Load Balancing Approach in Cloud Computing Using Genetic Algorithm

Abstract

The era of cloud computing where information are stored over the servers virtually, will flourish how viably the virtual infrastructure are started up and accessible resources are effectively used. In the new normal of pandemic, use of cloud services are increasing at a rapid rate day after day and for the outstanding performance it should be balanced in such a way so that increase demand can be handled & processed in minimal time to achieve business continuity. In cloud environments, heterogeneous virtual machine (VM) configurations are dynamically provisioned to process concurrent user requests. As network uncertainties and user traffic spikes intensify, resource contention becomes inevitable—leading to VM overloads and performance bottlenecks. This scenario triggers a critical need for real-time load balancing, a challenge often categorized as NP-Complete. Efficient load distribution is therefore pivotal in ensuring service-level objectives are met without overburdening specific nodes or leaving others underutilized. Load balancing in cloud computing involves the intelligent allocation of incoming workloads across virtualized resources to optimize throughput and system responsiveness. Numerous algorithms have been proposed in this domain; however, this paper introduces a novel Genetic Algorithm (GA)-driven load balancing strategy that significantly enhances task distribution efficiency across virtual machines by leveraging evolutionary computation principles.