Resource configuration prediction method and equipment

Abstract

The invention provides a resource configuration prediction method and equipment, applied to predicting resource configuration of a cloud service system. According to the method and equipment, the resource distribution efficiency is improved, and the cost of the cloud service system is reduced. The method provided by the embodiment of the invention comprises the steps of acquiring original data ofthe cloud service system, wherein the original data comprises running data of the cloud service system in a production or quasi-production environment; acquiring training data according to the original data; performing deep learning according to the training data to build a resource configuration prediction model; when resource requirement data input by a user is acquired, generating input data ofthe resource configuration prediction model according to the resource requirement data; and predicting according to the input data and the resource configuration prediction model, to acquire resourceconfiguration data of the cloud service system.

Description

technical field [0001] The present application relates to the field of cloud computing, and in particular to a method and device for predicting resource allocation. Background technique [0002] With the continuous maturity of cloud computing technology, more and more enterprises build cloud service systems to support their business and serve customers. In order to meet the ever-increasing demand, various services have emerged. The cloud service system needs to allocate appropriate resources to each service, such as a virtual machine (Virtual Machine, VM). However, due to the different scales of cloud service systems required by different enterprises, the types of cloud services and resource requirements are also different. Cloud service system providers set up resource configurations for cloud services mainly in two parts: first, before setting up a cloud service system for an enterprise, the provider must set up reasonable resource configurations for each service and com...

AI Technical Summary

Problems solved by technology

[0004] However, using the above traditional methods to set the resource configuration of cloud services has the following problems: the iteration cycle is long, and it is impossible to quickly formulate resource configurations for new cloud services; for large-scale cloud service systems, it is difficult to build a test environment; service, it is necessary to test the entire cloud service system, wasting a lot of time and human resources; there are differences between the test environment and the production environment, and resource configurations that are feasible in the test environment may not be feasible in the production environment; Physical resource scaling, can not be well predicted

The above problems will cause the cloud service system to fail to accurately allocate and plan resources during the deployment and maintenance process, resulting in uncontrollable costs of the cloud service system

Images