Energy Aware Scheduling of HPC Tasks in Decentralised Cloud Systems

The increased computational needs in many sectors place huge demands on cloud computing. Power consumption and resource pool capacity are two of the challenges faced by the next generation of high performance computing (HPC). This paper aims at minimising the computing-energy consumption in decentralised multi-cloud systems using Dynamic Voltage and Frequency Scaling (DVFS) when scheduling dependent HPC tasks under deadline constraints. We propose an energy-aware scheduling algorithm EAGS. To demonstrate the efficiency of our algorithm EAGS, we compare it with the Cloud min-min Scheduling (CMMS) algorithm in different experiments. The simulation results show that our algorithm can produce energy consumption lower than CMMS by an average of 63.9%.