李海英,裴康鑫

• 1:上海理工大学机械工程学院

摘要(Abstract)：

针对电力系统量测数据不完整导致状态估计失效进而危害智能电网安全经济运行的问题，本文提出一种融合量测重构的残差生成对抗网络-无迹卡尔曼滤波状态估计方法，以进行电力系统状态估计。首先，分析模型重构量测的基本工作原理，以重构不完整量测数据；然后，结合Holt’s双参数平滑法与无迹卡尔曼滤波方法，构造了融合重构量测的动态估计方法；最后，在IEEE 30节点系统进行仿真，验证了所提方法的可行性和有效性。

关键词(KeyWords)： 智能电网;量测重构;状态估计;Holt's双参数平滑法;无迹卡尔曼滤波

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金资助项目（51777126）;; 山西省重点研发计划高新领域重点项目（202003011008）

作者(Author): 李海英,裴康鑫

DOI: 10.19635/j.cnki.csu-epsa.000863

参考文献(References)：

• [1]郑文迪，聂建雄，邵振国，等(Zheng Wendi,Nie Jianxiong,Shao Zhengguo,et al).智能配电网状态估计研究现状和展望(Status quo and prospect of researches on state estimation for smart distribution network)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2021,33(4):8-16.
• [2]赵俊华，梁高琪，文福拴，等(Zhao Junhua,Liang Gaoqi,Wen Fushuan,et al).乌克兰事件的启示：防范针对电网的虚假数据注入攻击(Lessons learnt from Ukrainian blackout:protecting power grids against false data injection attacks)[J].电力系统自动化(Automation of Electric Power Systems),2016,40(7):149-151.
• [3]刘鑫蕊，吴泽群(Liu Xinrui,Wu Zequn).面向智能电网的空间隐蔽型恶性数据注入攻击在线防御研究(Online defense research of spatial-hidden malicious data injection attacks in smart grid)[J].中国电机工程学报(Proceedings of the CSEE),2020,40(8):2546-2559.
• [4]Wang Xinan,Shi Di,Wang Jianhui,et al.Online identification and data recovery for PMU data manipulation attack[J].IEEE Trans on Smart Grid,2019,10(6):5889-5898.
• [5]Wu Tong,Zhang Ying-Jun A,Liu Yang,et al.Missing data recovery in large power systems using network embedding[J].IEEE Trans on Smart Grid,2021,12(1):680-691.
• [6]王守相，陈海文，潘志新，等(Wang Shouxiang,Chen Haiwen,Pan Zhixin,et al).采用改进生成式对抗网络的电力系统量测缺失数据重构方法(A reconstruction method for missing data in power system measurement using an improved generative adversarial network)[J].中国电机工程学报(Proceedings of the CSEE),2019,39(1):56-64.
• [7]Mahmud M,Kaiser M S,Hussain A,et al.Applications of deep learning and reinforcement learning to biological data[J].IEEE Trans on Neural Networks and Learning Systems,2018,29(6):2063-2079.
• [8]Miranda V,Krstulovic J,Keko H,et al.Reconstructing missing data in state estimation with autoencoders[J].IEEE Trans on Power Systems,2012,27(2):604-611.
• [9]Khare G,Singh S N,Mohapatra A,et al.Prediction of missing PMU measurement using artificial neural network[C]//National Power Systems Conference.Bhubaneswar,India,2016.
• [10]辜超，白德盟，王晶，等(Gu Chao,Bai Demeng,Wang Jing,et al).LSTM在输变电设备缺失值填补中的应用(Application of LSTM in filling missing value of power transmission and transformation equipment)[J].电测与仪表(Electrical Measurement&Instrumentation),2019,56(5):63-69.
• [11]Lin You,Wang Jianhui,Cui Mingjian.Reconstruction of power system measurements based on enhanced denoising autoencoder[C]//IEEE Power and Energy Society General Meeting.Atlanta,USA,2019.
• [12]杨玉莲，齐林海，王红，等(Yang Yulian,Qi Linhai,Wang Hong,et al).基于生成对抗和双重语义感知的配电网量测数据缺失重构(Reconstruction of missing measurement data in distribution network based on generative adversarial network and double semantic perception)[J].电力系统自动化(Automation of Electric Power Systems),2020,44(18):46-56.
• [13]陈碧云，李弘斌，李滨(Chen Biyun,Li Hongbin,Li Bin).伪量测建模与AUKF在配电网虚假数据注入攻击辨识中的应用(Application research on pseudo measurement modeling and AUKF in FDIAs identification of distribution network)[J].电网技术(Power System Technology),2019,43(9):3226-3236.
• [14]李雪，李雯婷，杜大军，等(Li Xue,Li Wenting,Du Dajun,et al).拒绝服务攻击下基于UKF的智能电网动态状态估计研究(Dynamic state estimation of smart grid based on UKF under denial of service attacks)[J].自动化学报(Acta Automatica Sinica),2019,45(1):120-131.
• [15]Dini D H,Mandic D P,Julier S J.A widely linear complex unscented Kalman filter[J].IEEE Signal Processing Letters,2011,18(11):623-626.
• [16]Muhammad Umer R,Luca Foresti G,Micheloni C.Deep generative adversarial residual convolutional networks for real-world super-resolution[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.Seattle,USA,2020:1769-1777.
• [17]Ran M,Hu Jinrong,Chen Yang,et al.Denoising of 3Dmagnetic resonance images using a residual encoder decoder Wasserstein generative adversarial network[C]//Medical Image Analysis,2019,55:165-180.
• [18]Qian Sheng,Liu Hua,Liu Cheng,et al.Adaptive activation functions in convolutional neural networks[J].Neurocomputing,2018,272:204-212.
• [19]Chen Yize,Wang Yishen,Kirschen D,et al.Model-free renewable scenario generation using generative adversarial networks[J].IEEE Trans on Power Systems,2018,33(3):3265-3275.
• [20]Li Sen,Hu You,Zheng Lini,et al.Stochastic event-triggered cubature Kalman filter for power system dynamic state estimation[J].IEEE Trans on Circuits and Systems II:Express Briefs,2019,66(9):1552-1556.
• [21]Netto M,Mili L.A robust data-driven Koopman Kalman filter for power systems dynamic state estimation[J].IEEETrans on Power Systems,2018,33(6):7228-7237.
• [22]王玉彬，夏明超，李鹏，等(Wang Yubin,Xia Mingchao,Li Peng,et al).基于改进鲁棒自适应UKF的配电网动态状态估计方法(Dynamic state estimation method of distribution network based on improved robust adaptive unscented Kalman filter)[J].电力系统自动化(Automation of Electric Power Systems),2020,44(1):92-100.
• [23]Valverde G,Terzija V.Unscented Kalman filter for power system dynamic state estimation[J].IET Generation,Transmission&Distribution,2011,5(1):29-37.
• [24]Qi Junjian,Sun Kai,Wang Jianhui,et al.Dynamic state estimation for multi-machine power system by unscented Kalman filter with enhanced numerical stability[J].IEEETrans on Smart Grid,2018,9(2):1184-1196.
• [25]王依宁，解大，王西田，等(Wang Yining,Xie Da,Wang Xitian,et al).基于PCA-LSTM模型的风电机网相互作用预测(Prediction of interaction between grid and wind farms based on PCA-LSTM model)[J].中国电机工程学报(Proceedings of the CSEE),2019,39(14):4070-4081.
• [26]Ho C H,Wu H C,Chan S C,et al.A robust statistical approach to distributed power system state estimation with bad data[J].IEEE Trans on Smart Grid,2020,11(1):517-527.
• [27]曲正伟，董一兵，王云静，等(Qu Zhengwei,Dong Yibing,Wang Yunjing,et al).用于电力系统动态状态估计的改进鲁棒无迹卡尔曼滤波算法(Improved robust unscented Kalman filtering algorithm for dynamic state estimation of power systems)[J].电力系统自动化(Automation of Electric Power Systems),2018,42(10):87-92.
• [28]Massignan J A D,London J B A,Maciel C D,et al.PMUs and SCADA measurements in power system state estimation through Bayesian inference[C]//IEEE Milan Power Tech.Milan,Italy,2019.