Optimizing Resource Allocation in Cloud Infrastructure through AI Automation: A Comparative Study

Abstract

Optimizing resource allocation in cloud infrastructure is paramount for ensuring efficient utilization of computing resources and minimizing operational costs. With the proliferation of diverse workloads and dynamic user demands, manual resource management becomes increasingly challenging. In this context, artificial intelligence (AI) automation emerges as a promising approach to enhance resource allocation efficiency. This paper presents a comparative study of various AI techniques applied to optimize resource allocation in cloud environments. We explore the efficacy of machine learning, evolutionary algorithms, and deep reinforcement learning methods in dynamically allocating resources to meet performance objectives while minimizing costs. Through a comprehensive evaluation of these approaches using real-world datasets and simulation experiments, we highlight their strengths, limitations, and comparative performance. Our findings provide valuable insights into the effectiveness of AI-driven resource allocation strategies, enabling cloud providers and practitioners to make informed decisions for enhancing cloud infrastructure management