In this paper, we study the task offloading problem on mobile edge in vehicular networks. Specifically, we take computational resource constraints into consideration, and aim to simultaneously reduce latency and energy consumption. For this purpose, we establish an offloading model that consists of local edge computing resources, edge server resources of both macro and subsidiary base stations, as well as cloud computing server resources. Each task can be offloaded through one of five strategies, and is evaluated via a loss function determined by its latency and energy consumption. Based on this model, our goal is to solve a mixed-integer non-linear optimization problem (MINLP) whose objective function is the weighted sum of the task-specific loss functions. To address this optimization problem, we split it into two sub-problems, referred to as resource allocation and offloading strategy. We develop a method based on Block Coordinate Descent technique combining convex optimization and Gray Wolf algorithm (BCD-CONGW) that alternatively solves the two sub-problems, until convergence. The former sub-problem is convex and can be solved in polynomial time, whereas the latter is non-convex and hence NP-hard. For the latter, we relax discrete variables and employ Gray Wolf algorithm with elite strategy to approximate its optimal point. By numerical evaluations, we show that our method outperforms existent methods in terms of latency and energy consumption.

Spectrum sharing in cellular vehicle-to-everything (C-V2X) has been conceived as a promising solution to improve spectrum efficiency. However, the co-channel interference incurred with it may cause severe performance degradation to vehicular links. Thereby, radio resource management (RRM) is motivated and designed to ensure communication reliability and increase system capacity. One challenge is that RRM involves channel allocation and power control, which are tightly coupled and hard to optimize simultaneously. Another challenge for this is the difficulty adapting centralized RRM schemes, requiring global channel state information (CSI) and causing high signaling overhead. To tackle these challenges, we propose the hybrid centralized-distributed RRM scheme and the distributed RRM scheme. Specifically, we prove a decoupling method that provides a theoretical lower bound so that channel allocation and power control can be optimized independently. Given the decoupling method, the hybrid centralized-distributed RRM scheme is based on graph matching and reinforcement learning (GMRL) to maximize system capacity and guarantee reliability requirements. Further, to decrease computation complexity and signaling overhead, the distributed RRM scheme that only requires local CSI with hybrid-framework reinforcement learning (HFRL) is exploited. Finally, both schemes are numerically evaluated through experiments and outperform other deep Q-network (DQN)-based schemes.

This article develops a computationally efficient fault-detection method for power systems, by exploiting phasor measurement unit (PMU) data and Hessian locally linear embedding (HLLE) technique. First, via HLLE technique, high-dimensional PMU data are transformed into low-dimensional embedding coordinates, which effectively captures the fluctuations of PMU data. Next, based on the feature space of embedding coordinates, T-squared statistic is employed for online fault detection. The method is evaluated on IEEE 39-bus system and a real-world system, exhibiting decent fault-detection performance as well as a considerably lower computational complexity when compared with existent methods.

In the pursuit of achieving optimal functionality for Internet of Vehicles (IoV), the integration of multiaccess edge computing (MEC) emerges as a solution, offering high bandwidth, low latency, robust security, and reliability services. In this article, we consider a multiuser multiserver vehicular network scenario, where the nonorthogonal multiple access (NOMA) technology in 5G is used to optimize spectrum resource utilization. We first formulate the problem using mixed integer nonlinear programming (MINLP) and propose a task scheduling scheme based on deep reinforcement learning (DRL) to handle high-dimensional state and action spaces and to approximate the optimal solution. We then proposed solutions to the NOMA clustering and power allocation problems in order to further reducing system latency in the uplink transmission stage. Simulation results underscore the efficacy of our proposed algorithm in systems with unevenly distributed computing resources, showcasing superior performance compared to alternative algorithms.

We propose a hybrid centralized-distributed radio resource management (RRM) scheme for cellular vehicle-to-everything (C-V2X), which is to mitigate the interference caused by radio resource sharing between vehicle-to-infrastructure (V2I) links and vehicle-to-vehicle (V2V) links. Specifically, it contains two decoupled aspects: centralized channel allocation and distributed power control. The former is conducted by graph matching to decide spectrum sharing strategy; the latter is performed via actor-critic learning, a deep deterministic policy gradient (DDPG)-based algorithm, to increase the total system capacity. Finally, the proposed scheme is numerically evaluated and outperforms other deep Q-network (DQN)-based schemes in terms of the system capacity.