EUVIMEDEUVIMED entdecken
Crossref

Multiagent Reinforcement Learning for Offloading Cellular Communications With Cooperating UAVs

Abhishek Mondal, Deepak Mishra, George C. Alexandropoulos, Azzam Al-nahari, Riku Jäntti

IEEE Transactions on Aerospace and Electronic Systems · 2025-08 · 61 (4) · 9344-9358

DOI: 10.1109/taes.2025.3554150 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Aerospace and Electronic Systems, 2025-08. Verfasst von Abhishek Mondal und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Australian Research Council Discovery Early Career Researcher, Project 6GARROW, Smart Networks and Services Joint Undertaking.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Effective solutions for intelligent data collection in terrestrial cellular networks are crucial, especially in the context of Internet of Things applications. The limited spectrum and coverage area of terrestrial base stations (BSs) pose challenges in meeting the escalating data rate demands of network users. Uncrewedaerial vehicles (UAVs), known for their high agility, mobility, and flexibility, present an alternative means to offload data traffic from terrestrial BSs, serving as additional access points. In this article, we aim to efficiently maximize the utilization of multiple UAVs for data traffic offloading from terrestrial BSs. Specifically, the focus is on maximizing user association with UAVs by jointly optimizing UAV trajectories and users' association indicators under quality-of-service (QoS) constraints. Since the formulated practical UAV control problem is nonconvex and combinatorial, this study leverages the multiagent reinforcement learning (MARL) framework. Employing MARL, each UAV acts as an independent agent, aiming to maintain inter-UAV cooperative behavior. The proposed approach utilizes the finite-state Markov decision process to account for UAVs' velocity constraints and the relationship between their trajectories and state space. A low-complexity distributed state-action-reward-state-action algorithm is presented to determine UAVs' optimal sequential decision-making policies over training episodes. The extensive simulation results validate the proposed analysis and offer valuable insights into the optimal UAV trajectories. The derived trajectories demonstrate superior average UAV association performance compared to benchmark techniques, such as Q-learning and particle swarm optimization.

Förderung

  • Australian Research Council Discovery Early Career Researcher
  • Project 6GARROW
  • Smart Networks and Services Joint Undertaking
  • EU's Horizon Europe research and innovation program
  • Institute for Information & Communications Technology Promotion
  • Korean government

Zitieren

APA

Mondal, A., Mishra, D., Alexandropoulos, G. C., Al-nahari, A., & Jäntti, R. (2025). Multiagent Reinforcement Learning for Offloading Cellular Communications With Cooperating UAVs. IEEE Transactions on Aerospace and Electronic Systems, 61(4), 9344-9358. https://doi.org/10.1109/taes.2025.3554150

Vancouver

Mondal A, Mishra D, Alexandropoulos GC, Al-nahari A, Jäntti R. Multiagent Reinforcement Learning for Offloading Cellular Communications With Cooperating UAVs. IEEE Transactions on Aerospace and Electronic Systems. 2025;61(4):9344-9358. doi:10.1109/taes.2025.3554150

BibTeX
@article{Mondal2025,
  author = {Mondal, Abhishek and Mishra, Deepak and Alexandropoulos, George C. and Al-nahari, Azzam and Jäntti, Riku},
  title = {Multiagent Reinforcement Learning for Offloading Cellular Communications With Cooperating UAVs},
  journal = {IEEE Transactions on Aerospace and Electronic Systems},
  year = {2025},
  volume = {61},
  number = {4},
  pages = {9344--9358},
  doi = {10.1109/taes.2025.3554150}
}
Kostenlos starten →