A Green Support System Framework for Energy-Efficient Cloud Computing

The rapid expansion of cloud computing has significantly increased energy consumption and carbon emissions in global data centers, raising urgent sustainability concerns. This study introduces a Green Support System (GSS) Framework for energy-efficient cloud computing, integrating AI-driven optimization, carbon-aware scheduling, and responsible AI mechanisms to ensure environmentally and ethically responsible operations. The framework employs multi-layer data collection, preprocessing, predictive workload forecasting, and anomaly detection to optimize energy usage while maintaining high performance. Its effectiveness is demonstrated through real-world examples from major cloud providers, including Google Cloud, Microsoft Azure, and AWS, which showcase renewable energy integration, AI-powered workload management, and low-carbon computing practices. Simulation results indicate that the GSS framework can reduce energy consumption by 15–30%, lower modelled carbon emissions by 12–25%, and achieve 92% accuracy in detecting anomalies, highlighting its practical viability. Additionally, the framework supports alignment with multiple Sustainable Development Goals (SDGs 7, 9, 12, and 13), emphasizing its broader environmental and societal impact. These findings demonstrate that combining AI-based optimization, carbon-aware strategies, and responsible AI governance offers a scalable, sustainable, and ethical solution for cloud computing, providing both operational efficiency and measurable environmental benefits.

green cloud computing; energy-efficient cloud

1. Amazon Web Services (AWS). (2023). Sustainable cloud infrastructure. ttps://aws.amazon.com/sustainability/ https://cloud.google.com/sustainability [Google Scholar] [Crossref]

2. Microsoft Azure. (2023). AI-driven sustainable cloud operations. https://azure.microsoft.com/en-us/resources/sustainability [Google Scholar] [Crossref]

3. Patel, S., & Singh, V. (2022). Carbon-efficient cloud orchestration. Journal of Cloud Computing, 11(4), 1–15. [Google Scholar] [Crossref]

4. Wang, L., & Chen, M. (2023). AI-guided carbon-aware scheduling in data centers. Applied Energy, 340, 123456. [Google Scholar] [Crossref]

5. Tyagi, P., et al. (2024). Green cloud computing and carbon-aware scheduling: A review. Sustainable Computing: Informatics and Systems, 39, 100756. [Google Scholar] [Crossref]

6. Semwal, M., Tyagi, P., & Kumar, S. (2025). Energy-aware AI for cloud environments. Sustainable Computing: Informatics and Systems. https://link.springer.com/article/10.1007/s43621-024-00641-4 https://share.google/images/T5IM9UyO8kgG0VxKX [Google Scholar] [Crossref]

7. Alex, Maraga & Ojo, Sunday & Awuor, Fred. (2025). Carbon-Aware, Energy-Efficient, and SLA-Compliant Virtual Machine Placement in Cloud Data Centers Using Deep Q-Networks and Agglomerative Clustering. Computers. 14. 280. 10.3390/computers14070280. http://unglobalcompact.org/compactjournal/artificial-intelligence-and-sustainable-development-goals-operationalizing [Google Scholar] [Crossref]

8. Chatterjee, S., Rana, N. P., Tamilmani, K., & Sharma, A. (2024). AI-driven sustainability analytics: A multi-SDG evaluation framework. Sustainable Computing: Informatics and Systems, 41, 100897. [Google Scholar] [Crossref]

9. Raji, I. D., Smart, A., & Wu, T. (2020). Closing the AI accountability gap: Defining an auditing ecosystem for AI governance. Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 136–145. [Google Scholar] [Crossref]

10. Varshney, K., Gupta, R., & Ahmad, F. (2023). Carbon-emission reduction using intelligent orchestration in cloud systems. Journal of Sustainable Computing, 18, 52–67. [Google Scholar] [Crossref]

11. Yadav, N., & Bansal, S. (2021). SDG impact assessment using machine learning–based decision support systems. Sustainability, 13(16), 8944. [Google Scholar] [Crossref]

12. Falk, M., & Van Wynsberghe, A. (2024). Responsible AI for sustainable development: Ethical frameworks and implementation challenges. AI & Society, 39(2), 523–539. https://share.google/WEeFEV7Hokw7cZ8R2 [Google Scholar] [Crossref]

13. Google AI. (2020). Carbon-intelligent computing. Google Research Reports. [Google Scholar] [Crossref]

14. Baker, T., & Xiang, Y. (2023). Responsible AI frameworks for transparent and explainable decision-making. AI Ethics Journal, 5(1), 20–39. [Google Scholar] [Crossref]

15. Aragón, A., Arquier, M., Tokdemir, O. B., Enfedaque, A., Alberti, M. G., Lieval, F., ... & Yagüe, Á. (2025). Seeking a Definition of Digital Twins for Construction and Infrastructure Management. Applied Sciences, 15(3), 1557. [Google Scholar] [Crossref]

16. Calheiros, R. N., Ranjan, R., Beloglazov, A., De Rose, C. A., & Buyya, R. (2011). [Google Scholar] [Crossref]

17. CloudSim: A toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Software: Practice and Experience, 41(1), 23–50. [Google Scholar] [Crossref]

18. Beloglazov, A., & Buyya, R. (2012). Optimal online deterministic algorithms and adaptive heuristics for energy- and performance-efficient dynamic consolidation of virtual machines in cloud data centers. Concurrency and Computation: Practice and Experience, 24(13), 1397–1420. https://doi.org/10.1002/cpe.1867 [Google Scholar] [Crossref]

19. Dayarathna, M., Wen, Y., & Fan, R. (2016). Data center energy consumption modeling: A survey. IEEE Communications Surveys & Tutorials, 18(1), 732–794. https://doi.org/10.1109/COMST.2015.2481183 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet