Hybrid Red Fox and Remora Optimization Algorithm Expedites Optimal Load Balancing in Cloud Computing

Abstract Cloud task scheduling poses a complex optimization challenge due to dynamic nature of the cloud system and varying user demands. The system's load, determined by the cloud architecture and user requirements, can lead to failures such as increased power consumption and machine failures when the system is either under loaded or overloaded. Consequently, achieving task-load balancing on virtual machines (VMs) becomes crucial in cloud task scheduling to mitigate these issues. In this manuscript, proposed the Hybrid Red Fox and Remora Optimization Algorithm Expedites Optimum Load Balancing in Cloud Computing (HYB-RF-RO-LB-CC) to address the load equalizing problem in cloud networks. By incorporating the Red fox optimization algorithm (RFOA) into Remora Optimization Algorithm (ROA), achieve a useful load balancing algorithm. The proposed method focuses on identifying the optimal under load that considers multiple objective functions, like cost, response time, and resource utilization, ultimately minimizing the fitness function of load equalizing. The process HYB-RF-RO-LB-CC effectively assesses and balances the load of each virtual machine (VM) using fitness function. The proposed HYB-RF-RO-LB-CC approach is executed in CloudSim tool. The performance of the proposed HYB-RF-RO-LB-CC approach attains 3.101%, 7.12% and 6.7% higher makes span, 24.13%, 13.04% and 17.81% minimum energy utilization, 5.262%, 8.375% and 7.945% better throughput compared with existing methods such as Harris Hawk Optimization (HHO), Manta Ray Forging Optimization (MRFO) approach and Grey Wolf Optimization (GWO) algorithm respectively.