EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Task Offloading with LLM-Enhanced Multi-Agent Reinforcement Learning in UAV-Assisted Edge Computing

Feifan Zhu iD, Fei Huang, Yantao Yu iD, Guojin Liu iD, Tiancong Huang iD

Sensors · 31.12.2024 · 25 (1) · 175

DOI: 10.3390/s25010175 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 31.12.2024. Verfasst von Feifan Zhu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2021 State Grid Corporation of China Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unmanned aerial vehicles (UAVs) furnished with computational servers enable user equipment (UE) to offload complex computational tasks, thereby addressing the limitations of edge computing in remote or resource-constrained environments. The application of value decomposition algorithms for UAV trajectory planning has drawn considerable research attention. However, existing value decomposition algorithms commonly encounter obstacles in effectively associating local observations with the global state of UAV clusters, which hinders their task-solving capabilities and gives rise to reduced task completion rates and prolonged convergence times. To address these challenges, this paper introduces an innovative multi-agent deep learning framework that conceptualizes multi-UAV trajectory optimization as a decentralized partially observable Markov decision process (Dec-POMDP). This framework integrates the QTRAN algorithm with a large language model (LLM) for efficient region decomposition and employs graph convolutional networks (GCNs) combined with self-attention mechanisms to adeptly manage inter-subregion relationships. The simulation results demonstrate that the proposed method significantly outperforms existing deep reinforcement learning methods, with improvements in convergence speed and task completion rate exceeding 10%. Overall, this framework significantly advances UAV trajectory optimization and enhances the performance of multi-agent systems within UAV-assisted edge computing environments.

Schlagwörter

Stichwörter der Autor:innen

LLMUAVmulti-agent deep learningtrajectory planning

Autor:innen und Institutionen

  • School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China.
  • State Grid Chongqing Electric Power Company, Electric Power Research Institute, Chongqing 401123, China.

ORCID-Profile: Feifan Zhu, Yantao Yu, Guojin Liu, Tiancong Huang

Förderung

  • 2021 State Grid Corporation of China Science and Technology Program

Zitieren

APA

Zhu, F., Huang, F., Yu, Y., Liu, G., & Huang, T. (2024). Task Offloading with LLM-Enhanced Multi-Agent Reinforcement Learning in UAV-Assisted Edge Computing. Sensors, 25(1), 175. https://doi.org/10.3390/s25010175

Vancouver

Zhu F, Huang F, Yu Y, Liu G, Huang T. Task Offloading with LLM-Enhanced Multi-Agent Reinforcement Learning in UAV-Assisted Edge Computing. Sensors. 2024;25(1):175. doi:10.3390/s25010175

BibTeX
@article{Zhu2024,
  author = {Zhu, Feifan and Huang, Fei and Yu, Yantao and Liu, Guojin and Huang, Tiancong},
  title = {Task Offloading with LLM-Enhanced Multi-Agent Reinforcement Learning in UAV-Assisted Edge Computing},
  journal = {Sensors},
  year = {2024},
  volume = {25},
  number = {1},
  pages = {175},
  doi = {10.3390/s25010175}
}
Kostenlos starten →