Energy-saving scheduling method for improving reliability of multiple workflows

Abstract

The invention provides an energy-saving scheduling method for improving reliability of multiple workflows. According to the energy-saving scheduling method for improving the reliability of the multiple workflows, the reliability of the workflows submitted by the multiple users is improved and the energy consumption of a data center is reduced by using a virtual machine frequency modulation technology through two phases of workflow pre-scheduling and task re-scheduling on the basis of the reliability and deadline requirements of the users. According to the multi-workflow energy-saving scheduling algorithm based on the two phases of pre-scheduling and re-scheduling, workflow task sorting and workflow reliability constraint decomposition are optimized in the workflow pre-scheduling phase; and, in a task rescheduling phase, a task reliability target value is obtained according to a pre-scheduling phase, the virtual machine frequency modulation technology is used, the virtual machine meeting the reliability target value and having the minimum energy consumption is reselected for the task, and the mapping relation between the optimized task and the virtual machine is obtained, so that the reliability of multiple workflows is improved, and meanwhile, the operation energy consumption of a data center is reduced.

Description

technical field [0001] The invention relates to the technical field of cloud computing, in particular to an energy-saving scheduling method for improving the reliability of multiple workflows. Background technique [0002] As a new computing model, cloud computing has attracted widespread attention because it can provide distributed computing, storage application services and charge on demand. As more and more enterprises and users submit their own application requests to the cloud, the number of cloud computing scientific workflows that need to be processed by the data center and the power consumption also increase sharply, and they are faced with the problem of simultaneous submission of multiple cloud workflows . Generally, different users have different time and reliability requirements. Virtual machines may fail at any time during actual operation. It is difficult to guarantee the reliability of task execution on virtual machines, which in turn reduces the reliability ...

AI Technical Summary

Problems solved by technology

[0003] It can be seen that in the traditional scheduling method, the energy consumption of the data center operation is large, the reliability constraints proposed by the user are not considered, and only the time factor is considered in the task sequencing. The reliability of the workflow is reduced, so improving the reliability of multiple workflows and the success rate of application scheduling, and at the same time adopting lower energy consumption for data center operation is a major challenge for the data center

Images