Energy-Aware Scheduler for HPC Parallel Task Base Applications in Cloud Computing

Abstract

In the world, distributed platforms such as clusters, grids, and clouds spend around 1.5%-2.0% of the total energy consumption and this demand is growing extremely fast. For reducing energy consumption one of the methods is providing scheduling policies in order to allocate tasks on specific resources that impact over the processing times and energy consumption. In this paper, we propose a scheduling system to execute efficiently task-based applications on distributed computing platforms in order to minimize the energy consumption, execution time or both, also we present a dynamic online polynomial-time algorithm that combines a set of heuristic rules and a resource allocation technique in order to get good solutions on an affordable time scale. A prototype implementation of the scheduler has been tested with matrix multiplication DAG generated at random as well as on real task-based COMPSs applications, concluding that our method is suitable for run-time scheduling.