数据驱动的共享单车停放区规划方法研究

Data-driven Planning and Design for Bike Sharing Parking Spots

从宏观和微观两个角度研究共享单车停放区规划方法,宏观层面解决停放区选址定容问题,微观层面进一步优化每个停放区内部的停车位布局问题。宏观层面利用DBSCAN对共享单车停/取点进行聚类分析得到停/取需求点;然后考虑共享单车使用者路径选择、停/取点选择和停放区服务能力约束,建立混合整数线性规划模型优化停放区选址及容量。微观层面充分考虑行人、自行车与汽车之间的影响,其中行人和自行车采用改进社会力模型进行仿真,并考虑共享单车使用者最优停放区选择;汽车采用智能驾驶模型进行仿真。停车位布局通过仿真通行效率及混合交通流风险进行评价,并基于代理模型进行优化。该方法应用于北京市崇文门地铁站周边共享单车停放区规划,验证了方法的有效性,该方法可提高混合交通流通行效率,降低交通风险。

This paper investigates the bike-sharing parking spots planning from both macro and micro perspectives.The proposed method optimizes the location,capacity,and layout of the parking areas.At the macro level,the DBSCAN(Density-Based Spatial Clustering of Applications with Noise)generates the feasible parking locations through the bike parking/renting data cluster analysis.Then a mixed-integer linear programming model is developed to optimize the site and capacity of parking areas,considering users'path choice and parking spots choice and capacity.The micro-level analysis taking account of the interaction between pedestrians,bicycles,and vehicles.The improved social force model is used to simulate the movement of pedestrians and shared bike users.The parking area layout is evaluated through the traffic efficiency analysis.The risk level of mixed traffic simulation and is optimized by surrogate-based optimization.The proposed method has been applied to plan the bike-sharing parking areas around Chongwenmen metro station in Beijing,China.The implementation verifies the effectiveness of the method,improves the mixed traffic efficiency,and reduces the traffic risk.