Nature Inspired Schedulers in Computational Grids

ARTICLE 1. Introduction Computational Grids (CGs) are a natural extension of classical distributed systems. CGs are expected to leverage unprecedented larger computing capacities by virtually joining together geographically distributed resources at large scale. To achieve this objective, the design of ecient Grid schedulers that map and allocate tasks and applications onto Grid resources is a key issue. In fact, CGs introduce new complexities to the scheduling problem making it even more challenging for the design of ecient schedulers. In this article, we illustrate how various nature inspired heuristic and meta-heuristic methods can be used to design ecient schedulers in CGs. Such heuristic and meta-heuristics include ad hoc methods, local search, population-based and hybrid approaches. In using these methods for designing ecient Grid schedulers we take into account the new characteristics of CGs and tackle the Grid scheduling as a family of problems.