Multi-target task scheduling method for power cloud data center

Abstract

The invention discloses a power cloud data center multi-target task scheduling method, and belongs to the technical field of power informatization. The invention aims to provide a power cloud data center multi-target task scheduling method for performing multi-target task scheduling on efficiency and energy consumption so as to uniformly coordinate the power cloud data center multi-target task scheduling. The method comprises the steps of establishing a model, selecting variables to be optimized and an optimization target, determining constraint conditions, setting initial variables, giving a range of the variables to be optimized, taking the variables to be optimized as population individuals in the optimization process, and updating corresponding data in task scheduling of the power cloud data center according to values of the variables to be optimized contained in the individuals in the population. Solving an optimization objective function value corresponding to each individual in the population; and performing rapid non-dominated sorting on population individuals. According to the multi-target task scheduling method for the power cloud data center, the relation among multiple targets such as efficiency and energy consumption of power cloud data task scheduling can be coordinated in a unified mode, and the method has the advantages of being scientific, high in applicability, good in effect and the like.

Description

technical field [0001] The invention belongs to the technical field of electric power informationization. Background technique [0002] A scientific and reasonable task scheduling method is an important measure to ensure energy saving and consumption reduction in data centers, and it is also an important means to promote safe and economical operation of power grid enterprises. As a new computing model, cloud computing can use virtualization technology to uniformly allocate heterogeneous hardware resources; when the data center receives user task data, it can assign tasks to virtualized hardware resources for processing and return corresponding result. However, when the tasks are in peak hours, the load of the data center will increase sharply, and the power consumption will also rise correspondingly, resulting in high heat dissipation pressure. Therefore, how to allocate and schedule tasks to hardware resources in an efficient and energy-saving manner is the key to the effi...

AI Technical Summary

Problems solved by technology

Task scheduling in the cloud environment often takes efficiency as the primary goal. At the same time, a large number of processing machine operations in the data center consume a lot of power, which is very unfavorable for the data center with a large number of hosts. It not only wastes energy and increases costs, but also causes heat dissipation problems in the data center.

However, most of the existing methods only focus on single-objective optimization of efficiency or energy consumption, and there are few research reports on multi-objective task scheduling for efficiency and energy consumption.

Images