A multi-dimensional resource scheduling method for cloud environment data center

Abstract

The invention provides a multidimensional resource scheduling system and method for a cloud environment data center, belonging to the field of cloud computing. The system provided by the invention comprises a user application request submitting module, a resource status acquiring module, a resource scheduling module, an application request priority queuing module and a virtualized physical resource pool. The method provided by the invention comprises the following steps of: firstly detecting the status information of multidimensional resources in the virtualized physical resource pool and a current application request set in the user application request submitting module, which are acquired by the resource status acquiring module; then defining an application request priority queue which is suitable for the status balanced consumption of the current multidimensional resources in the virtualized physical resource pool by using a multiple-attribute-decision-making application priority scheduling algorithm; and finally submitting the application request which has the highest priority and meets resource constraints to the cloud environment data center for execution.

Description

Technical field [0001] The invention belongs to the field of cloud computing, and specifically relates to a cloud environment data center multi-dimensional resource scheduling system and method, which are used for efficient scheduling of pooled resources of a data center in a cloud computing multi-tenant environment. Background technique [0002] With the rapid development of the information industry and the widespread popularity of the Internet, IT infrastructure has played a vital role as an operating platform for the provision of information service capabilities. The contradiction between the rapidly rising demand for IT resources and a single expensive resource provision method has caused the traditional IT industry to face unprecedented severe challenges with high cost, low efficiency, and high energy consumption. The research report shows that more than 50% of the annual input cost of the data center is used for the power and cooling consumption of the infrastructure, while...

AI Technical Summary

Problems solved by technology

Figure 2-1 Although the memory is fully utilized, there are many remaining CPU resources and cannot be used at the same time due to the small amount of memory capacity. The hidden waste phenomenon is serious.

Images