Establishing and maintaining end-to-end connections in a vehicular ad hoc network (VANET) is challenging due to the high vehicle mobility, dynamic inter-vehicle spacing, and variable vehicle density. Mobility prediction of vehicles can address the aforementioned challenge since it can provide better routing planning and improve overall VANET performance in terms of continuous service availability. In this paper, a centralized routing scheme is proposed for VANET assisted by an artificial intelligence-powered software-defined network (SDN) controller. Specifically, the SDN controller can perform accurate mobility prediction through advanced artificial neural network (ANN) technique. Then, based on the mobility prediction, the successful transmission probability and the average delay of each vehicle's request under frequent network topology changes can be estimated by the roadside units (RSUs) or the base station (BS). The estimation is performed based on a stochastic urban traffic model that the vehicle arrival follows a non-homogeneous Poisson process (NHPP). The SDN controller gathers network information from RSUs and BS which are considered as the switches. Based on the global network information, the SDN controller computes optimal routing paths for switches (i.e., BS and RSU). While the source vehicle and destination vehicle are located in the coverage area of the same switch, further routing decision will be made by the RSUs or the BS independently to minimize the overall vehicular service delay. The RSUs or the BS schedules the requests of vehicles by either vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) communication, from the source vehicle to the destination vehicle. Simulation results demonstrate that our proposed centralized routing scheme outperforms others in terms of transmission delay, and the transmission performance of our proposed routing scheme is more robust with varying vehicle velocity.

In this article, we study the application of unmanned aerial vehicle (UAV) for data collection with wireless charging, which is crucial for providing seamless coverage and improving system performance in the next-generation wireless networks. To this end, we propose a reinforcement learning-based approach to plan the route of UAV to collect sensor data from sensor devices scattered in the physical environment. Specifically, the physical environment is divided into multiple grids, where one spot for UAV hovering as well as the wireless charging of UAV is located at the center of each grid. Each grid has a spot for the UAV to hover, and moreover, there is a wireless charger at the center of each grid, which can provide wireless charging to UAV when it is hovering in the grid. When the UAV lacks energy, it can be charged by the wireless charger at the spot. By taking into account the collected data amount as well as the energy consumption, we formulate the problem of data collection with UAV as a Markov decision problem, and exploit Q-learning to find the optimal policy. In particular, we design the reward function considering the energy efficiency of UAV flight and data collection, based on which Q-table is updated for guiding the route of UAV. Through extensive simulation results, we verify that our proposed reward function can achieve a better performance in terms of the average throughput, delay of data collection, as well as the energy efficiency of UAV, in comparison with the conventional capacity-based reward function.

In this paper, we study unmanned aerial vehicle (UAV) aided internet of things (IoT) networks, where UAVs facilitate data transmission of IoT devices. We focus on uplink transmission from IoT devices to base station (BS). Multiple UAVs are employed as UAV relays between IoT devices and BS to enhance received signal strength at BS. Specifically, IoT devices periodically detect wireless channel quality between IoT devices and BS, as well as that among IoT devices. Based on the wireless channel quality, we propose a distributed user cluster (UC) algorithm to cluster IoT devices as multiple UCs. One IoT device in a UC, which is named cluster head (CH), is selected to connect to the BS and gather uplink signals of IoT devices. If the wireless channel quality between CH and BS is good, a direct connection between CH and the BS can be built. Otherwise, UAVs are divided into multiple UAV cooperative relay clusters (CRCs). The UAVs in a CRC are located between a specific CH and BS to relay uplink signals. We then formulate a system optimization model to minimize system power consumption, where UAV deployment and transmission power of UAV are jointly optimized. We solve this optimization problem by dual decomposition method. By extensive simulations, we demonstrate the effectiveness of the proposed algorithm. We also reveal several interesting insights for practical UAV aided IoT networks.

Edge caching is emerging as the most promising solution to reduce the content retrieval delay and relieve the huge burden on the backhaul links in the ultra-dense networks by proactive caching popular contents in the small base station (SBS). However, constraint cache resource of individual SBSs significantly throttles the performance of edge caching. In this paper, we propose a device-to-device (D2D) assisted cooperative edge caching (DCEC) policy for millimeter (mmWave) dense networks, which cooperatively utilizes the cache resource of users and SBSs in proximity. In the proposed DCEC policy, a content can be cached in either users' devices or SBSs according to the content popularity, and a user can retrieve the requested content from neighboring users via D2D links or the neighboring SBSs via cellular links to efficiently exploit the cache diversity. Unlike existing cooperative caching policies in the lower frequency bands that require complex interference management techniques to suppress interference, we take advantage of directional antenna in mmWave systems to ensure high transmission rate whereas mitigating interference footprint. Taking the practical directional antenna model and the network density into consideration, we derive closed-form expressions of the backhaul offloading performance and content retrieval delay based on the stochastic information of network topology. In addition, analytical results indicate that, with the increase of the network density, the content retrieval delay via D2D links increases significantly while that via cellular links increases slightly. Comprehensive simulations validate our theoretical analysis and demonstrate that the proposed policy can achieve higher performance in offloading the backhaul traffic and reducing the content retrieval delay compared with the state-of-the-art most popular caching (MPC) policy.

The proper functioning of connected and autonomous vehicles (CAVs) is crucial for the safety and efficiency of future intelligent transport systems. Meanwhile, transitioning to fully autonomous driving requires a long period of mixed autonomy traffic, including both CAVs and human-driven vehicles. Thus, collaborative decision-making technology for CAVs is essential to generate appropriate driving behaviors to enhance the safety and efficiency of mixed autonomy traffic. In recent years, deep reinforcement learning (DRL) methods have become an efficient way in solving decision-making problems. However, with the development of computing technology, graph reinforcement learning (GRL) methods have gradually demonstrated the large potential to further improve the decision-making performance of CAVs, especially in the area of accurately representing the mutual effects of vehicles and modeling dynamic traffic environments. To facilitate the development of GRL-based methods for autonomous driving, this paper proposes a review of GRL-based methods for the decision-making technologies of CAVs. Firstly, a generic GRL framework is proposed in the beginning to gain an overall understanding of the decision-making technology. Then, the GRL-based decision-making technologies are reviewed from the perspective of the construction methods of mixed autonomy traffic, methods for graph representation of the driving environment, and related works about graph neural networks (GNN) and DRL in the field of decision-making for autonomous driving. Moreover, validation methods are summarized to provide an efficient way to verify the performance of decision-making methods. Finally, challenges and future research directions of GRL-based decision-making methods are summarized.