
1.南京邮电大学自动化学院,江苏省南京市 210023
2.新型电力系统运行与控制全国重点实验室(清华大学),北京市100084
3.国电南瑞科技股份有限公司,江苏省南京市 211106
Received:10 July 2025,
Revised:2025-12-02,
Online First:12 February 2026,
Published:25 September 2026
移动端阅览
杨璐彤,高辉,邢强等.基于知识嵌入超图深度学习的城市快充站运行状态估计[J].电力系统自动化,2026,50(18):97-107.
YANG Lutong,GAO Hui,XING Qiang,et al.Operation State Estimation for Urban Fast-charging Stations Based on Knowledge-embedded Hypergraph Deep Learning[J].Automation of Electric Power Systems,2026,50(18):97-107.
杨璐彤,高辉,邢强等.基于知识嵌入超图深度学习的城市快充站运行状态估计[J].电力系统自动化,2026,50(18):97-107. DOI: 10.7500/AEPS20250710002.
YANG Lutong,GAO Hui,XING Qiang,et al.Operation State Estimation for Urban Fast-charging Stations Based on Knowledge-embedded Hypergraph Deep Learning[J].Automation of Electric Power Systems,2026,50(18):97-107. DOI: 10.7500/AEPS20250710002.
城市快充站运行状态精准估计是电动汽车充电网络高效利用的重要前提,现有工作缺乏对快充站实际运行机理的考虑,未能挖掘多站点运行状态的时空交互特性。为此,文中将状态估计转换为融合快充站运行知识与历史数据的样本生成过程,提出基于知识嵌入超图深度学习架构的城市快充站运行状态估计方法。首先,将快充站的动态运行状态与多空间位置分布表征为超图模型,采用时间卷积注意力网络和超图卷积网络捕捉图结构化特征信息的时序相似性与空间关联性。其次,将快充站运行策略、物理规则以及约束条件解耦为知识损失函数,融入生成对抗网络的样本学习过程中,构建知识-数据双重驱动的损失函数,通过“编码-解码”范式隐式学习样本条件概率分布,估计不同快充站个体充电桩的运行状态。最后,以中国南京城区实际交通路网和运营快充站为例设计仿真算例,结果表明所提方法能精准刻画快充站运行状态的时空分布特征,为后续电动汽车充电调度提供了理论支撑。
Accurate operation state estimation for urban fast-charging stations is a crucial prerequisite for the efficient utilization of electric vehicle charging networks. Existing studies lack the consideration of the actual operation mechanisms of fast-charging stations
failing to explore the spatio-temporal interaction characteristics of multi-station operation states. To address this
by transforming state estimation into a sample generation process that integrates operation knowledge and historical data of fast-charging stations
this paper proposes an operation state estimation method for urban fast-charging stations based on knowledge-embedded hypergraph deep learning architecture. First
the dynamic operation states of fast-charging stations and their multi-spatial distribution are represented as a hypergraph model
and the temporal convolution attention network and hypergraph convolution network are used to capture temporal similarity and spatial correlation in graph-structured feature information. Second
operation strategies of fast-charging stations
physical rules
and constraints are decoupled into a knowledge loss function
which is integrated into the sample learning process of generative adversarial networks to construct a knowledge-data dual-driven loss function. Through the “encoding-decoding” paradigm
the conditional probability distribution of samples is implicitly learned to estimate the operation state of individual charging piles across different fast-charging stations. Finally
using the actual road network and operating fast-charging stations in Nanjing
China
as a case study
simulation results demonstrate that the proposed method can accurately characterize the spatio-temporal distribution characteristics of operation states for fast-charging stations
providing theoretical support for subsequent electric vehicle charging scheduling.
黄学良 , 刘永东 , 沈斐 , 等 . 电动汽车与电网互动:综述与展望 [J]. 电力系统自动化 , 2024 , 48 ( 7 ): 3 - 23 .
Huang Xueliang , Liu Yongdong , Shen Fei , et al . Vehicle to grid: review and prospect [J]. Automation of Electric Power Systems , 2024 , 48 ( 7 ): 3 - 23 .
胡俊杰 , 潘羿 , 徐成明 , 等 . 基于动态交通推演的电动汽车充电快速引导策略 [J]. 电工技术学报 , 2025 , 40 ( 9 ): 2880 - 2896 .
Hu Junjie , Pan Yi , Xu Chengming , et al . Fast charging guidance strategy for electric vehicles based on dynamic traffic deduction [J]. Transactions of China Electrotechnical Society , 2025 , 40 ( 9 ): 2880 - 2896 .
国务院办公厅 . 2020新能源汽车产业发展规划 ( 2021 — 2035 年)[EB/OL].[ 2025-11-02 ]. https://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm https://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm .
General Office of the State Council . New energy vehicle industry development plan in 2020 ( 2021 — 2035 )[EB/OL]. [ 2025-11-02 ]. https://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm https://www.gov.cn/zhengce/content/2020-11/02/content_5556716.htm .
王明深 , 袁晓冬 , 曾飞 , 等 . 电动汽车充电设施规划运行关键技术研究综述 [J]. 电力自动化设备 , 2025 , 45 ( 5 ): 65 - 76 .
Wang Mingshen , Yuan Xiaodong , Zeng Fei , et al . Review of key technologies research for electric vehicle charging facilities planning and scheduling [J]. Electric Power Automation Equipment , 2025 , 45 ( 5 ): 65 - 76 .
钱涛 , 方铭宇 , 束雯暄 , 等 . 基于微观交通流模型的城市快充负荷精细化实时仿真框架 [J]. 中国电机工程学报 , 2025 , 45 ( 11 ): 4117 - 4130 .
Qian Tao , Fang Mingyu , Shu Wenxuan , et al . Real-time simulation framework of urban EVs charging loads based on micro-level modeling of transportation network [J]. Proceedings of the CSEE , 2025 , 45 ( 11 ): 4117 - 4130 .
邢强 , 陈中 , 冷钊莹 , 等 . 基于实时交通信息的电动汽车路径规划和充电导航策略 [J]. 中国电机工程学报 , 2020 , 40 ( 2 ): 534 - 550 .
Xing Qiang , Chen Zhong , Leng Zhaoying , et al . Route planning and charging navigation strategy for electric vehicles based on real-time traffic information [J]. Proceedings of the CSEE , 2020 , 40 ( 2 ): 534 - 550 .
张睿骐 , 阳辉 , 王子睿 , 等 . 面向车-库-网多层级协调控制系统的电动汽车多时段可调度域的构建和分析 [J]. 电工技术学报 , 2025 , 40 ( 13 ): 4256 - 4275 .
Zhang Ruiqi , Yang Hui , Wang Zirui , et al . Construction and analysis of multi-time schedulable region for electric vehicles oriented to vehicle-parking garage-grid multi-level coordinated control system [J]. Transactions of China Electrotechnical Society , 2025 , 40 ( 13 ): 4256 - 4275 .
袁晓冬 , 甘海庆 , 王明深 , 等 . 车联网环境下电动汽车主动充电引导模型 [J]. 电力系统自动化 , 2024 , 48 ( 7 ): 159 - 168 .
Yuan Xiaodong , Gan Haiqing , Wang Mingshen , et al . Active charging guidance model of electric vehicles based on Internet of vehicles [J]. Automation of Electric Power Systems , 2024 , 48 ( 7 ): 159 - 168 .
邵尹池 , 穆云飞 , 余晓丹 , 等 . “车-路-网”模式下电动汽车充电负荷时空预测及其对配电网潮流的影响 [J]. 中国电机工程学报 , 2017 , 37 ( 18 ): 5207 - 5219 .
Shao Yinchi , Mu Yunfei , Yu Xiaodan , et al . A spatial-temporal charging load forecast and impact analysis method for distribution network using EVs-traffic-distribution model [J]. Proceedings of the CSEE , 2017 , 37 ( 18 ): 5207 - 5219 .
谢仕炜 , 胡志坚 , 王珏莹 . 考虑时-空耦合的城市电力-交通网络动态流量均衡 [J]. 中国电机工程学报 , 2021 , 41 ( 24 ): 8408 - 8423 .
Xie Shiwei , Hu Zhijian , Wang Jueying . Dynamic flow equilibrium of urban power and transportation networks considering the coupling in time and space [J]. Proceedings of the CSEE , 2021 , 41 ( 24 ): 8408 - 8423 .
Chen Z Y , Xiong R , Cao J Y . Particle swarm optimization-based optimal power management of plug-in hybrid electric vehicles considering uncertain driving conditions [J]. Energy , 2016 , 96 : 197 - 208 .
马文帅 , 胡俊杰 , 房宇轩 , 等 . 电动汽车用户参与调控意愿的多代理表征与可信容量量化 [J]. 电力系统自动化 , 2023 , 47 ( 18 ): 122 - 131 .
Ma Wenshuai , Hu Junjie , Fang Yuxuan , et al . Multi-agent representation for willingness of electric vehicle users to participate in regulation and quantification of reliable reserve capacity [J]. Automation of Electric Power Systems , 2023 , 47 ( 18 ): 122 - 131 .
Qian T , Liang Z Y , Chen S , et al . A tri-level demand response framework for EVCS flexibility enhancement in coupled power and transportation networks [J]. IEEE Transactions on Smart Grid , 2025 , 16 ( 1 ): 598 - 611 .
Li Y J , Su S , Zhang M H , et al . Multi-agent graph reinforcement learning method for electric vehicle on-route charging guidance in coupled transportation electrification [J]. IEEE Transactions on Sustainable Energy , 2024 , 15 ( 2 ): 1180 - 1193 .
姚程文 , 杨苹 , 刘泽健 . 基于CNN-GRU混合神经网络的负荷预测方法 [J]. 电网技术 , 2020 , 44 ( 9 ): 3416 - 3424 .
Yao Chengwen , Yang Ping , Liu Zejian . Load forecasting method based on CNN-GRU hybrid neural network [J]. Power System Technology , 2020 , 44 ( 9 ): 3416 - 3424 .
Kong W C , Dong Z Y , Jia Y W , et al . Short-term residential load forecasting based on LSTM recurrent neural network [J]. IEEE Transactions on Smart Grid , 2019 , 10 ( 1 ): 841 - 851 .
王华彪 , 李小勇 . 基于融合注意力机制改进双向长短时记忆网络在电动汽车充电负荷中的预测研究 [J]. 电网与清洁能源 , 2022 , 38 ( 6 ): 104 - 112 .
Wang Huabiao , Li Xiaoyong . Prediction of electric vehicle charging load based on integrating attention mechanism to improve BiLSTM [J]. Advances of Power System & Hydroelectric Engineering , 2022 , 38 ( 6 ): 104 - 112 .
刘巍炜 , 周羽生 , 周文晴 , 等 . 考虑异方差性的城市电网电动汽车充电负荷预测 [J]. 电力系统自动化 , 2024 , 48 ( 15 ): 54 - 63 .
Liu Weiwei , Zhou Yusheng , Zhou Wenqing , et al . Charging load forecasting for electric vehicles in urban power grid considering heteroscedasticity [J]. Automation of Electric Power Systems , 2024 , 48 ( 15 ): 54 - 63 .
Lin W X , Wu D , Boulet B . Spatial-temporal residential short-term load forecasting via graph neural networks [J]. IEEE Transactions on Smart Grid , 2021 , 12 ( 6 ): 5373 - 5384 .
Shi J K , Zhang W G , Bao Y , et al . Load forecasting of electric vehicle charging stations: attention based spatiotemporal multi-graph convolutional networks [J]. IEEE Transactions on Smart Grid , 2024 , 15 ( 3 ): 3016 - 3027 .
Kipf T , Welling M . Semi-supervised classification with graph convolutional networks [PP/OL]. [ 2025-11-01 ]. https://arxiv.org/abs/1609.02907 https://arxiv.org/abs/1609.02907 .
Sun Y F , Jiang X H , Hu Y L , et al . Dual dynamic spatial-temporal graph convolution network for traffic prediction [J]. IEEE Transactions on Intelligent Transportation Systems , 2022 , 23 ( 12 ): 23680 - 23693 .
Xue R , Zhao S J , Han F X . An embedding-driven multi-hop spatio-temporal attention network for traffic prediction [J]. IEEE Transactions on Intelligent Transportation Systems , 2023 , 24 ( 11 ): 13192 - 13207 .
Goodfellow I J , Pouget-Abadie J , Mirza M , et al . Generative adversarial networks [PP/OL]. [ 2025-11-01 ]. https://arxiv.org/abs/1406.266 https://arxiv.org/abs/1406.266 .
邢强 . 电动汽车与交通电气化耦合网络互动关键技术研究 [D]. 南京 : 东南大学 , 2023 .
Xing Qiang . Research on key technologies of interaction between electric vehicle and traffic electrification coupling network [D]. Nanjing : Southeast University , 2023 .
苏粟 , 李玉璟 , 夏明超 , 等 . 基于时空耦合特性的充电站运行状态预测 [J]. 电力系统自动化 , 2022 , 46 ( 3 ): 23 - 32 .
Su Su , Li Yujing , Xia Mingchao , et al . Operation state prediction of charging station based on spatio-temporal coupling characteristics [J]. Automation of Electric Power Systems , 2022 , 46 ( 3 ): 23 - 32 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621