Adaptive Mayfly Optimization Based Multi-objective Task Scheduling on Cloud Environment

Scheduling applications poses a significant challenge in cloud computing, attributed to the dynamic mapping of tasks by the scheduler between upcoming workloads and cloud resources. The demand for an effective scheduling algorithm arises to efficiently manage diverse workloads, enhancing performance metrics by minimizing makespan, reducing energy consumption, and maximizing resource utilization. Therefore in this paper, efficient multi-objective task scheduling technique is proposed. To achieve this objective adaptive mayfly optimization (AMO) algorithm is developed. The proposed multi-objective function is designed based on three parameters namely, energy consumption, makespan and resource utilization. The task scheduling problem is solved based on solution encoding, fitness and updation function. The efficiency of the presented technique is discussed on the basis of different measurements and performance compared to other approaches.