Hybrid Ant Colony and Whale Optimization algorithms for QoS-aware loading balancing in cloud computing environment

Abstract Cloud computing is gaining traction, thanks to adaptable platforms, diverse applications, and cost-effective infrastructures. With the ever-growing volume of cloud tasks and subscribers, scheduling and balancing workloads across virtual machines are increasingly challenging. These challenges have been widely addressed using meta-heuristic algorithms. This study presents a novel load balancing mechanism that combines Ant Colony Optimization (ACO) and Whale Optimization Algorithm (WOA), referred to as LBAW. The ACO algorithm optimizes task allocation and scheduling, while the WOA algorithm manages resource utilization and migration. Performance analysis revealed that LBAW has a positive effect on load balancing in cloud computing, achieving up to 12% improvement in resource utilization, a 13% reduction in makespan, a 16% decrease in imbalance degree, and a 27% decline in response time over previous methods. These enhancements enable LBAW to deliver significant improvements in resource provisioning and task scheduling, along with compatibility for use in real-world cloud infrastructures, such as elastic service environments and dynamic workload systems, as well as distributed data centers.