EUVIMEDEUVIMED entdecken
Crossref

Multi-Agent Deep Reinforcement Learning With Trajectory Prediction for Task Migration-Assisted Computation Offloading

Xinyi Zhang, Chunyang Wang, Yanmin Zhu, Jian Cao, Tong Liu

IEEE Transactions on Mobile Computing · 2025-07 · 24 (7) · 5839-5856

DOI: 10.1109/tmc.2025.3539945 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-07. Verfasst von Xinyi Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Program of Technology Innovation of the Science and Technology, Shanghai East Talents Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-access edge computing has become an effective paradigm to provide offloading services for computation-intensive and delay-sensitive tasks on vehicles. However, high mobility of vehicles usually incurs spatio-temporal load-imbalances among edge servers. Therefore, task migration is employed to maintain dynamic workload balancing by transmitting excessive tasks from overloaded to underloaded servers. Recent studies adopt deep reinforcement learning approaches to generate offloading and migration decisions based on current observations of systems. However, we argue that the migration direction is highly dependent on vehicular movements, and task migration towards the wrong direction could lead to additional delays. Therefore, we emphasize the importance of guiding task migration via exploring prospective trajectories of vehicles. We propose a Mobility-Aware Cooperative Multi-Agent (MCMA) deep reinforcement learning approach to make vehicle-by-vehicle decisions in multi-edge computation offloading scenarios. A two-stage decision framework is designed to solve the joint optimization problem of computation offloading and resource allocation. Additionally, an Informer-based multi-step vehicular trajectory prediction module is incorporated to enhance the capability of forecasting vehicular movements. Extensive experiments and analysis are conducted on synthetic and realistic scenarios, showing that our approach consistently outperforms both heuristic and DRL-based methods. The simulation scenarios and source codes are publicly available here.

Förderung

  • National Natural Science Foundation of China
  • Program of Technology Innovation of the Science and Technology
  • Shanghai East Talents Program

Zitieren

APA

Zhang, X., Wang, C., Zhu, Y., Cao, J., & Liu, T. (2025). Multi-Agent Deep Reinforcement Learning With Trajectory Prediction for Task Migration-Assisted Computation Offloading. IEEE Transactions on Mobile Computing, 24(7), 5839-5856. https://doi.org/10.1109/tmc.2025.3539945

Vancouver

Zhang X, Wang C, Zhu Y, Cao J, Liu T. Multi-Agent Deep Reinforcement Learning With Trajectory Prediction for Task Migration-Assisted Computation Offloading. IEEE Transactions on Mobile Computing. 2025;24(7):5839-5856. doi:10.1109/tmc.2025.3539945

BibTeX
@article{Zhang2025,
  author = {Zhang, Xinyi and Wang, Chunyang and Zhu, Yanmin and Cao, Jian and Liu, Tong},
  title = {Multi-Agent Deep Reinforcement Learning With Trajectory Prediction for Task Migration-Assisted Computation Offloading},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2025},
  volume = {24},
  number = {7},
  pages = {5839--5856},
  doi = {10.1109/tmc.2025.3539945}
}
Kostenlos starten →