Connected and automated vehicles (CAVs) will become the mainstream of urban traffic. However, the existing scheduling schemes, such as traffic lights, are difficult to guide CAVs to pass through intersections efficiently. In order to improve vehicle traffic efficiency, a scheduling scheme based on sequential selection is designed for intersections without traffic lights. A feasible time for a vehicle to arrive at the intersection is planned according to its physical abilities and status of other CAVs. Extensive simulation experiments are conducted on the SUMO platform to verify the effectiveness of the proposed scheme. From the experimental results, it is revealed that the proposed scheme improves the traffic efficiency at intersections, comparing with other methods. Especially, when the traffic load is heavy, the performance gain of the proposed scheme is more obvious.

Special roads set up in highway used to realize dynamic wireless charging for In-motion electric vehicles that leads to a profound change in the field of traffic engineering. However, on the premise of the maximum charging effect of EV, how to schedule and manage such vehicles to improve traffic safety and road capacity is a key issue that cannot be avoided. Therefore, this paper first establishes the vehicle scheduling model of the system. A new reverse elitist mutation particle swarm optimization (REMPSO) algorithm is proposed.And its rapidity, stability and optimization ability are proved by comparing with the traditional particle swarm optimization and genetic algorithm. Finally, this algorithm is used to solve the system model, and the optimal moving isolation partition is obtained. Based on cooperative vehicle infrastructure system, the paper provides a feasible control strategy for the right of way scheduling of dynamic wireless charging for In-motion EV.

In order to solve the problems of considering only one transportation mode and neglecting user preference in transportation recommendation problem, and class imbalance problem in multi-class task, a context-aware multi-modal transportation recommendation method based on particle swarm optimization and LightGBM is proposed. This method comprehensively considers the user’s travel preferences in terms of time, space and travel cost, and uses mathematical statistics and representation learning methods to capture the internal relationship between user travel and various elements. At the same time, in order to alleviate the negative impact caused by the imbalance of sample class, the index optimization method based on particle swarm optimization algorithm is used to search for the optimal weight for each class, and the prediction results of the model are modified to achieve the purpose of maximizing the evaluation index. Experimental results show that compared with traditional algorithms, the model proposed in this paper has better performance in spatio-temporal feature extraction, alleviating class imbalance and recommendation accuracy.

A three dimensional (3D) modified tunnel multi-bounced scattering channel model for vehicle to vehicle mobile communication is proposed under the assumption of equivalent scattering point. In this model, multi-antenna technology is adapted in both the mobile transmitter and receiver and there are line of sight (LOS) and non-LOS (NLOS) propagation paths between the transmitter and receiver. Analytical expressions of the probability density function (PDF) of the angle-of-departure (AOD) and angle-of-arrival (AOA) are presented according to the 3D MIMO channel model. Results show good agreement with the existing V2V scattering channel models and measured data in real tunnel environment,demonstrating the rationality of the underlying channel model.

Focusing on the weakness of the balance capability between global exploration and local search in the classical GWO algorithm, a novel grey wolf algorithm based on opposition learning (OLGWO), which can evolve the hyper-parameters of forecasting model, is proposed to improve the accuracy and enhance the robustness of traffic flow forecasting models. This algorithm is designed to take advantage of opposition learning strategy with the iterative process, and exploits the concept of rank correlation that can describe the Spearman correlation coefficients between the target wolf and the common wolves, and then selectively updates the each wolf of the whole population according to their values. Firstly, the performance comparison of four algorithms (OLGWO, TGWO, GWO, PSO), based on 12 benchmark functions, is conducted in terms of the two metrics, namely the optimization means and standard deviations. The results verify the outstanding performance of the proposed algorithm. Furthermore, based on the California highway traffic flow data, the four models optimized by the concerned algorithms are compared under different loss rates. The results show that the prediction accuracy of OLGWO-BP is higher than that of the others by 1.95%, 3.98% and 11.07%, respectively, and the stability is better.

In the three-dimensional vehicular ad-hoc networks (3D-VANET), high-speed moving vehicle nodes and changeable link states lead to unstable inter-vehicle communication links. Aiming at this problem, the time-space evolution graph model is constructed by introducing software define network technology to obtain network state in real-time and predict the process of time change and the link utility index is defined to quantify the wireless link performance. Then the weighted time-space evolution graph model based on link utility is established.Finally, the routing decision-making problem is transformed into a multi-attribute decision-making problem, and a link utility based reliable routing (LURR) algorithm is designed. Simulation results show that, compared with the existing four routing protocols, LURR algorithm has significantly improved packet transmission rate, end-to-end delay and routing load rate.

With the integration of mobile edge computing offloading into internet of vehicles, vehicular edge computing offloading can support low-latency, high-bandwidth and high-reliability application services. We first introduce the background and significance of vehicular edge computing offloading technology as well as the contributions of this survey. Then, we describe the network architecture, key challenges as well as popular application scenarios of vehicular edge computing offloading, respectively. After that, we provide the comprehensive survey of the state-of-the-art vehicular edge computing offloading from the different dimensions, including mobility analysis, offloading model, resource cooperation as well as management. Finally, we point out the future work about vehicular edge computing offloading, which can provide valuable reference and guidance for the in-depth study in vehicular edge computing offloading.

In vehicular edge computing environments, the Co-channel interferences (CCI) is a critical problem when edge nodes allocate channels for different data transmission tasks. This article formulates the problem of channel allocation in vehicular edge computing, aiming at allocating sub-channels for different data transmission tasks and maximizing the ratio of successful data transmission. We transform the global optimization problem of channel allocation into a channel allocation potential game, and prove the existence of nash equilibrium. We propose an Incentive-based probability update and strategy selection algorithm, which updates the strategy selection probability according to the incentive value of the selected strategy in each iteration, and further analyzes the Nash equilibrium converge of the algorithm. Finally, we verify the convergence of the proposed algorithm and the effectiveness of the Nash equilibrium. The experimental results show that the proposed algorithm outperforms existing representative algorithms in terms of the ratio of successful data transmission and channel utilization efficiency.

The emergence and development of intelligent transportation system (ITS) put forward higher requirements for the medium access control (MAC) protocol of vehicle communication. The widely used carrier sense multiple access (CSMA) protocol based on channel competition has the problem of uncertain time delay. MAC protocol based on time division multiple access (TDMA) can effectively solve this problem. However, TDMA protocols cannot eliminate data transmission collisions. This paper propose a communication framework combining fog computing.And a centralized TDMA MAC protocol is proposed, which could predict upcoming data transmission collisions by taking advantage of the low-latency of fog computing. Then, time slots could be well scheduled to reduce data transmission collisions. Experimental simulation results show that this method effectively reduces data transmission collisions, and improves channel resource utilization.

Internet of vehicles has strict requirements in Ultra-Reliable and Low Latency Communications (URLLC). Especially in vehicle to infrastructure (V2I) scenario, URLLC is crucial to correctly transport and manage traffic conditions. 3GPP Cellular-V2X (C-V2X), as the current mainstream wireless technology supporting the URLLC, still has technical challenges. In order to further improve the communication performance, this paper designs an intelligent channel estimation framework based on C-V2I specification based on the interaction between vehicle terminal, road side unit (RSU) and edge computing Internet of Vehicles server (IoV Server) in V2I communication scenario. In IoV Server, this paper proposes a channel estimation algorithm based on deep learning, which uses one-dimensional convolutional neural network (1D CNN) to complete frequency-domain interpolation and conditional recurrent unit (CRU) to predict the time-domain state. By introducing additional velocity coding vector and multipath coding vector, the channel data in different mobile environments are accurately trained. Finally, system simulation and analysis show that the proposed algorithm can track the channel changes in different high-speed mobile environments through channel parameter coding, and realize the accurate training of channel data. Compared with the representative channel estimation algorithms in the IoV, the proposed algorithm improves the channel estimation accuracy, reduces the bit error rate and enhances the robustness.