[1]韩　涛,丁乐言,马　明,等.基于参数优化和注意力机制的电动汽车充电负荷预测[J].郑州大学学报(工学版),2026,47(02):85-93.[doi:10.13705/j.issn.1671-6833.2026.02.001]
　HAN Tao,DING Leyan,MA Ming,et al.Charging Load Prediction for Electric Vehicle Based on Parameter Optimization and Attention Mechanism[J].Journal of Zhengzhou University (Engineering Science),2026,47(02):85-93.[doi:10.13705/j.issn.1671-6833.2026.02.001]
点击复制

基于参数优化和注意力机制的电动汽车充电负荷预测()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
47
期数:
2026年02期
页码:
85-93
栏目:
出版日期:
2026-02-13

文章信息/Info

Title:
Charging Load Prediction for Electric Vehicle Based on Parameter Optimization and Attention Mechanism
文章编号:
1671-6833(2026)02-0085-09
作者:
韩　涛1;  丁乐言2;  马　明1;  颜　安3;  潘中奇3;  颜　俊3;  杨　军2
1.中国长江电力股份有限公司,北京 100032;2.武汉大学 电气与自动化学院,湖北 武汉 430072;3.中国长江三峡集团有限公司,湖北 武汉 430010
Author(s):
HAN Tao1;  DING Leyan2;  MA Ming1;  YAN An3;  PAN Zhongqi3;  YAN Jun3;  YANG Jun2
1.China Yangtze Power Co., Ltd., Beijing 100032; 2.School of Electrical Engineering, Wuhan University, Wuhan 430072;3.China Three Gorges Corporation, Wuhan 430010
关键词:
电动汽车;  负荷预测;  深度学习;  组合预测;  特征筛选;  参数优化
Keywords:
electric vehicle;  load forecasting;  deep learning;  combination forecasting;  feature selection;  parameter optimization
分类号:
TM73
DOI:
10.13705/j.issn.1671-6833.2026.02.001
文献标志码:
A
摘要:
在规模化电动汽车(electric vehicle, EV)充电负荷接入配电网的背景下,EV充电行为的时空不确定性导致传统预测方法难以准确刻画其动态特性,直接影响配电网运行优化与充电调度决策的有效性。针对EV充电负荷时序依赖性强、影响因素复杂等问题,提出了一种基于参数优化和注意力机制(attention mechanism, AM)的EV充电负荷预测方法。首先,应用皮尔逊偏相关系数对输入数据进行特征筛选(feature screening, FS),并引入AM改进CNN网络,构建CNNAM网络;其次,提出EV充电负荷CNNAM-BiLSTM组合预测模型,其利用多层卷积层、AM和BiLSTM双向结构提升了对充电负荷特征数据和时间序列的挖掘力度;再次,利用麻雀搜索算法(sparrow search algorithm, SSA)自适应优化预测模型中的超参数;最后,基于武汉市实际充电站负荷数据,将所提SSA-FS-CNNAMBiLSTM组合预测模型与传统深度学习预测模型、组合预测模型进行对比。结果表明:所提预测算法能取得更优的预测效果并在复杂动态环境中具备更强的适应性。
Abstract:
In the context of large-scale electric vehicle (EV) charging load of to the distribution network, the spatio-temporal uncertainty of EV charging behavior makes it difficult for traditional prediction methods to accurately describe its dynamic characteristics, which directly affects the effectiveness of distribution network operation optimization and charging scheduling decisions. In order to solve the problem of strong dependence on the timing of EV charging load and complex influencing factors, a charging load prediction method for EVs based on parameter optimization and attention mechanism (AM) was proposed. Firstly, the input feature data were screened by Pearson for feature screening (FS). Then, based on the CNN network, an improved AM network was introduced to construct the CNNAM network. Furthermore, an EV charge load CNNAM-BiLSTM combined forecasting model was proposed, which used a multi-layer convolution layer, AM, and two-way structure of BiLSTM to improve the mining of charge load characteristic data and time series, and sparrow search algorithm (SSA) to adaptively optimize the parameters in the forecasting model. Finally, based on the actual load data of charging stations in Wuhan, the SSAFS-CNNAM-BiLSTM combination forecasting model proposed was compared with the traditional deep learning forecasting model and combination forecasting model. The results showed that the proposed forecasting method achieved better forecasting results and had stronger adaptability in the complex dynamic environment.

参考文献/References:

[1]HUANG N T, HE Q K, QI J J, et al. Multinodes interval electric vehicle day-ahead charging load forecasting based on joint adversarial generation[J]. International Journal of Electrical Power & Energy Systems, 2022, 143: 108404.

[2]孙国强, 徐广开, 沈培锋, 等. 规模化电动汽车负荷的柔性台区协同经济调度[J]. 电网技术, 2020, 44(11): 4395-4404.
SUN G Q, XU G K, SHEN P F, et al. Coordinated economic dispatch of flexible district for large-scale electric vehicle load[J]. Power System Technology, 2020, 44(11): 4395-4404.
[3]孙辉, 沈钟浩, 周玮, 等. 电动汽车群响应的主动配电网阻塞调度研究[J]. 中国电机工程学报, 2017, 37(19): 5549-5559,5832.
SUN H, SHEN Z H, ZHOU W, et al. Congestion dispatch research of active distribution network with electric vehicle group response[J]. Proceedings of the CSEE, 2017, 37(19): 5549-5559,5832.
[4]YANG T Y, GUO Q L, XU L, et al. Dynamic pricing for integrated energy-traffic systems from a cyber-physicalhuman perspective[J]. Renewable and Sustainable Energy Reviews, 2021, 136: 110419.
[5]XU Y Y, ÇOLAK S, KARA E C, et al. Planning for electric vehicle needs by coupling charging profiles with urban mobility[J]. Nature Energy, 2018, 3(6): 484493.
[6]BAO Z Y, HU Z C, KAMMEN D M, et al. Data-driven approach for analyzing spatiotemporal price elasticities of EV public charging demands based on conditional random fields[J]. IEEE Transactions on Smart Grid, 2021, 12(5): 4363-4376.
[7]祁宇轩, 范俊岩, 吴定会, 等. 基于相似日与BiLSTM组合的短期电力负荷预测[J]. 控制理论与应用, 2024, 41(12): 2304-2314.
QI Y X, FAN J Y, WU D H, et al. Short term power load forecasting based on the combination of similar days and BiLSTM[J]. Control Theory & Applications, 2024, 41(12): 2304-2314.
[8]丁乐言, 柯松, 张帆, 等. 考虑出行需求和引导策略的电动汽车充电负荷预测[J]. 电力建设, 2024, 45(6): 10-26. 
DING L Y, KE S, ZHANG F, et al. Forecasting of electric-vehicle charging load considering travel demand and guidance strategy [J]. Electric Power Construction, 2024, 45(6): 10-26.
[9]李宏伟, 宋玉峰, 李帅兵, 等. 基于ArcGIS路网结构与交通拥挤度分析的电动汽车充电负荷预测方法[J]. 电网技术, 2025, 49(5): 1920-1930.
LI H W, SONG Y F, LI S B, et al. Electric vehicle charging load prediction based on ArcGIS road network structure and traffic congestion analysis[J]. Power System Technology, 2025, 49(5): 1920-1930.
[10]龙雪梅, 杨军, 吴赋章, 等. 考虑路网-电网交互和用户心理的电动汽车充电负荷预测[J]. 电力系统自动化, 2020, 44(14): 86-93.
LONG X M, YANG J, WU F Z, et al. Prediction of electric vehicle charging load considering interaction between road network and power grid and user′s psychology[J]. Automation of Electric Power Systems, 2020, 44(14): 86-93.
[11]张美霞, 孙铨杰, 杨秀. 考虑多源信息实时交互和用户后悔心理的电动汽车充电负荷预测[J]. 电网技术, 2022, 46(2): 632-645. 
ZHANG M X, SUN Q J, YANG X. Electric vehicle charging load prediction considering multi-source information real-time interaction and user regret psychology[J]. Power System Technology, 2022, 46(2): 632-645.
[12] XIONG J L, PENG T, TAO Z H, et al. A dual-scale deep learning model based on ELM-BiLSTM and improved reptile search algorithm for wind power prediction[J]. Energy, 2023, 266: 126419.
[13]孙庆凯, 王小君, 张义志, 等. 基于LSTM和多任务学习的综合能源系统多元负荷预测[J]. 电力系统自动化, 2021, 45(5): 63-70. 
SUN Q K, WANG X J, ZHANG Y Z, et al. Multiple load prediction of integrated energy system based on long short-term memory and multi-task learning[J]. Automation of Electric Power Systems, 2021, 45(5): 63-70.
[14]赵倩, 郑贵林. 基于WD-LSSVM-LSTM模型的短期电力负荷预测[J]. 电测与仪表, 2023, 60(1): 23-28.
ZHAO Q, ZHENG G L. Short-term load forecasting based on WD-LSSVM-LSTM model[J]. Electrical Measurement & Instrumentation, 2023, 60(1): 23-28.
[15]杨龙, 吴红斌, 丁明, 等. 新能源电网中考虑特征选择的Bi-LSTM网络短期负荷预测[J]. 电力系统自动化, 2021, 45(3): 166-173.
YANG L, WU H B, DING M, et al. Short-term load forecasting in renewable energy grid based on bi-directional long short-term memory network considering feature selection[J]. Automation of Electric Power Systems, 2021, 45(3): 166-173.
[16]谢文举, 薛贵军, 白宇. 基于PSO-CNN-LSTM的短期热负荷预测模型[J]. 计算机仿真, 2024, 41(4): 102107,278.
XIE W J, XUE G J, BAI Y. Short-time heating load prediction model based on PSO-CNN-LSTM[J]. Computer Simulation, 2024, 41(4): 102-107,278.
[17]保拉, 李庆兵, 侯保建, 等. 基于改进多核极限学习机算法的电力负荷预测方法研究[J]. 电工技术, 2024(22): 39-42.
BAO L, LI Q B, HOU B J, et al. Modified multi-kernel extreme learning machine-based electric load prediction[J]. Electric Engineering, 2024(22): 39-42.
[18]刘翘楚, 王杰, 秦文萍, 等. 基于嵌套优化的GAPSO-BP神经网络短期风功率预测方法研究[J]. 电网与清洁能源, 2025, 41(2): 138-146.
LIU Q C, WANG J, QIN W P, et al. Research on shortterm wind power prediction methods based on GA-PSOPB neural network with nested optimization[J]. Power System and Clean Energy, 2025, 41(2): 138-146.
[19]陈振宇, 杨斌, 阮文俊, 等. 基于LSTM神经网络的短期电能负荷预测[J]. 电力大数据, 2021, 24(4): 8-15.
CHEN Z Y, YANG B, RUAN W J, et al. Short-term power load forecasting based on LSTM neural network[J]. Power Systems and Big Data, 2021, 24(4): 8-15.
[20]高明,郝妍.基于BiLSTM网络与误差修正的超短期负荷预测[J].综合智慧能源,2023,45(1):31-40.
GAO P F, HAO Y. Ultra-short-term load forecasting based on BiLSTM network and error correction[J]. Integrated Intelligent Energy, 2023, 45(1):31-40.
[21]昌志阳,朱飞,高斯佳,等.应用CNN-BiLSTM-SE Attention模型预测电池超声测厚间隙[J].中国测试,2025,51(9):158-166.
CHANG Z Y, ZHU F, GAO S J, et al. Gap prediction for electromagnetic ultrasonic thickness measurement based on CNN-BiLSTM-SE Attention model[J]. China Measurement & Test, 2025,51(9):158-166. 
[22]熊鹏飞,张赛,王宪军.基于波动特征提取的CNN-BiLSTM光伏功率短期预测[J].热能动力工程,2025,40(7):180-189.
XIONG P F, ZHANG S, WANG X J. Short-term prediction of CNN-BiLSTM photovoltaic power based on fluctuation feature extraction[J]. Journal of Engineering for Thermal Energy and Power, 2025, 40(7):180-189.
[23]任建吉,位慧慧,邹卓霖,等.基于CNN-BiLSTM-Attention的超短期电力负荷预测[J].电力系统保护与控制,2022,50(8):108-116.
REN J J, WEI H H, ZOU Z L, et al. Ultra-short-term power load forecasting based on CNN-BiLSTM-Attention[J]. Power System Protection and Control, 2022, 50(8):108-116.
[24]潘婧, 柴洪峰, 孙权, 等. 超高维删失数据的联合特征筛选方法研究[J]. 系统工程理论与实践, 2023, 43(1): 169-190.
PAN J, CHAI H F, SUN Q, et al. Joint feature screening method for ultrahigh dimensional censored data[J]. Systems Engineering-Theory & Practice, 2023, 43(1): 169-190.
[25]柯松, 陈磊, 杨军, 等. 基于半动态交通流模型的电动汽车出行引导策略[J]. 电网技术, 2023, 47(8): 3362-3380. 
KE S, CHEN L, YANG J, et al. Electric vehicles travel guidance strategy based on semi-dynamic traffic flow state model[J]. Power System Technology, 2023, 47(8): 3362-3380.
[26] YU E B, XU G J, HAN Y, et al. An efficient short-term wind speed prediction model based on cross-channel data integration and attention mechanisms[J]. Energy, 2022, 256: 124569.
[27]周颖, 乔婧, 陈宋宋, 等. 基于麻雀搜寻优化算法的代理购电用户用电量多维度协同校核[J]. 电网技术, 2025, 49(2): 604-612.
ZHOU Y, QIAO J, CHEN S S, et al. Multi-dimensional collaborative checking of power consumption of purchasing agent users based on ISSA optimization algorithm[J]. Power System Technology, 2025, 49(2): 604-612.

相似文献/References:

[1]朱永胜,杨振涛,丁同奎,等.考虑用户动态充电需求的电动汽车充电站规划[J].郑州大学学报(工学版),2023,44(02):82.[doi:10.13705/j.issn.1671-6833.2023.02.001]
　ZHU Yongsheng,YANG Zhentao,DING Tongkui,et al.Electric Vehicle Charging Station Planning Considering Users′ Dynamic Charging Demand[J].Journal of Zhengzhou University (Engineering Science),2023,44(02):82.[doi:10.13705/j.issn.1671-6833.2023.02.001]
[2]包毅,胡静,郭含,等.郑州轨道交通供电系统负荷预测及影响研究[J].郑州大学学报(工学版),2013,34(03):18.[doi:10.3969/j.issn.1671-6833.2013.03.005]
　BAO Yi,HU Jing,GUO Han,et al.Study on Zhengzhou Metro Traction Power System Load Forecast and Impact[J].Journal of Zhengzhou University (Engineering Science),2013,34(02):18.[doi:10.3969/j.issn.1671-6833.2013.03.005]
[3]秦东晨,谢银倩,潘守辰,等.某纯电动汽车动力系统的建模与仿真分析研究[J].郑州大学学报(工学版),2013,34(05):48.[doi:10.3969/j.issn.1671-6833.2013.05.010]
　LIU Xian-lin,QIAO Yun-fei.Study on PSS Parameter Optimization Based on Artificial Fish-swarm Algorithm[J].Journal of Zhengzhou University (Engineering Science),2013,34(02):48.[doi:10.3969/j.issn.1671-6833.2013.05.010]
[4]蔡泽祥,侯汝锋,尹亮..考虑最大负荷预测的地区电网静态安全分析研究[J].郑州大学学报(工学版),2005,26(02):18.[doi:10.3969/j.issn.1671-6833.2005.02.005]
　Zhou Renjun,XU Zhisheng,Yang Hongming.Application of fuzzy optimization in comprehensive decision-making of power grid planning[J].Journal of Zhengzhou University (Engineering Science),2005,26(02):18.[doi:10.3969/j.issn.1671-6833.2005.02.005]
[5]蒋建东,韩文轩,赵云飞,等.基于优化VMD二次分解的短期电力负荷预测[J].郑州大学学报(工学版),2026,47(01):124.[doi:10.13705/j.issn.1671-6833.2025.04.016]
　JIANG Jiandong,HAN Wenxuan,ZHAO Yunfei,et al.Short-term Power Load Forecasting Based on Optimized VMD Secondary Decomposition[J].Journal of Zhengzhou University (Engineering Science),2026,47(02):124.[doi:10.13705/j.issn.1671-6833.2025.04.016]

更新日期/Last Update: 2026-03-04