Multi-objective reinforcement learning for responsive grids

Julien Perez 1 Cecile Germain-Renaud 1, 2 Balázs Kégl 1, 2, 3 Charles Loomis 3
2 TAO - Machine Learning and Optimisation
Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, CNRS - Centre National de la Recherche Scientifique : UMR8623, LRI - Laboratoire de Recherche en Informatique
Abstract : Grids organize resource sharing, a fundamental requirement of large scientific collaborations. Seamless integration of grids into everyday use requires responsiveness, which can be provided by elastic Clouds, in the Infrastructure as a Service (IaaS) paradigm. This paper proposes a model-free resource provisioning strategy supporting both requirements. Provisioning is modeled as a continuous action-state space, multi-objective reinforcement learning (RL) problem, under realistic hypotheses; simple utility functions capture the high level goals of users, administrators, and shareholders. The model-free approach falls under the general program of autonomic computing, where the incremental learning of the value function associated with the RL model provides the so-called feedback loop. The RL model includes an approximation of the value function through an Echo State Network. Experimental validation on a real data-set from the EGEE grid shows that introducing a moderate level of elasticity is critical to ensure a high level of user satisfaction.
Type de document :
Article dans une revue
Journal of Grid Computing, Springer Verlag, 2010, 8 (3), pp.473-492. <10.1007/s10723-010-9161-0>


https://hal.archives-ouvertes.fr/hal-00491560
Contributeur : Cecile Germain-Renaud <>
Soumis le : samedi 12 juin 2010 - 20:08:37
Dernière modification le : mardi 19 janvier 2016 - 14:59:56
Document(s) archivé(s) le : vendredi 19 octobre 2012 - 13:35:13

Fichier

RLGrid_JGC09_V7.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Julien Perez, Cecile Germain-Renaud, Balázs Kégl, Charles Loomis. Multi-objective reinforcement learning for responsive grids. Journal of Grid Computing, Springer Verlag, 2010, 8 (3), pp.473-492. <10.1007/s10723-010-9161-0>. <hal-00491560>

Exporter

Partager

Métriques

Consultations de
la notice

277

Téléchargements du document

303