An optimization model of airport shuttle bus routes is constructed by taking operational reliability maximization as a main goal in this paper. Also, a hybrid genetic algorithm is designed to solve this problem. Then the theoretical method is applied to the case of Nanjing Lukou International Airport. During the research, a travel time reliability estimation method is proposed based on back propagation (BP) neural network. Absolute error and regression fitting methods are used to test the measurement results. It is proved that this method has higher accuracy and is applicable to calculate airport bus routes reliability. In algorithm design, the hill-climbing algorithm with strong local search ability is integrated into genetic algorithm. Initial solution is determined by hill-climbing algorithm so as to avoid the search process falling into a local optimal solution, which makes the accuracy of calculation result improved. However, the calculation results show that the optimization process of hybrid genetic algorithm is greatly affected by both the crossover rate and mutation rate. A higher mutation rate or lower crossover rate will decrease the stability of the optimization process. Multiple trials are required to determine the optimal crossover rate and mutation rate. The proposed method provides a scientific basis for optimizing the airport bus routes and improving the efficiency of airport’s external transportation services.

SummaryIn this article, a reliability‐based method for optimizing the road network is presented. A bi‐level optimization model for the road network, of which the lower model is the optimal user equilibrium of the road impedance function and the upper model is the maximum reliability of the network, is constructed and solved by using the genetic algorithm. Moreover, a model for measuring the travel time reliability of the airport collection and distribution network is built based on the improved Bureau of Public Roads (BPR) function, and the reliability of this road network is quantified. Results of our case study show that the mean travel time reliability of all roads in the collection and distribution network of Nanjing Lukou Airport is 0.74, showing a good status on the whole level compared with other roads. The mean travel time reliability of the roads near the airport is higher by 25% or so, indicating that the reliability distribution is significantly uneven. It is proved that this method has higher accuracy and is applicable to calculate airport collection and distribution network reliability. After optimized by using the bi‐level model, the reliability of the road network is increased by about 11%, showing a good optimization effect. However, the optimization process of genetic algorithm is greatly affected by both crossover rate and mutation rate. A higher mutation rate or lower crossover rate will decrease the stability of optimization process. This method can be used as a theoretical reference for optimizing airport collection and distribution networks and improving the efficiency of airport's external transportation service.

Numerous strategies have been proposed to modify and transform passengers’ travel mode and departure time with the purpose of mitigating landside traffic pressure of airports. A core solution to tackle this problem is to build a travel behavior model so that pertinent predictions about the extent to which passengers shift their patterns of travel can hopefully be obtained. This paper aims at studying the passengers’ behaviors with respect to the travel mode and departure time based on agent theory. What distinguishes this model from traditional utility maximization theory is that it specifically places emphasis on the decision-making process with imperfect information and bounded rationality. Passengers continuously renew their knowledge of time management and their surrounding environment in the duration of the Bayesian learning process. It is evident that decisions about whether to substitute their current travel mode and departure time will be given thoughtful consideration before traveling, in relation to their presumptive gain and cost for searching. When performing additional searches, passengers tend to depend on a range of decision-making conditions to determine the necessity of converting to a new travel pattern. The process of both searching and deciding can be indicated by production (if–then) rules. These rules basically stem from the data gathered from Nanjing Lukou International Airport (NKG). Furthermore, this paper studies and discusses to what extent passengers will change their travel behaviors under variable costs of public transportation. Finally, this paper provides some recommendations on how to formulate appropriate subway fares.