Federated Multi-Agent DRL for Task Offloading in Vehicular Edge Computing
Electronics · 2025-09-01 · 14 (17) · 3501
DOI: 10.3390/electronics14173501 ↗At a glance
Journal article in Electronics, published online on 2025-09-01. Written by Hongwei Zhao and 3 co-authors. Cited 13 times so far (Crossref); 29 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Northeast Geoscience and Science and Technology Innovation Center Regional Innovation Fund Project.
Abstract (original language)
With the expansion of vehicle-to-everything (V2X) networks and the rising demand for intelligent services, vehicle edge computing encounters heightened requirements for more efficient task offloading. This study proposes a task offloading technique that utilizes federated collaboration and multi-agent deep reinforcement learning to reduce system latency and energy consumption. The task offloading issue is formulated as a Markov decision process (MDP), and a framework utilizing the Multi-Agent Dueling Double Deep Q-Network (MAD3QN) is developed to facilitate agents in making optimal offloading decisions inside intricate environments. Secondly, Federated Learning (FL) is implemented during the training phase, leveraging local training outcomes from many vehicles to enhance the global model, thus augmenting the learning efficiency of the agents. Experimental results indicate that, compared to conventional baseline algorithms, the proposed method decreases latency and energy consumption by at least 10% and 9%, respectively, while enhancing the average reward by at least 21%.
Funding
- National Natural Science Foundation of China
- Northeast Geoscience and Science and Technology Innovation Center Regional Innovation Fund Project
Cite
APA
Zhao, H., Li, Y., Pang, Z., & Ma, Z. (2025). Federated Multi-Agent DRL for Task Offloading in Vehicular Edge Computing. Electronics, 14(17), 3501. https://doi.org/10.3390/electronics14173501
Vancouver
Zhao H, Li Y, Pang Z, Ma Z. Federated Multi-Agent DRL for Task Offloading in Vehicular Edge Computing. Electronics. 2025;14(17):3501. doi:10.3390/electronics14173501
BibTeX
@article{Zhao2025,
author = {Zhao, Hongwei and Li, Yu and Pang, Zhixi and Ma, Zihan},
title = {Federated Multi-Agent DRL for Task Offloading in Vehicular Edge Computing},
journal = {Electronics},
year = {2025},
volume = {14},
number = {17},
pages = {3501},
doi = {10.3390/electronics14173501}
}
EUVIMED