EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HOODIE: Hybrid Computation Offloading via Distributed Deep Reinforcement Learning in Delay-Aware Cloud-Edge Continuum

Anastasios E. Giannopoulos, Ilias Paralikas, Sotirios T. Spantideas, Panagiotis Trakadas

IEEE Open Journal of the Communications Society · 2024 · 5 · 7818-7841

DOI: 10.1109/ojcoms.2024.3514456 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Open Journal of the Communications Society, 2024. Verfasst von Anastasios E. Giannopoulos und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EU HORIZON Research and Innovation Programme through “Towards a Functional Continuum Operating System”, ENACT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloud-Edge Computing Continuum (CEC) system, where edge and cloud nodes are seamlessly connected, is dedicated to handle substantial computational loads offloaded by end-users. These tasks can suffer from delays or be dropped entirely when deadlines are missed, particularly under fluctuating network conditions and resource limitations. The CEC is coupled with the need for hybrid task offloading, where the task placement decisions concern whether the tasks are processed locally, offloaded vertically to the cloud, or horizontally to interconnected edge servers. In this paper, we present a distributed hybrid task offloading scheme (HOODIE) designed to jointly optimize the tasks latency and drop rate, under dynamic CEC traffic. HOODIE employs a model-free deep reinforcement learning (DRL) framework, where distributed DRL agents at each edge server autonomously determine offloading decisions without global task distribution awareness. To further enhance the system pro-activity and learning stability, we incorporate techniques such as Long Short-term Memory (LSTM), Dueling deep Q-networks (DQN), and double-DQN. Extensive simulation results demonstrate that HOODIE effectively reduces task drop rates and average task processing delays, outperforming several baseline methods under changing CEC settings and dynamic conditions.

Förderung

  • EU HORIZON Research and Innovation Programme through “Towards a Functional Continuum Operating System”
  • ENACT

Zitieren

APA

Giannopoulos, A. E., Paralikas, I., Spantideas, S. T., & Trakadas, P. (2024). HOODIE: Hybrid Computation Offloading via Distributed Deep Reinforcement Learning in Delay-Aware Cloud-Edge Continuum. IEEE Open Journal of the Communications Society, 5, 7818-7841. https://doi.org/10.1109/ojcoms.2024.3514456

Vancouver

Giannopoulos AE, Paralikas I, Spantideas ST, Trakadas P. HOODIE: Hybrid Computation Offloading via Distributed Deep Reinforcement Learning in Delay-Aware Cloud-Edge Continuum. IEEE Open Journal of the Communications Society. 2024;5:7818-7841. doi:10.1109/ojcoms.2024.3514456

BibTeX
@article{Giannopoulos2024,
  author = {Giannopoulos, Anastasios E. and Paralikas, Ilias and Spantideas, Sotirios T. and Trakadas, Panagiotis},
  title = {HOODIE: Hybrid Computation Offloading via Distributed Deep Reinforcement Learning in Delay-Aware Cloud-Edge Continuum},
  journal = {IEEE Open Journal of the Communications Society},
  year = {2024},
  volume = {5},
  pages = {7818--7841},
  doi = {10.1109/ojcoms.2024.3514456}
}
Kostenlos starten →