AI-DRIVEN GREEN CLOUD COMPUTING: A SUSTAINABLE FRAMEWORK FOR CARBON FOOTPRINT REDUCTION AND ENERGY OPTIMIZATION

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:GX researchers can use this empirical evidence of AI-driven energy optimization in cloud data centers as a reference for similar sustainable infrastructure studies.

🏢実務担当者:Corporate sustainability teams can adopt this framework to reduce operational carbon footprint and report energy savings under Scope 2 and 3.

🏛政策担当者:Policymakers should note the potential of AI in decarbonizing digital infrastructure, supporting policies that incentivize green cloud computing.

The rapid expansion of cloud computing has transformed modern digital systems by enabling scalable, flexible, and high-performance computing services. Organizations across sectors increasingly rely on cloud platforms to enhance productivity, support innovation, and meet growing computational demands. However, this widespread adoption has also led to a sharp increase in energy consumption and carbon emissions. Data centers, which serve as the foundation of cloud infrastructure, are among the most energy-intensive facilities, making them significant contributors to environmental degradation. Projections suggest that by 2030, data centers in the United States alone may account for nearly 12% of total electricity consumption, highlighting the urgent need for sustainable cloud solutions. This research presents a sustainable green cloud computing framework aimed at improving energy efficiency and reducing carbon emissions without compromising system performance and scalability. The proposed approach combines intelligent workload management, dynamic resource allocation, energy-aware task scheduling, and adaptive cooling strategies to lower overall power consumption in cloud environments. By using predictive models and real-time monitoring, the framework enables effective balancing of computational workloads and energy usage, resulting in improved operational efficiency and reduced environmental impact. Comprehensive experimental evaluation using real-world cloud workloads demonstrates that the proposed framework achieves up to 35–45% reduction in energy consumption and 30–40% decrease in carbon emissions, while maintaining reliable service performance. These results confirm the effectiveness of sustainable optimization techniques in developing environmentally responsible cloud infrastructures. This study contributes a practical, scalable, and eco-friendly solution, offering a viable pathway toward carbonneutral and sustainable cloud computing systems capable of supporting future high-performance applications.

• openalex https://doi.org/10.5281/zenodo.20552272first seen 2026-06-23 05:45:14 · last seen 2026-06-23 05:45:30