EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Reinforcement Learning for Workload Prediction in Federated Cloud Environments

Zaakki Ahamed iD, Maher Khemakhem iD, Fathy Eassa iD, Fawaz Alsolami iD, Abdullah Basuhail, Kamal Jambi iD

Sensors · 03.08.2023 · 23 (15) · 6911

DOI: 10.3390/s23156911 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.08.2023. Verfasst von Zaakki Ahamed und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University (KAU), Jeddah 21589, Saudi Arabia. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Abdulaziz University, Deanship of Scientific Research (DSR), King Abdulaziz University, Jeddah.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Federated Cloud Computing (FCC) paradigm provides scalability advantages to Cloud Service Providers (CSP) in preserving their Service Level Agreement (SLA) as opposed to single Data Centers (DC). However, existing research has primarily focused on Virtual Machine (VM) placement, with less emphasis on energy efficiency and SLA adherence. In this paper, we propose a novel solution, Federated Cloud Workload Prediction with Deep Q-Learning (FEDQWP). Our solution addresses the complex VM placement problem, energy efficiency, and SLA preservation, making it comprehensive and beneficial for CSPs. By leveraging the capabilities of deep learning, our FEDQWP model extracts underlying patterns and optimizes resource allocation. Real-world workloads are extensively evaluated to demonstrate the efficacy of our approach compared to existing solutions. The results show that our DQL model outperforms other algorithms in terms of CPU utilization, migration time, finished tasks, energy consumption, and SLA violations. Specifically, our QLearning model achieves efficient CPU utilization with a median value of 29.02, completes migrations in an average of 0.31 units, finishes an average of 699 tasks, consumes the least energy with an average of 1.85 kWh, and exhibits the lowest number of SLA violations with an average of 0.03 violations proportionally. These quantitative results highlight the superiority of our proposed method in optimizing performance in FCC environments.

Schlagwörter

Stichwörter der Autor:innen

Deep Q learningDeep Reinforcement LearningFederated Cloud ComputingMachine LearningVirtual Machine placementenergy efficiencyworkload prediction

Autor:innen und Institutionen

  • Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University (KAU), Jeddah 21589, Saudi Arabia.

ORCID-Profile: Zaakki Ahamed, Maher Khemakhem, Fathy Eassa, Fawaz Alsolami, Kamal Jambi

Förderung

  • King Abdulaziz University
  • Deanship of Scientific Research (DSR), King Abdulaziz University, Jeddah

Zitieren

APA

Ahamed, Z., Khemakhem, M., Eassa, F., Alsolami, F., Basuhail, A., & Jambi, K. (2023). Deep Reinforcement Learning for Workload Prediction in Federated Cloud Environments. Sensors, 23(15), 6911. https://doi.org/10.3390/s23156911

Vancouver

Ahamed Z, Khemakhem M, Eassa F, Alsolami F, Basuhail A, Jambi K. Deep Reinforcement Learning for Workload Prediction in Federated Cloud Environments. Sensors. 2023;23(15):6911. doi:10.3390/s23156911

BibTeX
@article{Ahamed2023,
  author = {Ahamed, Zaakki and Khemakhem, Maher and Eassa, Fathy and Alsolami, Fawaz and Basuhail, Abdullah and Jambi, Kamal},
  title = {Deep Reinforcement Learning for Workload Prediction in Federated Cloud Environments},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {15},
  pages = {6911},
  doi = {10.3390/s23156911}
}
Kostenlos starten →