Vehicular ad hoc networks (VANETs) are a type of mobile ad hoc network that forms a unified wireless communication network between vehicles and roadside nodes. Roadside units (RSUs), as the infrastructure and key component of VANETs, play a critical role in improving the performance of VANETs. Their deployment can effectively improve the communication performance of the network. The goal of the RSU deployment (RSUD) problem is to install as few RSUs as possible on both sides of roads or intersections so that they can cover most areas and achieve better communication performance. This paper proposes a multi-objective optimization model to solve the RSUD problem using the characteristics of RSUDs on urban roads. Our optimized target includes three performance indicators, which are the deployment cost of RSUs, their coverage area, and communications. Since these three indicators cannot achieve consensus, this paper proposes a multi-objective evolutionary algorithm, the NSGA-II Pareto optimal solution, to solve the RSUD problem. The simulation results show the effectiveness of the multi-objective model and method. Finally, we present an experiment featuring RSU deployment that is based on a real traffic environment and uses OpenStreetMap; this experiment proves that our proposed method is practical.

With the continuous progress of UAV technology and the rapid development of mobile edge computing (MEC), the UAV-assisted MEC system has shown great application potential in special fields such as disaster rescue and emergency response. However, traditional deep reinforcement learning (DRL) decision-making methods suffer from limitations such as difficulty in balancing multiple objectives and training convergence when making mixed action space decisions for UAV path planning and task offloading. This article innovatively proposes a hybrid decision framework based on the improved Dynamic Adaptive Genetic Optimization Algorithm (DAGOA) and soft actor–critic with hierarchical action decomposition, an uncertainty-quantified critic ensemble, and adaptive entropy temperature, where DAGOA performs an effective search and optimization in discrete action space, while SAC can perform fine control and adjustment in continuous action space. By combining the above algorithms, the joint optimization of drone path planning and task offloading can be achieved, improving the overall performance of the system. The experimental results show that the framework offers significant advantages in improving system performance, reducing energy consumption, and enhancing task completion efficiency. When the system adopts a hybrid decision framework, the reward score increases by a maximum of 153.53% compared to pure deep reinforcement learning algorithms for decision-making. Moreover, it can achieve an average improvement of 61.09% on the basis of various reinforcement learning algorithms such as proposed SAC, proximal policy optimization (PPO), deep deterministic policy gradient (DDPG), and twin delayed deep deterministic policy gradient (TD3).

Appropriate task offloading management strategy is a challenging problem for high delay-sensitive and heavy-task applications. This paper proposes a fuzzy-based mobile edge manager with task partitioning, which can handle the multi-criteria decision-making process by considering multiple parameters in the MEC network framework and make appropriate offloading decisions for incoming tasks of IoT applications. Considering that the mobile devices are becoming more and more powerful, this paper also takes WLAN delay and the computing power of mobile devices into account, forming a three-level fuzzy logic system. In addition, since many tasks of Internet of Things applications are composed of several independent modules, this paper also sets two optimal task partitioning ratios, which have symmetry, so that each module can be independently executed in each layer of the MEC network. In addition, results will return to the mobile devices after execution, so as to minimize the service time and improve QoS. Finally, several indexes such as task failure rate and service time are simulated, and the results show that the proposed scheme has better performance compared with the other four comparison schemes, especially for high-latency sensitivity and heavy-task applications.

The signal control system for multi-intersection traffic management is an extensive complex nonlinear and non-equilibrium system and usually leads to a weak control strategy. Existing studies of traffic dynamics mainly focus on the applications to the single network, whereas how the structure of multiple intersections affects the dynamical behaviors is unclear. Connected vehicles in recent studies have shown the potential to eliminate traffic communication barriers and balance the traffic load. For this consideration, we propose a new multi-intersection model based on Vehicle-to-Everything (V2X) network to capture the features of traffic flow, which employs vehicular communication to obtain real-time traffic information and share it among the adjacent intersections. Focus on smoothing traffic flow without stop-and-go driving and improving the coordination of multiple traffic lights, we develop a multi-intersection coordination algorithm based on V2X (MICA-V for short) to maximize the green waveband in the arterial road. Due to the establishment of registration list yielding the average saturated headway time, our method is of high efficiency—the distributed process of data makes the convergence to be very fast with nearly linear time. Simulation results via MATLAB with Simulation of Urban Mobility (SUMO) showed the effectiveness of the proposed MICA-V in improving traffic capacity, reducing the number of stop behaviors, and improve the average speed of vehicles moving on the arterial road.