Energy-Efficient Artificial Intelligence: Evaluating Sustainable Model Design in Data-Intensive Systems
Article Sidebar
Energy-Efficient Models,
Green AI,
Model Optimization,
Sustainable Computing
Main Article Content
Deshinta Arrova Dewi
Firdhaus Hari Saputra Al Haris
Abstract
Background: The rapid growth of artificial intelligence (AI) in data-intensive systems has significantly increased computational demand, raising concerns regarding energy consumption and environmental sustainability.
Aims: This study aims to develop a unified benchmarking framework that integrates predictive performance, computational complexity, and real-time energy consumption into a sustainability-aware evaluation protocol.
Methods: The proposed framework evaluates multiple model families by jointly measuring accuracy metrics, computational complexity, and real-time energy consumption during training and inference. Experiments were conducted under controlled hardware and dataset configurations to ensure comparability. Trade-off analysis was performed using sustainability-adjusted efficiency metrics and Pareto-optimal frontier evaluation to assess energy-performance balance.
Result: Experimental results show that deep neural networks achieved the highest predictive accuracy, with improvements of up to 2.1% over ensemble-based baselines. However, these gains required substantially higher energy consumption during training and inference. Gradient Boosting models demonstrated the most favorable sustainability-adjusted efficiency, reducing total energy usage by approximately 35–45% compared to deep architectures while maintaining competitive accuracy. Lightweight neural networks further achieved an optimal balance, occupying the Pareto-efficient frontier in energy-performance trade-off analysis.
Conclusion: The findings confirm that marginal accuracy improvements often incur disproportionate energy costs, underscoring the importance of sustainability-integrated benchmarking frameworks.
Article Details
Copyright (c) 2026 Deshinta Arrova Dewi, Firdhaus Hari Saputra Al Haris
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
Abdelmoniem, A. M., Ho, C. Y., Papageorgiou, P., & Canini, M. (2023). A Comprehensive Empirical Study of Heterogeneity in Federated Learning. IEEE Internet of Things Journal, 10(16), 14071–14083. https://doi.org/10.1109/JIOT.2023.3250275
Al-Wreikat, Y., Serrano, C., & Sodré, J. R. (2022). Effects of ambient temperature and trip characteristics on the energy consumption of an electric vehicle. Energy, 238, 122028. https://doi.org/10.1016/j.energy.2021.122028
Apicella, A., Isgrò, F., & Prevete, R. (2025). Don’t push the button! Exploring data leakage risks in machine learning and transfer learning. Artificial Intelligence Review 2025 58:11, 58(11), 339-. https://doi.org/10.1007/s10462-025-11326-3
Aquino-Brítez, S., García-Sánchez, P., Ortiz, A., & Aquino-Brítez, D. (2025). Towards an Energy Consumption Index for Deep Learning Models: A Comparative Analysis of Architectures, GPUs, and Measurement Tools. Sensors 2025, Vol. 25, 25(3). https://doi.org/10.3390/s25030846
Banha, F., Coelho, L. S., & Flores, A. (2022). Entrepreneurship Education: A Systematic Literature Review and Identification of an Existing Gap in the Field. Education Sciences 2022, Vol. 12, 12(5). https://doi.org/10.3390/educsci12050336
Bharany, S., Sharma, S., Khalaf, O. I., Abdulsahib, G. M., Al Humaimeedy, A. S., Aldhyani, T. H. H., Maashi, M., & Alkahtani, H. (2022). A Systematic Survey on Energy-Efficient Techniques in Sustainable Cloud Computing. Sustainability 2022, Vol. 14, 14(10). https://doi.org/10.3390/su14106256
Bo, F., Jiwen, F., Jiuchun, Z., Chong, L., Jia, W., & Mingming, L. (2025). AI-driven predictive models for sustainability. Journal of Environmental Management, 373, 123472. https://doi.org/10.1016/j.enconman.2022.116319
Bragolusi, P., & D’Alpaos, C. (2022). The valuation of buildings energy retrofitting: A multiple-criteria approach to reconcile cost-benefit trade-offs and energy savings. Applied Energy, 310, 118431. https://doi.org/10.1016/j.apenergy.2021.118431
Dorrich, M., Fan, M., & Kist, A. M. (2023). Impact of Mixed Precision Techniques on Training and Inference Efficiency of Deep Neural Networks. IEEE Access, 11, 57627–57634. https://doi.org/10.1109/ACCESS.2023.3284388
Fan, Z., Yan, Z., & Wen, S. (2023). Deep Learning and Artificial Intelligence in Sustainability: A Review of SDGs, Renewable Energy, and Environmental Health. Sustainability 2023, Vol. 15, 15(18). https://doi.org/10.3390/su151813493
Farrelly, D., Bhogal, M. S., & Badham, L. (2024). The email conservation task: Testing the validity of an online measure of direct pro-environmental behavior. Journal of Environmental Psychology, 99(2), 102442. https://doi.org/10.1016/j.jenvp.2024.102442
Fernandez, J., Na, C., Tiwari, V., Bisk, Y., Luccioni, S., & Strubell, E. (2025). Energy Considerations of Large Language Model Inference and Efficiency Optimizations. http://arxiv.org/abs/2504.17674
Gallardo-Gómez, D., Pedder, H., Welton, N. J., Dwan, K., & Dias, S. (2024). Variability in meta-analysis estimates of continuous outcomes using different standardization and scale-specific re-expression methods. Journal of Clinical Epidemiology, 165. https://doi.org/10.1016/j.jclinepi.2023.11.003
Gelenbe, E. (2025). Minimizing Delay and Power Consumption at the Edge. Sensors 2025, Vol. 25, 25(2). https://doi.org/10.3390/s25020502
Karl, F., Pielok, T., Moosbauer, J., Pfisterer, F., Coors, S., Binder, M., Schneider, L., Thomas, J., Richter, J., Lang, M., Garrido-Merchán, E. C., Branke, J., & Bischl, B. (2023). Multi-Objective Hyperparameter Optimization in Machine Learning—An Overview. ACM Transactions on Evolutionary Learning and Optimization, 3(4). https://doi.org/10.1145/3610536
Kovács, G., & Fazekas, A. (2024). mlscorecheck: Testing the consistency of reported performance scores and experiments in machine learning. Neurocomputing, 583, 127556. https://doi.org/10.1016/j.neucom.2024.127556
Kuzmina, J., Atstaja, D., Purvins, M., Baakashvili, G., & Chkareuli, V. (2023). In Search of Sustainability and Financial Returns: The Case of ESG Energy Funds. Sustainability 2023, Vol. 15, 15(3). https://doi.org/10.3390/su15032716
Maghami, M. R., Yaghoubi, E., Mohamed, M., Yaghoubi, E., Jahromi, M. Z., & Fei, T. K. (2025). Multi-objective optimization of unbalanced power distribution systems: a comprehensive approach to address uncertainties and enhance performance. Energy Conversion and Management: X, 27(2), 101087. https://doi.org/10.1016/j.ecmx.2025.101087
Maier, H. R., Zheng, F., Gupta, H., Chen, J., Mai, J., Savic, D., Loritz, R., Wu, W., Guo, D., Bennett, A., Jakeman, A., Razavi, S., & Zhao, J. (2023). On how data are partitioned in model development and evaluation: Confronting the elephant in the room to enhance model generalization. Environmental Modelling & Software, 167(1), 105779. https://doi.org/10.1016/j.envsoft.2023.105779
Margara, A., Cugola, G., Felicioni, N., & Cilloni, S. (2024). A Model and Survey of Distributed Data-Intensive Systems. ACM Computing Surveys, 56(1). https://doi.org/10.1145/3604801
Moscovich, A., & Rosset, S. (2022). On the Cross-Validation Bias due to Unsupervised Preprocessing. Journal of the Royal Statistical Society Series B: Statistical Methodology, 84(4), 1474–1502. https://doi.org/10.1111/rssb.12537
Naser, M. Z. (2023a). Do We Need Exotic Models? Engineering Metrics to Enable Green Machine Learning from Tackling Accuracy-Energy Trade-offs. Journal of Cleaner Production, 382, 135334. https://doi.org/10.1016/j.jclepro.2022.135334
Naser, M. Z. (2023b). Do We Need Exotic Models? Engineering Metrics to Enable Green Machine Learning from Tackling Accuracy-Energy Trade-offs. Journal of Cleaner Production, 382, 135334. https://doi.org/10.1016/j.jclepro.2022.135334
Raman, R., Pattnaik, D., Lathabai, H. H., Kumar, C., Govindan, K., & Nedungadi, P. (2024). Green and sustainable AI research: an integrated thematic and topic modeling analysis. Journal of Big Data 2024 11:1, 11(1), 55-. https://doi.org/10.1186/s40537-024-00920-x
Saxena, D., Kumar, J., Singh, A. K., & Schmid, S. (2023). Performance Analysis of Machine Learning Centered Workload Prediction Models for Cloud. IEEE Transactions on Parallel and Distributed Systems, 34(4), 1313–1330. https://doi.org/10.1109/TPDS.2023.3240567
Seto, H., Oyama, A., Kitora, S., Toki, H., Yamamoto, R., Kotoku, J., Haga, A., Shinzawa, M., Yamakawa, M., Fukui, S., & Moriyama, T. (2022). Gradient boosting decision tree becomes more reliable than logistic regression in predicting probability for diabetes with big data. Scientific Reports 2022 12:1, 12(1), 15889-. https://doi.org/10.1038/s41598-022-20149-z
Shehbaz, W., & Peng, Q. (2025). Evaluation of Machine Learning Models for Enhancing Sustainability in Additive Manufacturing. Technologies 2025, Vol. 13, 13(6). https://doi.org/10.3390/technologies13060228
Shim, J. W. (2024). Enhancing cross entropy with a linearly adaptive loss function for optimized classification performance. Scientific Reports 2024 14:1, 14(1), 27405-. https://doi.org/10.1038/s41598-024-78858-6
Soman, K., Kokate, C., Mohite, A., Vispute, A., More, O., & Kasimali Mundargi, Z. (2022). Statistical Tests for Comparing Machine Learning Algorithms. 10. https://doi.org/10.22214/ijraset.2022.47955
Tabbakh, A., Al Amin, L., Islam, M., Mahmud, G. M. I., Chowdhury, I. K., & Mukta, M. S. H. (2024). Towards sustainable AI: a comprehensive framework for Green AI. Discover Sustainability 2024 5:1, 5(1), 408-. https://doi.org/10.1007/s43621-024-00641-4
Thiyagalingam, J., Shankar, M., Fox, G., & Hey, T. (2022). Scientific machine learning benchmarks. Nature Reviews Physics 2022 4:6, 4(6), 413–420. https://doi.org/10.1038/s42254-022-00441-7
Vamvakas, D., Papaioannou, I., Tsaknakis, C., Sgouros, T., & Korkas, C. (2025). Generative AI for Sustainable Smart Environments: A Review of Energy Systems, Buildings, and User-Centric Decision-Making. Energies 2025, Vol. 18, 18(23). https://doi.org/10.3390/en18236163
Van der Vlist, F., Helmond, A., & Ferrari, F. (2024). Big AI: Cloud infrastructure dependence and the industrialisation of artificial intelligence. Big Data and Society, 11(1). https://doi.org/10.1177/20539517241232630
Vos, G., van Eijk, L., Sarnyai, Z., & Azghadi, M. R. (2024). Stabilizing Machine Learning for Reproducible and Explainable Results: A Novel Validation Approach to Subject-Specific Insights. http://arxiv.org/abs/2412.16199
Wen, X., Zhao, D., Lv, Z., Zhang, K., & Zhang, Y. (2024). A sustainability-oriented approach for performance assessment of existing buildings and a case study. Heliyon, 10(12), e32151. https://doi.org/10.1016/j.heliyon.2024.e32151
Zhu, J., Yang, K., Guan, N., Yi, X., & Qiu, C. (2023). HCPNet: Learning discriminative prototypes for few-shot remote sensing image scene classification. International Journal of Applied Earth Observation and Geoinformation, 123(11), 103447. https://doi.org/10.1016/j.jag.2023.103447
Zieliński, G., & Więckiewicz, M. (2025). New effect size and sample size guidelines in dentistry. Dental and Medical Problems, 62(5), 907–917. https://doi.org/10.17219/dmp/210478