基于停车预约模式的差异化泊位定价优化  

Differentiated parking pricing optimization based on parking reservation mode

作　　者：李思奇 安正阳 孙迅 姚恩建[1,2] LI Siqi;AN Zhengyang;SUN Xun;YAO Enjian(Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport,Beijing Jiaotong University,Beijing 100044,China;School of Traffic and Transportation,Beijing Jiaotong University,Beijing 100044,China)

机构地区：[1]北京交通大学综合交通运输大数据应用技术交通运输行业重点实验室,北京100044 [2]北京交通大学交通运输学院,北京100044

出　　处：《北京交通大学学报》2023年第3期79-86,共8页JOURNAL OF BEIJING JIAOTONG UNIVERSITY

基　　金：北京市自然科学基金(L211025);国家自然科学基金(52172312);中国博士后科学基金(2021M700368)。

摘　　要：为解析驾驶者的预约停车选择行为,设计考虑驾驶者个人属性及出行场景的预约停车选择行为陈述性偏好(Stated Preference, SP)调查问卷,基于SP调查数据,构建预约停车选择行为巢式Logit(Nested Logit, NL)模型,采用Biogeme软件标定模型参数并分析标定结果 .根据效用理论,构建以停车场运营总收益最大化、用户总效用最大化以及停车场利用率均衡的多目标预约停车场差异化定价优化模型,采用带精英策略的非支配排序算法(Non-dominated Sorting Genetic Algorithm,NSGA-Ⅱ)算法求解模型,并以北京佑安医院及周边停车场景进行案例分析.研究结果表明:出行者更倾向于选择停车预约,且相较于费用等方案属性变量,出行者更关注停车等待时间;个人特征和出行目的等属性会对停车方案选择产生显著影响;算例中预约停车模式能够转移目的地停车场内约67%的车辆,实现高峰时段区域内停车需求的合理分配,为停车设施管理提供参考.To investigate the parking choice behavior of drivers,a Stated Preference(SP)questionnaire is designed,taking into account drivers’personal attributes and travel scenarios.Based on the SP sur⁃vey data,a Nested Logit(NL)model of parking choice behavior is constructed,and the model param⁃eters are calibrated and analyzed using Biogeme software.Based on the utility theory,a multiobjective reservation parking differential pricing optimization model is constructed to maximize the to⁃tal revenue of parking operation and users’total utility,and balance the parking utilization rate.The Non-dominated Sorting Genetic Algorithm(NSGA-Ⅱ)algorithm is used to solve the model,and a case study is conducted on the parking scenario around Beijing You’an Hospital.The results show that travelers are more inclined to choose parking reservation,and pay more attention to the parking wait⁃ing time than the cost and other program attributes.In addition,personal attributes,travel purpose,and other attributes significantly impact parking program selection.The reservation parking model can shift about 67% of the vehicles in the destination parking lot in the case study,reasonably allocate the parking demand in the area during peak hours,and provide guidance for parking facility management.

关 键 词：交通运输规划与管理 预约停车 选择行为 遗传算法 非集计模型 多目标优化 

分 类 号：U491[交通运输工程—交通运输规划与管理]