EUVIMEDEUVIMED entdecken
Crossref

Deep-Reinforcement-Learning-Based Resource Management for Task Offloading in Integrated Terrestrial and Nonterrestrial Networks

Nway Nway Ei, Pyae Sone Aung, Zhu Han, Walid Saad, Choong Seon Hong

IEEE Internet of Things Journal · 01.05.2025 · 12 (9) · 11977-11993

DOI: 10.1109/jiot.2024.3521095 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.05.2025. Verfasst von Nway Nway Ei und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Institute of Information and Communications Technology Planning and Evaluation, Korea Government, Evolvable Deep Learning Model Generation Platform for Edge Computing.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Integrated terrestrial-nonterrestrial networks have recently gained much attention because they can bridge the gap between the conventional terrestrial infrastructure and nonterrestrial networks. In addition to seamless connectivity, such networks can offer edge computing services to the users with real-time data processing demand. In this article, an integrated terrestrial-nonterrestrial network with multiaccess edge computing (ITNT-MEC) system is considered in which the aerial users (AUEs) share the resources of terrestrial base stations (TBSs) with their existing terrestrial users (TUEs) and that of low-Earth orbit (LEO) satellites with their neighboring satellites. The goal is to minimize the total energy consumption of AUEs, TUEs, and LEO satellites by jointly optimizing the AUE-TBS/LEO satellite association, AUEs’ trajectories, task allocation, as well as network resource allocation. Due to the dynamic nature of network environment and nonconvex characteristics, it is significantly challenging to solve the formulated optimization problem. Therefore, a block coordinate descent (BCD)-based algorithm that integrates deep reinforcement learning (DRL) methods, such as double deep Q-learning network (DDQN), deep deterministic policy gradient (DDPG), and convex optimization methods, is proposed. Simulation results show that the total energy consumption in the proposed approach is reduced by 14%, 26.9%, 34%, 35.8%, 45.5%, and 55.4%, respectively, when compared to the baselines, such as DDPG-based task offloading (DDPG-TO), DDQN-based task offloading (DDQN-TO), DQN-based task offloading (DQN-TO), equal resource allocation (ERA), random association (RA), and fixed trajectory (FT).

Förderung

  • Institute of Information and Communications Technology Planning and Evaluation
  • Korea Government
  • Evolvable Deep Learning Model Generation Platform for Edge Computing
  • National Research Foundation of Korea
  • Artificial Intelligence Convergence Innovation Human Resources Development (Kyung Hee University), and MSIT, South Korea, through the ITRC Support Program supe…
  • IITP
  • MSIT through the Global AI Frontier Lab
  • MSIT through the Convergence Security Core Talent Training Business Support Program supervised by the IITP

Zitieren

APA

Ei, N. N., Aung, P. S., Han, Z., Saad, W., & Hong, C. S. (2025). Deep-Reinforcement-Learning-Based Resource Management for Task Offloading in Integrated Terrestrial and Nonterrestrial Networks. IEEE Internet of Things Journal, 12(9), 11977-11993. https://doi.org/10.1109/jiot.2024.3521095

Vancouver

Ei NN, Aung PS, Han Z, Saad W, Hong CS. Deep-Reinforcement-Learning-Based Resource Management for Task Offloading in Integrated Terrestrial and Nonterrestrial Networks. IEEE Internet of Things Journal. 2025;12(9):11977-11993. doi:10.1109/jiot.2024.3521095

BibTeX
@article{Ei2025,
  author = {Ei, Nway Nway and Aung, Pyae Sone and Han, Zhu and Saad, Walid and Hong, Choong Seon},
  title = {Deep-Reinforcement-Learning-Based Resource Management for Task Offloading in Integrated Terrestrial and Nonterrestrial Networks},
  journal = {IEEE Internet of Things Journal},
  year = {2025},
  volume = {12},
  number = {9},
  pages = {11977--11993},
  doi = {10.1109/jiot.2024.3521095}
}
Kostenlos starten →