To execute large scale applications exploiting the unemployed aggregated power available on grid nodes, effective and efficient mapping algorithms must be designed. Since the problem of optimally mapping is NP-complete, heuristic techniques can be profitably adopted to find near-optimal solutions. Here a multiobjective Differential Evolution algorithm is implemented and tested on different mapping scenarios with the aim to fulll several optimization criteria. The results attained show the robustness of the evolutionary approach proposed in dealing with multisite grid mapping.
An Innovative Perspective on Mapping in Grids
I De Falco;D Maisto;U Scafuri;E Tarantino;
2009
Abstract
To execute large scale applications exploiting the unemployed aggregated power available on grid nodes, effective and efficient mapping algorithms must be designed. Since the problem of optimally mapping is NP-complete, heuristic techniques can be profitably adopted to find near-optimal solutions. Here a multiobjective Differential Evolution algorithm is implemented and tested on different mapping scenarios with the aim to fulll several optimization criteria. The results attained show the robustness of the evolutionary approach proposed in dealing with multisite grid mapping.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.
