Int-fGrid: A type-2 fuzzy approach for scheduling tasks of computational grids

Scheduling tasks is a known NP-Hard problem. As grow the number of variables such as computational power and network metrics, even heuristic-based schedulers start to become overwhelmed by the underlying complexity. Computational Grids (CGs) are known for their heterogeneity of resources and interconnections, and as these resources may be deployed throughout the world, it is not possible to have a single, centralized, precise view of the system at any given moment. This paper provides a new approach with Fuzzy Type-2 logics to treat uncertainties and dynamic behavior for scheduling tasks in grid environments, named Int-fGrid. The scheduler was validated through simulations in the SimGrid framework with a model of the GridRS architecture. Our results show that the Fuzzy Type-2 approach provides makespans up to 18.5 times better than the best alternative tested scheduler XSufferage.