Applying reinforcement learning to scheduling strategies in an actual grid environment

• Type: Article in International Scientific Journal
• Date: 2009

Authors

Costa, BF (Author) Other; Mattoso, M (Author) Other; Dutra, I (Author) FCUP

Journal

Title: International Journal of High Performance Systems Architecture

Vol. 2 No. 2

Pages: 116-128

ISSN: 1751-6528

Publisher: Inderscience Publishers

Indexing

Scopus - 4 Citations

Other information

Authenticus ID: P-007-SNT

DOI: 10.1504/ijhpsa.2009.032029

Abstract (EN): Grid environments are dynamic and heterogeneous by nature, therefore requiring adaptive scheduling strategies. Reinforcement learning is an interesting and simple adaptive approach that may work well in actual grid environments. In this work, we employ reinforcement learning to classify available resources in a grid environment, giving support to two scheduling algorithms, AG and MQD. We study the makespan optimisation and load balancing. An algorithm known as RR is used for normalising purposes. Copyright © 2009 Inderscience Enterprises Ltd.

Language: English

Type (Professor's evaluation): Scientific

Notes: Special issue on Parallel and Distributed Systems, Applications and Architectures. - DOI: 10.1504/IJHPSA.2009.032029. - Keywords: grid computing; scheduling strategies; load balancing algorithms; heterogeneous environments; reinforcement learning; resources classification; makespan optimisation.

No. of pages: 13