Data di Pubblicazione:
2008
Abstract:
This paper proposes a bio-inspired approach tailored to the construction of a Grid information system in which content, specifically metadata
descriptors that specify the characteristics of Grid resources, is disseminated and logically reorganized on the Grid. Content management is
achieved through the collective activity of a large number of ant-like agents, which perform simple operations at the local level, but together
engender an advanced form of "swarm intelligence" at the global level. Agents travel the Grid through P2P interconnections and use probability
functions to (i) replicate resource descriptors and (ii) collect similar descriptors in nearby Grid hosts. Simulation analysis shows that the proposed
ARMAP protocol (Ant-based Replication and MApping Protocol) is capable of reducing the entropy of the system and efficiently propagating
content. Furthermore, ARMAP allows to enforce the dissemination of descriptors related to high Quality of Service (QoS) resources. The Grid
information system built with the proposed protocol enables the use of a semi-informed discovery algorithm which drives query messages towards
"representative peers" that maintain information about high QoS resources having the required characteristics.
Tipologia CRIS:
01.01 Articolo in rivista
Keywords:
Ant systems; Content networks; Grid; P2P; Swarm intelligence
Elenco autori:
Spezzano, Giandomenico; Mastroianni, Carlo; Forestiero, Agostino
Link alla scheda completa:
Pubblicato in: