Research On Heuristic Workflow Scheduling In Cloud Computing Environment

Modern science simulates and analyzes real-life activities in the form of workflow in the fields of biological information and earth science.The rapid development of cloud computing provides a better computing platform for deploying these workflows.How to effectively implement workflow scheduling in heterogeneous cloud environment has become a research hotspot in recent years.Since existing researches on cloud workflow scheduling tend to focus on single-objective optimization such as cost or time minimization,which cannot meet the diverse needs of users,cloud service providers need to conduct researches from the perspective of multi-objective,so as to provide better services and increase economic efficiency.This paper proposes three heuristic scheduling algorithms based on time,cost and security as the optimization objectives of task scheduling.The main research work is as follows:Firstly,in view of the problem of minimizing workflow execution time and meeting the task execution security requirements in the cloud environment,the strategy of overall deficiency is proposed.Based on the heterogeneous earliest completion time algorithm,a security aware heuristic workflow algorithm is proposed to ensure the security of task execution while minimizing the execution time of workflow.Secondly,based on the strategy of overall deficiency,an improved workflow scheduling algorithm based on the ready critical path is proposed to minimize the execution of workflow costs while satisfying the task execution security under deadline constraints.The algorithm decomposes the workflow into ready critical path using the improved upward rank.Combined with the first fit algorithm to reduce the idle time gap and improve the cost optimization effect,the virtual machine selection strategy of timely completion and minimum cost increase is adopted to form the alternative resource set.The algorithm allocates the ready critical path to the cheapest and safe virtual machine instance,compressing data communication overhead and reducing workflow execution costs.Finally,from the perspective of workflow layering,an improved workflow scheduling algorithm based on strict layering is proposed on the basis of the overall deficiency strategy.Virtual nodes are added and the cross-layer edge is decomposed into layers.At the same time,sub-task upgrade strategy is adopted to balance the execution time of hierarchical tasks.The deadline of workflow is decomposed to each layer,and the priority sequence of tasks is determined according to the upward rank.Find the best virtual machine instance for each task according to the layer deadline,to minimize the execution cost and ensure the security of task execution.Comparative analysis of similar algorithms on the Workflow Sim simulation platform,the experimental results show that: the security-aware scheduling algorithm is superior to existing algorithms in terms of task execution security under the premise of ensuring reasonable execution time.Two algorithms based on the ready critical path and strict layering have lower execution costs under the constraints of deadlines than existing algorithms,and can ensure the security of task execution.