EACS approach for grid workflow scheduling in a computational grid

Abstract

Grid is a collection of heterogeneous resources for solving the complex computational problems. Workflow is a collection of atomic tasks. In this article we propose an Enhanced Ant Colony System (EACS) approach to solve grid workflow scheduling problem with two QoS parameters time and cost to minimize the makespan with low cost. We design a five heuristics for EACS approach and propose an adaptive scheme that allows ants to select heuristics in a quick convergence manner for mapping of tasks to resources based on the modified pheromone updating value. The experiment is done by the simulation with different tasks in various workflow applications and we achieve QoS as well as optimized performance. © 2011 Springer-Verlag.