Modelling and simulation of hierarchical scheduling of real-time responsive customised bus

A real-time responsive customised bus (RTRCB) provides demand-oriented and shared-ride service for passengers with random travel demands. Unlike other works in the literature, the authors developed a hierarchical methodology to optimise the RTRCB schedule. It involves a trade-off between the interests of the transporter and those of the passengers. After minimising the initial travel distance while maintaining a wide service range, the bus routes are planned holistically based on the main travel locations. Based on the initial routes, the buses are dispatched to satisfy the real-time travel demands. The procedure for solving the proposed problem is developed by modifying the genetic algorithm (GA) and non-dominated sorting GA with elite strategy. The proposed method is applied to a real-life problem in the city of Shenzhen, and certain extensional analyses are performed to demonstrate their feasibility. The computational results show that: (i) the travel distance limitation and tortuosity ratio of the bus route play the most important roles in planning bus routes; (ii) the designation of all the initial bus stops as the control stops results in comparatively stable service for more passengers; and (iii) a better service performance can be achieved by introducing the soft time window strategy with an acceptable delivery delay.