Energy Consumption in Data Centers and Efficiency Strategies: a Literature Review
DOI:
https://doi.org/10.31496/retii.v3i1.2038Keywords:
data centers, energy consumption, energy efficiency, renewable energy, artificial intelligenceAbstract
The twenty-first-century digitalization wave, propelled by cloud computing, big data, and generative artificial intelligence, has established data centers as critical infrastructure underpinning the global digital economy. Their energy consumption has surged from 80 TWh in 2000 to 620 TWh in 2024, currently accounting for 0.43% of global primary energy, with projections of reaching between 1,000 and 1,600 TWh by 2030. This article presents a literature review of data center energy consumption and the principal efficiency strategies available, covering cooling techniques, hardware optimization, workload orchestration, and renewable energy integration. The findings highlight significant technical advances alongside persistent regulatory gaps and geographic disparities that demand targeted public policy responses.
References
AMAZON SUSTAINABILITY. AWS Cloud Sustainability. Amazon, 2024. Available at: https://sustainability.aboutamazon.com/products-services/aws-cloud. Accessed: jan. 10, 2026.
ANDERSON, M. The shift to ARM-based servers: introduction to a changing landscape in server architecture. Medium, Jun. 2025. Available at: https://medium.com/@mike.anderson007/the-shift-to-arm-based-servers-87aaa749ac19. Accessed: jan. 10, 2026.
ASLAN, T. et al. Toward climate neutral data centers: greenhouse gas inventory, scenarios, and strategies. iScience, v. 28, n. 1, p. 111637, Jan. 2025. DOI: https://doi.org/10.1016/j.isci.2024.111637. Available at: https://pmc.ncbi.nlm.nih.gov/articles/PMC11773490/. Accessed: jan. 10, 2026.
AWS – AMAZON WEB SERVICES. ARM Processor – AWS EC2 Graviton. 2024a. Available at: https://aws.amazon.com/ec2/graviton/. Accessed: jan. 10, 2026.
AWS – AMAZON WEB SERVICES. Amazon EC2 R8g instances powered by AWS Graviton4 now generally available. AWS What's New, Jul. 2024b. Available at: https://aws.amazon.com/about-aws/whats-new/2024/07/amazon-ec2-r8g-instances-aws-graviton4-generally-available/. Accessed: jan. 10, 2026.
CHEN, R. et al. Fiber membrane evaporative cooling for high-power electronics in data centers. Joule, 2024. DOI: https://doi.org/10.1016/j.joule.2024.02.020.
DELOITTE. As generative AI asks for more power, data centers seek more reliable, cleaner energy solutions. Deloitte Insights, 2024. Available at: https://www2.deloitte.com/us/en/insights/industry/technology/technology-media-and-telecom-predictions/2024/data-center-energy-consumption-demand-growth.html. Accessed: jan. 10, 2026.
EMERGENTMIND. Dynamic voltage and frequency scaling (DVFS): overview and trends. 2025. Available at: https://www.emergentmind.com/topics/dynamic-voltage-and-frequency-scaling-dvfs. Accessed: jan. 10, 2026.
FEMP; NREL – FEDERAL ENERGY MANAGEMENT PROGRAM; NATIONAL RENEWABLE ENERGY LABORATORY. Best practices guide for energy-efficient data center design. Washington, D.C.: U.S. Department of Energy, Jul. 2024. Available at: https://www.energy.gov/sites/default/files/2024-07/best-practice-guide-data-center-design_0.pdf. Accessed: jan. 10, 2026.
GIL, A. C. Métodos e técnicas de pesquisa social. 7th ed. São Paulo: Atlas, 2019.
GOOGLE CLOUD. Introducing Google's new Arm-based CPU. Google Cloud Blog, Apr. 2024a. Available at: https://cloud.google.com/blog/products/compute/introducing-googles-new-arm-based-cpu. Accessed: jan. 10, 2026.
GOOGLE CLOUD. Try C4A, the first Google Axion Processor. Google Cloud Blog, Oct. 2024b. Available at: https://cloud.google.com/blog/products/compute/try-c4a-the-first-google-axion-processor. Accessed: jan. 10, 2026.
GOOGLE CLOUD. Ironwood TPUs and new Axion-based VMs for your AI workloads. Google Cloud Blog, Nov. 2025. Available at: https://cloud.google.com/blog/products/compute/ironwood-tpus-and-new-axion-based-vms-for-your-ai-workloads. Accessed: jan. 10, 2026.
HUANG, J. et al. Data centers cooling: a critical review of techniques, challenges, and energy saving solutions. Sustainable Computing: Informatics and Systems, v. 42, p. 100989, 2024. DOI: https://doi.org/10.1016/j.suscom.2024.100989. Available at: https://www.sciencedirect.com/science/article/abs/pii/S0140700724000458. Accessed: jan. 10, 2026.
IEA – INTERNATIONAL ENERGY AGENCY. Data centres and data transmission networks. Paris: IEA, 2023. Available at: https://www.iea.org/reports/data-centres-and-data-transmission-networks. Accessed: jan. 10, 2026.
IEA – INTERNATIONAL ENERGY AGENCY. Electricity 2024: analysis and forecast to 2026. Paris: IEA, 2024. Available at: https://www.iea.org/reports/electricity-2024. Accessed: jan. 10, 2026.
IEEE COMMUNICATIONS SOCIETY. Energy efficiency in data centers. IEEE Communications Society, 2025. Available at: https://www.comsoc.org/publications/tcn/2019-nov/energy-efficiency-data-centers. Accessed: jan. 10, 2026.
IPCC – INTERGOVERNMENTAL PANEL ON CLIMATE CHANGE. AR6 Synthesis Report: Climate Change 2022. Geneva: IPCC, 2022. Available at: https://www.ipcc.ch/report/ar6/syr/. Accessed: jan. 10, 2026.
JONES, N. How to stop data centres from gobbling up the world's electricity. Nature, v. 561, n. 7722, p. 163-166, 2018. DOI: https://doi.org/10.1038/d41586-018-06610-y.
KAHIL, H. et al. Reinforcement learning for data center energy efficiency optimization: a systematic literature review and research roadmap. Applied Energy, v. 389, p. 125004, 2025. DOI: https://doi.org/10.1016/j.apenergy.2025.125004. Available at: https://www.sciencedirect.com/science/article/pii/S0306261925004647. Accessed: jan. 10, 2026.
KISHORE, P. et al. MILP-based workload scheduling and energy management for AI data centers. Energy and Buildings, 2025.
KOOMEY, J. G. Worldwide electricity used in data centers. Environmental Research Letters, v. 3, n. 3, 2008. DOI: https://doi.org/10.1088/1748-9326/3/3/034008. Available at: https://iopscience.iop.org/article/10.1088/1748-9326/3/3/034008. Accessed: jan. 10, 2026.
KOOMEY, J. G. Growth in data center electricity use 2005 to 2010. Oakland: Analytics Press, 2011.
LAKATOS, E. M.; MARCONI, M. A. Fundamentos de metodologia científica. 8th ed. São Paulo: Atlas, 2017.
LIN, H. et al. A novel virtual machine consolidation algorithm with server power mode management for energy-efficient cloud data centers. Cluster Computing, v. 27, n. 8, p. 11709–11725, 2024. DOI: https://doi.org/10.1007/s10586-024-04555-8. Available at: https://link.springer.com/article/10.1007/s10586-024-04555-8. Accessed: jan. 10, 2026.
LIN, Y. et al. Green-aware data centers: workload management, thermal management, and waste heat recovery. Renewable and Sustainable Energy Reviews, v. 187, p. 113761, 2023. DOI: https://doi.org/10.1016/j.rser.2023.113761.
McKINSEY & COMPANY. How hyperscalers are fueling the race for 24/7 clean power. McKinsey Insights, Dec. 2024. Available at: https://www.mckinsey.com/capabilities/sustainability/our-insights/how-hyperscalers-are-fueling-the-race-for-247-clean-power. Accessed: jan. 10, 2026.
MICROSOFT. Azure Cobalt processor-based virtual machines. Microsoft Learn, 2024a. Available at: https://learn.microsoft.com/en-us/azure/virtual-machines/sizes/cobalt-overview. Accessed: jan. 10, 2026.
MICROSOFT. How Azure Cobalt 100 VMs are powering real-world solutions. Microsoft Azure Blog, Sep. 2024b. Available at: https://azure.microsoft.com/en-us/blog/how-azure-cobalt-100-vms-are-powering-real-world-solutions-delivering-performance-and-efficiency-results/. Accessed: jan. 10, 2026.
MICROSOFT. Announcing Cobalt 200: Azure's next cloud-native CPU. Microsoft Community Hub, Nov. 2025. Available at: https://techcommunity.microsoft.com/blog/AzureInfrastructureBlog/ announcing-cobalt-200-azure%E2%80%99s-next-cloud-native-cpu/4469807. Accessed: Jan. 10, 2026.
MOSTPOLICYINITIATIVE. POWERING DATA CENTERS. MOST Policy Initiative, 2025. Available at: https://mostpolicyinitiative.org/science-note/powering-data-centers/. Accessed: jan. 10, 2026.
SCIENCEDIRECT. DYNAMIC VOLTAGE AND FREQUENCY SCALING. ScienceDirect Topics, 2024. Available at: https://www.sciencedirect.com/topics/computer-science/dynamic-voltage-and-frequency-scaling. Accessed: jan. 10, 2026.
SILVA, L. A. et al. Consumo energético dos data centers e a métrica da energia primária: análise global 2000–2024 e projeções até 2030. Revista Observatório de la Economía Latinoamericana, Curitiba, v. 23, n. 10, p. 01–28, 2025. DOI: https://doi.org/10.55905/oelv23n10-063.
SMIL, V. Energy and civilization: a history. Cambridge: MIT Press, 2017.
THE GREEN GRID. Green grid metrics: describing data center power efficiency. White Paper, 2008. Available at: https://www.thegreengrid.org. Accessed: Jan. 10, 2026.
UPTIME INSTITUTE. Global data center survey results 2024. New York: Uptime Institute, 2024. Available at: https://uptimeinstitute.com/2024-data-center-industry-survey-results. Accessed: jan. 10, 2026.
Downloads
Published
How to Cite
Issue
Section
License
Os textos submetidos e aprovados pelo Conselho Editorial da RETII serão publicados, e seus autores poderão dispor deles para posteriores publicações, sempre fazendo constar a edição original (título, Revista de Engenharia, TI e Inovação, volume, número, ano de publicação e paginação do texto referido). Todos os artigos dessa Revista são de inteira responsabilidade de seus autores, não cabendo qualquer responsabilidade legal sobre seu conteúdo à Revista ou à Universidade de Uberaba.