Font Size: a A A

The Research On Scheduling Cloud Computing Task Based On CloudSim

Posted on:2020-02-15Degree:MasterType:Thesis
Country:ChinaCandidate:B Z ZhangFull Text:PDF
GTID:2428330602966838Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
With the rapid development of Internet technology,the network environment around the world is getting better and better,and the situation of operating remote computing resources through the network is increasing,and it has gradually become the "cloud computing" technology we are familiar with.Cloud computing is an Internet-based computing method developed on the basis of technologies such as virtualization,distributed computing,and grid computing.Cloud computing service providers manage software and hardware resources together and provide these resources to computers and other devices as needed.Compared with the provision of private computing resources,the advantages of the cloud computing environment itself on-demand and low cost make it an advantage in the choice of small and medium enterprises.However,due to the different needs of different enterprises,differences in software and hardware equipment of cloud computing providers,and the lack of unified standards and rules in the industry,the task scheduling of workflows in the cloud computing environment has become more complicated.In the cloud computing environment,reasonable task scheduling can improve the service performance of the entire system,so that limited computing resources are fully applied.Especially in today's cloud computing environment,in order to save hardware costs,small and medium enterprises need to put their data and information in the cloud environment.For a small and medium enterprise,efficient cloud task scheduling can reduce the company's cloud computing resources.Costs spent.Therefore,task scheduling in the cloud computing environment can not only improve the quality of service(QoS),but also save unnecessary computing costs for enterprises,and at the same time lay a solid foundation for future related scheduling research.This article mainly researched from the following aspects:(1)A brief overview of the ant colony algorithm,and mathematical description of how to apply the ant colony algorithm to solve task scheduling problems,improve the functional representation of the voxel volatility coefficient,and draw a task scheduling flowchart and main steps based on the ant colony algorithm;(2)A brief overview of the genetic algorithm,a mathematical description of the genetic algorithm for the task scheduling problem in the cloud computing environment,and a flowchart and main steps of the cloud algorithm task scheduling based on the genetic algorithm;(3)A fusion algorithm based on genetic and ant colony algorithms is proposed.The advantage of genetic algorithm is that it has high search efficiency in the early stage of the algorithm,but the disadvantage is that it is easy to fall into the local optimal solution in the later stage of the algorithm.The disadvantage of the ant colony algorithm is that the initial search efficiency is low,and the advantage is that its positive feedback mechanism is easier to obtain the optimal solution.Therefore,in order to make use of the advantages of both algorithms at the same time,a scheduling algorithm combining genetic algorithm and ant colony algorithm is proposed.Draw a cloud computing task scheduling flowchart and main steps for phased execution;(4)The CloudSim cloud platform developed by the University of Melbourne is used for simulation experiments.The two fusion algorithms are compared with the polling algorithm,ant colony algorithm and genetic algorithm.The experimental results show that compared with the other four algorithms,the fusion algorithm that inherits first and then the ant colony is slightly better than the other four algorithms in execution time;in the total task completion time and virtual machine load balancing,the genetic algorithm The fusion algorithm is significantly better than the other four algorithms.The algorithm is also applied to cloud workflow scheduling,which proves the effectiveness of the algorithm.The algorithm can improve the task execution efficiency for small and medium-sized enterprises,avoid unnecessary overhead for enterprises to a certain extent,and improve resource utilization.
Keywords/Search Tags:Cloud computing, task scheduling, ant colony algorithm, genetic algorithm, fusion algorithm, resource utilization
PDF Full Text Request
Related items