An innovative strategy, based on Extremal Optimization, to map the tasks making up a user application in grid environments is proposed. Differently from other evolutionary-based methods which simply search for one site onto which deploy the application, our method deals with a multisite approach. Moreover, we consider the nodes composing the sites as the lowest computational units and we take into account their actual loads. The proposed approach is tested on a group of different simulations representing a set of typical real-time situations.
Extremal Optimization as a Viable Means for Mapping in Grids
Ivanoe De Falco;Domenico Maisto;Umberto Scafuri;Ernesto Tarantino
2009
Abstract
An innovative strategy, based on Extremal Optimization, to map the tasks making up a user application in grid environments is proposed. Differently from other evolutionary-based methods which simply search for one site onto which deploy the application, our method deals with a multisite approach. Moreover, we consider the nodes composing the sites as the lowest computational units and we take into account their actual loads. The proposed approach is tested on a group of different simulations representing a set of typical real-time situations.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
