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

Data Center Workload Prediction Method Based on Wavelet Neural Network and Linear Regression

A wavelet neural network and workload technology, applied in neural learning methods, biological neural network models, predictions, etc., can solve problems that are not suitable for high-performance data center workload prediction

Inactive Publication Date: 2021-04-13
HUNAN AGRICULTURAL UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, none of these theories and methods are suitable for high-performance data center workload prediction

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
  • Data Center Workload Prediction Method Based on Wavelet Neural Network and Linear Regression
  • Data Center Workload Prediction Method Based on Wavelet Neural Network and Linear Regression
  • Data Center Workload Prediction Method Based on Wavelet Neural Network and Linear Regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] This embodiment includes the following steps:

[0057] 1. Establish a data center historical workload information database

[0058] Through the high-performance data center system log files, historical jobs and the amount of resources used by each job can be retrieved, so that the data center workload can be calculated using the following formula.

[0059]

[0060] Where N is the number of jobs, Job i is the i-th job, R i is the number of resources used by the i-th job, and TR is the total amount of resources in the data center. Using the formula (1) to calculate the data center workload, and according to the corresponding job number and time recorded in the log file, the data center historical workload database table can be established, and its table structure is shown in Table 1.

[0061] Table 1 Data center historical workload table

[0062] ID Num Workload Time 1800192809 305 0.93 2017-3-26 12:34

[0063] figure 1 It is a historic...

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 short-term workload prediction method based on the fusion of linear regression and wavelet neural network, which includes: first step, establishing a historical workload database through data center system log files; For the relative stability of the workload at the same time, linear regression is used to predict the short-term workload; in the third step, due to the relative volatility and local stability of the workload in each period of the day in the data center, this patent uses error feedback propagation wavelet neural network technology to predict Workload; the fourth step is to integrate linear regression and wavelet neural network prediction technology to predict the short-term workload of the data center; the fifth step is to update the historical workload information database with the actual workload of the data center in the current period, and execute the second, third and fourth cycles step-by-step forecast workload. Compared with the prior art, the invention has the advantages of high precision and can provide strong technical support for data center resource management and energy consumption control.

Description

technical field [0001] The invention relates to the technical field of high-performance data center resource management, in particular to a data center workload prediction method based on wavelet neural network fusion linear regression. Background technique [0002] The data center is the product of the development and integration of computer, communication and Internet technologies. It is the basic support platform for various large-scale enterprise-level services, big data, and cloud computing, and has been highly valued by the industry and academia. International IT giants such as IBM, Google, Microsoft, Cisco, and Hewlett-Packard have launched their data center solutions one after another, and have deployed and owned a large number of data centers. Domestic information technology companies such as GDS, Tencent, China Telecom, and Alibaba have also proposed their own solutions, and all of them have large-scale centralized or distributed data centers. These data centers a...

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 Patents(China)
IPC IPC(8): G06F17/18G06N3/04G06N3/08G06Q10/04
CPCG06F17/18G06N3/08G06Q10/04G06N3/045
Inventor 唐小勇
Owner HUNAN AGRICULTURAL 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