A Hybrid Model of Gray Wolf Optimization (GWO) and Modified Sunflower Optimization Algorithm (MSOA) for Efficient Task Scheduling in Cloud Computing

Objective: A hybrid GWO-MSOA model is developed for the task scheduling problem. It efficiently approximates solutions for the multi-objective task scheduling problem in a cloud environment. The model optimizes resource utilization, reduces execution time and cost, and improves overall system performance. Method: This study combines Gray Wolf Optimization (GWO) and Modified Sunflower Optimization Algorithm (MSOA) for efficient task scheduling in cloud. The GWO-MSOA methodology enhances convergence speed and identifies near-optimal solution. The proposed hybrid model efficiently schedules the task, which reduces makespan and cost, and improves the resource utilization. CloudSim is employed for an extensive performance assessment, evaluating GWO-MSOA with other algorithms for makespan, cost, and resource utilization. The randomly produced dataset, comprising 500 tasks and 50 virtual machines, is utilized to evaluate the performance of the GWO-MSOA. Findings: The hybrid GWO-MSOA experimental findings show outstanding makespan, cost, and resource usage performance. The proposed method decreases makespan by 15.05% relative to GWO and by 21.11% relative to MSOA. Furthermore, costs are diminished by 3.46% and 5.86% in comparison to GWO and MSOA, respectively, while resource utilization escalates by 5.69% and 0.46% relative to these methodologies. The results demonstrate that the hybrid GWO-MSOA significantly enhances task scheduling performance regarding makespan, cost efficiency, and resource consumption, establishing it as a viable strategy for cloud computing environments. Novelty: GWO is integrated with MSOA, which mitigates entrapment in local minima and early convergence, hence enhancing task scheduling performance. The methodology employs an elite archive that preserves the top-k solutions of the algorithm. Keywords: Meta-heuristic, Gray wolf optimization, Sunflower optimization, Task scheduling, Cloud