2023ICERD8-C03 -- An Energy-efficient Task Scheduling Algorithm to Reduce the Carbon Footprint of Datacenters

Carbon Dioxide (CO₂) emissions are a major contributor to the issues of global warming and climate change. The Information Technology sector contributes approximately 2% to 6% to the global CO₂ emissions with a possibility to reach 20% by 2030 and datacenters contribute to this percentage by the active usage of power grids. Since more than half the power consumption of datacenters is drawn by idle servers, it is critical to enhance the load distribution and scheduling algorithms to reach minimal energy consumption and therefore produce less CO₂ emissions. In this paper, we propose an energy-efficient scheduling algorithm that accounts for the estimated carbon emissions of tasks as well as the availability of renewable energy sources. We tested our algorithm on the CloudSim Plus cloud datacenter simulation tool. The results showed a 94% reduction in total carbon usage effectiveness values by using renewable energy sources.