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

Cloud server aging prediction method based on time series clustering and LSTM

A technology of time series and cloud server, applied in the direction of neural learning methods, instruments, character and pattern recognition, etc., can solve problems such as software aging, achieve accurate prediction, and overcome the effect of low prediction accuracy

Pending Publication Date: 2021-03-02
XIAN UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Solved the problem of how to regenerate software at the best time point in view of cloud server software aging phenomenon

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 server aging prediction method based on time series clustering and LSTM
  • Cloud server aging prediction method based on time series clustering and LSTM
  • Cloud server aging prediction method based on time series clustering and LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0036] Such as figure 1 As shown, the cloud server aging prediction method based on time series clustering and deep learning LSTM of the present invention specifically includes the following steps:

[0037] Step 1. Extract the time series data of performance resources on the cloud server, including CPU idle rate data and system available memory data. The specific time series data are as follows figure 2 and image 3 shown.

[0038]Step 2, preprocessing the data extracted in step 1. The cloud server resource time series is a non-stationary time series. In order to separate the high-frequency information from the low-frequency information and avoid over-fitting of the high-frequency information, the present invention performs three-level Wavelet packet decomposition processing. Wavelet packet decomposition can overcome the shortcomings of...

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 server aging prediction method based on time series clustering and deep learning LSTM. The method comprises the following steps of extracting performance resource timeseries data on a cloud server, wherein the performance resource time series data comprises CPU idle rate data and system available memory data; preprocessing and decomposing wavelet packets on the time series data; and carrying out K-means clustering on the preprocessed data, counting a clustering center with the highest occurrence frequency, constructing a deep learning LSTM model by utilizing aclustering result, and predicting a software aging trend according to a time sequence prediction value of the LSTM model. Wavelet packet decomposition is utilized to overcome the limitation that a traditional prediction method is relatively low in prediction accuracy of non-stationary time series data and time series data with relatively large fluctuation, so that the software aging trend can be predicted more accurately. The problem of how to regenerate the software at the optimal time point for the aging phenomenon of the cloud server software is solved.

Description

technical field [0001] The invention belongs to the technical field of time series prediction, and in particular relates to a cloud server aging prediction method based on time series clustering and deep learning LSTM. Background technique [0002] With the development of cloud computing technology, cloud servers are applied in more and more fields. Cloud server is a computing service that is simple, efficient, safe, reliable, and elastically scalable. Cloud servers have a completely different usage time than home hosting. The home host does not need to be used continuously, so the home host can have a relatively long sleep time. However, cloud servers are different. Different companies use cloud servers for different periods of time, which means that some servers do not have dormancy time at all, and need to run for a long time and exchange resources frequently. Cloud servers that run for a long time often have software aging problems. Software aging is caused by the ac...

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): G06F11/34G06K9/62G06N3/04G06N3/08
CPCG06F11/3476G06F11/3452G06F11/3447G06N3/08G06F2201/865G06N3/044G06N3/045G06F18/23213
Inventor 孟海宁冯锴朱磊童新宇李维黑新宏
Owner XIAN UNIV OF TECH
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