

浏览全部资源
扫码关注微信
1.武汉理工大学自动化学院,湖北省武汉市 430070
2.广东省电力装备可靠性重点实验室(广东电网有限责任公司电力科学研究院),广东省广州市 510080
3.华中科技大学电气与电子工程学院,湖北省武汉市 430074
Received:17 April 2024,
Revised:2024-10-12,
Online First:17 December 2024,
Published:10 December 2025
移动端阅览
高富,侯慧,魏瑞增等.台风灾害下基于非平衡样本数据的配电网杆塔受损预测[J].电力系统自动化,2025,49(23):89-98.
GAO Fu,HOU Hui,WEI Ruizeng,et al.Tower Damage Prediction for Distribution Network Based on Unbalanced Sample Data Under Typhoon Disasters[J].Automation of Electric Power Systems,2025,49(23):89-98.
高富,侯慧,魏瑞增等.台风灾害下基于非平衡样本数据的配电网杆塔受损预测[J].电力系统自动化,2025,49(23):89-98. DOI: 10.7500/AEPS20240417004.
GAO Fu,HOU Hui,WEI Ruizeng,et al.Tower Damage Prediction for Distribution Network Based on Unbalanced Sample Data Under Typhoon Disasters[J].Automation of Electric Power Systems,2025,49(23):89-98. DOI: 10.7500/AEPS20240417004.
针对低概率高影响极端天气事件往往具有样本数据失衡的特征,提出一种基于Wasserstein距离改进的生成对抗网络-深度集成学习模型,用于实现非平衡样本数据场景中配电网受损杆塔精准预测。首先,以预处理后的气象、地理、电气等数据作为输入,利用Wasserstein距离改进的生成对抗网络生成杆塔受损样本。然后,使用Bagging集成随机森林、Boosting集成梯度提升决策树作为基学习器,神经网络作为元学习器,通过Stacking构建深度集成学习模型。最后,以2023年4号台风“泰利”期间中国湛江市配电网杆塔为例,将预测受损杆塔分布结果可视化,并利用SHAP法对模型进行解释性评估,分析特征变量对预测结果的影响机制。结果表明,相比传统数据增强与机器学习算法,所提模型具有更高的预测精度与数据信息挖掘能力,可在数据样本不足时有效预测配电网杆塔受损情况。
Given that extreme weather events with low probability but high impact often exhibit the characteristic of imbalanced sample data
a Wasserstein generative adversarial network (WGAN) based deep ensemble learning (DEL) model is proposed to achieve the accurate prediction of damaged towers in distribution network in scenarios with imbalanced sample data. Firstly
using preprocessed meteorological
geographical
and electrical data as inputs
the WGAN is employed to generate samples of damaged towers. Subsequently
a DEL model is constructed through Stacking
utilizing Bagging-integrated random forest and boosting-integrated gradient boosting decision tree as base learners
and a neural network as a meta-learner. Finally
taking the distribution network towers in Zhanjiang City of China during Typhoon Talim (No. 4 in 2023) as an example
the predicted distribution of damaged towers is visualized. The model is evaluated for interpretability using the SHAP method to analyze the influence mechanism of feature variables on the prediction results. The results demonstrate that
compared to traditional data augmentation and machine learning algorithms
the proposed model exhibits higher prediction accuracy and superior data information mining capabilities
enabling effective tower damage prediction in distribution network even when data samples are insufficient.
侯慧 , 朱韶华 , 吴细秀 , 等 . 数据与模型驱动在输电杆塔风致灾损预测中的应用对比分析 [J]. 电网技术 , 2023 , 47 ( 4 ): 1721 - 1727 .
HOU Hui , ZHU Shaohua , WU Xixiu , et al . Comparative analysis of data-driven method and model-driven method in wind-induced damage prediction of transmission towers [J]. Power System Technology , 2023 , 47 ( 4 ): 1721 - 1727 .
卢锦玲 , 张祥国 , 张伟 , 等 . 基于改进辅助分类生成对抗网络的风机主轴承故障诊断 [J]. 电力系统自动化 , 2021 , 45 ( 7 ): 148 - 154 .
LU Jinling , ZHANG Xiangguo , ZHANG Wei , et al . Fault diagnosis of main bearing of wind turbine based on improved auxiliary classifier generative adversarial network [J]. Automation of Electric Power Systems , 2021 , 45 ( 7 ): 148 - 154 .
LIU S M , CHEN J H , LIU Z H . An empirical study of dynamic selection and random under-sampling for the class imbalance problem [J]. Expert Systems with Applications , 2023 , 221 : 119703 .
HAYATY M , MUTHMAINAH S , GHUFRAN S M . Random and synthetic over-sampling approach to resolve data imbalance in classification [J]. International Journal of Artificial Intelligence Research , 2020 , 4 ( 2 ): 86 - 94 .
谢桦 , 亚夏尔·吐尔洪 , 陈昊 , 等 . 基于支持向量机算法的配电线路时变状态预测方法 [J]. 电力系统自动化 , 2020 , 44 ( 18 ): 74 - 80 .
XIE Hua , TURGUN Yaxar , CHEN Hao , et al . Prediction method for time-variant states of distribution line based on support vector machine algorithm [J]. Automation of Electric Power Systems , 2020 , 44 ( 18 ): 74 - 80 .
TENG Z Y , CAO P , HUANG M , et al . Multi-label borderline oversampling technique [J]. Pattern Recognition , 2024 , 145 : 109953 .
GU X W , ANGELOV P P , SOARES E A . A self-adaptive synthetic over-sampling technique for imbalanced classification [J]. International Journal of Intelligent Systems , 2020 , 35 ( 6 ): 923 - 943 .
郑凌铭 , 舒胜文 , 陈彬 , 等 . 强台风环境下基于格点化和支持向量机的10 kV杆塔受损量预测方法 [J]. 高电压技术 , 2020 , 46 ( 1 ): 42 - 50 .
ZHENG Lingming , SHU Shengwen , CHEN Bin , et al . Prediction method for amount of 10 kV damaged poles under severe typhoon environment based on meshing and support vector machine [J]. High Voltage Engineering , 2020 , 46 ( 1 ): 42 - 50 .
侯慧 , 于士文 , 肖祥 , 等 . 基于空间多源异构数据的台风下输电杆塔风险评估 [J]. 电力系统自动化 , 2020 , 44 ( 10 ): 127 - 134 .
HOU Hui , YU Shiwen , XIAO Xiang , et al . Risk assessment of transmission tower in typhoon based on spatial multi-source heterogeneous data [J]. Automation of Electric Power Systems , 2020 , 44 ( 10 ): 127 - 134 .
侯慧 , 俞菊芳 , 谢宇风 , 等 . 数据驱动的台风灾害下配网10 kV杆塔受损空间分布预测 [J]. 电网技术 , 2021 , 45 ( 9 ): 3681 - 3689 .
HOU Hui , YU Jufang , XIE Yufeng , et al . Data-driven prediction of spatial distribution of damage to 10 kV towers in distribution network under typhoon disaster [J]. Power System Technology , 2021 , 45 ( 9 ): 3681 - 3689 .
侯慧 , 耿浩 , 肖祥 , 等 . 台风灾害下用户停电区域预测及评估 [J]. 电网技术 , 2019 , 43 ( 6 ): 1948 - 1954 .
HOU Hui , GENG Hao , XIAO Xiang , et al . Research on prediction and evaluation of user power outage area under typhoon disaster [J]. Power System Technology , 2019 , 43 ( 6 ): 1948 - 1954 .
朱永利 , 张翼 , 蔡炜豪 , 等 . 基于辅助分类-边界平衡生成式对抗网络的局部放电数据增强与多源放电识别 [J]. 中国电机工程学报 , 2021 , 41 ( 14 ): 5044 - 5053 .
ZHU Yongli , ZHANG Yi , CAI Weihao , et al . Data augmentation and pattern recognition for multi-sources partial discharge based on boundary equilibrium generative adversarial network with auxiliary classifier [J]. Proceedings of the CSEE , 2021 , 41 ( 14 ): 5044 - 5053 .
游文霞 , 李清清 , 杨楠 , 等 . 基于多异学习器融合Stacking集成学习的窃电检测 [J]. 电力系统自动化 , 2022 , 46 ( 24 ): 178 - 186 .
YOU Wenxia , LI Qingqing , YANG Nan , et al . Electricity theft detection based on multiple different learner fusion by Stacking ensemble learning [J]. Automation of Electric Power Systems , 2022 , 46 ( 24 ): 178 - 186 .
侯慧 , 陈希 , 李敏 , 等 . 一种Stacking集成结构的台风灾害下停电空间预测方法 [J]. 电力系统保护与控制 , 2022 , 50 ( 3 ): 76 - 84 .
HOU Hui , CHEN Xi , LI Min , et al . A space prediction method for power outage in a typhoon disaster based on a Stacking integrated structure [J]. Power System Protection and Control , 2022 , 50 ( 3 ): 76 - 84 .
HOU H , CHEN X , LI M , et al . Prediction of user outage under typhoon disaster based on multi-algorithm Stacking integration [J]. International Journal of Electrical Power & Energy Systems , 2021 , 131 : 107123 .
肖白 , 张博 , 王辛玮 , 等 . 基于组合模态分解和深度学习的短期风电功率区间预测 [J]. 电力系统自动化 , 2023 , 47 ( 17 ): 110 - 117 .
XIAO Bai , ZHANG Bo , WANG Xinwei , et al . Short-term wind power interval prediction based on combined mode decomposition and deep learning [J]. Automation of Electric Power Systems , 2023 , 47 ( 17 ): 110 - 117 .
陈佳欣 . 基于改进随机森林的台风灾害下配电网杆塔故障预警 [D]. 南京 : 南京理工大学 , 2019 .
CHEN Jiaxin . Early warning of tower fault in distribution network under typhoon disaster based on improved random forest [D]. Nanjing : Nanjing University of Science and Technology , 2019 .
TANG L F , XIE H P , WANG Y , et al . Predicting typhoon-induced transmission line outages with coordination of static and dynamic data [J]. International Journal of Electrical Power & Energy Systems , 2022 , 142 : 108296 .
沈赋 , 张微 , 徐潇源 , 等 . 基于随机森林和最大互信息系数关键特征选择的配电网拓扑辨识研究 [J]. 电力系统保护与控制 , 2024 , 52 ( 17 ): 1 - 11 .
俞学豪 , 赵子岩 , 马应龙 , 等 . 基于BR和GBDT的电力信息通信客服系统多标签文本分类 [J]. 电力系统自动化 , 2021 , 45 ( 11 ): 144 - 151 .
YU Xuehao , ZHAO Ziyan , MA Yinglong , et al . Multi-label text classification for power ICT custom service system based on binary relevance and gradient boosting decision tree [J]. Automation of Electric Power Systems , 2021 , 45 ( 11 ): 144 - 151 .
KIM C I , KIM M , JUNG S , et al . Simplified Fréchet distance for generative adversarial nets [J]. Sensors , 2020 , 20 ( 6 ): E1548 .
ZHAO K , JIANG H K , WANG K B , et al . Joint distribution adaptation network with adversarial learning for rolling bearing fault diagnosis [J]. Knowledge-Based Systems , 2021 , 222 : 106974 .
吴建华 , 逯跃锋 . ArcGIS软件与应用 [M]. 北京 : 电子工业出版社 , 2017 .
WU Jianhua , LU Yuefeng . ArcGIS software and application [M]. Beijing : Publishing House of Electronics Industry , 2017 .
王小君 , 窦嘉铭 , 刘曌 , 等 . 可解释人工智能在电力系统中的应用综述与展望 [J]. 电力系统自动化 , 2024 , 48 ( 4 ): 169 - 191 .
WANG Xiaojun , DOU Jiaming , LIU Zhao , et al . Review and prospect of explainable artificial intelligence and its application in power systems [J]. Automation of Electric Power Systems , 2024 , 48 ( 4 ): 169 - 191 .
GOODFELLOW I J , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial nets [C]// Proceedings of the 27th International Conference on Neural Information Processing Systems , November 18-22 , 2014 , Montreal, Canada : 2672 - 2680 .
MAZUMDAR E V , JORDAN M I , SASTRY S . On finding local nash equilibria (and only local nash equilibria) in zero-sum games [J/OL]. [ 2024-01-20 ]. https://arxiv.org/abs/1901. 00838 https://arxiv.org/abs/1901.00838 .
FAN W T , XIAO F Y . A complex Jensen-Shannon divergence in complex evidence theory with its application in multi-source information fusion [J]. Engineering Applications of Artificial Intelligence , 2022 , 116 : 105362 .
ADLER J , LUNZ S . Banach Wasserstein GAN [C]// 32nd Conference on Neural Information Processing Systems (NeurIPS 2018 ), December 3-8 , 2018 , Montréal, Canada .
SANTURKAR S , TSIPRAS D , ILYAS A , et al . How does batch normalization help optimization? [J/OL]. [ 2024-01-20 ], https://doi.org/10.48550/arXiv.1805.11604 https://doi.org/10.48550/arXiv.1805.11604 .
POERNOMO A , KANG D K . Biased Dropout and Crossmap Dropout: learning towards effective Dropout regularization in convolutional neural network [J]. Neural Networks , 2018 , 104 : 60 - 67 .
PIRIZADEH M , ALEMOHAMMAD N , MANTHOURI M , et al . A new machine learning ensemble model for class imbalance problem of screening enhanced oil recovery methods [J]. Journal of Petroleum Science and Engineering , 2021 , 198 : 108214 .
广东电网有限责任公司电力科学研究院 . 台风“泰利”气象分析报告 [R]. 广州 : 广东电网有限责任公司电力科学研究院 , 2023 .
Electric Power Research Institute of Guangdong Power Grid Co., Ltd . Typhoon “Talim” meteorological analysis report [R]. Guangzhou : Electric Power Research Institute of Guangdong Power Grid Co., Ltd. , 2023 .
中央气象台 . 台风“泰利”为今年首个登陆我国的台风,初台登陆时间晚强度强 [EB/OL].( 2023-07-19 )[ 2024-03-30 ]. http://www. nmc.cn /publish/typhoon/warning_index.html http://www.nmc.cn/publish/typhoon/warning_index.html .
National Meteorological Center . Typhoon “Talim” makes first landfall in China, with a late and strong initial landfall [EB/OL]. ( 2023-07-19 )[ 2024-03-30 ]. http://www.nmc.cn/publish/typhoon/warning_index. html http://www.nmc.cn/publish/typhoon/warning_index.html .
中国气象局热带气旋资料中心 . CMA最佳路径数据集 [EB/OL].( 2023-08-01 )[ 2024-03-30 ]. https://tcdata.typhoon.org.cn https://tcdata.typhoon.org.cn .
Tropical Cyclone Data Center of China Meteorological Administration . CMA best track dataset [EB/OL]. ( 2023-08-01 )[ 2024-03-30 ]. https://tcdata.typhoon.org.cn https://tcdata.typhoon.org.cn .
全国地理信息资源目录服务系统 . 1 ∶ 100 万公众版基础地理信息数据 [EB/OL].( 2021-01-01 )[ 2024-03-30 ]. https://www.webmap.cn https://www.webmap.cn .
National Catalogue Service for Geographic Information . 1 ∶ 1 000 000 public version basic geographic information data [EB/OL]. ( 2021-01-01 )[ 2024-03-30 ]. https://www.webm ap.cn https://www.webmap.cn .
侯慧 , 朱韶华 , 俞菊芳 , 等 . 基于高效数据降维的配电网风灾停电用户数量预测模型 [J]. 电力系统自动化 , 2022 , 46 ( 7 ): 69 - 76 .
HOU Hui , ZHU Shaohua , YU Jufang , et al . Prediction model for user number in power outage caused by wind disaster for distribution networks based on high-efficient data dimensionality reduction [J]. Automation of Electric Power Systems , 2022 , 46 ( 7 ): 69 - 76 .
YU L A , ZHOU R T , CHEN R D , et al . Missing data preprocessing in credit classification: one-hot encoding or imputation? [J]. Emerging Markets Finance and Trade , 2022 , 58 ( 2 ): 472 - 482 .
DOUZAS G , BACAO F , LAST F . Improving imbalanced learning through a heuristic oversampling method based on k -means and SMOTE [J]. Information Sciences , 2018 , 465 : 1 - 20 .
LIASHCHYNSKYI P B , LIASHCHYNSKYI P . Grid search, random search, genetic algorithm: a big comparison for NAS [J/OL]. [ 2024-01-20 ]. https://arxiv.org/abs/1912.06059 https://arxiv.org/abs/1912.06059 .
李东东 , 刘宇航 , 赵阳 , 等 . 基于改进生成对抗网络的风机行星齿轮箱故障诊断方法 [J]. 中国电机工程学报 , 2021 , 41 ( 21 ): 7496 - 7506 .
LI Dongdong , LIU Yuhang , ZHAO Yang , et al . Fault diagnosis method of wind turbine planetary gearbox based on improved generative adversarial network [J]. Proceedings of the CSEE , 2021 , 41 ( 21 ): 7496 - 7506 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621