MACHINE LEARNING ENABLED ENERGY AWARE LOAD BALANCING FOR GREEN CLOUD INFRASTRUCTURES

Cloud computing has revolutionized modern IT infrastructure by providing scalable, flexible, and on-demand services. However, the rapid growth of cloud data centers has resulted in substantial energy consumption and environmental impact, accounting for nearly 2% of global greenhouse gas emissions (Josephine Nartey, 2025). This challenge has led to the emergence of green cloud computing, which aims to enhance energy efficiency and promote environmental sustainability through intelligent resource management and optimized workload scheduling. This project focuses on the design and optimization of energy-aware load balancing techniques to address key trade-offs among makespan, operational cost, and carbon emissions. It critically analyzes existing load balancing algorithms and highlights their limitations in achieving multi-objective optimization. To overcome these challenges, the study proposes advanced distributed architectures and hybrid optimization techniques. The proposed methods will be validated through simulations and real-world experiments using standard cloud benchmarks, aiming to significantly improve the environmental and operational performance of cloud computing environments.