融合数据驱动和充电行为的电动汽车能耗预测方法*

doi:10.11985/2024.01.010

摘要/Abstract

摘要：

电动汽车的能耗预测对于车辆路径规划与充电行为至关重要。提出一种考虑充电行为的多模型融合能耗预测方法，首先构建基于实车稀疏数据与有限参数的能耗计算模型，在此基础上构建充电行为模型，分析并提取能耗强相关的充电行为特征，最后基于长短期记忆循环神经网络(Long short-term memory neural network, LSTM)搭建能耗预测模型。使用实车数据对所提方法进行验证，结果表明，该方法可以精准预测相同车型不同起始电池荷电状态(State of charge, SOC)、不同温度、不同时间段下的汽车能耗，均方根误差(Root mean square error，RMSE)为1.27，与现有方法相比，RMSE至少降低4.5%。

关键词: 能耗预测, 电动汽车, 充电行为, LSTM神经网络

Abstract:

Accurately predicting the energy consumption of electric vehicles is essential for efficient vehicle path planning and charging. A multi-model fusion method for energy consumption prediction that takes into account charging behavior is proposed. Firstly, based on the limited parameters and sparse real vehicle data, the energy consumption calculation model is constructed. Then, the charging behavior model is created to analyze and extract features closely related to energy consumption. Finally, long short-term memory neural network(LSTM) is used to construct the energy consumption prediction model. The method is validated with real vehicle data. Results indicate that the proposed method accurately predicts the energy consumption for the given car model with differing starting battery states of charge(SOC), temperatures, and periods. The root mean square error(RMSE) recorded is 1.27, which shows a reduction of no less than 4.5% compared to the existing methods.

Key words: Energy consumption prediction, electric vehicles, charging behavior, long short-term memory neural network

中图分类号:

TM911

马军伟, 霍美如, 赵敏, 杜锋, 景峰, 冯煜. 融合数据驱动和充电行为的电动汽车能耗预测方法^*[J]. 电气工程学报, 2024, 19(1): 97-105.

MA Junwei, HUO Meiru, ZHAO Min, DU Feng, JING Feng, FENG Yu. Energy Consumption Prediction Method for Electric Vehicles by Integrating Charging Behavior with Data-driven Method[J]. Journal of Electrical Engineering, 2024, 19(1): 97-105.

图/表 11

表1

图1

图2

图3

图4

图5

图6

图7

图8

表2

图9

参考文献 20

[1]	杨扬, 张天雨, 朱宇婷, 等. 考虑建设时序和动态需求的城际公路充电设施优化布局[J]. 清华大学学报, 2022, 62(7):1163-1177,1219.
	YANG Yang, ZHANG Tianyu, ZHU Yuting, et al. Optimal layout of intercity highway charging facilities considering construction timing and dynamic needs[J]. Journal of Tsinghua University, 2022, 62(7):1163-1177,1219.
[2]	钟倩颖. 新能源汽车发展的政策研究[D]. 大连: 东北财经大学, 2019.
	ZHONG Qianying. Policy research on the development of new energy vehicles[D]. Dalian: Dongbei University of Finance and Economics, 2019.
[3]	左世全, 赵世佳, 祝月艳. 国外新能源汽车产业政策动向及对我国的启示[J]. 经济纵横, 2020, 410(1):113-122.
	ZUO Shiquan, ZHAO Shijia, ZHU Yueyan. Foreign new energy vehicle industry policy trends and their enlightenment to my country[J]. Economic Perspectives, 2020, 410(1):113-122.
[4]	吴巨爱, 薛禹胜, 谢东亮, 等. 电动汽车参与电量市场与备用市场的联合风险调度[J]. 电工技术学报, 2023, 38(23):6407-6418.
	WU Juai, XUE Yusheng, XIE Dongliang, et al. The joint risk dispatch of electric vehicle in day-ahead electricity energy market and reserve market[J]. Transactions of China Electrotechnical Society, 2023, 38(23):6407-6418.
[5]	王志远. 电动车完全替代燃油车必须跨过“里程焦虑”的门槛[N]. 中国青年报,2022-05-19(012).
	WANG Zhiyuan. Electric vehicles must cross the threshold of “range anxiety” to completely replace fuel vehicles[N]. China Youth Daily,2022-05-19(012).
[6]	李舒欣, 郎悦茹, 刘亚莉, 等. 基于车辆动力学的纯电动汽车能耗建模[J]. 汽车实用技术, 2022, 47(19):1-5. doi: 10.16638/j.cnki.1671-7988.2022.019.001
	LI Shuxin, LANG Yueru, LIU Yali, et al. Energy consumption modeling of pure electric vehicles based on vehicle dynamics[J]. Automobile Applied Technology, 2022, 47(19):1-5. doi: 10.16638/j.cnki.1671-7988.2022.019.001
[7]	李浩, 俞璐, 丁晓华, 等. 基于实际运行数据的混合动力汽车能耗分析[J]. 同济大学学报, 2021, 49(4):544-553.
	LI Hao, YU Lu, DING Xiaohua, et al. Energy consumption analysis of hybrid vehicles based on actual operating data[J]. Journal of Tongji University, 2021, 49(4):544-553.
[8]	MADHUSUDHANAN A K, NA X, CEBON D. A computationally efficient framework for modelling energy consumption of ICE and electric vehicles[J]. Energies, 2021, 14(7):2031-2031. doi: 10.3390/en14072031
[9]	王虹霞. 车路协同环境下纯电动公交车节能驾驶策略研究[D]. 西安: 长安大学, 2020.
	WANG Hongxia. Research on energy-saving driving strategy of pure electric buses in vehicle-road coordination environment[D]. Xi’an: Chang’an University, 2020.
[10]	胡杰, 蔡世杰, 黄腾飞, 等. 电动汽车动力电池充电能量的预测方法[J]. 机械科学与技术, 2020, 39(6):926-936.
	HU Jie, CAI Shijie, HUANG Tengfei, et al. Prediction method of charging energy of electric vehicle power battery[J]. Mechanical Science and Technology, 2020, 39(6):926-936.
[11]	YI Z, BAUER P H. Adaptive multiresolution energy consumption prediction for electric vehicles[J]. IEEE Transactions on Vehicular Technology, 2017, 66(11):10515-10525. doi: 10.1109/TVT.2017.2720587
[12]	任永昌. 基于SK-PSO-RBF的纯电动汽车动力电池SOC及剩余里程的预测研究[D]. 赣州: 江西理工大学, 2018.
	REN Yongchang. Research on prediction of pure electric vehicle power battery SOC and remaining range based on SK-PSO-RBF[D]. Ganzhou: Jiangxi University of Science and Technology, 2018.
[13]	GAO Kai, LUO Pan, XIE Jin, et al. Energy management of plug-in hybrid electric vehicles based on speed prediction fused driving intention and LIDAR[J]. Energy, 2023,284:128535.
[14]	ZHENG Jiafeng, ZHU Jinghua, XI Heran. Short-term energy consumption prediction of electric vehicle charging station using attentional feature engineering and multi-sequence stacked gated recurrent unit[J]. Computers and Electrical Engineering, 2023,108:108694.
[15]	SILVA D G, MENESES A A M. Comparing long short-term memory (LSTM) and bidirectional LSTM deep neural networks for power consumption prediction[J]. Energy Reports, 2023,10:3315-3334.
[16]	COHEN J. Statistical power analysis for the behavioral sciences[M]. The SAGE Encyclopedia of Research Design,1969.
[17]	LI X, LYU M, ZHANG Z, et al. Lithium-ion battery state of health estimation based on multi-source health indicators extraction and sparse Bayesian learning[J]. Energy, 2023,282:128445.
[18]	高锋阳, 张浩然, 王文祥, 等. 氢燃料电池有轨电车混合储能系统的节能运行优化[J]. 电工技术学报, 2022, 37(3):686-696.
	GAO Fengyang, ZHANG Haoran, WANG Wenxiang, et al. Energy saving operation optimization of hybrid energy storage system for hydrogen fuel cell tram[J]. Transactions of China Electrotechnical Society, 2022, 37(3):686-696.
[19]	梁海强, 何洪文, 代康伟, 等. 融合经验老化模型和机理模型的电动汽车锂离子电池寿命预测方法研究[J]. 汽车工程, 2023, 45(5):825-835,844.
	LIANG Haiqiang, HE Hongwen, DAI Kangwei, et al. Research on life prediction method of lithium-ion battery for electric vehicles by integrating empirical aging model and mechanism model[J]. Automotive Engineering, 2023, 45(5):825-835,844.
[20]	叶家豪, 魏霞, 黄德启, 等. 基于灰色关联分析的BSO-ELM-AdaBoost风电功率短期预测[J]. 太阳能学报, 2022, 43(3):426-432. doi: 10.19912/j.0254-0096.tynxb.2020-0524
	YE Jiahao, WEI Xia, HUANG Deqi, et al. Short-term forecast of wind power based on BSO-ELM-AdaBoost with grey correlation analysis[J]. Acta Energiae Solaris Sinica, 2022, 43(3):426-432. doi: 10.19912/j.0254-0096.tynxb.2020-0524

时间	车速	电量	状态	里程	电流
2022-4-10 18:15:16
2022-4-10 18:15:26
…
2022-4-10 20:19:46
2022-4-10 20:19:56
…

模型	RMSE
随机森林	1.35
支持向量回归	1.42
Adaboost	1.48
XGboost	1.33
BP神经网络	1.57
RBF神经网络	1.39
RNN	1.49
GRU	1.35
本文方法	1.27