Tan Yingjia, Sun Bo, Guo Li, Jing Binbin
Shenzhen General Integrated Transportation and Municipal Engineering Design & Research Institute Co., Ltd., Shenzhen 518003, China.
School of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China.
Math Biosci Eng. 2022 Aug 24;19(12):12371-12386. doi: 10.3934/mbe.2022577.
This research aims to develop an optimization model for optimizing demand-responsive transit (DRT) services. These services can not only direct passengers to reach their nearest bus stops but also transport them to connecting stops on major transit systems at selected bus stops. The proposed methodology is characterized by service time windows and selected metro schedules when passengers place a personalized travel order. In addition, synchronous transfers between shuttles and feeder buses were fully considered regarding transit problems. Aiming at optimizing the total travel time of passengers, a mixed-integer linear programming model was established, which includes vehicle ride time from pickup locations to drop-off locations and passenger wait time during transfer travels. Since this model is commonly known as an NP-hard problem, a new two-stage heuristic using the ant colony algorithm (ACO) was developed in this study to efficiently achieve the meta-optimal solution of the model within a reasonable time. Furthermore, a case study in Chongqing, China, shows that compared with conventional models, the developed model was more efficient formaking passenger, route and operation plans, and it could reduce the total travel time of passengers.
本研究旨在开发一种用于优化需求响应式公交（DRT）服务的优化模型。这些服务不仅可以引导乘客到达最近的公交站点，还能将他们运送到选定公交站点处主要公交系统的换乘站点。当乘客提交个性化出行订单时，所提出的方法以服务时间窗和选定的地铁时刻表为特征。此外，针对公交问题，充分考虑了穿梭巴士和支线巴士之间的同步换乘。为了优化乘客的总出行时间，建立了一个混合整数线性规划模型，该模型包括车辆从接载地点到下车地点的行驶时间以及乘客在换乘行程中的等待时间。由于该模型通常被认为是一个NP难问题，本研究开发了一种使用蚁群算法（ACO）的新的两阶段启发式算法，以便在合理的时间内有效地获得该模型的次优解。此外，在中国重庆进行的案例研究表明，与传统模型相比，所开发的模型在制定乘客、路线和运营计划方面更有效，并且可以减少乘客的总出行时间。
