Secure and Efficient Multi-Objective Resource Allocation in RIS-Assisted Vehicular Edge Computing via Blockchain and DRL
IEEE Transactions on Network Science and Engineering · 2026 · 13 · 6589-6607
DOI: 10.1109/tnse.2026.3661549 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Network Science and Engineering, 2026. Verfasst von Shilong Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: Open Fund of the State Key Laboratory of Intelligent Vehicle Safety Technology, Key Industry Innovation Chain Project of Shaanxi Provincial Science and the Technology Department.
Abstract (Originalsprache)
The rapid development of intelligent transportation systems raises stricter requirements for communication reliability, latency, and security. These growing demands are compounded by dynamic vehicular topology and high mobility, which make efficient resource allocation increasingly challenging. We propose SHIELD-VecNet, a blockchain-enabled and reconfigurable intelligent surface (RIS)-assisted vehicular edge computing (VEC) framework designed for secure and efficient resource allocation. The system is modeled as a Markov decision process (MDP) to achieve joint optimization across four dimensions: the age of information (AoI) of vehicle-to-infrastructure links, energy consumption, blockchain latency, and the reliability of vehicle-to-vehicle links. To tackle the high-dimensional hybrid action space and conflicting optimization objectives, we develop the Pareto-aware off-policy soft actor-critic (PAO-SAC) algorithm. This algorithm integrates a dynamic Pareto archive of non-dominated solutions into the replay buffer and incorporates a feature-crossing layer to capture latent correlations and trade-offs among the state space. Furthermore, a vehicular reputation-based byzantine fault tolerance (VRBFT) consensus protocol that utilizes an adaptive dual-threshold triggering mechanism and reputation-driven node selection is designed to reduce blockchain-induced overhead. Simulation results show that SHIELD-VecNet achieves balanced improvements in timeliness, energy efficiency, and reliability, providing an efficient and secure solution for vehicular communication networks.
Förderung
- Open Fund of the State Key Laboratory of Intelligent Vehicle Safety Technology
- Key Industry Innovation Chain Project of Shaanxi Provincial Science and the Technology Department
Zitieren
APA
Li, S., Liu, H., Ma, W., & Liu, X. (2026). Secure and Efficient Multi-Objective Resource Allocation in RIS-Assisted Vehicular Edge Computing via Blockchain and DRL. IEEE Transactions on Network Science and Engineering, 13, 6589-6607. https://doi.org/10.1109/tnse.2026.3661549
Vancouver
Li S, Liu H, Ma W, Liu X. Secure and Efficient Multi-Objective Resource Allocation in RIS-Assisted Vehicular Edge Computing via Blockchain and DRL. IEEE Transactions on Network Science and Engineering. 2026;13:6589-6607. doi:10.1109/tnse.2026.3661549
BibTeX
@article{Li2026,
author = {Li, Shilong and Liu, Hu and Ma, Wenping and Liu, Xuebei},
title = {Secure and Efficient Multi-Objective Resource Allocation in RIS-Assisted Vehicular Edge Computing via Blockchain and DRL},
journal = {IEEE Transactions on Network Science and Engineering},
year = {2026},
volume = {13},
pages = {6589--6607},
doi = {10.1109/tnse.2026.3661549}
}
EUVIMED