Intelligent Load Balancing Using Machine Learning for Cloud Computing Environments

Cloud computing provides scalable and on-demand computing resources but faces challenges in efficient workload distribution and resource utilization due to dynamic and heterogeneous environments. Conventional load balancing techniques often fail to adapt to changing workloads, resulting in increased response time and inefficient resource usage. This study proposes an Intelligent Load Balancing Using Machine Learning (ILBML) framework that predicts the optimal virtual machine for task allocation based on system parameters such as CPU utilization, memory usage, and network load. The proposed approach aims to improve resource utilization, reduce response time, enhance throughput, and minimize Service Level Agreement (SLA) violations. Performance is evaluated using cloud simulation tools and compared with traditional load balancing algorithms. Experimental results demonstrate that the proposed machine learning-based framework significantly enhances cloud service performance, scalability, and resource management efficiency.