Distribution Network Connectivity Recognition Based on Ensemble Deep Neural Network

Wei JIANG; Haibo TANG; Haoyuan CHEN; Jinming CHEN; Hao JIAO; Hui QI

doi:10.7500/AEPS20190411010

您当前的位置：

首页 >

文章列表页 >

Distribution Network Connectivity Recognition Based on Ensemble Deep Neural Network

Basic Research | 更新时间：2020-07-14

- Distribution Network Connectivity Recognition Based on Ensemble Deep Neural Network
- Automation of Electric Power Systems Vol. 44, Issue 1, Pages: 101-108(2020)
- 作者机构：
  
  1. 东南大学电气工程学院，江苏省南京市 210096
  2. 国网江苏省电力有限公司泰州供电分公司，江苏省泰州市 225300
  3. 国网江苏省电力有限公司电力科学研究院,江苏省南京市 211103
- 作者简介：
- 基金信息：
  
  State Grid Jiangsu Electric Power Co., Ltd.(J2018088)
- DOI：10.7500/AEPS20190411010
  CLC：
- Received：11 April 2019，
  
  Revised：2019-07-11，
  
  Published Online：21 August 2019，
  
  Published：10 January 2020
- 稿件说明：
移动端阅览
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(01):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(01):101-108.
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(01):101-108. DOI： 10.7500/AEPS20190411010.

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(01):101-108. DOI： 10.7500/AEPS20190411010.

摘要

随着城市配电网络规模不断扩大，配电网实时拓扑难以获取已成为观测其运行状态的主要瓶颈。为了解决传统拓扑辨识方法噪声敏感性高、在线运行难等问题，提出了一套基于集成深度神经网络的配电变压器（简称配变）联络关系辨识方案。首先，依据配电网测量的横纵连续性，对历史数据进行二维小波阈值去噪，降低噪声对辨识结果的影响。为提高深度学习算法的精度上限，采用搜索、生成与评价的策略对数据进行特征提取与选择。然后，以选择的特征为输入，构造交叉熵深度神经网络，通过网格搜索优化深度神经网络的超参数。采用集成学习的策略训练同质深度神经网络，保证模型的在线拓扑辨识能力。最后，通过在TensorFlow上进行的实验验证了提出的集成深度神经网络模型在配变联络关系辨识中的精确度与鲁棒性。

Abstract

With the development of the urban distribution network

the difficulty in obtaining the real-time distribution network topology has become an important bottleneck for observing its operational status. To tackle high noise sensitivity and difficult online operation in traditional topology recognition methods

this paper proposes a distribution transformers (DTs) connectivity recognition method based on ensemble deep neural network. Firstly

based on the horizontal and vertical continuity of distribution network measurements

the two-dimension wavelet threshold de-noising method is implemented on historical measurements to reduce the impact of noise on the recognition results. To improve the upper limit of deep learning algorithm

this work proposes the search

generation and evaluation strategy for feature extraction and feature selection. Secondly

we use the extracted features as inputs for the deep neural network with cross-entropy function. The grid search algorithm is used to optimize the hyperparameters of deep neural network. An ensemble learning strategy is utilized to train homogeneous deep neural networks to ensure the ability of online topology recognition. Finally

the experiments implemented on TensorFlow certificate the accuracy and robustness of proposed ensemble deep neural network models in distribution transformers connectivity recognition.

关键词

Keywords

references

张旭，王洪涛 . 高比例可再生能源电力系统的输配协同优化调度方法 [J]. 电力系统自动化 , 2019 , 43 ( 3 ): 89 - 105 . DOI: 10.7500/AEPS20180122003 http://dx.doi.org/10.7500/AEPS20180122003 .

ZHANG Xu , WANG Hongtao . Optimal dispatch method of transmission and distribution coordination for power systems with high proportion of renewable energy [J]. Automation of Electric Power Systems , 2019 , 43 ( 3 ): 89 - 105 . DOI: 10.7500/AEPS 20180122003 http://dx.doi.org/10.7500/AEPS 20180122003 .

康重庆 , 姚良忠 . 高比例可再生能源电力系统的关键科学问题与理论研究框架 [J]. 电力系统自动化 , 2017 , 41 ( 9 ): 2 - 11 .

KANG Chongqing , YAO Liangzhong . Key scientific issues and theoretical research framework for power systems with high proportion of renewable energy [J]. Automation of Electric Power Systems , 2017 , 41 ( 9 ): 2 - 11 .

YUAN Y , DEHGHANPOUR K , BU F , et al . A multi-timescale data-driven approach to enhance distribution system observability [J]. IEEE Transactions on Power Systems , 2019 , 34 （ 4 ）： 3168 - 3177 .

LIU Y , LI J , WU L . Coordinated optimal network reconfiguration and voltage regulator/DER control for unbalanced distribution systems [J]. IEEE Transactions on Smart Grid , 2018 , 10 ( 3 ): 2912 - 2922 .

GOLSHANNAVAZ S , AFSHARNIA S , AMINIFAR F . Smart distribution grid: optimal day-ahead scheduling with reconfigurable topology [J]. IEEE Transactions on Smart Grid , 2014 , 5 ( 5 ): 2402 - 2411 .

李碧君 . 电力系统状态估计问题的研究现状和展望 [J]. 电力系统自动化 , 1998 , 22 ( 11 ): 53 - 60 .

LI Bijun, Status quo and prospect of power system state estimation [J]. Automation of Electric Power Systems , 1998 , 22 ( 11 ): 53 - 60 .

PEPPANEN J , RENO M J , THAKKAR M , et al . Leveraging AMI data for distribution system model calibration and situational awareness [J]. IEEE Transactions on Smart Grid , 2015 , 6 ( 4 ): 2050 - 2059 .

JABR R A . Minimum loss operation of distribution networks with photovoltaic generation [J]. IET Renewable Power Generation , 2014 , 8 ( 1 ): 33 - 44 .

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 .

XUE Yusheng , LAI Yening . Integration of macro energy thinking and big data thinking： part one applications and explorations [J]. Automation of Electric Power Systems , 2016 ， 40 ( 1 ): 1 - 8 .

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 .

XUE Yusheng , LAI Yening . Integration of macro energy thinking and big data thinking: part two applications and explorations [J]. Automation of Electric Power Systems , 2016 , 40 ( 1 ): 1 - 13 .

YIZHENG L , YANG W , GUANGYI L , et al . Urban MV and LV distribution grid topology estimation via group lasso [J]. IEEE Transactions on Power Systems , 2018 , 34 ( 1 ): 12 - 27 .

RENO M J , BRODERICK R J , GRIJALVA S . Distribution system model calibration with big data from AMI and PV inverters [J]. IEEE Transactions on Smart Grid , 2016 , 7 ( 5 ): 2497 - 2506 .

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测量缺失数据重建方法 [J]. 中国电机工程学报 , 2019 , 39 ( 1 ): 58 - 66 .

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 ): 58 - 66 .

DEKA D , CHERTKOV M , BACKHAUS S . Structure learning in power distribution networks [J]. IEEE Transactions on Control of Network Systems , 2017 , 5 ( 3 ): 1061 - 1074 .

PEDREGOSA F , GRAMFORT A , MICHEL V , et al . Scikit-learn: machine learning in Python [J]. Journal of Machine Learning Research , 2013 , 12 ( 10 ): 2825 - 2830 .

蒋玮 , 黄丽丽 , 祁晖 , 等 . 基于分布式图计算的台区负荷预测技术研究 [J]. 中国电机工程学报 , 2018 , 38 ( 12 ): 3419 - 3430 .

JIANG Wei , HUANG Lili , QI Hui , et al . Research on load forecasting technology of transformer areas based on distributed graph computing [J]. Proceedings of the CSEE , 2018 , 38 ( 12 ): 3419 - 3430 .

刘羽霄 , 张宁 , 康重庆 . 数据驱动的电力网络分析与优化研究综述 [J]. 电力系统自动化 , 2018 , 42 ( 6 ): 157 - 167 . DOI： 10.7500/AEPS20170922003 http://dx.doi.org/10.7500/AEPS20170922003 .

LIU Yuxiao , ZHANG Ning , KANG Chongqing . A review on data-driven analysis and optimization of power grid [J]. Automation of Electric Power Systems , 2018 , 42 ( 6 ): 157 - 167 . DOI： 10.7500/AEPS20170922003 http://dx.doi.org/10.7500/AEPS20170922003 .

LUAN W , 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 .

CAVRARO G , KEKATOS V , VEERAMACHANENI S . Voltage analytics for power distribution network topology verification [J]. IEEE Transactions on Smart Grid , 2019 , 10 ( 1 ): 1058 - 1067 .

YU J , WENG Y , RAJAGOPAL R . PAToPA: a data-driven parameter and topology joint estimation framework in distribution grids [J]. IEEE Transactions on Power Systems , 2017 , 33 ( 4 ): 4335 - 4347 .

YU J , WENG Y , RAJAGOPAL R . PAToPAEM: a data-driven parameter and topology joint estimation framework for time varying system in distribution grids [J]. IEEE Transactions on Power Systems , 2018 , 34 ( 3 ): 1682 - 1692 .

WENG Y , LIAO Y , RAJAGOPAL R . Distributed energy resources topology identification via graphical modeling [J]. IEEE Transactions on Power Systems , 2017 , 32 ( 4 ): 2682 - 2694 .

PAPPU S J , BHATT N , PASUMARTHY R , et al . Identifying topology of low voltage (LV) distribution networks based on smart meter data [J]. IEEE Transactions on Smart Grid , 2018 , 9 ( 5 ): 5113 - 5122 .

LIU Y , LIU S , WANG Y , et al . A stochastic computational multi-layer perceptron with backward propagation [J]. IEEE Transactions on Computers , 2018 , 67 ( 9 ): 1273 - 1286 .

MASSIMILIANO L , MAURIZIO P , ANTONELLO R , et al . A novel neural networks ensemble approach for modeling electrochemical cells [J]. IEEE Transactions on Neural Networks and Learning Systems , 2019 ， 30 ( 2 ): 343 - 354 .

WEI X , WEN B , YANG D , et al . Fault line detection method based on the improved SVD de-noising and ideal clustering curve for distribution networks [J]. IET Science Measurement & Technology , 2018 , 12 ( 2 ): 262 - 270 .

童述林 , 文福拴 , 陈亮 . 电力负荷数据预处理的二维小波阈值去噪方法 [J]. 电力系统自动化 , 2012 , 36 ( 2 ): 101 - 105 .

TONG Shulin , WEN Fushuan , CHEN Liang . A two-dimension wavelet threshold de-noising method for electric load data pre-processing [J]. Automation of Electric Power Systems , 2012 , 36 ( 2 ): 1 01 - 105 .

BOCCALETTI S , BIANCONI G , CRIADO R , et al . The structure and dynamics of multilayer networks [J]. Physics Reports , 2014 , 544 ( 1 ): 1 - 122 .

TANG J , DENG C , HUANG G B . Extreme learning machine for multilayer perceptron [J]. IEEE Transactions on Neural Networks and Learning Systems , 2015 , 27 ( 4 ): 809 - 821 .

XIANG W , TRAN H D , JOHNSON T T . Output reachable set estimation and verification for multi-layer neural networks [J]. 2017 , 29 ( 11 ): 5777 - 5783 .

BARAN M E , WU F F , BIANCONI G , et al . The structure and dynamics of multilayer networks [J]. Physics Reports , 2014 , 544 ( 1 ): 1 - 122 .

ALAM S M S , NATARAJAN B , PAHWA A . Distribution grid state estimation from compressed measurements [J]. IEEE Transactions on Smart Grid , 2014 , 5 ( 4 ): 1631 - 1642 .

STEPHANIE S , JULIENVERGONJANNE A , CANCES J P . Soft decision LDPC decoding over chi-square based optical channels [J]. Journal of Lightwave Technology , 2011 , 27 ( 16 ): 3540 - 3545 .

WEBB G I , ZHENG Z . Multistrategy ensemble learning: reducing error by combining ensemble learning techniques [J]. IEEE Transactions on Knowledge and Data Engineering , 2004 , 16 ( 8 ): 980 - 991 .

LI H , CUI Y Y , LIU Y L , et al . Ensemble learning for overall power conversion efficiency of the all-organic dye-sensitized solar cells [J]. IEEE Access , 2018 , 6 : 34118-34126 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

Yugang SU

Jian YANG

Xin DAI

Jiaming LIU

Xinyu HOU

Related Institution

College of Automation, Chongqing University

China National Center for International Research on Wireless Power Transfer Technology

⁰