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

Cloud server performance degradation prediction method based on time sequence segmentation

A technology of time series and cloud servers, which is applied in neural learning methods, instruments, energy-saving computing, etc., can solve the problems of low prediction accuracy of cloud server performance decline and easy occurrence of overfitting, and overcome the problems of low prediction accuracy, The effect of avoiding overfitting and overcoming limitations

Pending Publication Date: 2022-05-24
XIAN UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Cloud server resources and performance data are characterized by nonlinearity, randomness, and suddenness. The prediction accuracy of the above-mentioned prediction method for cloud server performance decline is not high, and it is prone to overfitting

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 performance degradation prediction method based on time sequence segmentation
  • Cloud server performance degradation prediction method based on time sequence segmentation
  • Cloud server performance degradation prediction method based on time sequence segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0044] The present invention provides a time series segmentation based on the cloud server performance degradation prediction method, such as Figure 1 as shown, follow these steps:

[0045] Step 1, extract the performance resource time series data on the cloud server, including CPU idle rate data and system available memory data, such as time series data Figure 2 and Figure 3 as shown.

[0046] Wherein the segmentation process in step 2 is as follows: first of all, the preprocessing of the time series data; the time series data points of length T are connected in two, divided into T / 2 initial segments that do not coincide, and the similarity DTW value of the merged adjacent segments is calculated; then the smallest DTW value is selected cyclically, if the minimum value is less than the set segment threshold δ, the corresponding two segments are merged...

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 performance degradation prediction method based on time sequence segmentation. The method comprises the following steps: firstly, extracting performance resource time sequence data on a cloud server; decomposing the obtained time sequence data by adopting a DTW-BU time sequence segmentation algorithm; respectively constructing an LSTM model for the segmented subsequences, and predicting cloud server resource time sequence data; verifying the model precision by using a root-mean-square error and an average absolute percentage error; according to the time sequence prediction data of the LSTM model, predicting the performance degradation trend of the system, checking the fitting degree of the data, and judging the time node of software regeneration according to a prediction data threshold value; according to the method, the precision of the performance degradation prediction result of the cloud server can be improved, the overfitting phenomenon in the prediction process is avoided, and the problem of how to perform software regeneration at the optimal time point aiming at the performance degradation phenomenon of the cloud server is solved.

Description

Technical field [0001] The present invention belongs to the field of time series forecasting technology, specifically relates to a cloud server performance degradation prediction method based on time series segmentation. Background [0002] With the development of cloud computing technology, the use of cloud servers is becoming more and more common. Cloud servers are characterized by long-term operation, high complexity, and frequent exchange of resources, which increase the risk of resource exhaustion and software system abnormalities and failures. With the accumulation of resource consumption, the performance of the cloud server system will slowly decrease, the failure rate will increase, and even the system will crash. The main causes of system performance decline include the consumption of operating system resources, data corruption, and the accumulation of errors. In important systems, such as military defense, telecommunications systems, financial systems, securities system...

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): G06F11/00G06F11/07G06N3/04G06N3/08
CPCG06F11/008G06F11/079G06N3/08G06N3/044Y02D10/00
Inventor 孟海宁杨哲童新宇朱磊张嘉薇冯锴
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

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