Performance Comparison of Thermal Aware Job Scheduling Based on Multi Priorities on Computational Grid

Electricity consumption for cooling purpose is known to be the most expensive operational cost faetor in data eenters. Ineffieient eooling leads to high temperature and this in turn leads to hardware failure. This paper proposes a Thermal Aware Modified Least Slack Time Round Robin Based (MLST-RR) scheduling algorithm that can avoid high thermal stress eireumstances sueh as large hotspots, thermal violations as well as reduce electricity consumption for cooling in data eenter labs. The experimental results show that, the thermal aware MLST-RR is able to significantly decrease the electricity consumption while maintaining competitive performance. Specifically, the thermal aware scheduling algorithm saves electrieity eonsumption as much as 15000KW compared to the benehmark job scheduling algorithms such as Round Robin (RR) and First Come First Serve (FCFS) j this is an electrical saving of 8.4%.