Optimizing Cloud Computing Performance Through Green Infrastructure Strategies

Cloud Computing transformed the deployment and utilization of IT resources as on-demand, scalable, and cost-effective services. The high growth rate of cloud infrastructure, though, raised issues of power usage, carbon footprint, and the environment. All of these issues are solved by invoking energy-efficient hardware, the use of renewable resources, and green operation of data centers upon realization of Green Infrastructure in cloud computing infrastructure. This study employs a multicomponent model integrating atmospheric, terrestrial, geologic, and LiDAR-based urban data to describe resource consumption and environmental effects. Particle Swarm Optimization (PSO) feature selection determines the most significant factors, and a bi-stacked Long Short-Term Memory (LSTM) neural network learns time and space patterns in energy and resource data. The proposed methodology improves maximum workload allocation, energy prediction control, and green cloud operations.