RISCLESS: A Reinforcement Learning Strategy to Guarantee SLA on Cloud Ephemeral and Stable Resources - Archive ouverte HAL
Communication Dans Un Congrès Année : 2022

RISCLESS: A Reinforcement Learning Strategy to Guarantee SLA on Cloud Ephemeral and Stable Resources

Résumé

In this paper, we propose RISCLESS, a Reinforcement Learning strategy to exploit unused Cloud resources. Our approach consists in using a small proportion of stable on-demand resources alongside the ephemeral ones in order to guarantee customers SLA and reduce the overall costs. The approach decides when and how much stable resources to allocate in order to fulfill customers’ demands. RISCLESS improved the Cloud Providers (CPs)’ profits by an average of 15.9% compared to past strategies. It also reduced the SLA violation time by 36.7% while increasing the amount of used ephemeral resources by 19.5%.
Fichier non déposé

Dates et versions

hal-03921309 , version 1 (27-04-2022)
hal-03921309 , version 2 (05-01-2023)

Identifiants

Citer

Sidahmed Yalles, Mohamed Handaoui, Jean-Emile Dartois, Olivier Barais, Laurent d'Orazio, et al.. RISCLESS: A Reinforcement Learning Strategy to Guarantee SLA on Cloud Ephemeral and Stable Resources. 2022 PDP - 30th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, Mar 2022, Valladolid, Spain. pp.83-87, ⟨10.1109/PDP55904.2022.00021⟩. ⟨hal-03921309v1⟩
139 Consultations
110 Téléchargements

Altmetric

Partager

More