• Saturday, Aug 8th, 2026

International Journal of Multidisciplinary and Scientific
Emerging Research (IJMSERH)

|Peer Reviewed, Refereed & Open Access Journal | Follows UGC CARE Journal Norms and Guidelines|

|ISSN 2349-6037|Approved by ISSN, NSL & NISCAIR| Impact Factor: 9.274 |ESTD:2013|

|Scholarly Open Access Journal, Peer-Reviewed, and Refereed Journals, Impact factor 9.274 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Multidisciplinary, Quarterly, Citation Generator, Digital Object Identifier(DOI)|

Article

TITLE Energy-Efficient AI: Techniques for Green and Sustainable Machine Learning
ABSTRACT The rapid expansion of deep learning and large-scale artificial intelligence (AI) models has significantly increased computational demand and energy consumption, raising serious environmental and economic concerns. Training and deploying modern AI systems require extensive hardware resources, contributing to high carbon emissions and operational costs. This review provides a comprehensive analysis of energy-efficient techniques for green and sustainable machine learning. It presents a structured taxonomy covering model-level optimization (pruning, quantization, distillation), algorithm-level improvements, data-efficient strategies, hardware acceleration, and system-level energy management approaches. The study also examines energy measurement metrics, trade-offs between accuracy and power consumption, and emerging trends such as TinyML and edge intelligence. Furthermore, it identifies key research challenges, including standardized benchmarking and carbon-aware training. The review highlights future directions toward developing scalable, low-carbon AI ecosystems that balance performance, efficiency, and sustainability.
AUTHOR Nikita Ravindra Rajurkar Assistant Professor, Ranibai Agnihotri Institute of Computer Science & Information Technology, Wardha, Maharashtra, India
PUBLICATION DATE 2026-02-28 13:04:10
VOLUME 14
ISSUE 1
DOI DOI: 10.15662/IJMSERH.2026.1401015
PDF pdf/2026/1/15_Energy-Efficient AI Techniques for Green and Sustainable Machine Learning.pdf
KEYWORDS
References 1. Han, S., Pool, J., Tran, J., & Dally, W. (2015). Learning both weights and connections for efficient neural networks. Advances in Neural Information Processing Systems, 28, 1135–1143.
2. Horowitz, M. (2014). 1.1 Computing’s energy problem (and what we can do about it). IEEE International Solid-State Circuits Conference Digest of Technical Papers, 10–14. https://doi.org/10.1109/ISSCC.2014.6757323
3. Patterson, D., Gonzalez, J., Le, Q., Liang, C., Munguia, L., Rothchild, D., So, D., Texier, M., & Dean, J. (2021). Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350.
4. Schwartz, R., Dodge, J., Smith, N. A., & Etzioni, O. (2020). Green AI. Communications of the ACM, 63(12), 54–63. https://doi.org/10.1145/3381831
5. Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 3645–3650. https://doi.org/10.18653/v1/P19-1355
6. Sze, V., Chen, Y. H., Yang, T. J., & Emer, J. S. (2017). Efficient processing of deep neural networks: A tutorial and survey. Proceedings of the IEEE, 105(12), 2295–2329. https://doi.org/10.1109/JPROC.2017.2761740
7. Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, 6105–6114.
8. Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531.
9. Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.
10. Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018). Quantization and training of neural networks for efficient integer-arithmetic-only inference. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2704–2713.
11. Lane, N. D., Bhattacharya, S., Georgiev, P., Forlivesi, C., Jiao, Y., Kawsar, F., & Mascolo, C. (2015). DeepX: A software accelerator for low-power deep learning inference on mobile devices. Proceedings of the 14th International Conference on Information Processing in Sensor Networks, 1–12.
12. Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016). XNOR-Net: ImageNet classification using binary convolutional neural networks. Proceedings of the European Conference on Computer Vision, 525–542.
13. Zoph, B., & Le, Q. V. (2017). Neural architecture search with reinforcement learning. International Conference on Learning Representations.

Copyright@IJMSERH