Studies on CO2 Emission Minimization Strategies in Data Centers through Simulators

• Gabriella Saraiva USP
• Sarita Mazzini Bruschi USP
• Daniel Cordeiro USP

DOI: https://doi.org/10.5753/eradsp.2024.239598

Abstract

Platforms for parallel and distributed computing, such as data centers, have increased their processing capacity in pursuit of greater computational power. However, this performance gain is accompanied by a significant increase in energy consumption. In this scenario, research on energy efficiency in high-performance environments has emerged as a way to identify the causes and propose solutions for excessive energy consumption. In this work, we are investigating how simulators can contribute to the development of scheduling algorithms focused on reducing non-renewable energy consumption, thus aiming to significantly reduce CO₂ emissions.

References

Dutot, P.-F., Mercier, M., Poquet, M., and Richard, O. (2016). Batsim: a Realistic Language-Independent Resources and Jobs Management Systems Simulator. In 20th Workshop on Job Scheduling Strategies for Parallel Processing.

International Energy Agency (IEA) (2022). Data centres and data transmission networks. Technical report, IEA, Paris.

Masanet, E., Shehabi, A., Lei, N., Smith, S., and Koomey, J. (2020). Recalibrating global data center energy-use estimates. Science, 367(6481):984–986.

Poquet, M. (2017). Simulation approach for resource management. PhD thesis, Université Grenoble Alpes.

Vasconcelos, M. F. S., Cordeiro, D., Costa, G. d., Dufossé, F., Nicod, J.-M., et al. (2023). Optimal Sizing of a Globally Distributed Low Carbon Cloud Federation. PhD thesis, IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing.