朱天怡;艾芊;贺兴;李昭昱;孙东磊;李雪亮;

• 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)
• 2:国网山东省电力公司经济技术研究院

摘要(Abstract)：

数据驱动的用电行为分析方法更能够从用电大数据中挖掘出用户用电行为规律,从而提升电网侧管理服务质量。对数据驱动的用电行为分析研究模式进行综述,首先提出了一种典型的数据驱动研究架构,详细阐述了用电信息采集与聚合、用户精细化分类、关联因素辨识等环节的关键技术,深入分析了基于批处理的离线分析和基于流处理的实时分析2种典型数据分析平台以及边缘计算的应用,并探讨了用电行为分析在负荷预测、需求响应建模、异常用电行为检测等几种典型场景的综合应用,最后阐明了进一步研究可能遇到的挑战并对后续工作进行了展望。

关键词(KeyWords)： 用电行为分析;数据驱动;用户分类;关联分析;电力大数据

Abstract:

Keywords:

基金项目(Foundation): 国家电网总部科技项目(SGSDJY00GPJS1900179)~~

作者(Author): 朱天怡;艾芊;贺兴;李昭昱;孙东磊;李雪亮;

Email:

DOI: 10.13335/j.1000-3673.pst.2020.0226a

参考文献(References)：

• [1]陈启鑫，刘敦楠，林今，等．能源互联网的商业模式与市场机制(一)[J]．电网技术，2015,39(11):3050-3056.Chen Qixin,Liu Dunnan,Lin Jin,et al.Business models and market mechanisms of energy internet(I)[J].Power System Technology,2015,39(11):3050-3056(in Chinese).
• [2]何永秀，王冰，熊威，等．基于模糊综合评价的居民智能用电行为分析与互动机制设计[J]．电网技术，2012,36(10):247-252.He Yongxiu,Wang Bing,Xiong Wei,et al.Analysis of residents’smart electricity consumption behavior based on fuzzy synthetic evaluation and the design of interactive mechanism[J].Power System Technology,2012,36(10):247-252(in Chinese).
• [3] Zhang S,Zhang D,Zhang Y,et al.The research on smart power consumption technology based on big data[C]//International Conference on Smart Grid&Clean Energy Technologies.Chengdu:IEEE,2016:12-18.
• [4] Henkel J,Pagani S,Amrouch H,et al.Ultra-low power and dependability for IoT devices(invited paper for IoT technologies)[C]//2017 Design, Automation&Test in Europe Conference&Exhibition(DATE).Lausanne:IEEE,2017:954-959.
• [5] Erol-Kantarci M,Mouftah H T.Energy-efficient information and communication infrastructures in the smart grid:a survey on interactions and open issues[J].IEEE Communications Surveys&Tutorials,2015,17(1):179-197.
• [6] Abbas N,Zhang Y,Taherkordi A,et al.Mobile edge computing:a survey[J].IEEE Internet of Things Journal,2018,5(1):450-465.
• [7]薛禹胜，赖业宁．大能源思维与大数据思维的融合(二)应用及探索[J]．电力系统自动化，2016,40(8):1-13.XueYusheng,Lai Yening.Integration of macro energy thinking and big data thinking part two applications and explorations[J].Automation of Electric Power Systems,2016,40(8):1-13(in Chinese).
• [8]刘思放，邓春宇，张国宾，等．面向居民智能用电的边缘计算协同架构研究[J]．电力建设，2018,39(11):69-77.Liu Sifang,Deng Chunyu,Zhang Guobin,et al.Research on collaborative architecture for edge computing of residential intelligent usage of electricity[J].Electric Power Construction,2018,39(11):69-77(in Chinese).
• [9]陆俊，李子，朱炎平，等．智能配用电信息采集业务通信带宽预测[J]．电网技术，2016,40(4):1277-1282.Lu Jun,Li Zi,Zhu Yanping,et al.Communication bandwidth prediction for information gathering services in power distribution and utilization of smart grid[J].Power System Technology,2016,40(4):1277-1282(in Chinese).
• [10] HenrietS,SimsekliU,Fuentes B,et al.A generative model for non-intrusive load monitoring in commercial buildings[EB/OL].(2018-02-26).https://arxiv.org/abs/1803.00515.
• [11] Lu T,XuZ G,HuangB X.An event-based nonintrusive load monitoring approach:using the simplified Viterbi algorithm[J].IEEE Pervasive Computing,2017,16(4):54-61.
• [12] Nalmpantis C, Vrakas D. Machine learning approaches for non-intrusive load monitoring:from qualitative to quantitative comparation[J].Artificial Intelligence Review,2019,52(1):217-243.
• [13]许长清，赵华东，宋晓辉．基于大数据的电力用户群体识别与分析方法研究[J]．郑州大学学报(理学版)，2016,48(3):113-117.XuChangqing,Zhao Huadong,Song Xiaohui.Research on method of power user group identification and analysis based on large data[J].Journal of Zhengzhou University,2016,48(3):113-117(in Chinese).
• [14] Ch′evezP,BarberoD,Martini I,et al.Application of the K-means clustering method for the detection and analysis of areas of homogeneous residential electricity consumption at the Great La Plata Region,Buenos Aires,Argentina[J].Sustainable Cities and Society,2017(32):115-129.
• [15]刘洋，许立雄．适用于海量负荷数据分类的高性能反向传播神经网络算法[J]．电力系统自动化，2018,42(21):131-140.Liu Yang,XuLixiong.High-performance back propagation neural network algorithm for classification of mass load data[J].Automation of Electric Power Systems,2018,42(21):131-140(in Chinese).
• [16] Oprea S, Bara A. Electricity load profile calculation using self-organizing maps[C]//20th International Conference on System Theory,Control and Computing(ICSTCC).Sinaia:ICSTCC,2016:860-865.
• [17] Yang J,Zhao J,Wen F,et al.A model of customizing electricity retail prices based on load profile clustering analysis[J].IEEE Transactions on Smart Grid,2018,10(3):3374-3386.
• [18] Zhou K, Yang C, Shen J. Discovering residential electricity consumption patterns through smart-meter data mining:a case study from China[J].Utilities Policy,2017(44):73-84.
• [19]王德文，周昉昉．基于无监督极限学习机的用电负荷模式提取[J]．电网技术，2018,42(10):3393-3400.Wang Dewen,Zhou Fangfang.Extraction of electricity consumption load pattern based on unsupervised extreme learning machine[J].Power System Technology,2018,42(10):3393-3400(in Chinese).
• [20]陈俊艺，丁坚勇，田世明，等．基于改进快速密度峰值算法的电力负荷曲线聚类分析[J]．电力系统保护与控制，2018,46(20):91-99.Chen Junyi,Ding Jianyong,TianShiming,et al.An improved density peaks clustering algorithm for power load profiles clustering analysis[J].Power System Protection and Control,2018,46(20):91-99(in Chinese).
• [21]林顺富，田二伟，符杨，等．基于信息熵分段聚合近似和谱聚类的负荷分类方法[J]．中国电机工程学报，2017,37(8):2242-2252.Lin Shunfu,TianErwei,Fu Yang,et al.Power load classification method based on information entropy piecewise aggregate approximation and spectral clustering[J].Proceedings of the CSEE,2017,37(8):2242-2252(in Chinese).
• [22] Wang Y,Chen Q,Kang C,et al.Clustering of electricity consumption behavior dynamics toward big data applications[J].IEEE Transactions on Smart Grid,2017,7(5):2437-2447.
• [23] Bennasar M,Hicks Y,Setchi R.Feature selection using joint mutual information maximization[J].Expert Systems With Applications,2015,42(22):8520-8532.
• [24] He X,Ai Q,Qiu C,et al.A big data architecture design for smart grids based on random matrix theory[J].IEEE Transactions on Smart Grid,2015,8(2):674-686.
• [25] Qiu R,Chu L,He X,et al.Spatio-temporal big data analysis for smart grids based on random matrix theory:a comprehensive study[EB/OL].(2017-08-15).https://arxiv.org/abs/1708.04935.
• [26] He X,Chu L,Qiu R C,et al.A novel data-driven situation awareness approach for future grids—using large random matrices for big data modeling[J].IEEE Access,2018(6):13855-13865.
• [27]徐心怡，贺兴，艾芊，等．基于随机矩阵理论的配电网运行状态相关性分析方法[J]．电网技术，2016,40(3):781-790.Xu Xinyi,He Xing,Ai Qian,et al.A correlation analysis method for operation status of distribution network based on random matrix theory[J].Power System Technology,2016,40(3):781-790(in Chinese).
• [28] Xu X,He X,Ai Q,et al.A correlation analysis method for power systems based on random matrix theory[J].IEEE Transactions on Smart Grid,2015,8(4):1-10.
• [29]陈鹏伟，陶顺，肖湘宁，等．短时间尺度用电行为相关性分析网络模型[J]．电力系统自动化，2017,41(3):61-69.ChenPengwei,TaoShun,XiaoXiangning,et al.Network model for correlation analysis of short-term electricity consumption behavior[J].Automation of Electric Power Systems,2017,41(3):61-69(in Chinese).
• [30] Matthews S,Leger A S.Leveraging mapreduce and synchrophasors for real-time anomaly detection in the smart grid[J]. IEEE Transactions on Emerging Topics in Computing,2017,7(3):392-403.
• [31] Qureshi N M F,Siddiqui I F,Unar M A,et al.An aggregate mapreduce data block placement strategy for wireless IoT edge nodes in smart grid[J].Wireless Personal Communications,2019(106):2225-2236.
• [32]郝然，艾芊，肖斐．基于多元大数据平台的用电行为分析构架研究[J]．电力自动化设备，2017,37(8):20-27.Hao Ran,Ai Qian,Xiao Fei.Architecture based on multivariate big data platform for analyzing electricity consumption behavior[J].Electric Power Automation Equipment,2017,37(8):20-27(in Chinese).
• [33] Zhang W,Mu G,Yan G,et al.A power load forecast approach based on spatial-temporal clustering of load data[J].Concurrency and Computation:Practice and Experience,2018(30):e4386.
• [34]薛禹胜，赖业宁．大能源思维与大数据思维的融合(一)大数据与电力大数据[J]．电力系统自动化，2016,40(1):1-8.XueYusheng,Lai Yening.Integration of macro energy thinking and big data thinking part one big data and power big data[J].Automation of Electric Power Systems,2016,40(1):1-8(in Chinese).
• [35]屈志坚，王冬．面向智能调度监测的流计算并行滑动窗口技术[J]．电网技术，2016,40(7):2219-2226.QuZhijian,Wang Dong.Stream computing parallel sliding window technique for intelligent dispatching monitoring[J].Power System Technology,2016,40(7):2219-2226(in Chinese).
• [36] Domoney W F,Ramli N M,Alarefi S A S,et al.Smart city solutions to water management using self-powered,low-cost,water sensors and apache spark data aggregation[C]//Renewable&Sustainable Energy Conference.Marrakech:IEEE,2015:1-4.
• [37]田璐，齐林海，李青，等．基于Spark Streaming的电力流式大数据分析架构及应用[J]．电力信息与通信技术，2019,17(2):27-33.Tian Lu,Qi Linhai,Li Qing,et al.Power streaming big data analysis architecture and application based on spark streaming[J].Electric Power Information and Communication Technology,2019,17(2):27-33(in Chinese).
• [38] Wu K,Zhu Y,Li Q,et al.A distributed real-time data prediction framework for large-scale time-series data using stream processing[J].International Journal of Intelligent Computing and Cybernetics,2017,10(2):145.
• [39]刘纪平，吴立新，董春，等．一种大规模空间数据流式并行处理方法研究[J]．测绘科学，2016,41(1):89-93.Liu Jiping,Wu Lixin,Dong Chun,et al.Study on a streaming parallel method for massive spatial data processing[J].Science of Surveying and Mapping,2016,41(1):89-93(in Chinese).
• [40] Qiu Y,Chen Y,Jiao L,et al.RTA:real time actionable events detection as a service[C]//IEEE International Conference on Web Services.San Francisco,CA:IEEE,2016:514-521.
• [41] Salman O,Elhajj I,Kayssi A,et al.Edge computing enabling the internet of things[C]//2015 IEEE 2nd World Forum on Internet of Things(WF-IoT).Milan:IEEE,2015:603-608.
• [42] Shi W,Cao J,Zhang Q,et al.Edge computing:vision and challenges[J].IEEE Internet of Things Journal,2016,3(5):637-646.
• [43] Li H,Shou G,Hu Y,et al.Mobile edge computing:progress and challenges[C]//IEEE International Conference on Mobile Cloud Computing,Services,and Engineering.Oxford,UK:IEEE,2016:83-84.
• [44] Saputro N,Akkaya K.Investigation of smart meter data reporting strategies for optimized performance in smart grid AMI networks[J].IEEE Internet of Things Journal,2017,4(4):894-904.
• [45]李彬，贾滨诚，曹望璋，等．边缘计算在电力需求响应业务中的应用展望[J]．电网技术，2018,42(1):79-87.Li Bin,JiaBincheng,Cao Wangzhang,et al.Application prospect of edge computing in power demand response business[J].Power System Technology,2018,42(1):79-87(in Chinese).
• [46] Samie F,Bauer L,Henkel J.IoT for smart grids[M].Berlin:Springer International Publishing,2019:21-42.
• [47]张聪，樊小毅，刘晓腾，等．边缘计算使能智慧电网[J]．大数据，2019,5(2):67-81.Zhang Cong,Fan Xiaoyi,Liu Xiaoteng,et al.Edge computing enabled smart grid[J].Big Data Research,2019,5(2):67-81(in Chinese).
• [48] Thapa R,Jiao L,Oommen B J,et al.A learning automaton-based scheme for scheduling domestic shiftable loads in smart grids[J].IEEE Access,2018(6):5348-5361.
• [49] Yu-Hsiu L,Yu-Chen H.Residential consumer-centric demand-side management based on energy disaggregation-piloting constrained swarm intelligence:towards edge computing[J].Sensors,2018,18(5):1365.
• [50] Cao Y,Song H,Kaiwartya O,et al.Mobile edge computing for big-data-enabled electric vehicle charging[J].IEEE Communications Magazine,2018,56(3):150-156.
• [51] Quilumba F L,Lee W J,Huang H,et al.Using smart meter data to improve the accuracy of intraday load forecasting considering customer behavior similarities[J].IEEE Transactions on Smart Grid,2015,6(2):911-918.
• [52]赵腾，王林童，张焰，等．采用互信息与随机森林算法的用户用电关联因素辨识及用电量预测方法[J]．中国电机工程学报，2016,36(3):604-614.Zhao Teng,Wang Lintong,Zhang Yan,et al.Relation factor identification of electricity consumption behavior of users and electricity demand forecasting based on mutual information and random forests[J].Proceedings of the CSEE,2016,36(3):604-614(in Chinese).
• [53] Wang Y,Gan D H,Sun M Y,et al.Probabilistic individual load forecasting using pinball loss guided LSTM[J].Applied Energy,2019(235):10-20.
• [54]王玥，张宇帆，李昭昱，等．即插即用能量组织日前负荷概率预测方法[J]．电网技术，2019,43(9):3053-3060.Wang Yue,Zhang Yufan,Li Zhaoyu,et al.Day-ahead probability load forecasting of energy tissues with plug-and-play function[J].Power System Technology,2019,43(9):3053-3060(in Chinese).
• [55]王保义，王冬阳，张少敏．基于Spark和IPPSO_LSSVM的短期分布式电力负荷预测算法[J]．电力自动化设备，2016,36(1):117-122.Wang Baoyi, Wang Dongyang, Zhang Shaomin. Distributed short-term load forecasting algorithm based on spark and IPPSO_LSSVM[J].Electric Power Automation Equipment,2016,36(1):117-122(in Chinese).
• [56]李同智．灵活互动智能用电的技术内涵及发展方向[J]．电力系统自动化，2012,36(2):11-17.LiTongzhi.Technical implications and development trends of flexible and interactive utilization of intelligent power[J].Automation of Electric Power Systems,2012,36(2):11-17(in Chinese).
• [57]杨旭英，周明，李庚银．智能电网下需求响应机理分析与建模综述[J]．电网技术，2016,40(1):220-226.Yang Xuying,Zhou Ming,Li Gengyin.Survey on demand response mechanism and modeling in smart grid[J]. Power System Technology,2016,40(1):220-226(in Chinese).
• [58]蔡珑，顾洁，金之俭．居民用户需求响应行为影响因素辨识与响应特性提取[J]．电网技术，2017,41(7):346-353.Cai Long,GuJie,Jin Zhijian.Study on factor identification and feature extraction of residential demand response behavior[J].Power System Technology,2017,41(7):346-353(in Chinese).
• [59]徐青山，吴枭，杨斌．考虑状态差异性聚类的空调负荷直接负荷控制动态优化方法[J]．电力系统自动化，2016,40(14):33-42.XuQingshan,Wu Xiao,Yang Bin.Dynamic optimization method of direct load control for air-conditioning load considering status diversity clustering[J].Automation of Electric Power Systems,2016,40(14):33-42(in Chinese).
• [60] Wang Z,Paranjape R.Optimal residential demand response for multiple heterogeneous homes with real-time price prediction in ashould be a spacemultiagent framework[J].IEEE Transactions on Smart Grid,2017,8(3):1173-1184.
• [61] Zheng Z,Yatao Y,Niu X,et al.Wide&deep convolutional neural networks for electricity-theft detection to secure smart grids[J].IEEE Transactions on Industrial Informatics,2017,14(4):1606-1615.
• [62] Júnior L A P,Ramos C C O,Rodrigues D,et al.Unsupervised non-technical losses identification through optimum-path forest[J].Electric Power Systems Research,2016(140):413-423.
• [63] Zanetti M,Jamhour E,Pellenz M,et al.A tunable fraud detection system for advanced metering infrastructure using short-lived patterns[J].IEEE Transactions on Smart Grid,2017,10(1):830-840.
• [64] Cui W,Wang H.Anomaly detection and visualization of school electricity consumption data[C]//IEEE International Conference on Big Data Analysis.Beijing:IEEE,2017:606-611.
• [65] He X,Qiu R C,Chu L,et al.Invisible units detection and estimation based on random matrix theory[EB/OL].(2017-10-30).https://arxiv.org/abs/1710.10745.
• [66] Xiao F,Ai Q.Electricity theft detection in smart grid using random matrix theory[J].IET Generation Transmission&Distribution,2017,12(2):371-378.
• [67] Liu X,Nielsen P S.Regression-based online anomaly detection for smart grid data[EB/OL].(2016-06-18).https://arxiv.org/abs/1606.05781.
• [68]谢涛，靳丹，马志程，等．基于智能电网的分布式非法用电行为检测方法[J]．微型电脑应用，2015,31(2):54-57,60.Xie Tao,Jin Dan,Ma Zhicheng,et al.Distributed detection method of energy theft based on smart power grid[J]. Microcomputer Applications,2015,31(2):54-57,60(in Chinese).
• [69]周杨珺，梁朔，俞小勇，等．基于多源异构数据的配电网运行分析平台：系统架构与技术实现[J]．南方电网技术，2018,12(8):65-70.Zhou Yangjun,Liang Shuo,Yu Xiaoyong,et al.Research and implementation of distribution network operating analysis platform based on multi-source heterogeneous data[J].Southern Power System Technology,2018,12(8):65-70(in Chinese).
• [70] Singh S,Yassine A.IoT big data analytics with fog computing for household energy management in smart grids[C]//SGIoT 2018-2nd EAI International Conference on Smart Grid and Internet of Things.Springer:Cham,2018:13-22.
• [71] Wang C,Zhu Y,Ma Y,et al.A query-oriented adaptive indexing technique for smart grid big data analytics[J].Journal of Signal Processing Systems,2017(4):1-13.
• [72] Liu Y,Guo W,Fan C I,et al.A practical privacy-preserving data aggregation(3PDA)scheme for smart grid[J].IEEE Transactions on Industrial Informatics,2018,15(3):1767-1774.
• [73] Pan B,Zeng P,Choo K K R.A new multidimensional and fault-tolerable data aggregation scheme for privacy-preserving smart grid communications[C]//International Conference on Applications and Techniques in Cyber Security and Intelligence.EdizionidellaNormale:Cham,2018:206-219.
• [74]邓松，岳东，朱力鹏，等．电力大数据智能化高效分析挖掘技术框架[J]．电子测量与仪器学报，2016,30(11):1679-1686.Deng Song,Yue Dong,Zhu Lipeng,et al.Framework of intelligent and efficient analysis and mining technology for power big data[J].Journal of Electronic Measurement and Instrumentation,2016,30(11):1679-1686(in Chinese).
• [75]陈敬德，盛戈皞，吴继健，等．大数据技术在智能电网中的应用现状及展望[J]．高压电器，2018,54(1):35-43.Chen Jingde,Sheng Gehao,WuJijian,et al.Application status and prospect of big data technology in smart grid[J].High Voltage Apparatus,2018,54(1):35-43(in Chinese).
• [76]周念成，廖建权，王强钢，等．深度学习在智能电网中的应用现状分析与展望[J]．电力系统自动化，2019,43(4):267-284.Zhou Niancheng,Liao Jianquan,Wang Qianggang,et al.Analysis and prospect of deep learning application in smart grid[J].Automation of Electric Power Systems,2019,43(4):267-284(in Chinese).
• [77]李刚，焦谱，文福拴，等．基于偏序约简的智能电网大数据预处理方法[J]．电力系统自动化，2016,40(7):104-112.Li Gang,Jiao Pu,Wen Fushuan,et al.A partial order reduction based method for big data preprocessing in smart grid environment[J].Automation of Electric Power Systems,2016,40(7):104-112(in Chinese).
• [78] Cai Y,Huang T,Bompard E,et al.Self-sustainable community of electricity prosumers in the emerging distribution system[J].IEEE Transactions on Smart Grid,2017,8(5):2207-2216.
• [79] Rathnayaka A J D,Potdar V M,Dillon T S,et al.A methodology to find influential prosumers in prosumer community groups[J].IEEE Transactions on Industrial Informatics,2014,10(1):706-713.
• [80]韦晓广，高仕斌，臧天磊，等．社会能源互联网：概念、架构和展望[J]．中国电机工程学报，2018,38(17):4969-4986.Wei Xiaoguang,GaoShibin,ZangTianlei,et al.Social energy internet:concept,architecture and outlook[J].Proceeding of the CSEE,2018,38(17):4969-4986(in Chinese).