Search

Due to the rapid development of the Internet of Vehicles (IoV), the combination of IoV and edge computing, known as vehicle edge computing (VEC), has received considerable attention from both academia and industry. However, task offloading in diverse intersection scenarios remains suffering from inefficiency of resource allocation and low quality of service for task execution due to the imbalance of traffic flow and the rigid requirement of latency. To address these issues, we develop a task offloading strategy by a fuzzy decision-making algorithm to handle uncertainty and imprecision. This task offloading strategy comprises two components: (1) A VEC resource pool with available vehicles at each intersection is constructed when taking the rotating direction of the recognition region. Then, we introduce a fuzzy decision-making algorithm to select a set of high-quality service vehicles from this VEC resource pool as an auxiliary edge server (AS). (2) We employ an edge service provider (ESP) to manage the computational resources of a main edge server (MS) and an AS deployed at a traffic intersection. The negotiation between the ESP and the task vehicles is modeled as a Stackelberg game. We prove the existence of the unique perfect Nash equilibrium, and a genetic algorithm is applied to find the optimum. Finally, we conduct simulation experiments with datasets collected in real-world scenarios. The results demonstrate that our scheme decreases task execution time by 9.73% compared to the cloud server scheme and reduces energy consumption by 13.78% compared to the state-of-the-art reinforcement learning (RL) strategy. [ABSTRACT FROM AUTHOR]

With the rapid advancement of Internet of vehicles and autonomous driving technology, there is a growing need for increased computing power in vehicle operations. However, the strict latency requirements of vehicle tasks may pose challenges to communication and computing resources within the vehicle edge computing network. This paper introduces a two-stage joint optimization to address challenges, focusing on minimizing vehicle task latency and optimizing resource allocation. In addition, the task completion rate is considered an important indicator to ensure safety and reliability in practical application scenarios. Next, we propose a global adaptive offloading and resource allocation optimization model named GOAL. The GOAL model dynamically adjusts the weight coefficients of the reward function to optimize the model, integrating the actor-critic algorithm to effectively adapt to uncertain environments. Through experimental comparisons of various weight coefficients for task arrival rates and reward functions, we were able to determine the optimal hyperparameters for our proposed model. The simulation results show that the GOAL model outperforms the benchmark methods by over 30% in reward value. It also performs better in terms of task delay and energy consumption. Additionally, the GOAL model has a higher task completion rate compared to the benchmark methods, and it exhibits strong search capabilities and faster convergence speed. [ABSTRACT FROM AUTHOR]

The rapid growth and technological progressions in the vehicle edge computing and networks (VECON) enhanced existing vehicular administrations through information sharing and information investigation, which further incremented traffic security difficulties. This carries the need to verify vehicle networks with gigantic information stockpiling substances. Recognizing the vehicles that communicate fashioned messages and ensuring the protection of every vehicle is an essential assignment. Blockchain can be utilized as an effective solution to provide security during vehicle edge computing. Every transaction and data is recorded in the blockchain, which expands the number of blocks after some time. Another test in blockchain methods is utilizing a consensus mechanism, which can be effectively undermined by the attackers. Artificial intelligence (AI) trained by machine learning (ML) algorithms as an amazing paradigm can be incorporated with blockchain to settle these issues. The data storing methods of blockchain can likewise be enhanced with the assistance of ML algorithms. In this paper, a two-tier authenticated consortium blockchain (TTA-CB) protocol is proposed for secure information partaking in Vehicle Edge Computing and Networks (VECONs). Utilizing a one-time password (OTP) based notoriety estimation calculation, the misbehaving vehicles are recognized. The use of Particle Swarm Optimization (PSO) understands the ideal data provider selection issue utilizing notoriety esteems. Exploratory outcomes demonstrate the importance of the proposed strategy, and the correlation results demonstrate that the proposed technique is unrivaled and secure. [ABSTRACT FROM AUTHOR]