Application-Aware AI Load Balancing in Hybrid...

Application-Aware AI Load Balancing in Hybrid Cloud Environments

Author Name : Prasanna Sankaran, Chandrashekhar Moharir, Neelam Kumar

ABSTRACT This paper presents a novel approach to load balancing in hybrid cloud environments through the implementation of an application-aware artificial intelligence (AI) framework. The proposed system leverages machine learning techniques, including BERT for semantic workload analysis and reinforcement learning for dynamic resource allocation, to optimize the distribution of tasks across heterogeneous cloud resources. By integrating real-time monitoring data and predictive modeling, the framework achieves significant improvements in response time, throughput, SLA compliance, and resource utilization compared to traditional load balancing algorithms. A comprehensive evaluation using simulated hybrid cloud scenarios demonstrates the model's ability to adapt to diverse and fluctuating workloads while maintaining operational efficiency and robustness. The system also incorporates explainable AI techniques to ensure transparency in decision-making and supports federated learning to preserve data privacy. The findings confirm the effectiveness of intelligent, context-aware load balancing in addressing the complexities of modern cloud computing environments, offering a scalable and resilient solution for optimizing cloud infrastructure performance.