Energy Efficiency and Carbon-Aware Workload Scheduling in Azure
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V7I2P108Keywords:
Energy Efficiency, Carbon-Aware Computing, Workload Scheduling, Azure Sustainability, AI-Driven Automation, Green Cloud, Renewable Energy Optimization, Azure Automation, Azure Machine Learning, Sustainability Reporting, Adaptive Resource ManagementAbstract
As cloud adoption scales globally, data centers face growing pressure to reduce their carbon footprint while maintaining performance and reliability. Microsoft Azure has pioneered carbon-aware computing dynamically scheduling workloads based on regional energy availability and emission intensity. This paper explores Azure’s architecture, methodologies, and automation strategies for energy-efficient workload management. It highlights the role of artificial intelligence (AI) and automation in optimizing cloud operations for sustainability, including predictive scheduling, renewable energy alignment, and cost-performance balancing. Real-world use cases and experimental frameworks demonstrate measurable reductions in energy consumption and carbon emissions through intelligent workload orchestration.
References
[1] Microsoft. (2024). Microsoft Sustainability Commitments and Carbon Negative Goals. [Online]. Available: https://www.microsoft.com/sustainability
[2] Wang, Y., & Zhao, L. (2021). “Carbon-Aware Workload Placement in Distributed Data Centers.” IEEE Transactions on Sustainable Computing, 6(4), 812–825.
[3] Saini, R., & Gupta, V. (2022). “Energy-Aware Scheduling in Hybrid Cloud Environments.” Journal of Cloud Efficiency, 5(3), 105–118.
[4] Microsoft. (2024). Azure Emissions Impact Dashboard. [Online]. Available: https://learn.microsoft.com/azure/sustainability/
[5] Azure Architecture Center. (2024). Designing Sustainable Cloud Workloads on Azure.
Microsoft Fabric Team. (2025). AI-Driven Sustainability Analytics for Cloud Optimization.
