Improved Informer Based Multi-timescale Spatio-temporal Distribution Prediction of Electric Vehicle Schedulable Capacity

MAO Meiqin; LIU Zhibo; WANG Jiwen; ZHU Minglei; DU Yan; SHI Yong

doi:10.7500/AEPS20241216002

您当前的位置：

首页 >

文章列表页 >

Improved Informer Based Multi-timescale Spatio-temporal Distribution Prediction of Electric Vehicle Schedulable Capacity

Key Technologies and Practical Applications of Vehicle\-to\-Grid in New Power System | 更新时间：2026-08-21

- Improved Informer Based Multi-timescale Spatio-temporal Distribution Prediction of Electric Vehicle Schedulable Capacity
- Automation of Electric Power Systems Vol. 50, Issue 15, Pages: 123-133(2026)
- 作者机构：
  
  1.教育部光伏系统工程研究中心，合肥工业大学，安徽省合肥市 230009
  2.国网安徽省电力有限公司，安徽省合肥市 230022
  3.国网安徽省电动汽车服务有限公司，安徽省合肥市 230000
  4.功率半导体封装与可靠性安徽省重点实验室，安徽省合肥市 230009
- 作者简介：
- 基金信息：
  
  Anhui Province Natural Science Foundation(2108085UD02);National Natural Science Foundation of China(51577047);Program of Introducing Talents of Discipline to Universities (“111” Program)(BP0719039)
- DOI：10.7500/AEPS20241216002
  CLC：
- Received：16 December 2024，
  
  Revised：2025-04-09，
  
  Online First：04 March 2026，
  
  Published：10 August 2026
- 稿件说明：
移动端阅览
茆美琴,刘志博,王吉文等.基于改进Informer的多时间尺度电动汽车可调度容量时空分布预测[J].电力系统自动化,2026,50(15):123-133.

MAO Meiqin,LIU Zhibo,WANG Jiwen,et al.Improved Informer Based Multi-timescale Spatio-temporal Distribution Prediction of Electric Vehicle Schedulable Capacity[J].Automation of Electric Power Systems,2026,50(15):123-133.
茆美琴,刘志博,王吉文等.基于改进Informer的多时间尺度电动汽车可调度容量时空分布预测[J].电力系统自动化,2026,50(15):123-133. DOI： 10.7500/AEPS20241216002.

MAO Meiqin,LIU Zhibo,WANG Jiwen,et al.Improved Informer Based Multi-timescale Spatio-temporal Distribution Prediction of Electric Vehicle Schedulable Capacity[J].Automation of Electric Power Systems,2026,50(15):123-133. DOI： 10.7500/AEPS20241216002.

摘要

高精度和细粒度的电动汽车(EV)可调度容量多时间尺度预测对大规模EV参与电网辅助服务具有重要意义。然而，现有EV可调度容量预测在预测序列较长时，存在预测精度和效率显著降低的问题。为此，面向电力系统多调度场景需求，文中提出一种改进Informer算法，构建EV聚合商日前、超短时和实时的多时间尺度聚合可调度容量预测模型。首先，将大规模单个EV充电记录处理得到的EV聚合商历史可调度容量数据作为改进Informer预测算法的数据集；其次，采用卷积稀疏注意力机制代替传统Informer算法中的注意力机制，构建改进Informer预测算法，提高其捕获历史时间序列趋势信息的能力，从而提升长序列的预测精度；最后，以某市50余万条实际历史充电记录作为样本，在多时间尺度和空间维度下对所提模型进行验证。结果表明，所提方法可以显著提升不同时间尺度的预测精度，并降低长序列的预测时间。

Abstract

High-precision and fine-grained multi-timescale prediction of electric vehicle (EV) schedulable capacity is of great significance for large-scale EV participating in power grid ancillary services. However

existing EV schedulable capacity prediction algorithms suffer from a significant reduction in prediction accuracy and efficiency when the prediction sequences are long. To address the requirements of multiple dispatching scenarios in the power system

this paper proposes an improved Informer algorithm to construct a multi-timescale

aggregated

schedulable capacity prediction model for electric vehicle aggregators (EVAs) in terms of day-ahead

ultra-short-term

and real-time scales. First

the historical schedulable capacity data of EVAs obtained from processing large-scale individual EV charging records is used as the data set of the improved Informer prediction algorithm. Then

the convolutional sparse attention mechanism is used to replace the attention mechanism in the traditional Informer algorithm

and an improved Informer algorithm is constructed to enhance its performance in capturing trend information of historical time sequences

thereby improving the prediction accuracy of long sequences. Finally

more than half a million actual historical charging records of EVs in a city are used as samples to validate the proposed model at multiple timescales and spatial dimensions. The results show that the proposed method significantly improves the prediction accuracy on different timescales as well as reduces the prediction time of long sequences.

关键词

Keywords

references

新华社：超 3 000 万辆！我国新能源汽车保有量高速增长［EB/OL］.（ 2025-01-11 ）［ 2025-03-01 ］. https：//www.gov.cn/zhengce/jiedu/tujie/202501/content_6999527.htm https://www.gov.cn/zhengce/jiedu/tujie/202501/content_6999527.htm .

Xinhua News Agency： over 30 million vehicles！ The number of new energy vehicles in China is growing rapidly ［EB/OL］. （ 2025-01-11 ）［ 2025-03-01 ］. https：//www.gov.cn/zhengce/jiedu/tujie/202501/content_6999527.htm https://www.gov.cn/zhengce/jiedu/tujie/202501/content_6999527.htm .

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 .

王杨洋，茆美琴，杨铖，等 . 面向多场景辅助服务的大规模电动汽车聚合可调度容量建模［J］. 电力系统自动化， 2024 ， 48 （ 7 ）： 103 - 115 .

WANG Yangyang ， MAO Meiqin ， YANG Cheng ， et al . Aggregated and schedulable capacity modeling of large-scale electric vehicles for multi-scenario auxiliary services ［J］. Automation of Electric Power Systems ， 2024 ， 48 （ 7 ）： 103 - 115 .

潘建辉，张宁，雍培，等 . 面向海量灵活性资源的两阶段分布式协同调度方法［J］. 电力系统自动化， 2023 ， 47 （ 15 ）： 67 - 79 .

PAN Jianhui ， ZHANG Ning ， YONG Pei ， et al . Two-stage distributed collaborative dispatching method for massive flexible resources ［J］. Automation of Electric Power Systems ， 2023 ， 47 （ 15 ）： 67 - 79 .

WANG Y C ， SHI P ， CHEN G ， et al . A multi-time scale schedulable capacity evaluation method for stations considering user wishes ［J］. Energy Reports ， 2023 ， 9 ： 321 - 325 .

文欣，黄学良，高山，等 . 考虑区域差异性的电动私家车网格化充电需求预测［J］. 电力系统自动化， 2025 ， 49 （ 7 ）： 158 - 168 .

WEN Xin ， HUANG Xueliang ， GAO Shan ， et al . Grid charging demand forecasting for private electric vehicles considering regional differences ［J］. Automation of Electric Power Systems ， 2025 ， 49 （ 7 ）： 158 - 168 .

LAM A Y S ， LEUNG K C ， LI V O K . Capacity estimation for vehicle-to-grid frequency regulation services with smart charging mechanism ［J］. IEEE Transactions on Smart Grid ， 2016 ， 7 （ 1 ）： 156 - 166 .

VARSHOSAZ F ， MOAZZAMI M ， FANI B ， et al . Day-ahead capacity estimation and power management of a charging station based on queuing theory ［J］. IEEE Transactions on Industrial Informatics ， 2019 ， 15 （ 10 ）： 5561 - 5574 .

WANG M S ， MU Y F ， LI F X ， et al . State space model of aggregated electric vehicles for frequency regulation ［J］. IEEE Transactions on Smart Grid ， 2020 ， 11 （ 2 ）： 981 - 994 .

WANG Y Y ， MAO M Q ， CHANG L C . Multi-time scales prediction of aggregated schedulable capacity of electric vehicle fleets based on enhanced Prophet-LGBM algorithm ［J］. Applied Energy ， 2024 ， 374 ： 124018 .

MAO M Q ， ZHANG S L ， CHANG L C ， et al . Schedulable capacity forecasting for electric vehicles based on big data analysis ［J］. Journal of Modern Power Systems and Clean Energy ， 2019 ， 7 （ 6 ）： 1651 - 1662 .

LI S Q ， GU C H ， LI J W ， et al . Boosting grid efficiency and resiliency by releasing V2G potentiality through a novel rolling prediction-decision framework and deep-LSTM algorithm ［J］. IEEE Systems Journal ， 2020 ， 15 （ 2 ）： 2562 - 2570 .

NOGAY H S . Estimating the aggregated available capacity for vehicle to grid services using deep learning and nonlinear autoregressive neural network ［J］. Sustainable Energy， Grids and Networks ， 2022 ， 29 ： 100590 .

SHEN L ， WANG Y Z . TCCT： Tightly-coupled convolutional transformer on time series forecasting ［J］. Neurocomputing ， 2022 ， 480 ： 131 - 145 .

VASWANI A ， SHAZEER N M ， PARMAR N ， et al . Attention is all you need ［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems ， December 4-9 ， 2017 ， Long Beach， USA .

骆钊，吴谕侯，朱家祥，等 . 基于多尺度时间序列块自编码Transformer神经网络模型的风电超短期功率预测［J］. 电网技术， 2023 ， 47 （ 9 ）： 3527 - 3537 .

LUO Zhao ， WU Yuhou ， ZHU Jiaxiang ， et al . Wind power forecasting based on multi-scale time series block auto-encoder transformer neural network model ［J］. Power System Technology ， 2023 ， 47 （ 9 ）： 3527 - 3537 .

HU J J ， ZHOU H ， ZHOU Y H ， et al . Flexibility prediction of aggregated electric vehicles and domestic hot water systems in smart grids ［J］. Engineering ， 2021 ， 7 （ 8 ）： 1101 - 1114 .

任惠，陈萍，韩璐，等 . 共享电动汽车可调度容量时空预测［J］. 电网技术， 2023 ， 47 （ 7 ）： 2732 - 2743 .

REN Hui ， CHEN Ping ， HAN Lu ， et al . Spatio-temporal forecasting of schedulable capacity of shared electric vehicles ［J］. Power System Technology ， 2023 ， 47 （ 7 ）： 2732 - 2743 .

ZHOU H Y ， ZHANG S H ， PENG J Q ， et al . Informer： beyond efficient transformer for long sequence time-series forecasting ［J］. Proceedings of the AAAI Conference on Artificial Intelligence ， 2021 ， 35 （ 12 ）： 11106 - 11115 .

赵洪山，林诗雨，孙承妍，等 . 考虑多时间尺度信息的风力发电机滚动轴承故障预测［J］. 中国电机工程学报， 2024 ， 44 （ 22 ）： 8908 - 8920 .

ZHAO Hongshan ， LIN Shiyu ， SUN Chengyan ， et al . Fault prediction of wind turbine rolling bearing considering multi-time scale information ［J］. Proceedings of the CSEE ， 2024 ， 44 （ 22 ）： 8908 - 8920 .

裴振坤，王学梅，康龙云 . 电动汽车参与电网辅助服务的控制策略综述［J］. 电力系统自动化， 2023 ， 47 （ 18 ）： 17 - 32 .

PEI Zhenkun ， WANG Xuemei ， KANG Longyun . Review on control strategies for electric vehicles participating in ancillary services of power grid ［J］. Automation of Electric Power Systems ， 2023 ， 47 （ 18 ）： 17 - 32 .

关于发布《可调节负荷并网运行与控制技术规范》系列 13 项电力行业标准报批稿的通知［EB/OL］.（ 2022-01-20 ）［ 2025-03-01 ］. https：//news.bjx.com.cn/html/20220120/1200478.shtml https://news.bjx.com.cn/html/20220120/1200478.shtml .

Notice on issuing the approval draft of 13 electric power industry standards in the “technical specification for grid-connected operation and control of adjustable load” series ［EB/OL］. （ 2022-01-20 ）［ 2025-03-01 ］. https：//news.bjx.com.cn/html/20220120/1200478.shtml https://news.bjx.com.cn/html/20220120/1200478.shtml .

胡俊杰，陆家悦，马文帅，等 . 面向电网调峰的电动汽车聚合商多层级实时控制策略［J］. 电力系统自动化， 2024 ， 48 （ 22 ）： 84 - 95 .

HU Junjie ， LU Jiayue ， MA Wenshuai ， et al . Multi-layer real-time control strategy of electric vehicle aggregators for peak regulation of power grid ［J］. Automation of Electric Power Systems ， 2024 ， 48 （ 22 ）： 84 - 95 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Vehicle-to-Grid for Large-scale Applications: Practical Progress, Key Bottlenecks, and Technical Pathways

Optimal Low-carbon Scheduling with Vehicle-Grid Spatio-temporal Coordination Considering Carbon Quotas for Life Cycle of Electric Vehicles

Convexification of Charging and Discharging Model and Constraint Set Contraction Method for Accurate Electric Vehicle Aggregation

Review of Key Vehicle-side Technologies for Vehicle-to-Grid

Decision-making Method of Risk Emergency Coordination for Urban Distribution and Drainage Networks Considering Spatio-Temporal Nonuniformity of Rainstorms

Related Author

HUANG Xueliang

LIU Yongdong

ZHANG Ziqi

GONG Chengming

GAO Shan

YAO Hanyi

WANG Zicheng

WANG Mingshen

Related Institution

School of Electrical Engineering, Southeast University

Standardization Center, China Electricity Council

NARI School of Electrical and Automation Engineering, Nanjing Normal University

DERI-TELD Energy Research Institute Co., Ltd.

School of Electric Power Engineering, Nanjing Institute of Technology

⁰