

浏览全部资源
扫码关注微信
天津大学电气自动化与信息工程学院,天津市 300072
Received:24 December 2021,
Revised:2022-03-23,
Published Online:27 May 2022,
Published:25 August 2022
移动端阅览
潘毓笙,秦超.基于两阶段特征选择和格拉姆角场的配电网拓扑辨识方法[J].电力系统自动化,2022,46(16):170-177.
PAN Yusheng,QIN Chao.Identification Method for Distribution Network Topology Based on Two-stage Feature Selection and Gramian Angular Field[J].Automation of Electric Power Systems,2022,46(16):170-177.
潘毓笙,秦超.基于两阶段特征选择和格拉姆角场的配电网拓扑辨识方法[J].电力系统自动化,2022,46(16):170-177. DOI: 10.7500/AEPS20211224003.
PAN Yusheng,QIN Chao.Identification Method for Distribution Network Topology Based on Two-stage Feature Selection and Gramian Angular Field[J].Automation of Electric Power Systems,2022,46(16):170-177. DOI: 10.7500/AEPS20211224003.
分布式能源并网、辐射状与环状拓扑混合运行、量测误差等影响因素使得配电网在线拓扑难以准确获得。为此,文中提出了一种基于两阶段特征选择和格拉姆角场(GAF)的配电网拓扑辨识方法。首先,基于XGBoost和最大信息系数的两阶段特征选择方法筛选出不含冗余拓扑特征信息的重要量测。其次,基于GAF特征变换,将一维的配电网时间断面量测数据变换为二维的GAF,在保留时间断面的节点电压分布规律的同时,有效表征节点电压幅值分布中的拓扑特征信息。最后,设计了一种适用于拓扑辨识的三卷积层神经网络模型,凭借卷积和池化的运算特性以及抗噪性,稳定地提取GAF所蕴含的拓扑特征信息,从而准确建立配电网节点电压幅值分布到拓扑的映射关系。通过IEEE 33节点系统验证了所提方法的有效性,并分析了所提方法对不同噪声水平、数据缺失比例以及其他场景的适应性。
The influencing factors such as the grid connection of distributed energy sources
the mixed operation of radial and toroidal topologies
and the measurement errors make it difficult to accurately obtain the online topology of distribution networks. For this purpose
this paper proposes an identification method for the distribution network topology based on two-stage feature selection and Gramian angle field (GAF). Firstly
the two-stage feature selection method based on XGBoost and maximal information coefficient is used to filter out the important measurement data that do not contain redundant topology feature information. Secondly
the one-dimensional time-section measurement data of the distribution network are transformed into two-dimensional GAF based on GAF feature transformation. While preserving the nodal voltage distribution pattern of the time section
the topological feature information in the nodal voltage magnitude distribution is effectively characterized. Finally
a three-convolutional-layer neural network model for topology identification is designed. With the operation characteristics of convolution and pooling and noise immunity
the topological feature information embedded in GAF is stably extracted. Thus
the mapping relationship from the nodal voltage-amplitude distribution to the topology of the distribution network is accurately established. The effectiveness of the proposed method is verified by the IEEE 33-bus system
and the adaptability of the proposed method to different noise levels
missing data ratios
and other scenarios is analyzed.
王成山 , 王瑞 , 于浩 , 等 . 配电网形态演变下的协调规划问题与挑战 [J]. 中国电机工程学报 , 2020 , 40 ( 8 ): 2385 - 2396 .
WANG Chengshan , WANG Rui , YU Hao , et al . Challenges on coordinated planning of smart distribution networks driven by source-network-load evolution [J]. Proceedings of the CSEE , 2020 , 40 ( 8 ): 2385 - 2396 .
高纯 , 于艾清 , 丁雨 . 基于改进递归有序聚类的有源配电网多时段动态重构 [J]. 电力自动化设备 , 2021 , 41 ( 2 ): 84 - 90 .
GAO Chun , YU Aiqing , DING Yu . Multi-period dynamic reconfiguration of active distribution network based on improved recursive ordered clustering [J]. Electric Power Automation Equipment , 2021 , 41 ( 2 ): 84 - 90 .
郝丽丽 , 王辉 , 王国栋 , 等 . 含分布式电源配电网运行风险的影响因素溯源 [J]. 电力自动化设备 , 2021 , 41 ( 1 ): 27 - 37 .
HAO Lili , WANG Hui , WANG Guodong , et al . Influence factor tracing of operation risk for distribution network with distributed generations [J]. Electric Power Automation Equipment , 2021 , 41 ( 1 ): 27 - 37 .
赵平 , 赵期期 , 艾小猛 . 考虑极限场景的主动配电网重构与无功电压调整联合鲁棒优化 [J]. 电工技术学报 , 2021 , 36 ( 增刊2 ): 496 - 506 .
ZHAO Ping , ZHAO Qiqi , AI Xiaomeng . Network reconfiguration and reactive power voltage regulation coordinated robust optimization for active distribution network considering extreme scenarios [J]. Transactions of China Electrotechnical Society , 2021 , 36 ( Supplement 2 ): 496 - 506 .
LUAN W P , PENG J , MARAS M , et al . Smart meter data analytics for distribution network connectivity verification [J]. IEEE Transactions on Smart Grid , 2015 , 6 ( 4 ): 1964 - 1971 .
JIANG W , CHEN J M , TANG H B , et al . A physical probabilistic network model for distribution network topology recognition using smart meter data [J]. IEEE Transactions on Smart Grid , 2019 , 10 ( 6 ): 6965 - 6973 .
ZHAO J , LI L , XU Z , et al . Full-scale distribution system topology identification using Markov random field [J]. IEEE Transactions on Smart Grid , 2020 , 11 ( 6 ): 4714 - 4726 .
蒋玮 , 汤海波 , 祁晖 , 等 . 基于集成深度神经网络的配电网联络关系辨识技术 [J]. 电力系统自动化 , 2020 , 44 ( 1 ): 101 - 108 .
JIANG Wei , TANG Haibo , QI Hui , et al . Distribution network connectivity recognition based on ensemble deep neural network [J]. Automation of Electric Power Systems , 2020 , 44 ( 1 ): 101 - 108 .
ZHANG J W , WANG Y , WENG Y , et al . Topology identification and line parameter estimation for non-PMU distribution network: a numerical method [J]. IEEE Transactions on Smart Grid , 2020 , 11 ( 5 ): 4440 - 4453 .
杨冬锋 , 付强 , 刘晓军 , 等 . 配电网动态拓扑与线路参数联合在线辨识方法 [J]. 电力系统自动化 , 2022 , 46 ( 2 ): 101 - 108 .
YANG Dongfeng , FU Qiang , LIU Xiaojun , et al . Joint online identification method for dynamic topology and line parameters of distribution network [J]. Automation of Electric Power Systems , 2022 , 46 ( 2 ): 101 - 108 .
KARIMI H S , NATARAJAN B . Joint topology identification and state estimation in unobservable distribution grids [J]. IEEE Transactions on Smart Grid , 2021 , 12 ( 6 ): 5299 - 5309 .
任鹏哲 , 刘友波 , 刘挺坚 , 等 . 基于互信息贝叶斯网络的配电网拓扑鲁棒辨识算法 [J]. 电力系统自动化 , 2021 , 45 ( 9 ): 55 - 62 .
REN Pengzhe , LIU Youbo , LIU Tingjian , et al . Robust identification algorithm for distribution network topology based on mutual-information Bayesian network [J]. Automation of Electric Power Systems , 2021 , 45 ( 9 ): 55 - 62 .
ZHAO L , LIU Y B , ZHAO J B , et al . Robust PCA-deep belief network surrogate model for distribution system topology identification with DERs [J]. International Journal of Electrical Power & Energy Systems , 2021 , 125 : 106441 .
CHEN T H , HUANG W T , GU J C , et al . Feasibility study of upgrading primary feeders from radial and open-loop to normally closed-loop arrangement [J]. IEEE Transactions on Power Systems , 2004 , 19 ( 3 ): 1308 - 1316 .
LIAO Y Z , WENG Y , LIU G Y , et al . Urban MV and LV distribution grid topology estimation via group lasso [J]. IEEE Transactions on Power Systems , 2019 , 34 ( 1 ): 12 - 27 .
裴宇婷 , 秦超 , 余贻鑫 . 基于LightGBM和DNN的智能配电网在线拓扑辨识 [J]. 天津大学学报(自然科学与工程技术版) , 2020 , 53 ( 9 ): 939 - 950 .
PEI Yuting , QIN Chao , YU Yixin . Online topology identification for smart distribution grids based on LightGBM and deep neural networks [J]. Journal of Tianjin University (Science and Technology) , 2020 , 53 ( 9 ): 939 - 950 .
GOTTI D , AMARIS H , LARREA P L . A deep neural network approach for online topology identification in state estimation [J]. IEEE Transactions on Power Systems , 2021 , 36 ( 6 ): 5824 - 5833 .
肖浩 , 裴玮 , 邓卫 , 等 . 分布式电源对配电网电压的影响分析及其优化控制策略 [J]. 电工技术学报 , 2016 , 31 ( 增刊1 ): 203 - 213 .
XIAO Hao , PEI Wei , DENG Wei , et al . Analysis of the impact of distributed generation on distribution network voltage and its optimal control strategy [J]. Transactions of China Electrotechnical Society , 2016 , 31 ( Supplement 1 ): 203 - 213 .
许栋梁 , 赵健 , 王小宇 , 等 . 基于有向邻接矩阵的配电网拓扑检测与识别 [J]. 电力系统保护与控制 , 2021 , 49 ( 16 ): 76 - 85 .
XU Dongliang , ZHAO Jian , WANG Xiaoyu , et al . Distribution network topology detection and identification based on a directed adjacency matrix [J]. Power System Protection and Control , 2021 , 49 ( 16 ): 76 - 85 .
刘健 , 孙泉 , 张小庆 , 等 . 配电网合环分析与合环条件判断 [J]. 电力系统自动化 , 2014 , 38 ( 11 ): 130 - 135 .
LIU Jian , SUN Quan , ZHANG Xiaoqing , et al . Analysis on and criteria for loop closing operation for distribution grids [J]. Automation of Electric Power Systems , 2014 , 38 ( 11 ): 130 - 135 .
Synchrophasor for power systems measurements : IEC/IEEE 60255-118: 2018 [S]. IEEE , 2018 .
ZHANG S , HAO Y S , WANG M , et al . Multichannel Hankel matrix completion through nonconvex optimization [J]. IEEE Journal of Selected Topics in Signal Processing , 2018 , 12 ( 4 ): 617 - 632 .
CHEN T Q , GUESTRIN C . XGBoost: a scalable tree boosting system [C]// KDD'16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , August 13-17 , 2016 , San Francisco, USA : 785 - 794 .
RESHEF D N , RESHEF Y A , FINUCANE H K , et al . Detecting novel associations in large data sets [J]. Science , 2011 , 334 ( 6062 ): 1518 - 1524 .
WANG Z G , OATES T . Imaging time-series to improve classification and imputation [EB/OL]. [ 2021-12-24 ]. https://arxiv.org/abs/1506.00327 https://arxiv.org/abs/1506.00327 .
GOODFELLOW I , BENGIO Y , COURVILLE A . Deep learning [M]. Cambridge, USA : MIT press , 2016 .
GU J X , WANG Z H , KUEN J , et al . Recent advances in convolutional neural networks [J]. Pattern Recognition , 2018 , 77 : 354 - 377 .
BARAN M E , WU F F . Network reconfiguration in distribution systems for loss reduction and load balancing [J]. IEEE Transactions on Power Delivery , 1989 , 4 ( 2 ): 1401 - 1407 .
DOROSTKAR-GHAMSARI M R , FOTUHI-FIRUZABAD M , LEHTONEN M , et al . Value of distribution network reconfiguration in presence of renewable energy resources [J]. IEEE Transactions on Power Systems , 2016 , 31 ( 3 ): 1879 - 1888 .
ZIMMERMAN R D , MURILLO-SÁNCHEZ C E , THOMAS R J . MATPOWER: steady-state operations, planning, and analysis tools for power systems research and education [J]. IEEE Transactions on Power Systems , 2011 , 26 ( 1 ): 12 - 19 .
WENG Y , LIAO Y Z , RAJAGOPAL R . Distributed energy resources topology identification via graphical modeling [J]. IEEE Transactions on Power Systems , 2017 , 32 ( 4 ): 2682 - 2694 .
WU T , ZHANG Y J A , LIU Y , et al . Missing data recovery in large power systems using network embedding [J]. IEEE Transactions on Smart Grid , 2021 , 12 ( 1 ): 680 - 691 .
TROYANSKAYA O , CANTOR M , SHERLOCK G , et al . Missing value estimation methods for DNA microarrays [J]. Bioinformatics , 2001 , 17 ( 6 ): 520 - 525 .
GISBRECHT A , SCHULZ A , HAMMER B . Parametric nonlinear dimensionality reduction using kernel t -SNE [J]. Neurocomputing , 2015 , 147 : 71 - 82 .
0
Views
0
下载量
11
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621