基于多主体依互与在线学习的图神经网络“网-源-储-车”协同供能系统能量超前管控方法

doi:10.19595/j.cnki.1000-6753.tces.251030

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (0 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Byintegratingnew energy systems and energy storage systems into the traction power supply system, a “grid-source-storage-train” coordinated power supply system has beenestablished. This system serves as a key measure to promote green, low-carbon development in rail transit. However, new energy sources exhibit fluctuating and unpredictable output characteristics. Electric locomotives show impactful power demands. These factors make the real-time energy management and control of the cooperative power supply system significantly more challenging. Therefore, this paper proposes a “grid-source-storage-train” collaborative energy supply system energy-overrun control method based on multi-subject dependencies and an online-learning-based graph neural network.
First, K-Means clustering and kernel density estimation methods were used. Operating conditions were classified for multiple entities. These entities included new energy systems, energy storage systems, and electric locomotives. Second, an objective function was constructed within the optimization model to determine the optimal transition paths. For the new energy system, the energy management strategy maximized the utilization efficiency of the new energy. It also promoted local consumption. For the energy storage system, both the absorption efficiency of regenerative braking energy and the energy feedback efficiency were enhanced, reducing traction losses. An objective function was formulated to generate an optimal graph of transition relationships for operating conditions. Nodes represented the operating conditions of different entities, and edges denoted transition probabilities or conditions.
Graph convolutional networks and multi-head attention mechanisms were employed to extracts patio temporal features. A multi-level feature extraction network architecture was established. Specifically, the graph convolutional layer aggregated information from local neighbors. Connectivity features among multiple entities were extracted. Subsequently, the multi-head attention mechanism extracted temporal features, enhancing the model's ability to capture non-local relationships. Next, local spatial features and non-local temporal features were fused. Two layers of graph convolutions were used to further extract deep global features. Finally, the energy management layer mapped the deep representations to corresponding operating states. To enhance the applicability and robustness of the graph neural network model, an online learning strategy was implemented. Real-time operational data were collected. The model was incrementally updated. New data were progressively incorporated without discarding existing information. This approach strengthened the model's ability to handle anomalies, thereby improving the graph neural network's energy management accuracy.
Simulation results validate the effectiveness of the proposed method. For the photovoltaic system, the energy management strategy achieves a PV energy absorption of 10 556.59 kW·h. It also reaches a high energy utilization efficiency of 81.81%. For the energy storage system, the proposed energy management strategy achieves a regenerative braking energy absorption efficiency of 38.35% and a storage system feedback efficiency of 53.82%, saving a total of 13 539.41 kW·h of traction energy per day.
In summary, a collaborative energy-supply system for a “grid-source-storage-train” with an overrun-control method was proposed. This method achieves efficient control of energy interaction. Future applications can extend this proposed graph neural network model to energy interaction management across multiple stations. This expansion of the model's applicability will provide stronger technical support for the green transformation of rail transit systems.

Key words： Graph neural networks rail transport electrified railways online learning energy control

Received: 13 June 2025

PACS:

TM731

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Fu Jiaxing
	Wei Xiaoguang
	Gao Shibin
	Luo Jiaming
	Mi Jiayu
	Ling Weize

Cite this article:

Fu Jiaxing,Wei Xiaoguang,Gao Shibin等. “Grid-Source-Storage-Train” Collaborative Energy Supply System Energy Overrun Control Method Based on Multi-Subject Dependency and Online Learning-Based Graph Neural Network[J]. Transactions of China Electrotechnical Society, 2026, 41(12): 4246-4267.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.251030 OR https://dgjsxb.ces-transaction.com/EN/Y2026/V41/I12/4246

[1] 何正友, 向悦萍, 廖凯, 等. 能源-交通-信息三网融合发展的需求、形态及关键技术[J]. 电力系统自动化, 2021, 45(16): 73-86.
He Zhengyou, Xiang Yueping, Liao Kai, et al.Demand, form and key technologies of integrated development of energy-transport-information networks[J]. Automation of Electric Power Systems, 2021, 45(16): 73-86.
[2] 中国国家铁路集团有限公司. 中国国家铁路集团有限公司2024年统计公报[Z]. 北京: 中国国家铁路集团有限公司, 2025.
China State Railway Group Co, Ltd. 2024 Statistical Bulletin of China National Railway Group Co, Ltd[Z]. Beijing: China State Railway Group Co, Ltd, 2025.
[3] 郭亚, 陈小强, 王英, 等. 计及电网电压不平衡的储能型铁路功率调节器负序优化补偿策略[J]. 高电压技术, 2023, 49(2): 772-780.
Guo Ya, Chen Xiaoqiang, Wang Ying, et al.Negative sequence optimization compensation strategy for energy storage type railway power conditioner considering grid voltage imbalance[J]. High Voltage Engineering, 2023, 49(2): 772-780.
[4] 胡田飞, 刘济华, 李天峰, 等. 铁路与新能源融合发展现状及展望[J]. 中国工程科学, 2023, 25(2): 122-132.
Hu Tianfei, Liu Jihua, Li Tianfeng, et al.Current status and prospect of the integration of railway and new energy[J]. Strategic Study of CAE, 2023, 25(2): 122-132.
[5] 高仕斌, 罗嘉明, 陈维荣, 等. 轨道交通“网-源-储-车”协同供能技术体系[J]. 西南交通大学学报, 2024, 59(5): 959-979, 989.
Gao Shibin, Luo Jiaming, Chen Weirong, et al.Rail transit “network-source-storage-vehicle” collaborative energy supply technology system[J]. Journal of Southwest Jiaotong University, 2024, 59(5): 959-979, 989.
[6] 王玙, 杨中平, 李峰, 等. 有轨电车混合动力系统能量交互型管理策略与容量配置协同优化研究[J]. 电工技术学报, 2019, 34(8): 1780-1788.
Wang Yu, Yang Zhongping, Li Feng, et al.Energy management strategy with energy interaction and configuration optimization for the tram’s hybrid storage system[J]. Transactions of China Electro-technical Society, 2019, 34(8): 1780-1788.
[7] 曹佳峰. 城市轨道交通列车节能操纵策略研究[J]. 铁道运输与经济, 2019, 41(10): 108-113, 118.
Cao Jiafeng.A study on the energy-efficient manipulation strategy of urban rail transit train[J]. Railway Transport and Economy, 2019, 41(10): 108-113, 118.
[8] 廖勤宇. 高速铁路同相储能供电系统及能量管理技术研究[D]. 成都: 西南交通大学, 2021.
Liao Qinyu.Research on same-phase energy storage power supply system and energy management technology for high-speed railway[D]. Chengdu: Southwest Jiaotong University, 2021.
[9] 张晓虎, 张熊, 张克良, 等. 储能技术在轨道交通再生制动能量回收的应用[J]. 电气工程学报, 2023, 18(2): 210-220.
Zhang Xiaohu, Zhang Xiong, Zhang Keliang, et al.Application of energy storage technology in regenerative braking energy recovery of rail transit[J]. Journal of Electrical Engineering, 2023, 18(2): 210-220.
[10] 邓文丽, 戴朝华, 陈维荣. 轨道交通能源互联网背景下光伏在交/直流牵引供电系统中的应用及关键问题分析[J]. 中国电机工程学报, 2019, 39(19): 5692-5702.
Deng Wenli, Dai Chaohua, Chen Weirong.Appli-cation of PV generation in AC/DC traction power supply system and the key problem analysis under the background of rail transit energy Internet[J]. Pro-ceedings of the CSEE, 2019, 39(19): 5692-5702.
[11] 高锋阳, 宋志翔, 高建宁, 等. 计及光伏和储能接入的牵引供电系统能量管理策略[J]. 电工技术学报, 2024, 39(3): 745-757.
Gao Fengyang, Song Zhixiang, Gao Jianning, et al.Energy management strategies for traction power systems with PV and energy storage access[J]. Transactions of China Electrotechnical Society, 2024, 39(3): 745-757.
[12] Teleke S, Baran M E, Bhattacharya S, et al.Rule-based control of battery energy storage for dispatching intermittent renewable sources[J]. IEEE Transactions on Sustainable Energy, 2010, 1(3): 117-124.
[13] 邓文丽, 戴朝华, 韩春白雪, 等. 计及再生制动能量回收和电能质量改善的铁路背靠背混合储能系统及其控制方法[J]. 中国电机工程学报, 2019, 39(10): 2914-2923.
Deng Wenli, Dai Chaohua, Han Chunbaixue, et al.Back-to-back hybrid energy storage system of electric railway and its control method considering regenerative braking energy recovery and power quality improvement[J]. Proceedings of the CSEE, 2019, 39(10): 2914-2923.
[14] 赵靖英, 黄麟然, 姚帅亮. 考虑容量再生的锂离子电池健康状态估计方法[J]. 电源学报, 2026, 24(1): 242-251.
Zhao Jingying, Huang Linran, Yao Shuailiang.State-of-health estimation method for lithium-ion battery considering capacity regeneration[J]. Journal of Power Supply, 2026, 24(1): 242-251.
[15] 钟志宏, 李炎, 米佳雨, 等. 基于牵引网电压和空载电压的多储能系统区间能量管理策略[J]. 电工技术学报, 2024, 39(15): 4583-4598.
Zhong Zhihong, Li Yan, Mi Jiayu, et al.Interval energy management strategy for multiple energy storage systems based on traction network voltage and No-load voltage[J]. Transactions of China Electro-technical Society, 2024, 39(15): 4583-4598.
[16] Chen Jian, Xu Chenfeng, Wu Chengshuai, et al.Adaptive fuzzy logic control of fuel-cell-battery hybrid systems for electric vehicles[J]. IEEE Transac-tions on Industrial Informatics, 2018, 14(1): 292-300.
[17] 欧志新, 李继侠, 邓春兰. 基于模糊控制理论集的自适应数据融合与修正研究[J]. 电气传动, 2023, 53(12): 55-61.
Ou Zhixin, Li Jixia, Deng Chunlan.Research on adaptive data fusion and correction based on fuzzy control theory set[J]. Electric Drive, 2023, 53(12): 55-61.
[18] 文英杰. 基于工况识别的PHEV自适应能量管理策略研究[D]. 长春: 吉林大学, 2022.
Wen Yingjie.Research on PHEV adaptive energy management strategy based on working condition identification[D]. Changchun: Jilin University, 2022.
[19] 陈维荣, 胡斌彬, 李奇, 等. 基于动态规划的混合动力有轨电车能量管理方法[J]. 西南交通大学学报, 2020, 55(5): 903-911.
Chen Weirong, Hu Binbin, Li Qi, et al.Energy management method for hybrid electric tram based on dynamic programming algorithm[J]. Journal of Southwest Jiaotong University, 2020, 55(5): 903-911.
[20] 王志福, 徐崧, 罗崴. 基于动态规划的燃料电池车能量管理策略研究[J]. 太阳能学报, 2023, 44(10): 550-556.
Wang Zhifu, Xu Song, Luo Wei.Research on energy management strategy of fuel cell vehicle based on dynamic programming[J]. Acta Energiae Solaris Sinica, 2023, 44(10): 550-556.
[21] Chen Minwu, Cheng Zhe, Liu Yuanli, et al.Multitime-scale optimal dispatch of railway FTPSS based on model predictive control[J]. IEEE Transac-tions on Transportation Electrification, 2020, 6(2): 808-820.
[22] Luo Jiaming, Gao Shibin, Wei Xiaoguang, et al.Parallel-reinforcement-learning-based online energy management strategy for energy storage traction substations in electrified railroad[J]. IEEE Transac-tions on Transportation Electrification, 2024, 10(1): 2112-2123.
[23] Wu Mei, Lin Yiqian, Jiang Tianfan, et al.MHGNet: multi-heterogeneous graph neural network for traffic prediction[C]//ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025: 1-5.
[24] Li He, Jin Duo, Li Xuejiao, et al.Multi-view spatial-temporal graph neural network for traffic predi-ction[J]. The Computer Journal, 2023, 66(10): 2393-2408.
[25] 张其, 陈旭, 王叔洋, 等. 动态图神经网络链接预测综述[J]. 计算机工程与应用, 2024, 60(20): 49-67.
Zhang Qi, Chen Xu, Wang Shuyang, et al.Survey of dynamic graph neural network for link prediction[J]. Computer Engineering and Applications, 2024, 60(20): 49-67.
[26] Wen Mingjian, Blau S M, Spotte-Smith E W C, et al. BonDNet: a graph neural network for the prediction of bond dissociation energies for charged mole-cules[J]. Chemical Science, 2021, 12(5): 1858-1868.
[27] 刘洪波, 王铎皓, 石鹏, 等. 基于图神经网络的多光伏场站出力短期时-空预测[J]. 电网与清洁能源, 2025, 41(1): 89-96.
Liu Hongbo, Wang Duohao, Shi Peng, et al.Short term time-space prediction of multi-photovoltaic plant output based on graph neural network[J]. Power System and Clean Energy, 2025, 41(1): 89-96.
[28] 白铂, 刘玉婷, 马驰骋, 等. 图神经网络[J]. 中国科学: 数学, 2020, 50(3): 367-384.
Bai Bo, Liu Yuting, Ma Chicheng, et al.Graph neural network[J]. Scientia Sinica (Mathematica), 2020, 50(3): 367-384.
[29] Luo Ruikang, Zhang Yicheng, Zhou Yao, et al.Deep learning approach for long-term prediction of electric vehicle (EV) charging station availability[C]//2021 IEEE International Intelligent Transportation Systems Conference (ITSC), Indianapolis, IN, USA, 2021: 3334-3339.
[30] 谢小瑜, 周俊煌, 张勇军, 等. 基于W-BiLSTM的可再生能源超短期发电功率预测方法[J]. 电力系统自动化, 2021, 45(8): 175-184.
Xie Xiaoyu, Zhou Junhuang, Zhang Yongjun, et al.W-BiLSTM based ultra-short-term generation power prediction method of renewable energy[J]. Auto-mation of Electric Power Systems, 2021, 45(8): 175-184.
[31] 张延宇, 张智铭, 刘春阳, 等. 基于动态自适应图神经网络的电动汽车充电负荷预测[J]. 电力系统自动化, 2024, 48(7): 86-93.
Zhang Yanyu, Zhang Zhiming, Liu Chunyang, et al.Electric vehicle charging load prediction based on dynamic adaptive graph neural network[J]. Auto-mation of Electric Power Systems, 2024, 48(7): 86-93.
[32] 陈恺, 付宇, 孙毅, 等. 基于计算热点转移的5G车联网能量实时协同管理策略[J]. 电工技术学报, 2024, 39(23): 7481-7497.
Chen Kai, Fu Yu, Sun Yi, et al.Online energy management strategy for 5G-vehicle network based on computing hotspot transfer[J]. Transactions of China Electrotechnical Society, 2024, 39(23): 7481-7497.
[33] 高锋阳, 苏红宇, 查鹏堂, 等. 基于工况预测和动力源寿命衰减协同的燃料电池有轨电车能量管理策略[J]. 电工技术学报, 2025, 40(13): 4316-4329.
Gao Fengyang, Su Hongyu, Zha Pengtang, et al.Energy management strategy for fuel cell hybrid tram system based on driving cycle prediction and power source lifespan decay synergy[J]. Transactions of China Electrotechnical Society, 2025, 40(13): 4316-4329.
[34] 王伟, 宋卫国, 刘士兴, 等. Kmeans聚类与多光谱阈值相结合的MODIS云检测算法[J]. 光谱学与光谱分析, 2011, 31(4): 1061-1064.
Wang Wei, Song Weiguo, Liu Shixing, et al.A cloud detection algorithm for MODIS images combining Kmeans clustering and multi-spectral threshold method[J]. Spectroscopy and Spectral Analysis, 2011, 31(4): 1061-1064.
[35] 李俊林, 符红光. 改进的基于核密度估计的数据分类算法[J]. 控制与决策, 2010, 25(4): 507-514.
Li Junlin, Fu Hongguang.Improved KDE-based data classification algorithm[J]. Control and Decision, 2010, 25(4): 507-514.
[36] Ta Xuxiang, Liu Zihan, Hu Xiao, et al.Adaptive spatio-temporal graph neural network for traffic forecasting[J]. Knowledge-Based Systems, 2022, 242: 108199.
[37] 王若冰. 基于多图结构和注意力机制的图卷积网络预测lncRNA-疾病关联[D]. 北京: 北京工业大学, 2024.
Wang Ruobing.Prediction of lncRNA-disease association by graph convolution network based on multi-graph structure and attention mechanism[D]. Beijing: Beijing University of Technology, 2024.
[38] Yu Yunluo, Li Wei.A hybrid short-term load forecasting method based on improved ensemble empirical mode decomposition and back propagation neural network[J]. Journal of Zhejiang University Science A, 2016, 17: 101-114.
[39] 顾雪平, 魏佳俊, 白岩松, 等. 基于分层模型预测控制的含风电电力系统恢复在线决策方法[J]. 电工技术学报, 2025, 40(5): 1471-1486.
Gu Xueping, Wei Jiajun, Bai Yansong, et al.Online decision-making method for wind power integrated power system restoration based on hierarchical model predictive control[J]. Transactions of China Electro-technical Society, 2025, 40(5): 1471-1486.
[40] 李蓉蓉. 高速铁路牵引变电所储能技术研究[D]. 成都: 西南交通大学, 2019.
Li Rongrong.Research on energy storage technology of traction substation of high-speed railway[D]. Chengdu: Southwest Jiaotong University, 2019.
[41] 毛业军, 文午. 基于改进动态规划算法的混合动力有轨电车能量管理策略[J]. 电力机车与城轨车辆, 2022, 45(5): 1-5.
Mao Yejun, Wen Wu.Energy management strategy of hybrid tram based on improved dynamic pro-gramming algorithm[J]. Electric Locomotives & Mass Transit Vehicles, 2022, 45(5): 1-5.