摘要
提出了一种在智能网联汽车环境下的混合交通流的生态车辆跟驰(ECF)策略,探索其跟驰行为的CO_(2)排放。基于车辆轨迹数据,提取多测度的跟驰行为特征参数。建立了极端梯度提升(XGBoost)模型,利用加性解释(SHAP)算法计算并分析了跟驰行为特征参数对跟驰过程中CO_(2)排放量的影响规律。标定了人工驾驶车辆的智能驾驶员模型,并基于城市交通仿真(SUMO)平台以及自动驾驶车辆(CAV)的自适应巡航控制(ACC)、协同式自适应巡航控制(CACC)模型;在11个混合交通流仿真场景下,分析ECF策略的CO_(2)减排有效性。结果表明:当CACC车辆占比50%以上时,CACC-CACC跟驰对的CO_(2)瞬时质量排放量减少比例超过60%。从而,本文ECF策略能够降低车辆在混合交通流场景下跟驰过程中CAV和CACC-CACC跟驰对的CO_(2)排放。
An eco-car-following(ECF)strategies was explored with the CO_(2) emissions of car-following behavior in mixed traffic flow under the environment of intelligent connected vehicles.The vehicle trajectory data was used to extract multi-dimensional car-following behavior feature parameters.An eXtreme Gradient Boosting(XGBoost)model was established with calculating and analyzing the effects of car-following behavior feature parameters on CO_(2) emissions during the car-following process by using the Shapley Additive exPlanations(SHAP)algorithm.The intelligent driver model of human-driven vehicles was calibrated.The Simulation of Urban MObility(SUMO)platform was using to simulate 11 mixed traffic scenarios.The Adaptive Cruise Control(ACC)and the Cooperative Adaptive Cruise Control(CACC)models were employed for Connected and Automated Vehicles(CAVs).The results show that the instantaneous mass CO_(2) emissions of CACC-CACC vehicle pairs de-crease by more than 60%when the proportion of CACC vehicles exceeds 50%.There-fore,the strategy reduces CO_(2) emissions for CAVs and CACC-CACC car-following pairs in mixed traffic flow scenarios.
作者
于谦
郭圆圆
杨鸣鹏
张玉婷
YU Qian;GUO Yuanyuan;YANG Mingpeng;ZHANG Yuting(School of Transportation Engineering,Chang'an University,Xi’an 710064,China;Chengdu Branch,Tianjin Municipal Engineering Design and Research Institute,Chengdu 610041,China)
出处
《汽车安全与节能学报》
北大核心
2025年第4期577-586,共10页
Journal of Automotive Safety and Energy
基金
国家自然科学基金青年科学基金(52002032)
陕西省自然科学基础研究计划资助项目(2024JX-YBQN-0427
2025JC-YBMS-446)。
