Performance Evaluation of Load Balancing Techniques in Cloud Computing

Abstract

Load balancing plays a crucial role in maintaining optimal performance and reliability in cloud computing environments. As the demand for scalable cloud services continues to grow, traditional algorithms often struggle to handle dynamic workloads effectively. This paper presents a hybrid load balancing approach that combines Reinforcement Learning (RL) with optimization algorithms such as Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) to enhance task allocation and resource utilization. The proposed model adapts intelligently to changing workloads while minimizing response time and ensuring Service Level Agreement (SLA) compliance. Experimental analysis shows that the hybrid RL–PSO/GWO technique achieves better throughput, scalability, and fault tolerance compared to conventional methods, making it a promising solution for modern cloud infrastructures.