Emergent algorithms for replica location and selection in data grid

Grid infrastructures for e-Science projects are growing in magnitude terms. Improvements in data Grid replication algorithms may be critical in many of these infrastructures. This paper shows a decentralized replica optimization service, providing a general Emergent Artificial Intelligence (EAI) alg...

Full description

Saved in:

Bibliographic Details
Published in:	Future generation computer systems Vol. 26; no. 7; pp. 934 - 946
Main Authors:	Méndez Muñoz, Víctor, Amorós Vicente, Gabriel, García Carballeira, Félix, Salt Cairols, José
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01-07-2010
Subjects:	Algorithms Artificial intelligence Grid computing Optimization methods Grid computing Algorithms Artificial intelligence Optimization methods
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Grid infrastructures for e-Science projects are growing in magnitude terms. Improvements in data Grid replication algorithms may be critical in many of these infrastructures. This paper shows a decentralized replica optimization service, providing a general Emergent Artificial Intelligence (EAI) algorithm for the problem definition. Our aim is to set up a theoretical framework for emergent heuristics in Grid environments. Further, we describe two EAI approaches, the Particle Swarm Optimization PSO-Grid Multiswarm Federation and the Ant Colony Optimization ACO-Grid Asynchronous Colonies Optimization replica optimization algorithms, with some examples. We also present extended results with best performance and scalability features for PSO-Grid Multiswarm Federation.
ISSN:	0167-739X 1872-7115
DOI:	10.1016/j.future.2010.03.007