Dynamic Speed Scaling Minimizing Expected Energy Consumption for Real-Time Tasks - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2017

Dynamic Speed Scaling Minimizing Expected Energy Consumption for Real-Time Tasks

Sélection en-ligne de la vitesse minimisant l'énergie dans les systèmes temps-réels

(1) , (2) , (1)
1
2

Abstract

This paper proposes a Markov Decision Process (MDP) approach to compute the optimal on-line speed scaling policy to minimize the energy consumption of a processor executing a finite or infinite set of jobs with real-time constraints. The policy is computed off-line but used on-line. We provide several qualitative properties of the optimal policy: monotonicity with respect to the jobs parameters, comparison with on-line deterministic algorithms. Numerical experiments show that our proposition performs well when compared with off-line optimal solutions and outperforms on-line solutions oblivious to statistical information on the jobs. Several extensions are also explained when speed changes as well as context switch costs are taken into account. Nonconvex power functions are also taken into account to model leakage. Finally, state space reduction using a coarser discretization is presented to deal with the curse of dimensionality of the MDP.
Cet article propose d’utiliser la technique des processus de décision markovien (PDM) pour calculer la politique optimale en-ligne de choix de vitesses afin de minimiser l’énergie consommée par un processeur exécutant un ensemble de tâches avec des contraintes temps-réel. La politique est calculée avant l’exécution du système temps réel (hors ligne), mais utilisée en ligne. Cette méthode est efficace et proche de la solution optimale hors-ligne et elle est plus performante que les solutions en-ligne qui ne prennent pas en compte les informations statistiques sur les tâches futures.
Fichier principal
Vignette du fichier
RR-9101.pdf (1.11 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01615835 , version 1 (13-10-2017)
hal-01615835 , version 2 (22-11-2017)

Identifiers

  • HAL Id : hal-01615835 , version 2

Cite

Bruno Gaujal, Alain Girault, Stéphan Plassart. Dynamic Speed Scaling Minimizing Expected Energy Consumption for Real-Time Tasks. [Research Report] RR-9101, UGA - Université Grenoble Alpes; Inria Grenoble Rhône-Alpes; Université de Grenoble. 2017, pp.1-35. ⟨hal-01615835v2⟩
592 View
441 Download

Share

Gmail Facebook Twitter LinkedIn More