The skip-stop operation strategy (SOS) is rarely applied to Chinese urban rail transit networks because it is a simple scheme and a less universally popular transportation service. However, the SOS has performance advantages, in that the total trip time can be reduced depending on the number of skipped stations, crowds of passengers can be rapidly evacuated at congested stations in peak periods, and the cost to transit companies is reduced. There is a contradiction between reducing the trip time under the SOS and increasing the passengers’ waiting times under an all-stop scheme. Given this situation, the three objectives of our study were to minimize the waiting and trip times of all passengers and the travel times of trains. A comprehensive estimation model is presented for the SOS. The mechanism through which the trip time for all passengers is affected by the SOS is analyzed in detail. A 0–1 integer programming formulation is established for the three objectives, and is solved using a tabu search algorithm. Finally, an example is presented to demonstrate that the estimation method for the SOS is capable of optimizing the timetable and operation schemes for a Chinese urban rail transit network.

This study provides a novel solution for the synchronized and coordinated railway scheduling optimization (SCSO) problem by the determination of the departure times of a public transit network. Railway timetable optimization is dealt with maximizing the number of synchronized meetings to allow for smooth transfers at interchanges. The developed model uses binary variables to record the number of synchronized meetings considering the importance of transfer stations and rail lines without the need to apply the modeling of passenger assignments. The model allows for a permissible and flexible transfer waiting time for making a connection between rails instead of the commonly used and assumed values. The solution of the mixed-integer programing problem of larger-sized railway networks is based on a synchronized and coordinated scheduling optimization genetic algorithm (SCSO-GA) with a local search strategy (LSS). This solution method is proved to be more efficient and accurate than the CPLEX solver. In addition it is proven to be a periodic event-scheduling problem (PESP) solver. The model is tested computationally on the Beijing urban rail transit network. The results demonstrate the advantage of the novel approach over other methods.

Travel time data is an important factor for evaluating the performance of a public transport system. In terms of time and space within the nature of uncertainty, bus travel time is dynamic and flexible. Since the change of traffic status is periodic, contagious or even sudden, the changing mechanism of that is a hidden mode. Therefore, bus travel time prediction is a challenging problem in intelligent transportation system (ITS). Allowing for a large amount of traffic data can be collected at present but lack of precisely-conducting, it is still worth exploring how to extract feature sets that can accurately predict bus travel time from these data. Hence, a feature extraction framework based on the deep learning models were developed to reflect the state of bus travel time. First, the study introduced different historical stages of bus signaling time, taxi speed, the stop identity (ID) of spatial characteristics, and real-time possible arrival time, signified by fourteen spatiotemporal characteristic values. Then, an embedding network is proposed to leverage a wide and deep structure to mate the spatial and temporal data. In order to meet the temporal dependence requirements, an attention mechanism for a Recurrent Neural Network (RNN) was designed in this research in order to capture the temporal information. Finally, a Deep Neural Networks (DNN) was implemented in this research in order to achieve the dynamic bus travel time prediction. Two case studies of Guangzhou and Shenzhen were tested. The results showed that the performance of the algorithm was more efficient than that of the traditional machine-learning model and promoted by 4.82% compared to the deep neural network applied to the initial feature space. Moreover, the study visualized the weighted cost of attention on the bus’s travel time features during a certain running state. Therefore, the study demonstrated the proposed model enabled to understand the characteristic data of transit travel time with visualization.

For dense railway lines, timetables are commonly designed periodically to provide regular services. However, such timetables may lead to many low‐occupancy departures and make it inefficient to a railway company. We combine the features of periodic timetabling with those of demand‐responsive timetabling design for a bidirectional rail transit line considering rolling stock circulation. A mixed‐integer programming model with the objective of minimizing total passenger waiting time and weighted total train travel time is formulated and a three‐phase heuristic algorithm is developed. Five performance indicators, namely, total train travel time, passenger average waiting time, event time deviation, event frequency deviation, and train connection time are introduced to evaluate the performance of the model. A case study on Jinshan railway corridor in Shanghai demonstrates that the proposed demand responsive periodic timetabling model can reduce passengers’ waiting time and keep periodicity in the meantime with short computational time