Load-balancing in Cloud Computing Environment using Hybrid Particle Swarm Optimization and Ant Colony Optimization Algorithm

Load-balancing is one of the most important parts of cloud computing, ensuring optimized resource use, reduced response times, and high availability. The traditional Round Robin, Throttled, and Least Connection algorithms fail to adapt to dynamic workloads and, therefore, are unable to provide optimal solutions for resource imbalances. This paper represents a hybrid load-balancing algorithm generated by using both PSO and ACO algorithms to overcome such limitations. The proposed Hybrid PSO-ACO algorithm exploits PSO’s strong ability for global search and ACO’s good efficiency for local optimization for the dynamic resource allocation over multiple servers. Key contributions are: robust framework developed for adaptive load distribution; improved effectiveness in task scheduling; and reduction in system bottlenecks. Through simulation, the combined hybrid approach shows drastic improvements in throughput, make span, response time, and resource utilization compared with traditional algorithms, and thus promises to be a good solution for effective load-balancing within cloud computing.