Search

With the rapid development of global trade, ports and terminals are playing an increasingly important role, and automatic guided vehicles (AGVs) have been used as the main carriers performing the loading/unloading operations in automated container terminals. In this paper, we investigate a multi-AGV dynamic scheduling problem to improve the terminal operational efficiency, considering the sophisticated complexity and uncertainty involved in the port terminal operation. We propose to model the dynamic scheduling of AGVs as a Markov decision process (MDP) with mixed decision rules. Then, we develop a novel adaptive learning algorithm based on a deep Q-network (DQN) to generate the optimal policy. The proposed algorithm is trained based on data obtained from interactions with a simulation environment that reflects the real-world operation of an automated in Shanghai, China. The simulation studies show that, compared with conventional scheduling methods using a heuristic algorithm, i.e., genetic algorithm (GA) and rule-based scheduling, terminal the proposed approach performs better in terms of effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

Calibrating the microsimulation model is essential to enhance its ability to capture reality. The paper proposes a Bayesian neural network (BNN)-based method to calibrate parameters of microscopic traffic simulators, which reduces repeated running of simulations in the calibration and thus significantly improves the calibration efficiency. We use BNN with probability distributions on the weights to quickly predict the simulation results according to the inputs of the parameters to be calibrated. Based on the BNN model with the best performance, heuristic algorithms (HAs) are performed to seek the optimal values of the parameters to be calibrated with the minimum difference between the predicted results of BNN and the field-measured values. Three HAs are considered, including genetic algorithm (GA), evolutionary strategy (ES), and bat algorithm (BA). A TransModeler case of highway links in Shanghai, China, indicates the validity of the proposed calibration method in terms of error and efficiency. The results demonstrate that the BNN model is able to accurately predict the simulation and adequately capture the uncertainty of the simulation. We also find that the BNN-BA model produces the best calibration efficiency, while the BNN-ES model offers the best performance in calibration accuracy. [ABSTRACT FROM AUTHOR]

The capacity allocation is a practically significant factor to influence the quality of the train timetables in the rail operations, especially under the fluctuation of passenger demands. This paper aims to investigate a detailed description for the structure and characteristics of the capacity allocation problem under random demand in the high-speed rail network. A two-stage stochastic integer programming model is provided to get the capacity allocation solutions to meet random fluctuations of passenger demands in the daily operations, which incorporates demand uncertainty and makes no assumptions for the rail network structure and distribution of passenger demands. Given the inherent complexity for solving this problem, we provide a solution framework including a heuristic algorithm based on tabu search in order to obtain a near-optimal solution and strategies to obtain an efficient timetable and train formation adjustment. Finally, two sets of examples, in which a sample rail network with 5 stations and the Beijing-Shanghai high-speed rail network data are adopted as the experimental environments to illustrate the performance and effectiveness of the proposed methods. • A two-stage stochastic program model for train capacity allocation is presented. • A heuristic algorithm based on tabu search is provided to solve the problem. • A strategy for an efficient timetable and train formation adjustment is provided. • Numerical experiments are given to illustrate the proposed approaches. [ABSTRACT FROM AUTHOR]

Studying the interaction between demand forecasting and train stop planning is important, as it ensures the sustainable development of high-speed rail (HSR). Forecasting the demand for high-speed rail (HSR), which refers to modal choice or modal split in this paper, is the first step in high-speed rail (HSR) planning. Given the travel demand and the number of train trips on each route, the train stop planning problem (TSPP) of line planning involves determining the stations at which each train trip stops, i.e., the stop-schedule of each train trip, so that the demand can be satisfied. To integrate and formulate the two problems, i.e., the modal choice problem (MCP) and train stop planning problem (TSPP), a nonlinear model is presented with the objective of maximizing the total demand captured by a high-speed rail system. To solve the model, a heuristic iterative algorithm is developed. To study the relationship between the demand and the service, the Beijing–Shanghai high-speed rail (HSR) corridor in China is selected. The empirical analysis indicates that combining modal choice and train stop planning should be considered for the sustainable design of high-speed rail (HSR) train services. Furthermore, the model simulates the impact of the number of stops on its mode share by reflecting changes in travelers' behaviors according to HSR train stop planning, and it also provides a theoretical basis for the evaluation of the adaptability of the service network to travel demand. [ABSTRACT FROM AUTHOR]