EUVIMEDEUVIMED entdecken
Crossref

Online Learning Aided Decentralized Multi-User Task Offloading for Mobile Edge Computing

Xiong Wang, Jiancheng Ye, John C.S. Lui

IEEE Transactions on Mobile Computing · 2024-04 · 23 (4) · 3328-3342

DOI: 10.1109/tmc.2023.3275851 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-04. Verfasst von Xiong Wang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Hubei Provincial Natural Science Foundation of China, National Natural Science Foundation of China, Research Grants Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Mobile edge computing facilitates users to offload computation tasks to edge servers for meeting their stringent delay requirements. Previous works mainly explore task offloading when system-side information is given (e.g., server processing speed, cellular data rate), or centralized offloading under system uncertainty. But both generally fall short of handling task placement involving many coexisting users in an uncertain environment. In this paper, we develop a multi-user offloading framework considering unknown yet stochastic system-side information to enable a decentralized user-initiated service placement under overlapping server coverage. Specifically, we formulate the dynamic task placement as an online multi-user multi-armed bandit process, and propose a decentralized epoch based offloading (DEBO) to optimize user rewards which are subjected under network delay. We consider both cases without and with neighboring edge feedback once users’ tasks are processed, where the latter incorporates system-side information sharing among edge servers for an enhanced task placement. For both cases, we show that DEBO can gradually deduce the optimal user-server assignment during dynamic offloading, thereby achieving a close-to-optimal service performance and tight $O(\log _{2}\!\!T)$ O ( log 2 T ) regret. Moreover, we generalize DEBO to various common scenarios such as unknown reward gap, dynamic entering or leaving of clients, and fair reward distribution, while further exploring when users’ offloaded tasks require heterogeneous computing resources. Particularly, we accomplish a sub-linear regret for each of these instances. Real measurements based evaluations corroborate the superiority of our offloading schemes over state-of-the-art approaches in optimizing delay-sensitive rewards.

Förderung

  • Hubei Provincial Natural Science Foundation of China
  • National Natural Science Foundation of China
  • Research Grants Council
  • Chinese University of Hong Kong

Zitieren

APA

Wang, X., Ye, J., & Lui, J. C. (2024). Online Learning Aided Decentralized Multi-User Task Offloading for Mobile Edge Computing. IEEE Transactions on Mobile Computing, 23(4), 3328-3342. https://doi.org/10.1109/tmc.2023.3275851

Vancouver

Wang X, Ye J, Lui JC. Online Learning Aided Decentralized Multi-User Task Offloading for Mobile Edge Computing. IEEE Transactions on Mobile Computing. 2024;23(4):3328-3342. doi:10.1109/tmc.2023.3275851

BibTeX
@article{Wang2024,
  author = {Wang, Xiong and Ye, Jiancheng and Lui, John C.S.},
  title = {Online Learning Aided Decentralized Multi-User Task Offloading for Mobile Edge Computing},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2024},
  volume = {23},
  number = {4},
  pages = {3328--3342},
  doi = {10.1109/tmc.2023.3275851}
}
Kostenlos starten →