Comparative Analysis of Energy Reduction and Service-Level Agreement Compliance in Cloud and Edge Computing: A Machine Learning Perspective

As cloud and edge computing continue to evolve, the demand for optimizing energy consumption while ensuring stringent Service-Level Agreement (SLA) compliance has intensified. This paper provides a comparative evaluation of energy reduction and SLA compliance performance across multiple machine learning classifiers employed in both cloud and edge computing ecosystems. The study contrasts the effectiveness of traditional and AI-driven models, such as Support Vector Machines, Neural Networks, Decision Trees, and Random Forests, in managing energy consumption and SLA adherence. By utilizing energy reduction percentages, SLA compliance rates, and execution time as key metrics, we present an in-depth analysis through a series of advanced visualizations, including stacked bar graphs, radar charts, bubble plots, and box plots. The findings reveal key insights into the trade-offs between energy efficiency and SLA compliance across classifiers, with AI models - particularly Neural Networks - demonstrating superior performance in achieving optimal energy savings while ensuring SLA adherence. This research offers critical implications for resource optimization strategies in cloud and edge computing frameworks, advancing the field of sustainable computing and adaptive resource management in next-generation distributed systems. The study contributes to sustainable computing by offering empirical evidence and a comparative analysis of machine learning models under relevant performance metrics.