulative sum, one-class classification

中图分类号:

TM714

郭治远, 李志勇, 邵洁, 黄婷, 周欢, 范帅, 何光宇. 基于智能用电网络的负荷状态与类型在线辨识[J]. 电力建设, 2022, 43(4): 69-80.

GUO Zhiyuan, LI Zhiyong, SHAO Jie, HUANG Ting, ZHOU Huan, FAN Shuai, HE Guangyu. Online Monitoring of Load States and Types Based on Smart Electric Appliance Network[J]. ELECTRIC POWER CONSTRUCTION, 2022, 43(4): 69-80.

图/表 17

图1 智能用电网络

Fig.1 Smart electric appliance network

图2 事件驱动量测机制下的负荷在线辨识流程

Fig.2 Load monitoring method based on event-driven multi-agent measurement mechanism

图A1 实时识别过程及各步骤中间数据形式

Fig.A1 Real-time identification process and intermediate data of each step

表A1 算法独立性与泛化性实验数据集构成

Table A1 Data set for the experiment of algorithm independece and generalization

图3 电器功率数据形态

Fig.3 Patterns of appliance power data

图4 电器功率数据特征分布对比

Fig.4 Comparison of characteristic distribution of power data

图5 扩展半径ISVDD算法

Fig.5 Incremental support vector data description with extended radius algorithm

图A3 基于智能用电网络的数据收集过程

Fig.A3 Data collection process based on Smart Electric Appliance Network

图6 本文建立的数据集

Fig.6 The data set built in this paper

表A2 算法自动扩展性实验数据集构成

Table A2 Data set for the experiment of algorithm outomatic scalability

图A2 部分电器的状态分析结果

Fig.A2 Analysis results of some electrical appliances states

表A3 电器功率状态特征统计

Table A3 State characteristic statistics of electrical appliances power

图7 本文方法与滑动窗、聚类方法对比

Fig.7 Comparison of segmentation results

表1 分段效果对比

Table 1 The result of segmentation

表2 训练集/测试集的类型识别结果

Table 2 Type classification result of train/test set

表3 训练集/补充测试集的类型识别结果

Table 3 Type classification result of train/extend test set

图8 扩展半径ISVDD算法结果

Fig.8 Result of incremental support vector data description with extended radius algorithm

参考文献 26

[1]	赵雪霖, 何光宇, 杨文轩, 等. 智能用电网络的设计与初步实现[J]. 电工电能新技术, 2014, 33(10):52-57.
	ZHAO Xuelin, HE Guangyu, YANG Wenxuan, et al. Design and initial implementation of smart electric appliance network[J]. Advanced Technology of Electrical Engineering and Energy, 2014, 33(10):52-57.
[2]	上海艾瑞市场咨询有限公司. 中国智能家居行业研究报告2018年[A]. 艾瑞咨询系列研究报告, 2018: 50.
[3]	黄海涛, 朱丰泽, 李小玉, 等. 负荷聚合商的多家庭用电能量控制与管理策略[J]. 电力建设, 2018, 39(1):54-60.
	HUANG Haitao, ZHU Fengze, LI Xiaoyu, et al. Multi-families electricity energy control and management strategy for load aggregator[J]. Electric Power Construction, 2018, 39(1):54-60.
[4]	原吕泽芮, 顾洁, 金之俭. 基于云-边-端协同的电力物联网用户侧数据应用框架[J]. 电力建设, 2020, 41(7):1-8.
	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.
[5]	KONG W, 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. doi: 10.1109/TSG.2016.2631238 URL
[6]	罗平, 樊星驰, 章坚民, 等. 基于电器运行状态和深度学习的非侵入式负荷分解[J]. 电力系统自动化, 2021, 45(12):49-56.
	LUO Ping, FAN Xingchi, ZHANG Jianmin, et al. Non-intrusive load decomposition based on operation state of electrical appliances and deep learning[J]. Automation of Electric Power Systems, 2021, 45(12):49-56.
[7]	孙毅, 李昊洋, 刘耀先, 等. 基于改进隐马尔科夫模型的非侵入式家居负荷识别[J]. 电力建设, 2020, 41(4):73-80.
	SUN Yi, LI Haoyang, LIU Yaoxian, et al. Non-intrusive home-load identification based on improved hidden Markov model[J]. Electric Power Construction, 2020, 41(4):73-80.
[8]	刘娟, 鞠登峰, 王勇, 等. 变电站设备智能状态监测系统的设计及应用[J]. 电力建设, 2012, 33(6):6-10.
	LIU Juan, JU Dengfeng, WANG Yong, et al. Design and application of intelligent condition monitoring system for substation equipment[J]. Electric Power Construction, 2012, 33(6):6-10.
[9]	KIM Y, SCHMID T, CHARBIWALA Z M, et al. ViridiScope: design and implementation of a fine grained power monitoring system for homes[C]// Proceedings of the 11th international conference on Ubiquitous computing. New York, NY, USA: ACM, 2009: 245-254.
[10]	高云, 杨洪耕. 基于暂态特征贴近度匹配的家用负荷识别[J]. 电力系统自动化, 2013, 37(9):54-59.
	GAO Yun, YANG Honggeng. Household load identification based on closeness matching of transient characteristics[J]. Automation of Electric Power Systems, 2013, 37(9):54-59.
[11]	TEKLER Z D, LOW R, ZHOU Y R, et al. Near-real-time plug load identification using low-frequency power data in office spaces: Experiments and applications[J]. Applied Energy, 2020, 275:115391. doi: 10.1016/j.apenergy.2020.115391 URL
[12]	TUNDIS A, FAIZAN A, MÜHLHÄUSER M. A feature-based model for the identification of electrical devices in smart environments[J]. Sensors (Basel, Switzerland), 2019, 19(11):2611. doi: 10.3390/s19112611 URL
[13]	江帆, 杨洪耕. 基于选择性贝叶斯分类的非侵入式负荷识别方法[J]. 电力建设, 2019, 40(2):94-99.
	JIANG Fan, YANG Honggeng. Non-intrusive load identification method based on selected Bayes classifier[J]. Electric Power Construction, 2019, 40(2):94-99.
[14]	杨东升, 孔亮, 胡博, 等. 基于多特征序列融合的负荷辨识方法[J]. 电力系统自动化, 2017, 41(22):66-73.
	YANG Dongsheng, KONG Liang, HU Bo, et al. Load identification method based on multi-feature sequence fusion[J]. Automation of Electric Power Systems, 2017, 41(22):66-73.
[15]	阳小丹, 李扬. 家庭用电响应模式研究[J]. 电力系统保护与控制, 2014, 42(12):51-56.
	YANG Xiaodan, LI Yang. Research on household electricity response mode[J]. Power System Protection and Control, 2014, 42(12):51-56.
[16]	郏琨琪, 何光宇. 智能用电网络数据采集与通信机制的研究[J]. 中国电机工程学报, 2016, 36(6):1544-1551.
	JIA Kunqi, HE Guangyu. Research of smart electric appliance network data collection and communication mechanism[J]. Proceedings of the CSEE, 2016, 36(6):1544-1551.
[17]	席军, 刘廷华. PTC热敏电阻的开发应用现状[J]. 塑料, 2005, 34(4):79-84.
	XI Jun, LIU Tinghua. State of development and application of PTC thermal resistance[J]. Plastics, 2005, 34(4):79-84.
[18]	徐磊. 动力锂电池充电技术研究[D]. 太原: 太原科技大学, 2014.
[19]	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.
[20]	JIANG P Y, KUROZUMI E. Monitoring parameter changes in models with a trend[J]. Journal of Statistical Planning and Inference, 2020, 207:288-319. doi: 10.1016/j.jspi.2020.01.004 URL
[21]	郭红霞, 陆进威, 杨苹, 等. 非侵入式负荷监测关键技术问题研究综述[J]. 电力自动化设备, 2021, 41(1):135-146.
	GUO Hongxia, LU Jinwei, YANG Ping, et al. Review on key techniques of non-intrusive load monitoring[J]. Electric Power Automation Equipment, 2021, 41(1):135-146.
[22]	TAX D M J, DUIN R P W. Support vector data description[J]. Machine Learning, 2004, 54(1):45-66. doi: 10.1023/B:MACH.0000008084.60811.49 URL
[23]	FORTMANN-ROE S. Understanding the bias-variance tradeoff[Z/OL]. [2021-06-12]. http://scott.fortmann-roe.com/docs/BiasVariance.html.
[24]	花小朋, 皋军, 田明, 等. 改进的SVDD增量学习算法[J]. 计算机工程, 2009, 35(22):210-211, 215.
	HUA Xiaopeng, GAO Jun, TIAN Ming, et al. Improved incremental learning algorithm for support vector data description[J]. Computer Engineering, 2009, 35(22):210-211, 215.
[25]	TSAI M S, LIN Y H. Modern development of an Adaptive Non-Intrusive Appliance Load Monitoring system in electricity energy conservation[J]. Applied Energy, 2012, 96:55-73. doi: 10.1016/j.apenergy.2011.11.027 URL
[26]	郏琨琪. 智能用电网络的数据驱动架构及其关键技术研究[D]. 上海交通大学, 2020.
	JIA Kunqi. Research on data-driven architecture and key technologies of smart consumption grid[D]. Shanghai Jiao Tong university, 2020.

基于智能用电网络的负荷状态与类型在线辨识

Online Monitoring of Load States and Types Based on Smart Electric Appliance Network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 26

相关文章 7

编辑推荐

Metrics

本文评价

[1]	王磊, 刘洋, 李文峰, 张杰, 许立雄, 邢哲铭. 基于用电行为数字特征画像的电力用户两阶段分类方法[J]. 电力建设, 2022, 43(2): 70-80.
[2]	张杰, 刘洋, 李文峰, 王磊, 许立雄. 基于两阶段数据增强和双向深度残差TCN的用户负荷曲线分类方法[J]. 电力建设, 2022, 43(2): 89-97.
[3]	刘敦楠, 张悦, 彭晓峰, 刘明光, 王文, 加鹤萍, 秦光宇, 王峻, 杨烨. 计及相似日与气象因素的电动汽车充电负荷聚类预测[J]. 电力建设, 2021, 42(2): 43-49.
[4]	陆晓, 徐春雷, 冷钊莹, 吴海伟, 陈中. 基于数据驱动方法的疫情阶段电力用户负荷特性画像模型[J]. 电力建设, 2021, 42(2): 93-106.
[5]	段秦刚, 王浩浩, 伍子东, 王一, 朱涛, 董萍, 刘明波. 基于改进蚁群算法的电力负荷半监督聚类[J]. 电力建设, 2020, 41(10): 81-89.
[6]	江友华,顾胜坚,方勇, . 电力电子技术在有载调压变压器中的应用[J]. 电力建设, 2006, 27(12): 75-77.
[7]	汪玉凤,张兰芬,贾建新 . 10 kV变电所动态无功补偿研究[J]. 电力建设, 2005, 26(12): 2-0.