&nbsp;智能电网环境下基于大数据挖掘的居民负荷设备识别与负荷建模
&nbsp;

杨甲甲; 赵俊华; 文福拴; 董朝阳; 薛禹胜

doi:10.3969/j.issn.1000-7229.2016.12.002

PDF(5122 KB)

电力建设 ›› 2016, Vol. 37 ›› Issue (12) : 11. DOI: 10.3969/j.issn.1000-7229.2016.12.002

电力大数据

智能电网环境下基于大数据挖掘的居民负荷设备识别与负荷建模

杨甲甲1，赵俊华2，文福拴3,4，董朝阳5，薛禹胜6

作者信息 +

Residential Appliance Identification and Load Modeling Based on Big Data Mining in Smart Grid Environment

YANG Jiajia1, ZHAO Junhua2, WEN Fushuan3,4, DONG Zhaoyang5, XUE Yusheng6

Author information +

文章历史 +

摘要

利用数据挖掘技术对用户负荷大数据进行处理，既可以通过识别用电负荷设备来分析用户的用电行为习惯，又可以辅助进行负荷精确建模，实现精确而有目标性的需求侧管理或制定具有针对性的零售商售电策略。在此背景下，基于动态时间弯曲(dynamic time warping，DTW)的时间序列匹配方法，提出了一种低频负荷数据下的居民电器设备识别方法。首先，将负荷数据分割成单负荷设备运行和多负荷设备同时运行2种情况下的负荷子序列；然后，依据待识别子序列的时间长度，参照实测的电器设备耗电功率数据，生成与其时间长度一致的电器设备耗电功率参考序列，其中包含了从电器设备启动前一时刻至设备关闭后一时刻的功率变化情形；最后，以DTW距离作为相似性度量指标确定识别结果。对于由多负荷设备运行产生的负荷序列，提出了一种剔除已识别设备后将序列再次分割，如此交替进行的识别策略。在获得识别结果后，构建了居民负荷统计模型。借助于高效数据分析软件R语言平台，实现了所提出的算法，并使用500组负荷数据进行了数据实验。结果表明，在对负荷数据每 min采样1次的情况下，所提出的负荷设备识别方法对单设备负荷序列识别的准确率超过93%，对多设备负荷序列识别的准确率接近83%。

Abstract

Through big data mining of residential load data, it can not only analyze the electricity consumption behaviour of residents by the identification of electrical load equipment, but also establish the load precise modeling, which can realize targeted demand-side management as well as develop customized electricity retailing strategies. Given this background, based on the dynamic time warping (DTW) time series matching method, this paper proposes a novel appliance identification algorithm for low frequency sampling load data. Firstly, the residential load sequence is segmented into subsequences composed of the single appliance load profile and multi-appliance load profile. Then, according to the time length of subsequences to be identified and measured electrical equipment power consumption data, reference load sequences of all given appliances are generated which have the same length of each query subsequence, including power change from the moment before equipment start to that after equipment shutdown. Finally, the DTW distance is taken as the similarity metric to determine recognition results. For a subsequence composed of multiple appliances, the best matched reference sequence is reduced after each DTW is matched, and then segmentation and DTW matching are carried on until all appliances are extracted. Given the status of all identified appliances, a statistical residential load model is developed. The proposed algorithm is coded in the R programming language and tested through a load dataset containing 500 households profiles. The simulation results show that the proposed algorithm could identify the single appliance load subsuquence at an accuracy above 93%, under the condition that the load data is sampled once every minute; while for the more difficult multi-appliance subsequence identification, the achieved accuracy is around 83%.

导出引用

杨甲甲, 赵俊华, 文福拴, 董朝阳, 薛禹胜. 智能电网环境下基于大数据挖掘的居民负荷设备识别与负荷建模

[J]. 电力建设. 2016, 37(12): 11 https://doi.org/10.3969/j.issn.1000-7229.2016.12.002

YANG Jiajia, ZHAO Junhua, WEN Fushuan, DONG Zhaoyang, XUE Yusheng. Residential Appliance Identification and Load Modeling Based on Big Data Mining in Smart Grid Environment[J]. Electric Power Construction. 2016, 37(12): 11 https://doi.org/10.3969/j.issn.1000-7229.2016.12.002

中图分类号： TM 73

参考文献

［1］REINHARDT A，BAUMANN P，BURGSTAHLER D，et al. On the accuracy of appliance identification based on distributed load metering data ［C］ // Proceedings of the Sustainable Internet and ICT for Sustainability. Pisa，Italy: IEEE，2012：1-9.

［2］XU Y，MILANOVIC J V. Artificial-intelligence-based methodology for load disaggregation at bulk supply point ［J］. IEEE Transactions on Power Systems，2015，30(2)：795-803.

［3］余贻鑫，刘博，栾文鹏. 非侵入式居民电力负荷监测与分解技术［J］. 南方电网技术，2013，7(4)：1-5.

YU Yixin，LIU Bo，LUAN Wenpeng. Noninstrusive residential load monitoring and decomposition technology ［J］. Southern Power System Technology，2013，7(4)：1-5.

［4］FIGUEIREDO M，DE-ALMEIDA A，RIBEIRO B. Home electrical signal disaggregation for non-intrusive load monitoring (NILM) systems ［J］. Neurocomputing，2012(96)：66-73.

［5］DONG M，MEIRA P C M，XU W，et al. Non-intrusive signature extraction for major residential loads ［J］. IEEE Transactions on Smart Grid，2013，4(3)：1421-1430.

［6］LIANG J，NG S K K，KENDALL G，et al. Load signature study—Part I：basic concept，structure，and methodology ［J］. IEEE Transactions on Power Delivery，2010，25(2)：551-560.

［7］MITTELSDORF M，HUWEL A，KLINGENBERG T，et al. Submeter based training of multi-class support vector machines for appliance recognition in home electricity consumption data ［C］ // Proceedings of the 2nd International Conference on Smart Grids and Green IT Systems，Aachen，Germany，2013：151-158.

［8］PARADISO F，PAGANELLI F，LUCHETTA A，et al. ANN-based appliance recognition from low-frequency energy monitoring data ［C］//Proceedings of the 2013 IEEE 14th International Symposium and Workshops on a World of Wireless，Mobile and Multimedia Networks (WoWMoM). Madrid，Spain：IEEE，2013：1-6.

［9］RUZZELLI A G，NICOLAS C，SCHOOFS A，et al. Real-time recognition and profiling of appliances through a single electricity sensor ［C］ // Proceedings of the 2010 7th Annual IEEE Communications Society Conference on Sensor Mesh and Ad Hoc Communications and Networks (SECON). Boston，MA：IEEE，2010：1-9.

［10］PAGANELLI F，PARADISO F，TURCHI S，et al. Appliance recognition in an OSGi-based home energy management gateway ［J/OL］. International Journal of Distributed Sensor Networks，2015：1-12. ［2016-11-20］.http：//www.hindawi.com/journals/ijdsn/2015/937356.

［11］BELLEY C，GABOURY S，BOUCHARD B，et al. An efficient and inexpensive method for activity recognition within a smart home based on load signatures of appliances ［J］. Pervasive and Mobile Computing，2014，12(3)：58-78.

［12］MCLOUGHLIN F，DUFFY A，CONLON M. Characterising domestic electricity consumption patterns by dwelling and occupant socio-economic variables：an irish case study ［J］. Energy and Buildings，2012，48(19)：240-248.

［13］林顺富, 黄娜娜, 赵伦加, 等. 基于用户行为的家庭日负荷曲线模型［J］. 电力建设, 2016, 37(10): 114-121.

LIN Shunfu,HUANG Nana, ZHAO Lunjia, et al. Domestic daily load curve modeling based on user behavior ［J］. Electric Power Construction, 2016, 37(10): 114-121.

［14］黎静华, 叶柳. 基于出线的变电站综合负荷建模方法［J］. 电力建设, 2014, 35(9): 7-12.

LI Jinghua，YE Liu. Outlet-based substation comprehensive load modeling method ［J］. Electric Power Construction, 2014, 35(9): 7-12.

［15］郑小霞，刘庆强，林顺富，等. 面向非干预式负荷监测的居民负荷微观特性研究［J］. 电力系统保护与控制，2014，42(10)：62-71.

ZHENG Xiaoxia，LIU Qingqiang，LIN Shunfu，et al. Research of the microscopic signatures of residential loads for NILM ［J］. Power System Protection and Control，2014，42(10)：62-71.

［16］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)：54-58.

GAO Yun，YANG Honggeng. Household load identification based on closeness matching of transient characteristics ［J］. Automation of Electric Power Systems，2013，37(9)：54-58.

［17］张红梅，孙洁，许仪勋，等. 基于暂态特征聚类的家用负荷识别［J］. 电子技术与软件工程，2015(6)：185-186.

［18］曲朝阳，于华涛，郭晓利. 基于开启瞬时负荷特征的家电负荷识别［J］. 电工技术学报，2015，30(1)：358-364.

QU Zhaoyang，YU Huatao，GUO Xiaoli. The recognition of appliances instantaneous load ［J］. Transactions of China Electrotechnical Society，2015，30(1)：358-364.

［19］林顺富，赵伦加，刘庆强，等. 基于0-1 二次规划的非干预式负荷识别算法研究［J］. 电力系统保护与控制，2016，44(8)：85-91.

LIN Shunfu，ZHAO Lunjia，LIU Qingqiang，et al. A nonintrusive load identification method based on quadratic 0-1 programming ［J］. Power System Protection and Control，2016，44(8)：85-91.

［20］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.

［21］赵云，钱斌，王科，等. 基于特征相似度的非侵入式用电负荷识别模型研究［J］. 电气应用，2015(S)：199-203.

［22］王庆玉，张青青，张高峰，等. 谱聚类算法在家用负荷识别中的应用［J］. 电测与仪表，2015，52(1)：119-123.

WANG Qingyu，ZHANG Qingqing，ZHANG Gaofeng，et al. Application of the spectral clustering algorithm to household load identification ［J］. Electrical Measurement & Instrumentation，2015，52(1)：119-123.

［23］李坦，杨洪耕，高云. 智能电表家用负荷识别技术综述［J］. 供用电，2011，28(6)：39-42.

LI Tan，YANG Honggeng，GAO Yun. Overview of exploration on household load identification of intelligent metering ［J］. Distribution & Utilization，2011，28(6)：39-42.

［24］BERNDT D，CLIFFORD J. Using dynamic time warping to find patterns in time series ［R］//AAAI-94 Workshop on Knowledge Discovery in Databases. New York: AAAI, 1994.

［25］KEOGH E，RATANAMAHATANA C A. Exact indexing of dynamic time warping ［J］. Knowledge and Information Systems，2005，7(3)：358-386.

［26］GIORGINO T. Computing and visualizing dynamic time warping alignments in R：the DTW package ［J］. Journal of Statistical Software，2009，31(7)：1-24.

［27］CORDER G W，FOREMAN D I. Nonparametric statistics for non-statisticians：a step-by-step approach ［M］. USA：John Wiley & Sons，2009.

［28］KONG W，DONG Z Y，CHEN G，et al. A rule based domestic load profile generator for future smart grid ［C］ // Proceedings of the 2014 IEEE Australasian Universities Power Engineering Conference (AUPEC). Perth，WA：IEEE，2014：1-5.

［29］EGARTER D，BHUVANA V P，ELMENREICH W. PALDi：online load disaggregation via particle filtering［J］. IEEE Transactions on Instrumentation and Measurement，2014，64（2）：467-477.