王晓虎

• 1:上海电机学院电气学院

摘要(Abstract)：

完整准确的运行数据是充分利用智能电网大数据的基础。针对当前配电网由于传感器不稳定等问题造成数据缺失问题，研究了一种基于张量分解理论的10 kV配电网电压数据修复方法。该方法首先提出了利用线路拓扑结构、时序数据和相似日数据构建时空张量的策略，充分挖掘现有数据中的内在关系，针对张量缺失使用规则化均值的方法进行初始化，利用贝叶斯CP分解张量并恢复缺失数据，以完成数据修复的目的，进而提高配电网电压数据的质量。算例结果表明：所提方法可以有效修复缺失数据，数据误差在0.5%以下。

关键词(KeyWords)： 数据修复;规则化均值;时空张量;智能电网大数据

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 王晓虎

DOI: 10.19635/j.cnki.csu-epsa.000924

参考文献(References)：

• [1]费思源(Fei Siyuan).大数据技术在配电网中的应用综述(Overview of application of big data technology in power distribution system)[J].中国电机工程学报(Proceedings of the CSEE),2018,38(1):85-96.
• [2]秦丽文，梁朔，高立克，等(Qin Liwen,Liang Shuo,Gao Like,et al).全面数据质量管理框架在配电网领域的应用分析(Application analysis of comprehensive data quality management framework in distribution network)[J].电力系统及其自动化学报(Proceedings of the CSU-EP-SA),2020,32(4):62-68.
• [3]赵俊华，董朝阳，文福拴，等(Zhao Junhua,Dong Zhaoyang,Wen Fushuan,et al).面向能源系统的数据科学：理论、技术与展望(Data science for energy systems:theory,techniques and prospect)[J].电力系统自动化(Automation of Electric Power Systems),2017,41(4):1-11,19.
• [4]叶锋，何桦，顾全，等(Ye Feng,He Hua,Gu Quan,et al).EMS中负荷预测不良数据的辨识与修正(Bad data identification and correction for load forecasting in energy management system)[J].电力系统自动化(Automation of Electric Power Systems),2006,30(15):85-88.
• [5]杨学良，陶晓峰，黄福兴，等.基于随机森林及时间序列模型的电能量异常数据检测及修复方法[C]//.中国电力科学研究院有限公司、国网电投(北京)科技中心、《电信科学》杂志社第三届智能电网会议.北京，2018.
• [6]张国江，邱家驹，李继红(Zhang Guojiang,Qiu Jiaju,Li Jihong).基于人工神经网络的电力负荷坏数据辨识与调整(Outlier identification and justification based on neural network)[J].中国电机工程学报(Proceedings of the CSEE),2001,21(8):104-107,113.
• [7]张晓星，程其云，周湶，等(Zhang Xiaoxing,Cheng Qiyun,Zhou Quan,et al).基于数据挖掘的电力负荷脏数据动态智能清洗(Dynamic intelligent cleaning for dirty electric load data based on data mining)[J].电力系统自动化(Automation of Electric Power Systems),2005,29(8):60-64.
• [8]皇甫汉聪(Huangpu Hancong).基于次序依赖的电力数据缺失自动修复方法研究(Research on automatic repair method of power data missing based on order dependence)[J].自动化与仪器仪表(Automation&Instrumentation),2020(12):233-236.
• [9]Qu Li,Zhang Yi,Hu Jianming,et al.A BPCA based missing value imputing method for traffic flow volume data[C]//IEEE Intelligent Vehicles Symposium.Eindhoven,Netherlands,2008:985s,gent
• [10]Qu Li,Li Li,Zhang Yi,et al.PPCA-based missing data imputation for traffic flow volume:A systematical approach[J].IEEE Trans on Intelligent Transportation Systems,2009,10(3):512-522.
• [11]梁寿愚，方文崇，王瑾，等(Liang Shouyu,Fang Wenchong,Wang Jin,et al).基于图规则化低秩矩阵恢复的用电数据修复与异常检测(Refinement and anomaly detection for power consumption data based on recovery of graph regularized low-rank matrix)[J].电力系统自动化(Automation of Electric Power Systems),2019,43(21):221-228.
• [12]Kolda T G,Bader B W.Tensor decompositions and applications[J].SIAM Review,2009,51(3):455-500.
• [13]王孝慈，董树锋，刘育权，等(Wang Xiaoci,Dong Shufeng,Liu Yuquan,et al).基于改进式k-prototypes聚类的坏数据辨识与修正(Industrial load data identification and correction method with improved k-prototypes clustering algorithm)[J].电测与仪表(Electrical Measurement&Instrumentation),2021，网络首发.
• [14]史加荣，张安银(Shi Jiarong,Zhang Anyin).概率张量分解综述(Review on probabilistic tensor decompositions)[J].陕西理工大学学报(自然科学版)(Journal of Shaanxi University of Technology(Natural Science Edution)),2018,34(4):70-79.
• [15]Zhao Qibin,Zhang Liqing,Cichocki Andrzej.Bayesian CPfactorization of incomplete tensors with automatic rank determination[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2015,37(9):1751-1763.
• [16]张安银(Zhang Anying).概率张量分解及应用(Probabilistic Tensor Decomposition and Its Applications)[D].西安：西安建筑科技大学(Xi’an:Xi’an University of Architecture and Technology),2018.--------