基于百度地图API的纯电动汽车未来行驶能耗预测

doi:10.3969/j.issn.1674-8484.2023.06.008

摘要/Abstract

摘要：

为了预测纯电动车的未来行驶能耗，利用从百度地图应用程序接口（API）所获取道路车流数据，并在云计算系统的在环平台（in-loop platform）上进行实车上路实验验证。用百度提供的道路车流数据，可以计算剩余里程、路径规划、能量管理策略以及充电桩布置等。这些数据与实车行驶数据结合，一并作为训练数据集。用k-means聚类分析算法与支持向量机（SVM）分类算法，来预测未来行驶能耗。对比池剩余电量（SOC）的预测值和实车上路实验所得的实际值。结果表明：对于一个40 min、约20 km的行驶工况，能耗预测的误差可以限制在一个标准差σ之内。从而验证了本文基于百度地图API车流数据的未来行驶能耗预测算法的准确性。

关键词: 自动驾驶汽车, 纯电动车, 车联网, 行驶工况, 百度地图应用程序接口（API）, 聚类分析, 支持向量机, 云计算

Abstract:

The road traffic flow data obtained from the Baidu Map Application Programming Interface (API) was used to predict the future driving energy-consumption of pure electric vehicles, and a vehicle on-road experimental verification was conducted on the in-loop platform of the cloud computing system. Used the road traffic data obtained by Baidu to calculate the remaining mileage, the path planning, the energy-management strategies, and the charging pile layout, etc. These data were combined with vehicle-driving data and used as a training data set. The future energy-consumption was predicted with the k-means cluster analysis algorithm and the support vector machine (SVM) classifcation algorithm. The predicted value of the remaining battery state of charge (SOC) was compared with the actual value obtained from the vehicle on-road experiments. The results show that the error of future driving energy-consumption prediction are limited to inset of one-standard-deviation σ for a 40 min driving condition (about 20 km), based on Baidu Map API traffic flow data. Therefore, the accuracy of the proposed prediction algorithm in this paper is verified.

Key words: autonomous vehicles, vehicle networking, driving conditions, Baidu maps API (application program interface), cluster analysis, support vector machine, cloud computing

中图分类号:

U467.1+4

黄新朝, 张毅. 基于百度地图API的纯电动汽车未来行驶能耗预测[J]. 汽车安全与节能学报, 2023, 14(6): 715-722.

HUANG Xinchao, ZHANG Yi. Prediction of future driving conditions for electrical vehicles based on Baidu maps API[J]. Journal of Automotive Safety and Energy, 2023, 14(6): 715-722.

图/表 16

参考文献 12

[1]	马建, 李学博, 赵轩, 等. 电动汽车复合制动控制研究现状综述[J]. 中国公路学报, 2022, 35(11): 272-294.
	MA Jian, LI Xuebo, ZHAO Xuan, et al. Review of electro-mechanical composite braking control for electric vehicles[J]. Chin J Highw Transport, 2022, 35(11) : 272-273. (in Chinese)
[2]	Smith R, Shahidinejad S, Blair D, et al. Characterization of urban commuter driving profiles to optimize battery size in light-duty plug-in electric vehicles[J]. Transport Res Part D: Transport Envir, 2011, 16(3): 218-224. doi: 10.1016/j.trd.2010.09.001 URL
[3]	Basso R, Kulcsár B, Egardt B, et al. Energy consumption estimation integrated into the electric vehicle routing problem[J]. Transport Res Part D: Transport Envir, 2019, 55: 141-167.
[4]	Speidel S, Bräunl T. Driving and charging patterns of electric vehicles for energy usage[J]. Renew Sustain Energy Rev, 2014, 40: 97-110. doi: 10.1016/j.rser.2014.07.177 URL
[5]	Moawad A, Balaprakash P, Rousseau A, et al. Novel large scale simulation process to support DOT’s CAFE modeling system[J]. Int’l J Autom Tech, 2016, 17(6): 1067-1077.
[6]	WU Xinkai, Freese D, Cabrera A, et al. Electric vehicles energy consumption measurement and estimation[J]. Transport Res Part D: Transport Envir 2015, 34: 52-67. doi: 10.1016/j.trd.2014.10.007 URL
[7]	QI Xuewei, WU Guoyuan, Boriboonsomsin K, et al. Data-driven decomposition analysis and estimation of link-level electric vehicle energy consumption under real-world traffic conditions. Transport Res Part D: Transport Envir, 2018, 64: 36-52. doi: 10.1016/j.trd.2017.08.008 URL
[8]	De Cauwer C, Verbeke W, Coosemans T, et al. A data-driven method for energy consumption prediction and energy-efficient routing of electric vehicles in real-world conditions[J]. Energies 2017, 10(5): 608-625.
[9]	张毅, 杨亚联, 陆帅, 等. 互联网分布式混合动力汽车实车在环仿真平台[J]. 汽车工程, 2017, 39(8): 849-857.
	ZHANG Yi, YANG Yalian, LU Shai, et al. Internet- distributed vehicle-in-the-loop simulation platform for hybrid electric vehicles[J]. Autom Engineering, 2017, 39(8): 849-857. (in Chinese)
[10]	ZHANG Yi, LIU Heping, ZHANG Zhigang, et al. Cloud computing-based real-time global optimization of battery aging and energy consumption for plug-in hybrid electric vehicles[J], J Power Sources, 2020, 479: 152-167.
[11]	DU Yongchang, ZHAO Yue, WANG Qinpu, et al. Triporiented stochastic optimal energy management strategy for plug-in hybrid electric bus[J]. Energy, 2016, 115: 1259-1271. doi: 10.1016/j.energy.2016.09.056 URL
[12]	WANG Shuning, TANG Yongchuan. An improved approach for generation of a basic probability assignment in the evidence theory based on gaussian distribution[J]. Arab J Sci Engi, 2022, 47(2): 1595-1607.

迎风面积	2.0 m²
整备质量	1.45 t
满载质量	100 kg
额定功率	40 kW
峰值功率	120 kW
电机—车轮减速比	9.1
车轮直径	0.595 m

迎风面积	2.0 m²
整备质量	1.45 t
满载质量	100 kg
额定功率	40 kW
峰值功率	120 kW
电机—车轮减速比	9.1
车轮直径	0.595 m

特征值	编号	物理意义
拥堵情况 (TrffStat)	0	未知路况
	1	畅通
	2	缓行
	3	拥堵
	4	严重拥堵
拥堵方向 (JamDrct)	0	无拥堵
	1	同向拥堵
	-1	异向拥堵
车流速度 (TrffSpd)	-	区域内的车辆平均速度

特征值	编号	物理意义
拥堵情况 (TrffStat)	0	未知路况
	1	畅通
	2	缓行
	3	拥堵
	4	严重拥堵
拥堵方向 (JamDrct)	0	无拥堵
	1	同向拥堵
	-1	异向拥堵
车流速度 (TrffSpd)	-	区域内的车辆平均速度

类型	E_s / (MJ·km^-1)	T_s / (s·km^-1)	能耗	拥堵
1	4.32	178.2	中等	较拥堵
2	3.20	121.9	低	畅通
3	5.09	113.9	高	畅通
4	2.98	214.1	低	拥堵
5	4.21	68.6	中	畅通
6	4.04	246.3	中	拥堵