Predicting the status of train delays, a complex and dynamic problem, is crucial for railway enterprises and passengers. This paper proposes a novel hybrid deep learning model composed of convolutional neural networks (CNN) and temporal convolutional networks (TCN), named the CNN + TCN model, for predicting train delays in railway systems. First, we construct 3D data containing the spatiotemporal characteristics of real‐world train data. Then, the CNN + TCN model employs a 3D CNN component, which is fed into the constructed 3D data to mine the spatiotemporal characteristics, and a TCN component that captures the temporal characteristics in railway operation data. Furthermore, the characteristic variables corresponding to the two components are selected. Finally, the model is evaluated by leveraging data from two railway lines in the United Kingdom. Numerical results show that the CNN + TCN model has greater accuracy and convergence performance in train delay prediction.

The separation of battery charging and swapping processes enables highway operators to more flexibly manage the recharging of depleted batteries at battery swapping stations (BSSs), while also leveraging renewable energy (RE) resources to lower electricity costs. However, previous studies have not addressed the connection between BSS recharging strategies and the demand for fully charged batteries, which is determined by EV swapping schemes. To address this gap, the paper proposes a joint optimization approach for scheduling EVs and managing BSSs, considering RE generation along the highway. Specifically, a spatial-temporal network model is developed to represent the transportation-energy characteristics of EVs, incorporating BSS selection and battery swapping processes. Additionally, a BSS management model is formulated to plan the recharging of depleted batteries and ensure the availability of fully charged batteries to meet the swapping demands of EVs. The Lagrange relaxation algorithm is employed to handle the interaction between EV scheduling and BSS operations. A case study shows that this method effectively coordinates EV swapping schemes with BSS recharging strategies, resulting in a 17.3% improvement in RE generation utilization and a reduction in grid electricity consumption by RMB 1753.8.

The highway transportation system exhibits immense potential for adaptive functioning due to its distinctive operational attributes. This capability permits to harness more renewable energy, leading to a reduction in energy consumption costs. In this article, an integrative energy system optimization model is introduced from the standpoint of highway service zone operators. To simulate the behavior of electric vehicles on highways, an expanded network flow model is formulated considering driving, queueing, and charging actions. This model comprehensively integrates dimensions of time, space, and the state of charge of the vehicles. Consequently, the proposed model is proficient in representing the spatiotemporal and flexible operational traits inherent to electric vehicles. Through a series of numerical case studies executed on a real-world highway system, the effectiveness of the proposed model is demonstrated. These findings substantiate the potential utility and efficacy of our model in enhancing the operation optimization of energy systems within highway transportation systems.