Optimizing Multi-Terminal Customized Bus Service With Mixed Fleet

Abstract

The customized bus (CB) transit is recognized as an effective transportation mode offering more flexible and demand-responsive service than traditional bus transit with fixed route and schedule, especially during the peak hours. The novelty of this study is the development of a mixed integer non-linear model for optimizing multi-terminal CB service in an urban setting. According to the estimated spatiotemporal passenger demand, the objective total cost, consisting of supplier's and users' costs, is minimized subject to capacity and time window constraints. A mixed bus fleet with various bus sizes is employed to accommodate passenger demand, which increases vehicle utilization and reduces supplier's cost. The inconvenience of passengers caused by early arrival at the destination is treated as penalty and considered in users' cost. The study optimization problem is combinatorial with many decision variables including trip assignment, bus routing and associated timetables, and fleet size. A hybrid genetic algorithm (HGA) which integrates the features of genetic algorithm (GA) and simulated annealing (SA) is developed to effectively search for the optimal solution. A real-world CB network is employed to demonstrate the applicability of the developed model and explore the relation between the model parameters and optimized results. It was found that the total cost can be reduced by 16.5% after employing multiple terminals and a mixed bus fleet.

Optimizing Customized Transit Service considering Stochastic Bus Arrival Time

“…Huang et al [17] modelled the decision-making process for CB service and optimized passenger assignment and bus routing that maximized total profit. Sun et al [5] optimized trip assignment, routing, timetabling, and bus fleet size for CB service considering the mixed fleet size and multi-terminal, which minimized total cost.…”

“…e service plan is updated on a short-term basis subject to the passenger demand change. To ensure service quality, CB does not take walk-in riders without reservation [5].…”

“…A hybrid heuristic algorithm that integrates the features of genetic algorithm (GA), simulated annealing (SA), and adaptive destroy-and-repair (ADAR) is proposed to efficiently search for the approximate optimal solution. e HGA hybridizing GA and SA [5] performs well in global exploration but spends much time converging to the optimal solution. In contrast, local search methods, such as ADAR, can find the optimal solution quickly.…”

Cross-Regional Customized Bus Route Planning Considering Staggered Commuting During the COVID-19

“…Population method mainly includes ant colony algorithm, bee colony algorithm, particle swarm algorithm, genetic algorithm and other intelligent algorithms [24] – [27] , while trajectory algorithm mainly includes simulated annealing algorithm, tabu search algorithm, iterative local search, variable neighborhood search, large-scale neighborhood search algorithm and so on [28] – [30] . Since the study CB optimization problem is combinatorial that is non-deterministic polynomial-time hard (NP-hard) [31] [32] . Lyu et al [8] used a variety of travel data to optimize the location, route, timetable, and the probability of passengers choosing CB.…”

Integrating Passenger Incentives to Optimize Routing for Demand-Responsive Customized Bus Systems

“…It is a variable route service, activated in response to users' requests or pre-planned based on the reservation in advance, provided as a shared ride, and operated on a point-to-point basis [2], comparing to conventional fixed-route bus transit systems. An instance of DRT is the customized bus (CB) [3,4], which requires reservation information to match passengers and vehicles as well as to plan routes. With the recent development and application of mobile internet and shared economy, the service modes of DRT have become various and are more competitive to conventional fixed-route bus transit [5].…”