The Internet of Vehicles (IoV) has become a key pillar in the future network system. However, intensive computing and task offloading required vehicles to compete for communication and computing resources, seriously affecting the systems time cost, robustness, and security. This paper focuses on solving resource management problems in the presence of interconnected multi-vehicles using shared information. We model this problem using a time-varying Markov decision process, addressing the challenges in task offloading for vehicles. The innovation lies in addressing different offloading scenarios, including vehicle-to-vehicle, vehicle-to-roadside unit (RSU) vehicle-to-multi-access edge computing (MAEC) server offloading, and vehicle-to-base station (BS). We propose a Quantum-inspired Dueling Deep Q-learning (QDDQL) algorithm to develop an Edge Intelligent (EI) offloading strategy. This method allows vehicles’ task offload to become an automated step based on network conditions and user status. The MAEC server offers computing offloading services, while the base station can submit offloading tasks to a cloud blockchain system. This innovative approach balances communication resource utilization, computational resource utilization, and transmission delay. Blockchain technology ensures transparency and security in resource allocation strategies, preventing edge nodes from making wrong decisions using consensus mechanism, and thereby improving the accuracy, timeliness, and security of resource allocation. Simulation results show that compared with existing methods, the proposed solution can significantly improve resource utilization, adaptability, and system scalability, and effectively address the defects of traditional methods.
The Permissioned Blockchain-Based Quantum-Inspired Edge Intelligence Approach for the Services of Future Internet of Vehicles
IEEE Transactions on Intelligent Transportation Systems ; 26 , 5 ; 6171-6185
2025-05-01
1613523 byte
Article (Journal)
Electronic Resource
English
Permissioned Blockchain for Efficient and Secure Resource Sharing in Vehicular Edge Computing
ArXiv | 2019
|