A Modified Multi-Verse Optimizer Based Workflow Scheduling in Cloud Computing Using Trust-Based Mechanism

The problem of task scheduling on Virtual Machines is selecting appropriate resources for a task so that its associated tasks have already been executed. Since the workflow contains a set of tasks, the likelihood of failure increases with the failure of a task throughout the workflow. The allocation of tasks on virtual machines with higher reliability improves workflow-scheduling efficiency.  Therefore, Trust relationship is an important factor of resource allocation and job scheduling, and in this paper, we have presented a good method to estimate the trust of virtual machines on which the workflow is run. In addition to the trust, which is an important factor in the workflow scheduling, there are other criteria for the satisfaction of service providers and customers. By increasing the number of requests and the diversity of virtual machines as well as the contradiction between objectives, finding the optimal Pareto front is more challenging. Therefore, multi-objective evolutionary algorithms face a large space of permutations to find an optimal tradeoff of objectives. In this paper, we present a multi-objective workflow-scheduling algorithm using Multi-Verse Optimizer algorithm with the aim of increasing diversity and convergence, so that the proposed method can consider Quality of Services requirements for service providers and customers simultaneously. In order to evaluate our proposed method, we have developed WorkflowSim tools. We have extended the original core of these tools to present our algorithm and then compared our proposed method with previous algorithms such as Pareto-Based Grey Wolf Optimizer, Parallel genetic and Strength Pareto Evolutionary Algorithm. The simulation results show that the proposed approach has a good improvement in service quality factors compared to previous methods.