

浏览全部资源
扫码关注微信
1.上海交通大学国家电投智慧能源创新学院,上海市 200240
2.上海非碳基能源转换与利用研究院,上海市 200240
3.电力传输与功率变换控制教育部重点实验室(上海交通大学),上海市 200240
4.中国电力科学研究院有限公司,北京市 100192
5.国网上海市电力公司,上海市 200122
Received:22 April 2025,
Revised:2025-08-05,
Online First:22 October 2025,
Published:10 February 2026
移动端阅览
刘润龙,李亦言,周正昊等.考虑用户行为基于扩散模型的电动汽车充电场景生成[J].电力系统自动化,2026,50(3):135-144.
LIU Runlong,LI Yiyan,ZHOU Zhenghao,et al.Diffusion Model Based Electric Vehicle Charging Scenario Generation Considering User Behavior[J].Automation of Electric Power Systems,2026,50(3):135-144.
刘润龙,李亦言,周正昊等.考虑用户行为基于扩散模型的电动汽车充电场景生成[J].电力系统自动化,2026,50(3):135-144. DOI: 10.7500/AEPS20250422006.
LIU Runlong,LI Yiyan,ZHOU Zhenghao,et al.Diffusion Model Based Electric Vehicle Charging Scenario Generation Considering User Behavior[J].Automation of Electric Power Systems,2026,50(3):135-144. DOI: 10.7500/AEPS20250422006.
针对大规模电动汽车无序充电对配电网稳定运行带来的挑战,提出一种基于条件去噪扩散概率模型的电动汽车充电场景生成方法。首先,构建多维用户行为特征矩阵和集群用户行为特征矩阵,提出考虑用户行为的多层级充电场景生成框架;然后,设计融合多头自注意力机制的条件去噪扩散概率模型,将用户行为特征作为条件嵌入扩散过程,挖掘用户行为与充电场景间的潜在关联,实现对充电场景的可控生成;最后,基于真实充电数据集开展用户级与站级场景生成实验。结果表明,所提方法在保真度、多样性和时序关联性等方面均优于基准模型。此外,选用中国上海市浦东新区场站数据集,通过日前市场投标优化案例验证了所提方法对实际工程的支撑价值。
To address the challenges posed by large-scale disordered electric vehicle (EV) charging on the stable operation of distribution networks
this paper proposes an EV charging scenario generation method based on conditional denoising diffusion probabilistic models. Firstly
a multidimensional user behavior characteristic matrix and a cluster-level user behavior characteristic matrix are constructed
and a hierarchical charging scenario generation framework considering user behavior is proposed. Secondly
a conditional diffusion model fused with a multi-head self-attention mechanism is designed
embedding user behavior characteristics as conditions into the diffusion process to explore the latent correlations between user behavior and charging scenarios
thereby achieving the controllable generation of charging scenarios. Finally
user-level and station-level scenario generation experiments are conducted based on real-world charging datasets. The results demonstrate that the proposed method outperforms baseline models in fidelity
diversity
and temporal correlation. Additionally
a case study using the charging station dataset from Pudong New Area
Shanghai
China
verifies the practical engineering value of the proposed method in day-ahead market bidding optimization.
国务院办公厅 . 新能源汽车产业发展规划 ( 2021 — 2035 年)[EB/OL].[ 2025-04-11 ]. https://www.gov.cn/zhengce/zhengceku/2020-11/02/content_5556716.htm https://www.gov.cn/zhengce/zhengceku/2020-11/02/content_5556716.htm .
General Office of the State Council . Development plan for the new energy vehicle industry ( 2021 — 2035 )[EB/OL]. [ 2025-04-11 ]. https://www.gov.cn/zhengce/zhengceku/2020-11/02/content_5556716.htm https://www.gov.cn/zhengce/zhengceku/2020-11/02/content_5556716.htm .
中华人民共和国公安部 . 全国机动车保有量达4.53亿辆 [EB/OL].[ 2025-04-11 ]. https://www.mps.gov.cn/n2254314/n6409334/n9194010/c9939035/content.html https://www.mps.gov.cn/n2254314/n6409334/n9194010/c9939035/content.html .
Ministry of Public Security of the People’s Republic of China . The number of motor vehicles in the country has reached 453 million [EB/OL]. [ 2025-04-11 ]. https://www.mps.gov.cn/n2254314/n6409334/n9194010/c9939035/content.html https://www.mps.gov.cn/n2254314/n6409334/n9194010/c9939035/content.html .
MUDIYANSELAGE M W , AGHDAM F H , KAZEMI-RAZI S M , et al . A multiagent framework for electric vehicles charging power forecast and smart planning of urban parking lots [J]. IEEE Transactions on Transportation Electrification , 2023 , 10 ( 2 ): 2844 - 2857 .
WU Y J , CONG P Z , WANG Y L . Charging load forecasting of electric vehicles based on VMD-SSA-SVR [J]. IEEE Transactions on Transportation Electrification , 2023 , 10 ( 2 ): 3349 - 3362 .
缪鹏彬 , 余娟 , 史乐峰 , 等 . 基于改进非参数核密度估计和拉丁超立方抽样的电动公共客车负荷模型 [J]. 电工技术学报 , 2016 , 31 ( 4 ): 187 - 193 .
MIAO Pengbin , YU Juan , SHI Lefeng , et al . Electric public bus load model based on improved kernel density estimation and Latin hypercube sampling [J]. Transactions of China Electrotechnical Society , 2016 , 31 ( 4 ): 187 - 193 .
ZHANG T Y , CHEN X , YU Z , et al . A Monte Carlo simulation approach to evaluate service capacities of EV charging and battery swapping stations [J]. IEEE Transactions on Industrial Informatics , 2018 , 14 ( 9 ): 3914 - 3923 .
LI J H , ZHOU J S , CHEN B . Review of wind power scenario generation methods for optimal operation of renewable energy systems [J]. Applied Energy , 2020 , 280 : 115992 .
钱涛 , 任孟极 , 邵成成 , 等 . 基于深度学习考虑出行模式的电动汽车充电负荷场景生成 [J]. 电力系统自动化 , 2022 , 46 ( 12 ): 67 - 75 .
QIAN Tao , REN Mengji , SHAO Chengcheng , et al . Deep-learning-based electric vehicle charging load scenario generation considering travel mode [J]. Automation of Electric Power Systems , 2022 , 46 ( 12 ): 67 - 75 .
JAHANGIR H , GOUGHERI S S , VATANDOUST B , et al . A novel cross-case electric vehicle demand modeling based on 3D convolutional generative adversarial networks [J]. IEEE Transactions on Power Systems , 2022 , 37 ( 2 ): 1173 - 1183 .
赵厚翔 , 沈晓东 , 吕林 , 等 . 基于GAN的负荷数据修复及其在EV短期负荷预测中的应用 [J]. 电力系统自动化 , 2021 , 45 ( 16 ): 143 - 151 .
ZHAO Houxiang , SHEN Xiaodong , LYU Lin , et al . Load data restoration based on generative adversarial network and its application in short-term load forecasting of electric vehicle [J]. Automation of Electric Power Systems , 2021 , 45 ( 16 ): 143 - 151 .
ZHOU Z H , LI Y Y , LIU R L , et al . Unsupervised and controllable synthesizing for imbalanced energy dataset based on AC-InfoGAN [J]. Applied Energy , 2025 , 393 : 126107 .
杨震 , 杨晶显 , 王凯 , 等 . 基于去噪扩散概率模型的水-光互补系统随机场景生成方法 [J]. 电力系统自动化 , 2024 , 48 ( 19 ): 171 - 180 .
YANG Zhen , YANG Jingxian , WANG Kai , et al . Stochastic scenario generation method based on denoising diffusion probabilistic model for hydro-photovoltaic complementary system [J]. Automation of Electric Power Systems , 2024 , 48 ( 19 ): 171 - 180 .
戴宇欣 , 张俊 , 乔骥 , 等 . 基于改进去噪扩散概率模型和模型迁移的新能源场站超短期出力场景生成 [J]. 电网技术 , 2025 , 49 ( 2 ): 511 - 521 .
DAI Yuxin , ZHANG Jun , QIAO Ji , et al . Ultra-short-term output scenario generation for renewable energy plants based on improved denoising diffusion probabilistic models and model-based transfer learning [J]. Power System Technology , 2025 , 49 ( 2 ): 511 - 521 .
DONG X C , MAO Z H , SUN Y Y , et al . Short-term wind power scenario generation based on conditional latent diffusion models [J]. IEEE Transactions on Sustainable Energy , 2023 , 15 ( 2 ): 1074 - 1085 .
窦迅 , 牛鹏艺 , 郑亚先 , 等 . 基于改进扩散模型的涵盖极端形态负荷场景生成方法 [J/OL]. 中国电机工程学报 [ 2024-12-31 ]. https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.241362 https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.241362 .
DOU Xun , NIU Pengyi , ZHENG Yaxian , et al . Scenario generation method covering extreme form load based on improved diffusion model [J/OL]. Proceedings of the CSEE [ 2024-12-31 ]. https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.241362 https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.241362 .
LI S Y , XIONG H , CHEN Y Z . DiffCharge: generating EV charging scenarios via a denoising diffusion model [J]. IEEE Transactions on Smart Grid , 2024 , 15 ( 4 ): 3936 - 3949 .
徐俊俊 , 程奕凌 , 张腾飞 , 等 . 计及充电行为特征与可调性的电动汽车集群优化调度 [J]. 电力系统自动化 , 2023 , 47 ( 23 ): 23 - 32 .
XU Junjun , CHENG Yiling , ZHANG Tengfei , et al . Optimal scheduling of electric vehicle clusters considering characteristics and adjustability of charging behavior [J]. Automation of Electric Power Systems , 2023 , 47 ( 23 ): 23 - 32 .
HO J , JAIN A , ABBEEL P . Denoising diffusion probabilistic models [J]. Advances in Neural Information Processing Systems , 2020 , 33 : 6840 - 6851 .
KINGMA D P , WELLING M . Auto-encoding variational Bayes [EB/OL]. [ 2025-01-11 ]. https://arxiv.org/abs/1312.6114 https://arxiv.org/abs/1312.6114 .
TASHIRO Y , SONG J , SONG Y , et al . CSDI: conditional score-based diffusion models for probabilistic time series imputation [C]// 35th International Conference on Neural Information Processing Systems , December 6-14 , 2021 .
SAHARIA C , HO J , CHAN W , et al . Image super-resolution via iterative refinement [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 4 ): 4713 - 4726 .
KONG Z , PING W , HUANG J , et al . Diffwave: a versatile diffusion model for audio synthesis [EB/OL]. [ 2025-01-11 ]. https://arxiv.org/abs/2009.09761 https://arxiv.org/abs/2009.09761 .
CAPEL E H , DUMAS J . Denoising diffusion probabilistic models for probabilistic energy forecasting [C]// 2023 IEEE Belgrade PowerTech , June 25-29 , 2023 , Belgrade, Serbia .
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [EB/OL]. [ 2025-01-11 ]. https://arxiv.org/abs/1706.03762 https://arxiv.org/abs/1706.03762 .
LEE Z J , LI T X , LOW S H . ACN-data: analysis and applications of an open EV charging dataset [C]// 10th ACM International Conference on Future Energy Systems , June 15 , 2019, Phoenix, USA .
LI Y Z , HE S Y , LI Y , et al . Probabilistic charging power forecast of EVCS: reinforcement learning assisted deep learning approach [J]. IEEE Transactions on Intelligent Vehicles , 2022 , 8 ( 1 ): 344 - 357 .
CHEN Y , WANG Y , KIRSCHEN D , et al . Model-free renewable scenario generation using generative adversarial networks [J]. IEEE Transactions on Power Systems , 2018 , 33 ( 3 ): 3265 - 3275 .
JI D Y , CHEN L D , MA T Y , et al . Research on adaptability of charging strategy for electric vehicle power battery [J]. Journal of Power Sources , 2019 , 437 : 226911 .
赵明宇 , 徐石明 , 高辉 , 等 . 基于模糊 K -means算法的电动汽车应急供电策略 [J]. 电力系统自动化 , 2016 , 40 ( 5 ): 91 - 95 .
ZHAO Mingyu , XU Shiming , GAO Hui , et al . Strategy of electric vehicle emergency power supply based on fuzzy K -means algorithm [J]. Automation of Electric Power Systems , 2016 , 40 ( 5 ): 91 - 95 .
LI Y , LI J Z , WANG Y . Privacy-preserving spatiotemporal scenario generation of renewable energies: a federated deep generative learning approach [J]. IEEE Transactions on Industrial Informatics , 2022 , 18 ( 4 ): 2310 - 2320 .
张文强 , 陈静 , 杨伟 , 等 . 基于VAE-CGAN的光伏不确定性建模方法 [J]. 电网技术 , 2021 , 45 ( 4 ): 1273 - 1280 .
ZHANG Wenqiang , CHEN Jing , YANG Wei , et al . Photovoltaic uncertainty modeling based on VAE-CGAN [J]. Power System Technology , 2021 , 45 ( 4 ): 1273 - 1280 .
董骁翀 , 孙英云 , 蒲天骄 . 基于条件生成对抗网络的可再生能源日前场景生成方法 [J]. 中国电机工程学报 , 2020 , 40 ( 17 ): 5527 - 5536 .
DONG Xiaochong , SUN Yingyun , PU Tianjiao . Day-ahead scenario generation of renewable energy based on conditional GAN [J]. Proceedings of the CSEE , 2020 , 40 ( 17 ): 5527 - 5536 .
JAHANGIR H , GOUGHERI S S , VATANDOUST B , et al . Plug-in electric vehicle behavior modeling in energy market: a novel deep learning-based approach with clustering technique [J]. IEEE Transactions on Smart Grid , 2020 , 11 ( 6 ): 4738 - 4748 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621