Resource utilization rate prediction method and device

Abstract

The invention provides a resource utilization rate prediction method and device. The resource utilization rate prediction method comprises the steps: processing a historical time sequence according toan ARIMA model, and obtaining a fitting time sequence and a primary prediction value corresponding to the historical time sequence, wherein the ARIMA model is obtained by training according to the historical time sequence, and the historical time sequence comprises a plurality of historical resource utilization rates sorted according to a time sequence; obtaining a residual error sequence according to the historical time sequence and the fitting time sequence; processing the residual error sequence according to an SRU model to obtain a secondary prediction value corresponding to the residualerror sequence, wherein the SRU model is obtained by training according to the residual error sequence; and determining a target prediction value of the resource utilization rate according to the primary prediction value and the secondary prediction value. According to the technical scheme of the invention, the resource utilization rate prediction method can achieve the prediction of the resourceutilization rate based on the ARIMA-SRU model, and obtains an accurate target prediction value.

Description

technical field [0001] The present application relates to the field of communication technologies, and in particular, to a method and device for predicting resource utilization. Background technique [0002] In the cloud computing mode, resources such as software, hardware, and platforms can be provided on demand and provided to users in the form of services, and users can access the leased resources through the Internet. For example, resources such as memory, I / O devices, storage, and computing are integrated into a virtual resource pool to provide users with various resources of the virtual resource pool. Virtualization technology is an important part of cloud computing. By deploying virtual machines on physical servers, services and applications are deployed on virtual machines to achieve application isolation, server integration, and better resource reuse. [0003] The application of cloud computing and virtualization technology, while providing users with better servic...

AI Technical Summary

Problems solved by technology

For example, the number of servers deployed in the data center is increasing continuously, but the CPU (Central Processing Unit, central processing unit) resource utilization rate of the server is low, and the CPU resources cannot be used reasonably

[0004] In order to realize the on-demand allocation of computing resources and the rational deployment of virtual machines, it is necessary to provide accurate CPU resource prediction methods. However, there is no accurate CPU resource prediction method in traditional methods.

Images