Sustainable Cloud Computing: AI-Enhanced Models for EnergyEfficient Data Centers

Session

Computer Science and Communication Engineering

Description

Cloud computing has revolutionized digital infrastructure by providing scalable, ondemand computing resources. However, the exponential growth of data centers has introduced significant environmental and energy challenges, making sustainability a central concern in modern computing. Data centers currently consume an estimated 1–2% of global electricity, and this percentage continues to rise. As a result, optimizing energy consumption while maintaining performance has become a key research and industrial priority.This study explores AI-enhanced models for sustainable cloud computing, focusing on how machine learning and predictive analytics can minimize energy usage and carbon emissions in large-scale data centers. The research investigates the integration of artificial intelligence into resource scheduling, workload prediction, and dynamic power management. By leveraging techniques such as reinforcement learning, neural networks, and intelligent auto-scaling, data centers can adapt resource allocation in real-time based on workload patterns and environmental conditions.The proposed framework aims to establish a balance between energy efficiency, computational performance, and cost optimization in cloud infrastructures. Case studies from major cloud providers, such as AWS, Azure, and Google Cloud, are analyzed to evaluate current sustainability practices and identify potential improvements enabled by AI Expected Results:The study is expected to demonstrate that AI-based optimization techniques can significantly reduce energy consumption—by up to 30% according to existing models— without compromising system reliability or throughput. The findings will contribute to a framework for designing energy-aware, self-adaptive, and environmentally sustainable cloud data centers.

Keywords:

Cloud Computing, Artificial Intelligence, Sustainability, Energy Efficiency, Data Centers, Machine Learning, Predictive Analytics, Green Computing, Reinforcement Learning, Auto-Scaling, Carbon Neutrality, Resource Management

Proceedings Editor

Edmond Hajrizi

ISBN

978-9951-982-41-2

Location

UBT Kampus, Lipjan

Start Date

25-10-2025 9:00 AM

End Date

26-10-2025 6:00 PM

DOI

10.33107/ubt-ic.2025.74

This document is currently not available here.

Share

COinS
 
Oct 25th, 9:00 AM Oct 26th, 6:00 PM

Sustainable Cloud Computing: AI-Enhanced Models for EnergyEfficient Data Centers

UBT Kampus, Lipjan

Cloud computing has revolutionized digital infrastructure by providing scalable, ondemand computing resources. However, the exponential growth of data centers has introduced significant environmental and energy challenges, making sustainability a central concern in modern computing. Data centers currently consume an estimated 1–2% of global electricity, and this percentage continues to rise. As a result, optimizing energy consumption while maintaining performance has become a key research and industrial priority.This study explores AI-enhanced models for sustainable cloud computing, focusing on how machine learning and predictive analytics can minimize energy usage and carbon emissions in large-scale data centers. The research investigates the integration of artificial intelligence into resource scheduling, workload prediction, and dynamic power management. By leveraging techniques such as reinforcement learning, neural networks, and intelligent auto-scaling, data centers can adapt resource allocation in real-time based on workload patterns and environmental conditions.The proposed framework aims to establish a balance between energy efficiency, computational performance, and cost optimization in cloud infrastructures. Case studies from major cloud providers, such as AWS, Azure, and Google Cloud, are analyzed to evaluate current sustainability practices and identify potential improvements enabled by AI Expected Results:The study is expected to demonstrate that AI-based optimization techniques can significantly reduce energy consumption—by up to 30% according to existing models— without compromising system reliability or throughput. The findings will contribute to a framework for designing energy-aware, self-adaptive, and environmentally sustainable cloud data centers.