Multi-Agent Reinforcement Learning for Task Offloading in Crowd-Edge Computing
IEEE Transactions on Mobile Computing · 2025-10 · 24 (10) · 9289-9302
DOI: 10.1109/tmc.2025.3531793 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-10. Verfasst von Su Yao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science Fund for Creative Research Groups of the National Natural Science Foundation of China, Ant Group.
Abstract (Originalsprache)
The Crowd-edge (CE) computing paradigm facilitates the utilization of the computational resources through simultaneously relying the edge computing and the collaboration among various mobile devices (MDs). Most existing works, focusing on offloading tasks from device to edge servers by centralized solutions, are unable to distribute tasks to massive MDs in CE. Meanwhile, designing a decentralized task offloading solution enabling task subscribers to individually make offloading decisions can be challenging given the randomness of crowd resource provisioning and limited knowledge of global status variations. In this paper, we propose a decentralized crowd-edge task offloading solution that enables users to optimally offload tasks to the CE in a distributed manner. Specifically, we formulate the corresponding problem as a stochastic optimization with partially observable status. By observing network and process delays at the crowd side, we further reform the optimization forms and provide a novel approximation policy, enabling users to optimize their offloading strategy based on local observations without interaction with each other. We then solve this task offloading problem by developing a Mixed Multi-Agent Proxy Policy Optimization algorithm (mixed MAPPO). Extensive testing, including numerical and system-level simulations, was conducted to validate the performance of the proposed algorithm in terms of task delay (including the processing delay and transmission delay), load rate, and resource utilization.
Förderung
- National Natural Science Foundation of China
- Science Fund for Creative Research Groups of the National Natural Science Foundation of China
- Ant Group
- Beijing National Research Center for Information Science and Technology
- State Key Laboratory of Networking and Switching Technology
Zitieren
APA
Yao, S., Wang, M., Ren, J., Xia, T., Wang, W., Xu, K., Xu, M., & Zhang, H. (2025). Multi-Agent Reinforcement Learning for Task Offloading in Crowd-Edge Computing. IEEE Transactions on Mobile Computing, 24(10), 9289-9302. https://doi.org/10.1109/tmc.2025.3531793
Vancouver
Yao S, Wang M, Ren J, Xia T, Wang W, Xu K, et al. Multi-Agent Reinforcement Learning for Task Offloading in Crowd-Edge Computing. IEEE Transactions on Mobile Computing. 2025;24(10):9289-9302. doi:10.1109/tmc.2025.3531793
BibTeX
@article{Yao2025,
author = {Yao, Su and Wang, Mu and Ren, Ju and Xia, Tianyu and Wang, Weiqiang and Xu, Ke and Xu, Mingwei and Zhang, Hongke},
title = {Multi-Agent Reinforcement Learning for Task Offloading in Crowd-Edge Computing},
journal = {IEEE Transactions on Mobile Computing},
year = {2025},
volume = {24},
number = {10},
pages = {9289--9302},
doi = {10.1109/tmc.2025.3531793}
}
EUVIMED