Cloud computing scheduling method and system based on big data and deep learning neural networks

Abstract

The invention discloses a cloud computing scheduling method and a system based on big data and deep learning neural networks. The method includes the steps that a cloud task type T to be scheduled, amount M of type T cloud tasks to be scheduled and a scheduled cloud resource candidate type are acquired; all past scheduling records scheduled from all the cloud tasks of the type T to the cloud resources of the candidate type are searched out from past ability big database; according to all the past scheduling records searched out, when T type cloud tasks of the amount M is scheduled to the cloudresources of the candidate type, the deep learning neural network is used to predict the amount of the can-be-occupied cloud resources of the candidate type; and according to the predicted results, the cloud computing scheduling is accomplished. The cloud computing scheduling method and the system based on the past ability big data and the deep learning neural networks, by a objective fact of occupation situation of the cloud resources when the cloud tasks of different types in the past are scheduled to different cloud resources, the predicting is carried out, the predicted results are more accurate, and the scheduling efficiency is higher. The cloud computing scheduling method and the system based on big data and deep learning neural networks are widely applicable to the field of cloud computing.

Description

technical field [0001] The invention relates to the field of cloud computing, in particular to a cloud computing scheduling method and system based on big data and deep learning neural network. Background technique [0002] Currently, cloud computing technology is one of the hottest topics in the field of computer services. Large industry leaders, such as IBM and Google, small private companies, and even some technicians who are willing to pursue new technologies are deploying or researching cloud computing, hoping to consolidate or enhance their position in the industry through cloud computing. In the cloud computing environment, virtualization technology is used to virtualize the server as a whole into a data resource pool. Due to the variety and large scale of data resources, cloud computing data resource scheduling has become one of the hot spots in cloud computing research. [0003] When performing cloud computing scheduling, the most important thing is to predict how ...

AI Technical Summary

Problems solved by technology

This estimation method in the prior art generally makes a rough estimate of the amount of cloud resources occupied based on the task type, but this rough estimate is not combined with the actual occupancy of cloud resources in the past, and is often inaccurate. As a result, the scheduling based on this may not be able to maximize the use of cloud resources, and the scheduling efficiency is not high

Images