A Metaheuristic for Energy Aware Scheduling for Cloud Computing System Using Hybrid GA
Energy is an expensive resource that is becoming more scarce with increasing population and demand. The authors' paper investigates the energy issue in task scheduling particularly on High Performance Systems (HCSs). The proposed approach analyzes the problem of scheduling precedence-constrained parallel applications on Heterogeneous Computing Systems (HCSs) like cloud computing infrastructures. A new parallel bi-objective hybrid Genetic Algorithm (GA and ECS+idle) that takes into account, not only makespan, but also energy consumption. This new method is based on Dynamic Voltage Scaling (DVS) methodology for reducing the cumulative power energy utilized by the system resources. The recent commodity processors are capable of DVS, which enables the processor to operate at different voltage supply levels at the expense of sacrificing clock frequencies.