IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v17y2025i12p5359-d1675875.html
   My bibliography  Save this article

Trade-Off Between Energy Consumption and Three Configuration Parameters in Artificial Intelligence (AI) Training: Lessons for Environmental Policy

Author

Listed:
  • Sri Ariyanti

    (Department of Electrical Engineering, Universitas Indonesia, Depok 16424, Indonesia)

  • Muhammad Suryanegara

    (Department of Electrical Engineering, Universitas Indonesia, Depok 16424, Indonesia)

  • Ajib Setyo Arifin

    (Department of Electrical Engineering, Universitas Indonesia, Depok 16424, Indonesia)

  • Amalia Irma Nurwidya

    (Research Center for Process and Manufacturing Industry Technology, National Research and Innovation Agency (BRIN), Tangerang 15314, Indonesia)

  • Nur Hayati

    (Department of Electrical Engineering, Universitas Muhammadiyah Yogyakarta, Yogyakarta 55183, Indonesia)

Abstract

Rapid advancements in artificial intelligence (AI) have led to a substantial increase in energy consumption, particularly during the training phase of AI models. As AI adoption continues to grow, its environmental impact presents a significant challenge to the achievement of the United Nations’ Sustainable Development Goals (SDGs). This study examines how three key training configuration parameters—early-stopping epochs, training data size, and batch size—can be optimized to balance model accuracy and energy efficiency. Through a series of experimental simulations, we analyze the impact of each parameter on both energy consumption and model performance, offering insights that contribute to the development of environmental policies that are aligned with the SDGs. The results demonstrate strong potential for reducing energy usage without compromising model reliability. The results highlight three lessons: promoting early-stopping epochs as an energy-efficient practice, limiting training data size to enhance energy efficiency, and developing standardized guidelines for batch size optimization. The practical applicability of these three lessons is illustrated through the implementation of a smart building attendance system using facial recognition technology within an Ecocampus environment. This real-world application highlights how energy-conscious AI training configurations support sustainable urban innovation and contribute to climate action and environmentally responsible AI development.

Suggested Citation

  • Sri Ariyanti & Muhammad Suryanegara & Ajib Setyo Arifin & Amalia Irma Nurwidya & Nur Hayati, 2025. "Trade-Off Between Energy Consumption and Three Configuration Parameters in Artificial Intelligence (AI) Training: Lessons for Environmental Policy," Sustainability, MDPI, vol. 17(12), pages 1-23, June.
    • Handle: RePEc:gam:jsusta:v:17:y:2025:i:12:p:5359-:d:1675875
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/17/12/5359/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2071-1050/17/12/5359/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Iakovina Kindylidi & Tiago Sérgio Cabral, 2021. "Sustainability of AI: The Case of Provision of Information to Consumers," Sustainability, MDPI, vol. 13(21), pages 1-14, November.
    2. Anders S. G. Andrae & Tomas Edler, 2015. "On Global Electricity Usage of Communication Technology: Trends to 2030," Challenges, MDPI, vol. 6(1), pages 1-41, April.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Zhenxiang Cao & Liqing Peng, 2023. "The Impact of Digital Economics on Environmental Quality: A System Dynamics Approach," SAGE Open, , vol. 13(4), pages 21582440231, December.
    2. Steffen Dalsgaard, 2022. "Can IT Resolve the Climate Crisis? Sketching the Role of an Anthropology of Digital Technology," Sustainability, MDPI, vol. 14(10), pages 1-17, May.
    3. Axenbeck, Janna & Niebel, Thomas, 2021. "Climate Protection Potentials of Digitalized Production Processes: Microeconometric Evidence," 23rd ITS Biennial Conference, Online Conference / Gothenburg 2021. Digital societies and industrial transformations: Policies, markets, and technologies in a post-Covid world 238007, International Telecommunications Society (ITS).
    4. Lange, Steffen & Pohl, Johanna & Santarius, Tilman, 2020. "Digitalization and energy consumption. Does ICT reduce energy demand?," Ecological Economics, Elsevier, vol. 176(C).
    5. Wilson, Christopher & van der Velden, Maja, 2022. "Sustainable AI: An integrated model to guide public sector decision-making," Technology in Society, Elsevier, vol. 68(C).
    6. Wen Chen & Changyi Zhu & Qi Cheung & Siying Wu & Jun Zhang & Jia Cao, 2024. "How does digitization enable green innovation? Evidence from Chinese listed companies," Business Strategy and the Environment, Wiley Blackwell, vol. 33(5), pages 3832-3854, July.
    7. Babasola Osibo & Simisola Adamo, 2023. "Data Centers and Green Energy: Paving the Way for a Sustainable Digital Future," International Journal of Latest Technology in Engineering, Management & Applied Science, International Journal of Latest Technology in Engineering, Management & Applied Science (IJLTEMAS), vol. 12(11), pages 15-30, November.
    8. Anders S. G. Andrae & Mengjun Xia & Jianli Zhang & Xiaoming Tang, 2016. "Practical Eco-Design and Eco-Innovation of Consumer Electronics—the Case of Mobile Phones," Challenges, MDPI, vol. 7(1), pages 1-19, February.
    9. Yuan, Rong & Ma, Tianhao & Jin, Yi, 2025. "Carbon footprints embodied in the value chain of multinational enterprises in the Information and Communication Technology sector," Energy, Elsevier, vol. 320(C).
    10. Muhammad Fahad & Arsalan Shahid & Ravi Reddy Manumachu & Alexey Lastovetsky, 2019. "A Comparative Study of Methods for Measurement of Energy of Computing," Energies, MDPI, vol. 12(11), pages 1-42, June.
    11. Tilman Santarius & Johanna Pohl & Steffen Lange, 2020. "Digitalization and the Decoupling Debate: Can ICT Help to Reduce Environmental Impacts While the Economy Keeps Growing?," Sustainability, MDPI, vol. 12(18), pages 1-20, September.
    12. John Martinovic & Markus Hähnel & Guntram Scheithauer & Waltenegus Dargie, 2022. "An introduction to stochastic bin packing-based server consolidation with conflicts," TOP: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 30(2), pages 296-331, July.
    13. Aimee van Wynsberghe & Tijs Vandemeulebroucke & Larissa Bolte & Jamila Nachid, 2022. "Special Issue “Towards the Sustainability of AI; Multi-Disciplinary Approaches to Investigate the Hidden Costs of AI”," Sustainability, MDPI, vol. 14(24), pages 1-4, December.
    14. Anders S. G. Andrae & Mikko Samuli Vaija, 2017. "Precision of a Streamlined Life Cycle Assessment Approach Used in Eco-Rating of Mobile Phones," Challenges, MDPI, vol. 8(2), pages 1-24, August.
    15. Salil Bharany & Sandeep Sharma & Osamah Ibrahim Khalaf & Ghaida Muttashar Abdulsahib & Abeer S. Al Humaimeedy & Theyazn H. H. Aldhyani & Mashael Maashi & Hasan Alkahtani, 2022. "A Systematic Survey on Energy-Efficient Techniques in Sustainable Cloud Computing," Sustainability, MDPI, vol. 14(10), pages 1-89, May.
    16. Elgaaied-Gambier, Leila & Bertrandias, Laurent & Bernard, Yohan, 2020. "Cutting the Internet's Environmental Footprint: An Analysis of Consumers' Self-Attribution of Responsibility," Journal of Interactive Marketing, Elsevier, vol. 50(C), pages 120-135.
    17. Sovacool, Benjamin K. & Martiskainen, Mari & Furszyfer Del Rio, Dylan D., 2021. "Knowledge, energy sustainability, and vulnerability in the demographics of smart home technology diffusion," Energy Policy, Elsevier, vol. 153(C).
    18. David Mytton & Dag Lundén & Jens Malmodin, 2024. "Network energy use not directly proportional to data volume: The power model approach for more reliable network energy consumption calculations," Journal of Industrial Ecology, Yale University, vol. 28(4), pages 966-980, August.
    19. Kosuke Sasakura & Takeshi Aoki & Masayoshi Komatsu & Takeshi Watanabe, 2020. "A Temperature-Risk and Energy-Saving Evaluation Model for Supporting Energy-Saving Measures for Data Center Server Rooms," Energies, MDPI, vol. 13(19), pages 1-22, October.
    20. Daniel Walia & Paul Schünemann & Hauke Hartmann & Frank Adam & Jochen Großmann, 2021. "Numerical and Physical Modeling of a Tension-Leg Platform for Offshore Wind Turbines," Energies, MDPI, vol. 14(12), pages 1-22, June.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:17:y:2025:i:12:p:5359-:d:1675875. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.