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

Load predicting method of cloud data center

A technology of load forecasting and cloud data, applied in forecasting, data processing applications, neural learning methods, etc., can solve problems such as increased server load, uncertain cloud data centers, and unpredictable computers, and achieve the effect of improving the accuracy of forecasting

Inactive Publication Date: 2016-01-20
SHANGHAI JIAO TONG UNIV
View PDF1 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] But even deep learning cannot completely solve many problems in life, especially in cloud data centers where there are a lot of uncertain situations that are difficult to predict
For example, if a website wants to pre-sell concert tickets for a certain singer at 10:00 p.m., people will naturally think that the server load will suddenly increase when the ticket grabbing channel opens. However, computers cannot predict this, so man-machine Interaction forecasts may be more in line with future forecast models

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
  • Load predicting method of cloud data center
  • Load predicting method of cloud data center
  • Load predicting method of cloud data center

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0028] Taking the CPU prediction of the data center as an example, other performance indicators (such as Memory, Disk, network I / O, etc.) are similar. A load forecasting method for a cloud data center mainly includes a deep learning feature extraction, a multi-performance index fusion and manual intervention. Specific steps are as follows:

[0029] Step 1, collect data. Since the service content of data centers is different, it is necessary to collect corresponding historical data to predict the load of different data centers. The relevant technologies involved in data collection will not be described in detail here, and the collection objects include CPU (there may be multiple CPUs), Memory, Disk, network I / O, etc. The longer the monitoring time, the better, preferably not less than one month. The monitoring granularity can be based on actual needs. Here,...

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 load predicting method of a cloud data center. The method comprises steps of: acquiring historical data of the cloud data center and normalizing the historical data; computing correlation between CPU historical data and other performance indexes; extracting a time window; extracting features; fusing the features: splicing the acquired performance indexes and then inputting the spliced performance indexes into an own-coding neural network in order to further compress the spliced performance and finally obtain a common compression characteristic; performing manual intervention; performing supervised learning; and predicting a result. The method may discover a potential change signal so as to accurately grasp a change direction and get close to an actual demand. The method may increase prediction accuracy by 5 to 10 percent in practical application.

Description

technical field [0001] The invention relates to the field of data center performance monitoring and prediction, and mainly relates to related technologies in the fields of machine learning and deep learning. Specifically, it mainly proposes a method of making an accurate prediction of the load of the data center through the fusion of various performance characteristics in the cloud computing data center and adding manual intervention, which is more suitable for the increasingly complex situation. Complex and changeable cloud data center. Background technique [0002] Today's era is an era of big data. According to statistics, in 2013, the global Internet will generate 1 EB of data (that is, 1 billion GB) every day, and as time goes by, the growth rate of data will only become faster and faster. There is huge value in these data, and to use them, you must first store them. The traditional data center can no longer meet the corresponding requirements. Compared with the trad...

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): G06Q10/04G06N3/08
Inventor 乔梁付周望戚正伟
Owner SHANGHAI JIAO TONG 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