A Quantitative Assessment of Energy and Carbon Efficiency in Green Cloud Data Centers Using Big Data Analytics

The rapid expansion of cloud computing, artificial intelligence, and data-intensive applications has significantly increased the energy consumption and carbon footprint of modern data centers. Improving energy efficiency has therefore become a critical sustainability objective. This paper presents a quantitative assessment of energy and carbon efficiency in green cloud data centers using Big Data analytics. Large-scale operational data collected from Internet of Things (IoT) sensors, server workload logs, and environmental monitoring systems are analyzed to enable real-time energy visibility, predictive modeling, and analytics-driven optimization. Machine learning techniques are employed to forecast energy consumption and guide workload consolidation and adaptive cooling strategies. Experimental evaluation using real operational datasets demonstrates consistent improvements in energy efficiency, achieving Power Usage Effectiveness (PUE) reductions of approximately 17–19% across multiple workload scenarios, along with corresponding reductions in energy consumption and estimated carbon emissions. The results confirm that data-driven energy management can significantly enhance the sustainability and operational efficiency of cloud data centers. The proposed framework demonstrates scalability and adaptability, indicating a practical pathway toward environmentally sustainable and energy-efficient green cloud infrastructures.