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

Software aging prediction method and device based on multi-model comparison

An aging prediction and software aging technology, applied in software testing/debugging, kernel methods, biological neural network models, etc., can solve problems affecting decision-making, reduce performance degradation or crash, alleviate software aging, and improve reliability Effect

Active Publication Date: 2020-11-03
WUHAN UNIV OF TECH
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects or improvement needs of the prior art, the present invention proposes a software aging prediction method and device based on multi-model comparison, which solves the problem that the prediction result of a single model may affect decision-making, and can be based on aging data characteristics and prediction The error automatically selects the appropriate model, avoiding the early or late execution of proactive maintenance measures, and reducing the impact on software reliability

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
  • Software aging prediction method and device based on multi-model comparison
  • Software aging prediction method and device based on multi-model comparison
  • Software aging prediction method and device based on multi-model comparison

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] A software aging prediction method based on multi-model comparison of the present invention includes three parts: a data collection process, a prediction process and a verification process;

[0042] The data collection process collects aging index data from the target system to form a data set with a time index;

[0043] The prediction process includes a series of machine learning and neural network models, and candidate models are selected according to the data characteristics and prediction error results of the data in the data set;

[0044] The validation process uses non-parametric testing methods to test the candidate model and other models to determine the final aging prediction model.

[0045] Such as figure 1Shown is a schematic flowchart of a software aging prediction method based on multi-model comparison provided by an embodiment of the present invention, including the following steps:

[0046] S1: Collect the original data of aging indicators of the target...

Embodiment 2

[0081] Such as Figure 7 Shown is a schematic structural diagram of a device provided by an embodiment of the present invention, including: a data acquisition module 701, a prediction module 702, and a verification module 703;

[0082] The data acquisition module 701 is used to collect the original data of the aging index from the target software system, and process the original data of the aging index into time series data to form a data set;

[0083] The prediction module 702 is used to design several aging prediction models for the scale of aging data, use the data set as the input of each aging prediction model, and calculate the prediction error of each aging prediction model, and select the smallest prediction error and the best fitting effect. A good aging prediction model is used as a candidate aging prediction model;

[0084] The verification module 703 is used to calculate whether there is a significant difference between the candidate aging prediction model and oth...

Embodiment 3

[0092] The present application also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read-Only Memory (PROM), Magnetic Storage, Magnetic Disk, Optical Disk, Server, App Store, etc., on which computer programs, program When executed by the processor, the software aging prediction method based on multi-model comparison in the method embodiment is realized.

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 software aging prediction method and device based on multi-model comparison, and belongs to the field of software aging, and the method comprises the steps: collecting agingindexes from a target software system, and processing the aging indexes into time sequence data as the pre-input of a model; for the aging data scale, designing an aging prediction model comprising machine learning and a neural network, calculating the prediction error of each model, and selecting the model with the minimum error as a candidate model; and calculating whether significant differences exist between the model and other models, and if the differences are obvious, selecting the model as a final aging prediction model. According to the method, the problem that the prediction result of a single model may influence decision making is solved, a user can automatically select a suitable model according to aging data features and prediction errors, active maintenance measures or earlyor late execution is avoided, and the influence on software reliability is reduced. More models can be expanded, and an optimal prediction model can be selected for different aging data scales to helpsystem operation and maintenance.

Description

technical field [0001] The invention belongs to the field of software aging, and more specifically relates to a software aging prediction method and device based on multi-model comparison. Background technique [0002] For various system software, such as Linux operating system, Apache server, middleware, J2EE application server, software system under the Internet of Things environment and various mobile devices, during the long-term running process, due to the accumulation of errors and the consumption of resources The resulting degradation in performance and eventually crashes is known as software aging. Software aging prediction is widely used as a proactive maintenance technique for software regeneration. This predictive approach can extrapolate and predict future states based on the current or past states of the system. Estimate next-state system resource usage by using techniques such as machine learning or time-series methods. This predictive mode estimates when sy...

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): G06F11/36G06N20/10G06N3/04
CPCG06F11/3668G06N20/10G06N3/044G06N3/045
Inventor 向剑文贾凯李滴萌赵冬冬
Owner WUHAN 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