

浏览全部资源
扫码关注微信
1.强电磁工程与新技术国家重点实验室(华中科技大学),湖北省武汉市 430074
2.电力安全与高效湖北省重点实验室(华中科技大学电气与电子工程学院),湖北省武汉市 430074
3.国网河南省电力公司电力科学研究院,河南省郑州市 450052
Received:29 June 2021,
Revised:2021-09-18,
Published Online:01 November 2021,
Published:10 January 2022
移动端阅览
殷浩然,苗世洪,韩佶等.基于三维卷积神经网络的配电物联网异常辨识方法[J].电力系统自动化,2022,46(1):42-50.
YIN Haoran,MIAO Shihong,HAN Ji,et al.Anomaly Identification Method for Distribution Internet of Things Based on Three-dimensional Convolutional Neural Network[J].Automation of Electric Power Systems,2022,46(1):42-50.
殷浩然,苗世洪,韩佶等.基于三维卷积神经网络的配电物联网异常辨识方法[J].电力系统自动化,2022,46(1):42-50. DOI: 10.7500/AEPS20210629004.
YIN Haoran,MIAO Shihong,HAN Ji,et al.Anomaly Identification Method for Distribution Internet of Things Based on Three-dimensional Convolutional Neural Network[J].Automation of Electric Power Systems,2022,46(1):42-50. DOI: 10.7500/AEPS20210629004.
由于配电物联网中电力网与通信网高度耦合,单一网络的异常状态会交互作用至另一网络,可能进一步造成异常范围扩大,而单独采用电力网或通信网的异动信息难以全面、准确地辨识配电物联网异动源的类型和位置。因此,提出一种基于三维卷积神经网络(3D-CNN)的配电物联网异常类型辨识及定位方法。首先,分析了配电物联网通信流量特征并构建了基于Simulink和OPNET的配电物联网交互仿真模型;其次,提出了一种面向3D-CNN的样本构建方法,将配电物联网中每个节点的电气量和通信流量信息组成一个特征子像素,进而将配电物联网每个时刻的状态表示为一幅特征帧画面,形成隐含配电物联网异动过程的立方样本矩阵;随后,构建了包含三维特征提取网络和层级softmax分类器的深度学习模型,通过提取和辨识立方样本矩阵中隐含的异常信息,可以同时实现配电物联网异常类型和位置的判定;最后,利用IEEE 33节点配电物联网异常数据对模型进行测试,结果表明,所提方法可以对电力网短路故障、通信中断故障、通信数据异常引起的保护误动和拒动进行精确的分类及定位。
The power grid and communication network are highly coupled in the distribution Internet of Things (DIoT). The anomalies of a single network interact with another network
which may lead to the expansion of anomaly range. However
it is difficult to comprehensively and accurately identify the types and locations of the anomaly source in the DIoT by using the information of the power grid or the communication network alone. Therefore
this paper proposes an anomaly type identification and location method for DIoT based on the three-dimensional convolutional neural network (3D-CNN). Firstly
the communication flow characteristics of DIoT are analyzed and an interactive simulation model of DIoT based on Simulink and OPNET is built. Secondly
a 3D-CNN oriented sample construction method is proposed
in which the electric parameters and communication flow information of each node in DIoT are composed into a feature sub-pixel
and the state of DIoT at each moment is represented as a feature frame
thus forming a cubic sample matrix that contains the anomaly process of DIoT. Thirdly
a deep learning model is built
which includes the three-dimensional feature extraction network and the hierarchical softmax classifier. By extracting and identifying the abnormal information hidden in the cubic sample matrix
the type and location of anomalies in DIoT could be determined simultaneously. Finally
the model is tested by using abnormal data of the IEEE 33-node DIoT. The results show that the proposed method can precisely classify and locate the short-circuit fault
communication interruption fault
and protection maloperation and rejection caused by abnormal communication data.
秦博雅 , 刘东 . 电网信息物理系统分析与控制的研究进展与展望 [J]. 中国电机工程学报 , 2020 , 40 ( 18 ): 5816 - 5827 .
QIN Boya , LIU Dong . Research progresses and prospects on analysis and control of cyber-physical system for power grid [J]. Proceedings of the CSEE , 2020 , 40 ( 18 ): 5816 - 5827 .
赵江河 , 王立岩 . 智能配电网的信息架构 [J]. 电网技术 , 2009 , 33 ( 15 ): 26 - 29 .
ZHAO Jianghe , WANG Liyan . Information structure of smart distribution network [J]. Power System Technology , 2009 , 33 ( 15 ): 26 - 29 .
张志丹 , 黄小庆 , 曹一家 , 等 . 基于虚拟局域网的变电站综合数据流分析与通信网络仿真 [J]. 电网技术 , 2011 , 35 ( 5 ): 204 - 209 .
ZHANG Zhidan , HUANG Xiaoqing , CAO Yijia , et al . Comprehensive data flow analysis and communication network simulation for virtual local area network-based substation [J]. Power System Technology , 2011 , 35 ( 5 ): 204 - 209 .
高洪建 . 配电通信网业务自相似特性研究 [D]. 昆明 : 云南大学 , 2014 .
GAO Hongjian . Research on self-similarity characteristics of distribution communication network service [D]. Kunming : Yunnan University , 2014 .
孙毅 , 李世豪 , 李彬 , 等 . 基于IEC 61850的智能配电通信网络仿真平台设计 [J]. 电力建设 , 2016 , 37 ( 2 ): 118 - 124 .
SUN Yi , LI Shihao , LI Bin , et al . Communication network simulation platform design of intelligent power distribution based on IEC 61850 [J]. Electric Power Construction , 2016 , 37 ( 2 ): 118 - 124 .
YANG T , ZHAO R , ZHANG W X , et al . On the modeling and analysis of communication traffic in intelligent electric power substations [J]. IEEE Transactions on Power Delivery , 2017 , 32 ( 3 ): 1329 - 1338 .
章坚民 , 张嘉誉 , 倪明 , 等 . 智能变电站通信网络的广义信源和流量计算模型 [J]. 电力系统自动化 , 2019 , 43 ( 13 ): 147 - 155 .
ZHANG Jianmin , ZHANG Jiayu , NI Ming , et al . Generic message source and flow calculation model for communication network in smart substation [J]. Automation of Electric Power Systems , 2019 , 43 ( 13 ): 147 - 155 .
ZHOU X , YANG Z , NI M , et al . Analysis of the impact of combined information-physical-failure on distribution network CPS [J]. IEEE Access , 2020 , 8 : 44140 - 44152 .
张嘉誉 , 章坚民 , 杨才明 , 等 . 基于信息物理融合的智能变电站过程层网络异常流量检测 [J]. 电力系统自动化 , 2019 , 43 ( 14 ): 173 - 181 .
ZHANG Jiayu , ZHANG Jianmin , YANG Caiming , et al . Abnormal traffic detection on process layer network of smart substation based on cyber physical fusion [J]. Automation of Electric Power Systems , 2019 , 43 ( 14 ): 173 - 181 .
张敖翔 . CRH5型高速列车通信网络故障诊断系统研究 [D]. 长春 : 长春工业大学 , 2019 .
ZHANG Aoxiang . Research on fault diagnosis system for CRH5 high speed train communication network [D]. Changchun : Changchun University of Technology , 2019 .
陈钊渊 , 黄良毅 , 张铁刚 , 等 . 基于特征流量分析的配电通信网数据侵入研究 [J]. 电气自动化 , 2019 , 41 ( 2 ): 53 - 55 .
CHEN Zhaoyuan , HUANG Liangyi , ZHANG Tiegang , et al . Research on data intrusion in the distribution communication networks based on characteristic flow analysis [J]. Electrical Automation , 2019 , 41 ( 2 ): 53 - 55 .
杨挺 , 侯昱丞 , 赵黎媛 , 等 . 基于时-频域混合特征的变电站通信网异常流量检测方法 [J]. 电力系统自动化 , 2020 , 44 ( 16 ): 79 - 86 .
YANG Ting , HOU Yucheng , ZHAO Liyuan , et al . Abnormal traffic detection method of substation communication network based on time-frequency domain mixed features [J]. Automation of Electric Power Systems , 2020 , 44 ( 16 ): 79 - 86 .
陈家璘 , 周正 , 李磊 , 等 . 配电网信息物理系统异常检测研究 [J]. 电测与仪表 , 2021 , 58 ( 8 ): 185 - 189 .
CHEN Jialin , ZHOU Zheng , LI Lei , et al . Research on anomaly detection of information physical system in distribution network [J]. Electrical Measurement & Instrumentation , 2021 , 58 ( 8 ): 185 - 189 .
张志鹏 , 李勇 , 曹一家 , 等 . 通信和电网联合仿真的配电网局部异常因子故障辨识算法 [J]. 电力系统自动化 , 2016 , 40 ( 17 ): 44 - 50 .
ZHANG Zhipeng , LI Yong , CAO Yijia , et al . A local outlier factor fault identification algorithm based on the co-simulation between cyber and power system for distribution network [J]. Automation of Electric Power Systems , 2016 , 40 ( 17 ): 44 - 50 .
周念成 , 廖建权 , 王强钢 , 等 . 深度学习在智能电网中的应用现状分析与展望 [J]. 电力系统自动化 , 2019 , 43 ( 4 ): 180 - 191 .
ZHOU Niancheng , LIAO Jianquan , WANG Qianggang , et al . Analysis and prospect of deep learning application in smart grid [J]. Automation of Electric Power Systems , 2019 , 43 ( 4 ): 180 - 191 .
杨毅 , 范栋琛 , 殷浩然 , 等 . 基于深度-迁移学习的输电线路故障选相模型及其可迁移性研究 [J]. 电力自动化设备 , 2020 , 40 ( 10 ): 165 - 172 .
YANG Yi , FAN Dongchen , YIN Haoran , et al . Transmission line fault phase selection model based on deep-transfer learning and its transferability [J]. Electric Power Automation Equipment , 2020 , 40 ( 10 ): 165 - 172 .
魏东 , 龚庆武 , 来文青 , 等 . 基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究 [J]. 中国电机工程学报 , 2016 , 36 ( 增刊1 ): 21 - 28 .
WEI Dong , GONG Qingwu , LAI Wenqing , et al . Research on internal and external fault diagnosis and fault-selection of transmission line based on convolutional neural network [J]. Proceedings of the CSEE , 2016 , 36 ( Supplement 1 ): 21 - 28 .
CHEN Y Q , FINK O , SANSAVINI G . Combined fault location and classification for power transmission lines fault diagnosis with integrated feature extraction [J]. IEEE Transactions on Industrial Electronics , 2018 , 65 ( 1 ): 561 - 569 .
YANG D S , PANG Y H , ZHOU B W , et al . Fault diagnosis for energy Internet using correlation processing-based convolutional neural networks [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2019 , 49 ( 8 ): 1739 - 1748 .
殷浩然 , 苗世洪 , 郭舒毓 , 等 . 基于S变换相关度和深度学习的配电网单相接地故障选线新方法 [J]. 电力自动化设备 , 2021 , 41 ( 7 ): 88 - 96 .
YIN Haoran , MIAO Shihong , GUO Shuyu , et al . Novel method for single-phase grounding fault line selection in distribution network based on S-transform correlation and deep learning [J]. Electric Power Automation Equipment , 2021 , 41 ( 7 ): 88 - 96 .
WANG S Y , FAN S X , CHEN J W , et al . Deep-learning based fault diagnosis using computer-visualised power flow [J]. IET Generation, Transmission & Distribution , 2018 , 12 ( 17 ): 3985 - 3992 .
JI S W , XU W , YANG M , et al . 3D convolutional neural networks for human action recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2013 , 35 ( 1 ): 221 - 231 .
徐访 , 黄俊 , 陈权 . 基于3D卷积神经网络的动态手势识别方法 [J/OL]. 计算机工程 [ 2021-04-27 ]. https://doi.org/10.19678/j.issn.1000-3428.0059314 https://doi.org/10.19678/j.issn.1000-3428.0059314 .
XU Fang , HUANG Jun , CHEN Quan . Dynamic gesture recognition method based on 3D convolutional neural network [J/OL]. Computer Engineering [ 2021-04-27 ]. https://doi.org/10.19678/j.issn.1000-3428.0059314 https://doi.org/10.19678/j.issn.1000-3428.0059314 .
杜帅煜 . 基于三维卷积神经网络的脑肿瘤分割算法研究 [D]. 南京 : 南京邮电大学 , 2020 .
DU Shuaiyu . Research on brain tumor segmentation algorithm based on 3D convolutional neural network [D]. Nanjing : Nanjing University of Posts and Telecommunications , 2020 .
吴优 , 付立军 , 马凡 , 等 . 基于HLA的舰船综合电力系统信息物理混合仿真 [J]. 电网技术 , 2019 , 43 ( 7 ): 2422 - 2429 .
WU You , FU Lijun , MA Fan , et al . Cyber-physical co-simulation of vessel integrated power system based on HLA [J]. Power System Technology , 2019 , 43 ( 7 ): 2422 - 2429 .
付灿宇 , 王立志 , 齐冬莲 , 等 . 有源配电网信息物理系统混合仿真平台设计方法及其算例实现 [J]. 中国电机工程学报 , 2019 , 39 ( 24 ): 7118 - 7125 .
FU Canyu , WANG Lizhi , QI Donglian , et al . Design and experiments of active distribution network CPS simulation platform [J]. Proceedings of the CSEE , 2019 , 39 ( 24 ): 7118 - 7125 .
梁英 , 王耀坤 , 刘科研 , 等 . 计及网络信息安全的配电网CPS故障仿真 [J]. 电网技术 , 2021 , 45 ( 1 ): 235 - 242 .
LIANG Ying , WANG Yaokun , LIU Keyan , et al . CPS fault simulation of distribution network considering network information security [J]. Power System Technology , 2021 , 45 ( 1 ): 235 - 242 .
陈寅 , 宋杨 , 费敏锐 . 基于Simulink和OPNET的交互式联合仿真研究 [J]. 系统仿真技术 , 2011 , 7 ( 3 ): 242 - 247 .
CHEN Yin , SONG Yang , FEI Minrui . Interactive cosimulation based on Simulink and OPNET [J]. System Simulation Technology , 2011 , 7 ( 3 ): 242 - 247 .
周飞燕 , 金林鹏 , 董军 . 卷积神经网络研究综述 [J]. 计算机学报 , 2017 , 40 ( 6 ): 1229 - 1251 .
ZHOU Feiyan , JIN Linpeng , DONG Jun . Review of convolutional neural network [J]. Chinese Journal of Computers , 2017 , 40 ( 6 ): 1229 - 1251 .
SRIVASTAVA N , HINTON G , KRIZHEVSKY A , et al . Dropout: a simple way to prevent neural networks from overfitting [J]. Journal of Machine Learning Research , 2014 , 15 ( 6 ): 1929 - 1958 .
LI H D , LI J C , GUAN X M , et al . Research on overfitting of deep learning [C]// 2019 15th International Conference on Computational Intelligence and Security (CIS) , December 13-16 , 2019 , Macao, China : 78 - 81 .
0
Views
0
下载量
6
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621