Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Self-adaptive resource supply method based on application load

A supply method and self-adaptive technology, applied in the field of cloud computing resource management, can solve the problems of large sequence randomness, prediction error, and affecting the overall supply of resources, etc., to reduce the amount of calculation, ensure accuracy, and overcome the reduction of prediction accuracy Effect

Inactive Publication Date: 2014-02-12
FUDAN UNIV
View PDF4 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the current resource provisioning methods, some directly build forecasting models without considering the load mode, and some methods consider the application mode to model the forecast
For these resource supply methods, if the load pattern changes and the forecast model cannot detect and adjust it in time, it will lead to serious forecast errors, which will affect the overall supply of resources.
[0005] 2. High cost
For non-periodic applications, especially those with many spikes, because there is no obvious autocorrelation in the load sequence, the randomness between sequences is very large, and the prediction of this load is very challenging

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
  • Self-adaptive resource supply method based on application load
  • Self-adaptive resource supply method based on application load
  • Self-adaptive resource supply method based on application load

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] 1. Extraction of historical data

[0039] In a cloud environment, applications are encapsulated in virtual machines, and an application can be encapsulated in one or more virtual machines. In the present invention, the virtual machine is used as a unit to predict the load. Various load information about virtual machines is stored in the database. In the implementation, take some kind of load as an example, such as traffic. For each VM, every 10 minutes is used as a sample interval, and the average visit volume in each time interval is calculated as the visit volume of the interval to form a visit volume sequence {X(t)}. Similarly, the load can also be selected as the object of prediction, wherein the length of the sample interval can be selected according to the characteristics of the application.

[0040] 2. Select the module

[0041] When the system starts running, there is no historical data of VM in the database. At this time, a certain quota of resources is all...

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 belongs to the field of cloud computing resource management, relates to an application load predicating technology, and particularly relates to a self-adaptive resource supply method based on application load in cloud computing. According to the method, an application mode is analyzed and a corresponding predicating model is dynamically selected according to historical data of application load, and the application load in a future period is predicated. The method can timely modify an applied predicating model and relevant parameters according to the accuracy degree of application, so as to obtain higher accuracy degree and provide decision support for the subsequent resource distribution.

Description

technical field [0001] The invention belongs to the field of cloud computing resource management, and relates to an application load prediction technology, in particular to an adaptive resource supply method based on application load in cloud computing. According to the historical data of the application load, the present invention analyzes the load mode and dynamically selects the corresponding prediction model to predict the load situation of the application within a certain period of time in the future. Background technique [0002] As a new type of service model, cloud computing has received widespread public attention. In recent years, advances in virtualization software have enabled cloud computing to flexibly provide scalability, elasticity, and low-cost infrastructure. With these advantages, cloud computing is gradually becoming a common choice in modern IT solutions. Infrastructure-as-a-service providers use virtualization to encapsulate applications and provide i...

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
IPC IPC(8): G06F9/50
Inventor 吴杰张飞飞吕智慧
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com