-
Adrien Berthelot,
Eddy Caron,
Mathilde Jay,
and Laurent Lefèvre.
Understanding the environmental impact of generative AI services.
Communications of the ACM,
Special Issue on Sustainability and Computing,
June, 3 2025.
Note: Hal-04920612v1. Online First.
Keywords:
Green,
Generative AI,
Life Cycle Analysis,
Digital services,
Greenhouse Gas Emission,
Energy,
Sustainability.
@Article{ ArticleBerthelot.BCJL_CA25,
author = {Berthelot, Adrien and Caron, Eddy and Jay, Mathilde and Lef{\`e}vre, Laurent},
issn = {0001-0782},
journal = {Communications of the ACM},
keywords = {{Green, Generative AI, Life Cycle Analysis, Digital services, Greenhouse Gas Emission, Energy, Sustainability}},
month = {June, 3},
note = {hal-04920612v1. {Online First}},
publisher = {{Association for Computing Machinery}},
title = {{Understanding the environmental impact of generative AI services}},
url = {https://dl.acm.org/doi/10.1145/3725984},
volume = {Special Issue on Sustainability and Computing},
year = {2025}
}
-
Simon Lambert,
Eddy Caron,
Laurent Lefèvre,
and Rémi Grivel.
Consolidation of virtual machines to reduce energy consumption of data centers by using ballooning, sharing and swapping mechanisms.
Future Generation Computer Systems,
(FGCS-D-24-03438R3),
2025.
Note: To appear, https://hal.science/hal-05143704.
@Article{ ArticleLambert.LCLG_FGCS25,
author = {Lambert, Simon and Caron, Eddy and Lef{\`e}vre, Laurent and Grivel, R{\'e}mi},
journal = {Future Generation Computer Systems},
note = {To appear, https://hal.science/hal-05143704},
number = {FGCS-D-24-03438R3},
title = {Consolidation of virtual machines to reduce energy consumption of data centers by using ballooning, sharing and swapping mechanisms},
year = {2025}
}
-
Simon Lambert,
Vladimir Ostapenco,
Lefèvre Laurent,
Eddy Caron,
Anne-Cécile Orgerie,
Benjamin Fichel,
and Rémi Grivel.
Revisiting virtual machine consolidation to save resources and energy in heterogeneous production cloud infrastructures.
International Journal of High Performance Computing Applications,
2025.
Note: To publish. hal-05457159.
Keywords:
Energy Efficiency,
Cloud,
Workload Consolidation,
Virtual Machines,
Migration.
| Abstract: |
Due to some overprovisioning policies and variable usage, data centers in production can face low average resource utilization. This can result in a waste of underused servers and energy. In this context, virtual machine (VM) consolidation combined with shutdown policies can be a pertinent approach for improving resource utilization and reducing energy consumption of the entire cloud infrastructure. However, VM consolidation requires expensive migration techniques, which can potentially affect performance. Consolidation of workload has been proposed and studied as a core capability since the invention of the Cloud. But after two decades of deployment of Cloud infrastructures, VM consolidation is still rarely used in production for small and large-scale environments. In this article, we explore and revisit the potential of savings that can be achieved through a versatile and efficient Virtual Machine consolidation in small and large-scale production infrastructures through usage analysis of two Cloud providers infrastructures. We show that potential benefits in terms of saved cloud resources and energy usage reduction can occur for systems in production. |
@Article{ ArticleLambert.LOLCOFG_IJHPCA25,
abstract = {Due to some overprovisioning policies and variable usage, data centers in production can face low average resource utilization. This can result in a waste of underused servers and energy. In this context, virtual machine (VM) consolidation combined with shutdown policies can be a pertinent approach for improving resource utilization and reducing energy consumption of the entire cloud infrastructure. However, VM consolidation requires expensive migration techniques, which can potentially affect performance. Consolidation of workload has been proposed and studied as a core capability since the invention of the Cloud. But after two decades of deployment of Cloud infrastructures, VM consolidation is still rarely used in production for small and large-scale environments. In this article, we explore and revisit the potential of savings that can be achieved through a versatile and efficient Virtual Machine consolidation in small and large-scale production infrastructures through usage analysis of two Cloud providers infrastructures. We show that potential benefits in terms of saved cloud resources and energy usage reduction can occur for systems in production.},
author = {Lambert, Simon and Ostapenco, Vladimir and Lef{\`e}vre Laurent and Caron, Eddy and Orgerie, Anne-C{\'e}cile and Fichel, Benjamin and Grivel, R{\'e}mi},
journal = {International Journal of High Performance Computing Applications},
keywords = {Energy Efficiency, Cloud, Workload Consolidation, Virtual Machines, Migration},
note = {To publish. hal-05457159},
publisher = {SAGE Publications},
title = {Revisiting virtual machine consolidation to save resources and energy in heterogeneous production cloud infrastructures},
year = {2025}
}
-
Maxime Agusti,
Eddy Caron,
Laurent Lefèvre,
and Anne-Cécile Orgerie.
PPEM-BM: Portable Power Estimation Methodology for Bare Metal Servers.
In The 31st IEEE International Conference on Parallel and Distributed Systems (ICPADS 2025),
Hefei, China,
December 14-18 2025.
IEEE.
Note: Hal-05365793.
Keywords:
Green IT.
@InProceedings{ InProceedingsAgusti.ACLO_25,
address = {Hefei, China},
author = {Agusti, Maxime and Caron, Eddy and Lef{\`e}vre, Laurent and Orgerie, Anne-C{\'e}cile},
booktitle = {The 31st IEEE International Conference on Parallel and Distributed Systems (ICPADS 2025)},
keywords = {Green IT},
month = {December 14-18},
note = {hal-05365793},
publisher = {IEEE},
title = {{PPEM-BM: Portable Power Estimation Methodology for Bare Metal Servers}},
url = {https://inria.hal.science/hal-05365793v1},
year = {2025}
}
-
Simon Lambert,
Vladimir Ostapenco,
Lefèvre Laurent,
Eddy Caron,
Anne-Cécile Orgerie,
Benjamin Fichel,
and Rémi Grivel.
Revisiting virtual machine consolidation to save resources and energy in heterogeneous production cloud infrastructures.
In ICT4S 2025 - International Conference on Information and Communications Technology for Sustainability,
Dublin,
June 2025.
SAGE Publications.
Note: Poster. hal-05100569.
Keywords:
Energy Efficiency,
Cloud,
Workload Consolidation,
Virtual Machines,
Migration.
| Abstract: |
Cloud data centers nowadays represent a significant share of global electricity consumption and have multiple environmental impacts as Greenhouse Gases (GHG) emissions or Abiotic resources Depletion (ADP). This assessment is reinforced by the fact that, due to their overprovisioning capacities, Cloud infrastructures tend to be oversized, which results in low average resource usage and potential resources waste. The scientific literature explored multiple methods to improve resource usage and reduce energy consumption on these Cloud infrastructures. Virtual machines (VM) consolidation has been studied alongside other techniques like shutdown policies to mitigate the power consumption of infrastructures, but they are still rarely used in production in small and large-scale environments. In this poster, we revisit the potential of VM consolidation on heterogeneous cloud infrastructures. We explore a versatile consolidation methodology to reduce the energy and resources consumption of both small and large-scale virtualization infrastructures through an evaluation made on two Cloud providers. The results show that both cloud resources and energy usage can be reduced on production infrastructures. |
@Conference{ Con-Lambert.LOLCOFG_25,
abstract = {Cloud data centers nowadays represent a significant share of global electricity consumption and have multiple environmental impacts as Greenhouse Gases (GHG) emissions or Abiotic resources Depletion (ADP). This assessment is reinforced by the fact that, due to their overprovisioning capacities, Cloud infrastructures tend to be oversized, which results in low average resource usage and potential resources waste. The scientific literature explored multiple methods to improve resource usage and reduce energy consumption on these Cloud infrastructures. Virtual machines (VM) consolidation has been studied alongside other techniques like shutdown policies to mitigate the power consumption of infrastructures, but they are still rarely used in production in small and large-scale environments. In this poster, we revisit the potential of VM consolidation on heterogeneous cloud infrastructures. We explore a versatile consolidation methodology to reduce the energy and resources consumption of both small and large-scale virtualization infrastructures through an evaluation made on two Cloud providers. The results show that both cloud resources and energy usage can be reduced on production infrastructures. },
address = {Dublin},
author = {Lambert, Simon and Ostapenco, Vladimir and Lef{\`e}vre Laurent and Caron, Eddy and Orgerie, Anne-C{\'e}cile and Fichel, Benjamin and Grivel, R{\'e}mi},
booktitle = {ICT4S 2025 - International Conference on Information and Communications Technology for Sustainability},
keywords = {Energy Efficiency, Cloud, Workload Consolidation, Virtual Machines, Migration},
month = {June},
note = {Poster. hal-05100569},
publisher = {SAGE Publications},
title = {Revisiting virtual machine consolidation to save resources and energy in heterogeneous production cloud infrastructures},
url = {https://inria.hal.science/hal-05100569},
year = {2025}
}
