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.

In the cooperative vehicle infrastructure system (CVIS), due to the limitation of deployment conditions, some roadside units (RSUs) need to use renewable energy to supply power and transmit the fused sensor network’s data to the backbone network through the passing vehicles. Aiming at the problem of energy consumption and time delay guarantee of multiple self‐powered RSUs in the CVIS, a distributed packet scheduling optimization strategy for energy‐delay trade‐off in self‐powered RSUs is proposed. The strategy can minimize the system energy consumption by constraining the packet queue length of the self‐powered RSUs. A dynamic optimization model of distributed packet adaptive scheduling for multiple self‐powered RSUs is established based on the Lyapunov optimization theory. Based on the knapsack algorithm, the analytical algorithm of the optimization model is proposed. The simulation results show that the packet scheduling strategy can reduce the energy consumption and delay of the system by satisfying the upper limit of the packet queue length.

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.

In Cooperative Vehicle Infrastructure System (CVIS), the roadside unit (RSU) obtains many kinds of monitoring data through observation equipment carried by the RSU. The monitoring data from RSUs are transmitted to an RSU that is connected to the backbone network using the “store–carry–forward” scheme through the mobile vehicle. The monitoring data obtained by RSUs are timely, and different types of monitoring data have corresponding timelines. Reducing end-to-end delays to ensure more packets can be transmitted before deadlines is challenging. In this paper, we propose a Distributed Packet Scheduling Scheme for Delay-Packets Queue Length Tradeoff System (DDPS) in CVIS to solve the multi-RSU-distributed packet transmission problem. We also establish the vehicle speed state, vehicle communication quantity prediction, data arrival, and end-to-end delay minimization models. After Lyapunov’s optimization theory transformed the optimization model, a knapsack problem was described. The simulation results verified that DDPS reduced the end-to-end average delay and ensured the data queue’s stability under packet deadline conditions.

Texture feature description is a remarkable challenge in the fields of computer vision and pattern recognition. Since the traditional texture feature description method, the local binary pattern (LBP), is unable to acquire more detailed direction information and always sensitive to noise, we propose a novel method based on generalized Gabor direction pattern (GGDP) and weighted discrepancy measurement model (WDMM) to overcome those defects. Firstly, a novel patch-structure direction pattern (PDP) is proposed, which can extract rich feature information and be insensitive to noise. Then, motivated by searching for a description method that can explore richer and more discriminant texture features and reducing the local Gabor feature vector’s high dimension problem, we extend PDP to form the GGDP method with multi-channel Gabor space. Furthermore, WDMM, which can effectively measure the feature distance between two images, is presented for the classification and recognition of image samples. Simulated experiments on olivetti research laboratory (ORL), Carnegie Mellon University pose, illumination, and expression (CMUPIE) and Yale B face databases under different illumination or facial expression conditions indicate that the proposed method outperforms other existing classical methods.

Video application is a research hotspot in cooperative vehicle-infrastructure systems (CVIS) which is greatly related to traffic safety and the quality of user experience. Dealing with large datasets of feedback from complex environments is a challenge when using traditional video application approaches. However, the in-depth structure of deep learning has the ability to deal with high-dimensional data sets, which shows better performance in video application problems. Therefore, the research value and significance of video applications over CVIS can be better reflected through deep learning. Firstly, the research status of traditional video application methods and deep learning methods over CVIS were introduced; the existing video application methods based on deep learning were classified according to generative and discriminative deep architecture. Then, we summarized the main methods of deep learning and deep reinforcement learning algorithms for video applications over CVIS, and made a comparative study of their performances. Finally, the challenges and development trends of deep learning in the field were explored and discussed.