Predicting High-Performance Computing’s Carbon Footprint: A Transformer-Based Analysis for Sustainable Development

Research Article
Open access

Predicting High-Performance Computing’s Carbon Footprint: A Transformer-Based Analysis for Sustainable Development

Hao Wang 1* , YiBo Dang 2 , ChenKai Zhang 3 , Richard Richard 4
  • 1 BThe Webb Schools, Claremont, USA    
  • 2 Beijing 21st Century School, Haidian Enjizhuang No.46, Beijing, China    
  • 3 Zhejiang RuiAn High School, Ruian No.398, Ruihu Road, Wenzhou, Zhejiang, China    
  • 4 STaipei Wego Private Senior High School, Taipei, China    
  • *corresponding author Mike.0077hh@gmail.com
TNS Vol.109
ISSN (Print): 2753-8826
ISSN (Online): 2753-8818
ISBN (Print): 978-1-80590-103-7
ISBN (Online): 978-1-80590-104-4

Abstract

High Performance Computing (HPC) refers to the use of powerful computers and advanced computational techniques to solve complex problems and perform large-scale processing tasks at high speed. As HPC technology development advances, emission from HPC began to raise numerous environmental concerns, such as carbon emissions, global warming, resource consumption, etc. This study focuses on the environmental impact of the HPC industry. First, the environmental impact of HPC was evaluated. We considered the two indicators of HPC energy, Full Capacity and Average Utilization Rates, to understand and define environmental problems that HPC energy consumption can cause, such as E-Waste. Secondly, we used the time series prediction model with the Transformer architecture to predict and analyze the carbon emissions from HPC energy consumption. Among them, we first obtained the carbon emission data of different sources of HPC energy composition through data collection. Our main data comes from the Kaggle machine learning platform. Our data set mainly records the HPC energy emissions in the United States and different energy mixes. Then, after constructing the transformer model, we let the model predict HPC carbon emissions through data analysis. Finally, we calculated the global temperature increase caused by HPC carbon emissions and the subsequent environmental problems through the prediction results. We also used the Transformer model to predict the amount of carbon emissions in 2030 caused by HPC and the possible environmental impacts it might have, in order to help environmental protection organizations around the world take appropriate measures.

Keywords:

HPC Carbon Emissions, Transformer Forecasting, Computational Sustainability, Energy Comsumption

Wang,H.;Dang,Y.;Zhang,C.;Richard,R. (2025). Predicting High-Performance Computing’s Carbon Footprint: A Transformer-Based Analysis for Sustainable Development. Theoretical and Natural Science,109,199-210.
Export citation

References

[1]. NREL. (n.d.). "High-Performance Computing Data Center Power Usage Effectiveness." https: //www.nrel.gov/computational-science/measuring-efficiency-pue.html.

[2]. ScienceDaily. (2021, September 21). "Emissions from Computing and ICT Could Be Worse Than Previously Thought." https://www.sciencedaily.com/releases/2021/09/210910121715.htm.

[3]. Vaswani, A. (2017). Attention is all you need. Advances in Neural Information Processing Systems.

[4]. Kassai, K., Dagiuklas, T., Bashir, S., & Iqbal, M. (2024, June). "GreenBytes: Intelligent Energy Estimation for Edge-Cloud." In IET Conference Proceedings CP879, Vol. 2024, No. 4, pp. 57-61. Stevenage, UK: The Institution of Engineering and Technology.

[5]. Kaggle. (2024, April). "CO2 Emissions (USA)." https://www.kaggle.com/datasets/ abdelrahman16/co2-emissions-usa?resource=download.

[6]. (2024). "Chasing Carbon: The Elusive Environmental Footprint of Computing." https://ar5iv.labs.arxiv.org/html/2011.02839.

[7]. The MIT Press Reader. (2022, February 22). "The Staggering Ecological Impacts of Computation and the Cloud." https://thereader.mitpress.mit.edu/the-staggering-ecological-impacts-of-computation-and-the-cloud/.

[8]. International Energy Agency. (2024). "Electricity 2024." https://www.iea.org/reports/electricity- 2024. Licence: CC BY 4.0.

[9]. Chinnici, A., Ahmadzada, E., Kor, A., De Chiara, D., Domínguez-Díaz, A., De Marcos Ortega, L., & Chinnici, M. (2024). "Towards Sustainability and Energy Efficiency Using Data Analytics for HPC Data Center." Electronics, 13(17), 3542.

[10]. IEEE. (2024, April). "An Efficient Energy Consumption Prediction Framework for High Performance Computing Cluster Jobs." In IEEE Conference Publication, IEEE Xplore. https: //ieeexplore.ieee.org/document/10603495.

Cite this article

Wang,H.;Dang,Y.;Zhang,C.;Richard,R. (2025). Predicting High-Performance Computing’s Carbon Footprint: A Transformer-Based Analysis for Sustainable Development. Theoretical and Natural Science,109,199-210.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About volume

Volume title: Proceedings of CONF-MPCS 2025 Symposium: Leveraging EVs and Machine Learning for Sustainable Energy Demand Management

ISBN：978-1-80590-103-7(Print) / 978-1-80590-104-4(Online)
Editor：Anil Fernando, Mustafa Istanbullu
Conference website: https://www.confmpcs.org/glasgow.html
Conference date: 16 May 2025
Series: Theoretical and Natural Science
Volume number: Vol.109
ISSN：2753-8818(Print) / 2753-8826(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

References

[1]. NREL. (n.d.). "High-Performance Computing Data Center Power Usage Effectiveness." https: //www.nrel.gov/computational-science/measuring-efficiency-pue.html.

[2]. ScienceDaily. (2021, September 21). "Emissions from Computing and ICT Could Be Worse Than Previously Thought." https://www.sciencedaily.com/releases/2021/09/210910121715.htm.

[3]. Vaswani, A. (2017). Attention is all you need. Advances in Neural Information Processing Systems.

[4]. Kassai, K., Dagiuklas, T., Bashir, S., & Iqbal, M. (2024, June). "GreenBytes: Intelligent Energy Estimation for Edge-Cloud." In IET Conference Proceedings CP879, Vol. 2024, No. 4, pp. 57-61. Stevenage, UK: The Institution of Engineering and Technology.

[5]. Kaggle. (2024, April). "CO2 Emissions (USA)." https://www.kaggle.com/datasets/ abdelrahman16/co2-emissions-usa?resource=download.

[6]. (2024). "Chasing Carbon: The Elusive Environmental Footprint of Computing." https://ar5iv.labs.arxiv.org/html/2011.02839.

[7]. The MIT Press Reader. (2022, February 22). "The Staggering Ecological Impacts of Computation and the Cloud." https://thereader.mitpress.mit.edu/the-staggering-ecological-impacts-of-computation-and-the-cloud/.

[8]. International Energy Agency. (2024). "Electricity 2024." https://www.iea.org/reports/electricity- 2024. Licence: CC BY 4.0.

[9]. Chinnici, A., Ahmadzada, E., Kor, A., De Chiara, D., Domínguez-Díaz, A., De Marcos Ortega, L., & Chinnici, M. (2024). "Towards Sustainability and Energy Efficiency Using Data Analytics for HPC Data Center." Electronics, 13(17), 3542.

[10]. IEEE. (2024, April). "An Efficient Energy Consumption Prediction Framework for High Performance Computing Cluster Jobs." In IEEE Conference Publication, IEEE Xplore. https: //ieeexplore.ieee.org/document/10603495.

For authors
Guide for authors Policies for authors Aims and scope Subscription Open access policy
For editors
Policies for editors Editorial board
For reviewers
Policies for reviewers Privacy policy

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.