Research On Cloud Task Scheduling Based On Symbiotic Organisms Search

Cloud computing has emerged as an important innovation in information and communication technologies that is potentially changing the way computing resources consumed and provided.Because hundreds of thousands of virtual machines are used in cloud computing environment,it is difficult to manually assign tasks to computing resources in clouds.So we need an effective algorithm to solve the task scheduling problem.Cloud task scheduling affects the overall operating efficiency of the cloud platform,thus,how to effectively use resources in the cloud environment and make a large number of tasks to carry out a reasonable and efficient scheduling becomes more crucial.The research on cloud task scheduling problem was carried out,and the related work was listed as follows:(1)Aiming at the problem of meta task scheduling in cloud computing,a scheduling strategy based on Symbiotic Organisms Search was proposed by considering the task completion time and user satisfaction.Firstly,the task model and scheduling model of cloud computing were reconstructed by adding the expected completion time to the task.Secondly,on the basis of the completion time as the fitness function,the task priority was dynamically adjusted by user satisfaction,which was added to reduce the user's completion time and improve the user's satisfaction.Thirdly,aiming at the continuous search space,the improved Symbiotic Organisms Search algorithm was applied to the discrete large-scale task scheduling problem.(2)According to the workflow task scheduling in cloud computing environment,the paper proposed a workflow scheduling algorithm with multiple QoS constraints based on Symbiotic Organisms Search algorithm(QoS-SOS)by considering the task completion time and the user cost of the two constraint conditions.Firstly,a new QoS-SOS scheduling model was devised for workflow task scheduling,and the task processing unit of the model cloud be designed as an independent middleware module for the actual task scheduling scenarios.Secondly,assign appropriate priorities for each subtask in the workflow.Thirdly,the idea of dominating solution was added to the Symbiotic Organisms Search algorithm,so as to obtain the Pareto optimal solution set with uniform distribution to solve the task scheduling problem of multi-dimensional QoS constraints.(3)The above two aspects are simulated.Experimental results showed that: the CTS-SOS algorithm could not only reduce the user's task completion time effectively,but also improve the user satisfaction,which proved the effectiveness of the algorithm;the QoS-SOS not only showed it not only had a significant performance,greatly optimized the time and cost of workflow scheduling,but could also get different optimization schemes based on the users' preferences,which could be adapted for the large-scale cloud environment.