EUVIMEDEUVIMED entdecken
Crossref

DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach

Zhang Liu, Hongyang Du, Junzhe Lin, Zhibin Gao, Lianfen Huang, Seyyedali Hosseinalipour, Dusit Niyato

IEEE Transactions on Mobile Computing · 2025-03 · 24 (3) · 1945-1962

DOI: 10.1109/tmc.2024.3486728 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-03. Verfasst von Zhang Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 94-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Fujian Province of China, China Scholarship Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of Artificial Intelligence (AI) has introduced Deep Neural Network (DNN)-based tasks to the ecosystem of vehicular networks. These tasks are often computation-intensive, requiring substantial computation resources, which are beyond the capability of a single vehicle. To address this challenge, Vehicular Edge Computing (VEC) has emerged as a solution, offering computing services for DNN-based tasks through resource pooling via Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communications. In this paper, we formulate the problem of joint DNN partitioning, task offloading, and resource allocation in VEC as a dynamic long-term optimization. Our objective is to minimize the DNN-based task completion time while guaranteeing the system stability over time. To this end, we first leverage a Lyapunov optimization technique to decouple the original long-term optimization with stability constraints into a per-slot deterministic problem. Afterwards, we propose a Multi-Agent Diffusion-based Deep Reinforcement Learning (MAD2RL) algorithm, incorporating the innovative use of diffusion models to determine the optimal DNN partitioning and task offloading decisions. Furthermore, we integrate convex optimization techniques into MAD2RL as a subroutine to allocate computation resources, enhancing the learning efficiency. Through simulations under real-world movement traces of vehicles, we demonstrate the superior performance of our proposed algorithm compared to existing benchmark solutions.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Fujian Province of China
  • China Scholarship Council
  • National Research Foundation Singapore
  • Infocomm Media Development Authority under its Future Communications Research & Development Programme, Defence Science Organisation
  • Singapore Ministry of Education (MOE) Tier 1
  • NTU Centre for Computational Technologies in Finance

Zitieren

APA

Liu, Z., Du, H., Lin, J., Gao, Z., Huang, L., Hosseinalipour, S., & Niyato, D. (2025). DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach. IEEE Transactions on Mobile Computing, 24(3), 1945-1962. https://doi.org/10.1109/tmc.2024.3486728

Vancouver

Liu Z, Du H, Lin J, Gao Z, Huang L, Hosseinalipour S, et al. DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach. IEEE Transactions on Mobile Computing. 2025;24(3):1945-1962. doi:10.1109/tmc.2024.3486728

BibTeX
@article{Liu2025,
  author = {Liu, Zhang and Du, Hongyang and Lin, Junzhe and Gao, Zhibin and Huang, Lianfen and Hosseinalipour, Seyyedali and Niyato, Dusit},
  title = {DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2025},
  volume = {24},
  number = {3},
  pages = {1945--1962},
  doi = {10.1109/tmc.2024.3486728}
}
Kostenlos starten →