基于曲线相似与低秩矩阵的缺失电量数据补全方法

doi:10.3969/j.issn.1000-7229.2020.01.004

电力建设 ›› 2020, Vol. 41 ›› Issue (1): 32-38.doi: 10.3969/j.issn.1000-7229.2020.01.004

• 泛在电力物联网 ·栏目主持杨挺教授、傅质馨副教授· • 上一篇下一篇

基于曲线相似与低秩矩阵的缺失电量数据补全方法

乔文俞1，李野2，刘浩宇2，李扬3，杨挺3

1.中国电力科学研究院有限公司，北京市 100192；2.国网天津市电力公司电力科学研究院，天津市 300384；3.天津大学电气自动化与信息工程学院，天津市 300072

出版日期:2020-01-01
作者简介:乔文俞（1987），女，硕士，主要研究方向为自动检测技术；李野（1983），男，硕士，主要研究方向为电能计量技术；刘浩宇（1995），男，学士，主要研究方向为电能计量技术；李扬（1995），男，硕士研究生，主要研究方向为电力信息物理系统；杨挺（1979），男，博士，教授，通信作者，主要研究方向为电力信息物理系统。
基金资助:
国家重点研发计划资助项目(2017YFE0132100)；国家自然科学基金项目(61571324)；国家电网公司总部科技项目（KJ18-1-39）

Missing Load Data Completion Based on Curve Similarity and Low-Rank Matrix

QIAO Wenyu1, LI Ye2, LIU Haoyu2, LI Yang3, YANG Ting3

1. China Electric Power Research Institute, Beijing 100192, China；2. Electric Power Research Institute of State Grid Tianjin Electric Power Corporation, Tianjin 300384, China；3. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

Online:2020-01-01
Supported by:
This work is supported by National Key Research and Development Program of China (No. 2017YFE0132100) , National Natural Science Foundation of China (No. 61571324) and State Grid Corporation of China Research Program (No. KJ18-1-39).

摘要/Abstract

摘要： 低压台区用电数据是电网运营中众多高级应用的基础。然而，在泛在电力物联网数据采集、传输、储存管理的过程中，会不可避免地出现数据缺失的情况，在一定程度上影响上层高级应用。针对这一问题，文章研究并提出曲线相似与低秩矩阵填充理论相结合的用电数据缺失补全方法。首先通过分析电量数据矩阵奇异值分布，揭示其低秩特性，完成数据恢复可行性判定。在此基础上，考虑用电曲线之间的差异性，提出预填充-曲线相似分类-二次填充的数据恢复方法，在对电量矩阵进行预填充之后，对于每一条待恢复的用电量曲线，基于考虑数据缺失的曲线相似性测度，找到与其最为相似的k条曲线构成数据矩阵，之后再次应用低秩矩阵填充理论恢复缺失数据，以提高恢复精度。以华北某电网居民用户电量数据进行试验，并将文章提出的方法与经典插值补齐法相比较，验证了所提出的电量曲线聚类与矩阵填充相结合的方法可以更有效补齐缺失电量数据。

关键词: 电量数据, 数据缺失, 曲线相似性, 低秩矩阵填充

Abstract: Many advanced applications in the power grid are based on load data. However, in the process of data collection, transmission and storage, there will inevitably meet with data missing, which may bring bad effect to data analysis. In allusion to the above problem, this paper proposes a missing data completion strategy combining load curve similarity and singular value threshold algorithm. Firstly, through analyzing the distribution of singular values in electric data matrix, a low rank characteristic is revealed. On the basis of that, considering the differences between power consumption curves, a data recovery method of pre-filling, curve similarity classification and secondary filling is proposed. After the pre-filling, for each power curve to be recovered, the k curves which are most similar to it are found on the basis of the improved similarity index to form the data matrix, and then the low-rank matrix completion is applied again. Through the above steps, the missing recovery is supposed to be improved. The load data from the power grid in north China is used for test, and the method proposed is compared with the classical interpolation method to verify the effectiveness. Results prove that the combination of load curve similarity and singular value thresholding (SVT) can effectively complete the missing data and provide strong support for load data repair.

Key words: load data, missing data, curve similarity, low-rank matrix completion

中图分类号:

TM 93

乔文俞，李野，刘浩宇，李扬，杨挺. 基于曲线相似与低秩矩阵的缺失电量数据补全方法[J]. 电力建设, 2020, 41(1): 32-38.

QIAO Wenyu, LI Ye, LIU Haoyu, LI Yang, YANG Ting. Missing Load Data Completion Based on Curve Similarity and Low-Rank Matrix[J]. Electric Power Construction, 2020, 41(1): 32-38.

参考文献

［1］张亚健,杨挺,孟广雨. 泛在电力物联网在智能配电系统应用综述及展望［J］. 电力建设, 2019, 40(6):1-12.
ZHANG Yajian, YANG Ting, MENG Guangyu. Review and prospect of ubiquitous power Internet of things in smart distribution system［J］. Electric Power Construction, 2019, 40(6):1-12.
［2］李含玉,杜兆斌,陈丽丹,等.基于出行模拟的电动汽车充电负荷预测模型及V2G评估［J］.电力系统自动化,2019,43(21):88-96.
LI Hanyu,DU Zhaobin,CHEN Lidan, et al.Trip simulation based charging load forecasting model and vehicle-to-grid evaluation of electric vehicles［J］.Automation of Electric Power Systems,2019,43(21):88-96.
［3］郑伟民,叶承晋,张曼颖，等.基于Softmax概率分类器的数据驱动空间负荷预测［J］.电力系统自动化,2019,43(9):117-124.
ZHENG Weimin, YE Chengjin, ZHANG Manying, et al. Data-driven spatial load forecasting method based on Softmax probabilistic classifier［J］. Automation of Electric Power Systems ,2019,43(9):117-124.
［4］闫志杰,张蕊萍,董海鹰,等.基于需求响应的电动汽车充放电电价与时段研究［J］.电力系统保护与控制,2018,46(15):16-22.
YAN Zhijie, ZHANG Ruiping, DONG Haiying, et al. Price and period research of electric vehicles charging and discharging based on demand response［J］. Power System Protection and Control,2018,46(15):16-22.
［5］蔡含虎,向月,杨昕然.计及需求响应的综合能源系统容量经济配置及效益分析［J］.电力自动化设备,2019，39(8): 186-194..
CAI Hanhu, XIANG Yue, YANG Xinran. Economic capacity allocation and benefit analysis of integrated energy system considering demand response［J］. Electric Power Automation Equipment, 2019，39(8): 186-194.
［6］杨挺, 赵黎媛, 王成山. 人工智能在电力系统及综合能源系统中的应用综述［J］. 电力系统自动化, 2019, 43(1):2-14.
YANG Ting, ZHAO Liyuan, WANG Chengshan. Review on application of artificial intelligence in power system and integrated energy system［J］. Automation of Electric Power Systems, 2019, 43(1):2-14.
［7］王守相,陈海文,潘志新,等.采用改进生成式对抗网络的电力系统量测缺失数据重建方法［J］.中国电机工程学报,2019,39(1):56-64.
WANG Shouxiang, CHEN Haiwen, PAN Zhixin, et al. A reconstruction method for missing data in power system measurement using an improved generative adversarial network［J］. Proceedings of the CSEE,2019,39(1):56-64.
［8］杨茂,孙涌,穆钢,等.基于自适应神经模糊推理系统的风功率缺失数据补齐［J］.电力系统自动化,2014,38(19):16-21.
YANG Mao, SUN Yong, MU Gang, et al. Data completing of missing wind power data based on adaptiveneuro-fuzzy inference system［J］. Automation of Electric Power Systems,2014,38(19):16-21.
［9］于华楠,杜瑶,郭树旭.基于压缩传感的高精度同步相量测量方法［J］.吉林大学学报(工学版),2018,48(1):312-318.
YU Huanan, DU Yao, GUO Shuxu. High-precision synchronous phasor measurement based on compressed sensing［J］. Journal of Jilin University(Engineering and Technology Edition), 2018,48(1):312-318.
［10］贾科,李论,杨哲,等.基于贝叶斯压缩感知理论的配网故障定位研究［J］.中国电机工程学报,2019,39(12):3475-3485.
JIA Ke, LI Lun, YANG Zhe, et al. Research on distribution network fault location based on bayesian compressed sensing theory［J］. Proceedings of the CSEE,2019,39(12):3475-3485.
［11］GAO Pengzhi, WANG Meng, GHIOCEL S G, et al. Missing data recovery by exploiting low-dimensionality in power system synchrophasor measurements［J］. IEEE Transactions on Power Systems, 2016, 31(2): 1006-1013.
［12］ CANDES E J, TAO T. The power of convex relaxation: Near-optimal matrixcompletion［J］. IEEE Transactions on Information Theory, 2010, 56(5): 2053-2080.
［13］王毅,李鼎睿,康重庆.低秩矩阵分解在母线坏数据辨识与修复中的应用［J］.电网技术,2017,41(6):1972-1979.
WANG Yi, LI Dingrui, KANG Chongqing. Application of low-rank matrix factorization in bad data identification and recovering for bus load［J］. Power System Technology, 2017,41(6):1972-1979.
［14］LIU Xiaoxue, ZHU Peidong, ZHANG Yan, et al. A collaborative intrusion detection mechanism against false data injection attack in advanced metering infrastructure［J］. IEEE Transactions on Smart Grid, 2015, 6(5):2435-2443.
［15］GUO Yonghe , TEN Chee-wooi , HU Shiyan , et al. Preventive maintenance for advanced metering infrastructure against malware propagation［J］. IEEE Transactions on Smart Grid, 2016, 7(3): 1314-1328.
［16］FAZEL M. Matrix rank minimization withapplications［D］. Stanford University, 2002.
［17］CAI Jianfeng, CANDS Emmanuel J, SHEN Zuowei. A singular value thresholding algorithm for matrix completion［J］. SIAM Journal on Optimization, 2010, 20(4): 1956-1982.
［18］PARIKH Neal. Proximal algorithms［J］. Foundations and Trends in Optimization, 2014, 1(3):127-239.

[1]	陈昊，乔亚男，刘婧，李扬，杨挺. 考虑模型病态性的智能电表运行误差分析方法[J]. 电力建设, 2020, 41(2): 94-100.
[2]	刘卿，张卫欣，王崇，王季孟，侯昱丞，赵俊杰，杨挺. 隧穿磁阻（TMR）电流传感器失调与噪声消除技术[J]. 电力建设, 2019, 40(11): 8-15.
[3]	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-.
[4]	李莉，朱永利，宋亚奇. 电力设备监测数据的流式计算与动态可视化展示[J]. 电力建设, 2017, 38(5): 91-.

基于曲线相似与低秩矩阵的缺失电量数据补全方法

Missing Load Data Completion Based on Curve Similarity and Low-Rank Matrix

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价