Economia de Energia usando Computação Voluntária Virtualizada

Abstract

Traditionally, workloads submitted to grid computing environments are bag-of-tasks that can be processed in a distributed way, and using idle hosts connected to a grid environment. Thus, in idle moments, these hosts are connected and the tasks are executed. This is a model designed to not interfere with the rate of use of such hosts. But even running, these hosts often do not utilize all its processing power. This paper proposes an approach that uses underutilized hosts through virtualization, adjusting the use of grid applications to the leftover resources from daily usage of hosts. This approach can reduce the runtime of the applications while saving energy.