Machine learning-based elastic resource expansion method and system

Abstract

The invention discloses a machine learning-based elastic resource expansion method and system, and belongs to the technical field of cloud computing and the field of deep learning, and the method comprises the steps: calculating the minimum total resource amount required for completing a task by utilizing a regression model under the condition that the operation cut-off time limit td and the taskcalculation amount of the to-be-operated task are known; continuously collecting the current running state and the resource utilization rate of the task in the running process of the task, and inputting the minimum total resource amount, the current running state of the task, the resource utilization rate and the task calculation amount into a prediction model for prediction to obtain the task completion time Tc; if Tc is larger than td, calculating the minimum total resource amount enabling the final task completion time Tc 'to be smaller than td; and if the task is not completed, continuingcollection, and if the task is completed, stopping collection. According to the method, the minimum total resource amount is calculated through the regression model to ensure that the task can be completed on time, the completion time is predicted in the operation process, and when the completion time exceeds the operation cut-off time limit, elastic expansion of the calculation resources is automatically carried out.

Description

technical field [0001] The invention belongs to the field of cloud computing technology and the field of deep learning, and more specifically relates to a method and system for expanding elastic resources based on machine learning. Background technique [0002] The cloud computing business model is generally that the tenant first tells the cloud service provider the number of cloud computing resources that need to be applied, and then the cloud service provider will allocate these resources according to the tenant's request. In this mode, tenants need to estimate the total amount of resources needed according to their own business. However, because cloud tenants lack the understanding of the underlying implementation of cloud service provider services, it is difficult for them to estimate the amount of computing resources required in the virtual environment of the cloud platform based on their previous experience of running business locally. Therefore, the tenant proposes a...

AI Technical Summary

Problems solved by technology

[0006] In view of the above defects or improvement needs of the prior art, the present invention provides a method and system for expanding elastic resources based on machine learning, thereby solving the technical problems of difficult elastic resource management and low estimation accuracy in the prior art

Images