Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for predicting storage equipment performance based on naive Bayesian machine learning model

A machine learning model and storage device technology, applied in machine learning, computing models, instruments, etc., can solve problems such as unguaranteed, time-consuming and labor-intensive conclusion errors, and achieve the effects of reducing workload, convenient operation, and highlighting substantive features

Pending Publication Date: 2020-06-30
INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For the IOPS performance of the above-mentioned existing storage devices in the prior art, it is usually necessary to repeatedly combine various condition parameters for debugging, and combine certain experience to determine the result, which is time-consuming and labor-intensive, and the conclusion error cannot be guaranteed. The present invention provides a simple Bayesian machine learning model predicts storage device performance method system to solve the above technical problems

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
  • Method and system for predicting storage equipment performance based on naive Bayesian machine learning model
  • Method and system for predicting storage equipment performance based on naive Bayesian machine learning model
  • Method and system for predicting storage equipment performance based on naive Bayesian machine learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Such as figure 1 As shown, the present invention provides a method for predicting storage device performance based on a naive Bayesian machine learning model, comprising the following steps:

[0066] S1. Create a storage device test environment, set the storage device in different configurations, and collect IOPS performance values ​​corresponding to different configurations to generate a test data set;

[0067] S2. Construct the data sample feature space vector of configuration information and IOPS performance value, build a naive Bayesian algorithm model according to the data sample feature space vector, and set the data sample input and output interface;

[0068] S3. Automatically train and test the Naive Bayesian algorithm model repeatedly through the test data set until the accuracy of the Naive Bayesian algorithm model reaches expectations, and generate a Naive Bayesian machine learning model;

[0069] S4. Input the configuration of the storage device, and predic...

Embodiment 2

[0071] Such as figure 2 As shown, the present invention provides a method for predicting storage device performance based on a naive Bayesian machine learning model, comprising the following steps:

[0072] S1. Create a storage device test environment, set the storage device in different configurations, and collect the IOPS performance values ​​corresponding to different configurations to generate a test data set; the specific steps are as follows:

[0073] S11. Create a storage device test environment;

[0074] S12. Set the storage device to be in different configurations, and collect the corresponding IOPS performance values ​​of different configurations, set the corresponding IOPS performance levels of different IOPS performance values, and generate a test data set; the configuration of the storage device includes RAID level parameters, RAID disk quantity parameters, Stored output link quantity parameters, each RAID creates LUN quantity parameters and concurrent number pa...

Embodiment 3

[0092] The IOPS performance of the storage device is the performance level of the storage device. The data index is I / Opersecond, which is the maximum number of I / Os per second.

[0093] The present invention provides a method for predicting storage device performance based on a naive Bayesian machine learning model, comprising the following steps:

[0094] S11. Create a storage device test environment;

[0095] S12. Set the storage device to be in different configurations, and collect the corresponding IOPS performance values ​​of different configurations, set the corresponding IOPS performance levels of different IOPS performance values, and generate a test data set; the configuration of the storage device includes RAID level parameters, RAID disk quantity parameters, Stored output link quantity parameters, each RAID creates LUN quantity parameters and concurrent number parameters for testing performance; the IOPS performance level includes poor performance level, qualified ...

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 provides a method and system for predicting storage equipment performance based on a naive Bayesian machine learning model, and the method comprises the following steps: S1, building a storage equipment testing environment, setting the storage equipment to be in different configurations, collecting IOPS performance values corresponding to the different configurations, and generatinga testing data set; S2, constructing a data sample feature space vector of the configuration information and the IOPS performance value, building a naive Bayesian algorithm model according to the datasample feature space vector, and setting a data sample input and output interface; S3, repeatedly training and testing the naive Bayesian algorithm model through the test data set until the accuracyof the naive Bayesian algorithm model reaches expectation, and generating a naive Bayesian machine learning model; and S4, inputting configuration of the storage equipment, and predicting the IOPS performance corresponding to the input storage device model through the naive Bayesian machine learning model.

Description

technical field [0001] The invention belongs to the technical field of computer storage devices, and in particular relates to a method system for predicting storage device performance based on a naive Bayesian machine learning model. Background technique [0002] With the rapid development of scientific computing and various network applications, the amount of information generated by human beings is increasing, which makes the storage of data more and more people's attention, thus making the status of storage components in the entire computer system More and more important, storage has changed from a single disk and tape to a disk array, and then developed to the current popular storage network. The demand for large-scale data applications is constantly emerging, and massive data and its applications have become a new development direction. Data storage has had a huge impact on people's work and life, and the improvement of the performance of the storage devices used is als...

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): G06F11/34G06N20/00
CPCG06F11/3447G06N20/00
Inventor 李闯李玲侠
Owner INSPUR SUZHOU INTELLIGENT TECH CO LTD