Cloud computing resource scheduling method based on game theory

A resource scheduling and cloud computing technology, applied in the field of data processing, can solve problems such as the lack of unified standards or management norms

Inactive Publication Date: 2017-09-22
CHONGQING INST OF ENG
View PDF2 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Current cloud providers, such as Mesos and Yarn resource management frameworks, and cloud open source products have their own cloud platform architecture products and cloud resource management solutions, but they have not formed a unified standard or management specification, and most of them use existing The cloud resource management control of cloud middleware is used to manage the resource requests of cloud resource users, but the main function of cloud middleware is to provide system managers or external users with an edited management layer for deployment and management of cloud basic platforms, while cloud resources Performance (resource utilization), quality (QoS or energy consumption) and other indicators optimization strategies and the trade-off relationship between indicators, there are still many problems to be solved, and further research is needed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Cloud computing resource scheduling method based on game theory
  • Cloud computing resource scheduling method based on game theory
  • Cloud computing resource scheduling method based on game theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example 2

[0111] Implementation Case 2: If Figure 8 shown. In the cloud resource model, other methods are the same, as a modification, from the perspective of the cloud provider, the available physical machines of the cloud data center in the cloud provider resource scheduling game model are game participants, specifically:

[0112] exist Figure 8 In the cloud provider resource scheduling game, cloud users do not need multi-dimensional resources, such as memory, hard disk, network bandwidth, etc. Take e-commerce applications as an example: the resources requested by users are mainly CPU and memory resources. For physical machines, the main determinant factor is memory, so memory is the bottleneck resource. The cloud provider simulates the resource scheduling problem as a binning problem between the virtual unit to be created and the physical machine, and defines each available physical machine resource as a box, and the virtual unit carrying such applications is the item packed in t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a cloud computing resource scheduling method based on game theory. The method is characterized by including the specific steps of step 1, receiving a user request, analyzing and judging whether available resources meet a demand, rejecting the request if the available resources do not meet the demand, and otherwise, entering the next step; step 2, issuing a receiving request confirmation message; step 3, establishing a cloud user resource scheduling game model with users as game participants or a cloud provider resource scheduling game model with available physical machines of a cloud data center as game participants, and forming an optimal resource allocation scheme; and step 4, completing a virtual unit creation process, and executing the task request of the user. According to the method, a theory method of the game theory is introduced, different optimization targets are customized for different cloud computing environments, the corresponding resource scheduling game models are established, the cloud user resource scheduling game model with the cloud users and cloud providers as the game participants is established, and problems of unfair resource allocation and an insufficient resource utilization ratio are solved by corresponding resource scheduling algorithms.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for scheduling cloud computing resources based on game theory. Background technique [0002] Because cloud computing is in a dynamic environment, and the group of cloud users is very large, the resource requirements of each user's application program are constantly changing, that is, the dynamic requirements of resources must meet their performance requirements . The continuous change of application resource requirements is at any time, without prior warning and unpredictable, making it impossible for suppliers to find rules and grasp them. From another perspective, cloud computing uses virtualization technology to shield the complexity of the underlying hardware, thereby improving the flexibility of the hardware. In a multi-user environment, there are different user applications running on the same physical host, and they share hardware, software, and storage ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F9/50
CPCG06F9/5038G06F9/5083
Inventor 万川梅曹天人钟璐
Owner CHONGQING INST OF ENG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products