A system and method for evaluating database performance load based on machine learning

An evaluation system and machine learning technology, applied in database design/maintenance, database distribution/replication, electronic digital data processing, etc., can solve problems such as high requirements for personnel circulation, time-consuming and high labor costs, etc., to achieve The analysis of characteristics is reasonable, the effect of reducing knowledge and ability requirements and reducing labor costs

Inactive Publication Date: 2019-02-15
INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER +2
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 1) The expert model is the accumulation of knowledge and experience of senior DBAs over the years, which has high requirements for the experience and proficiency of database operation and maintenance personnel, which virtually increases the labor cost
[0006] 2) In addition to rule definitions, the expert model also has complex scripts and codes, which require stable developers and operation and maintenance teams, and have high requirements for personnel circulation
If there are some small-probability abnormalities that are not involved in the indicators of the expert model, then an advanced DBA is required to find factors that affect performance and load from a large amount of historical data. This process is very time-consuming.

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
  • A system and method for evaluating database performance load based on machine learning
  • A system and method for evaluating database performance load based on machine learning
  • A system and method for evaluating database performance load based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Please combine figure 1 as shown,

[0064] The present invention provides a database performance load evaluation system based on machine learning, comprising:

[0065] The data acquisition module is used to capture characteristic data from the database awr report and the database log;

[0066] The data preprocessing module is used to delete single-value features, missing features, and high-correlation features in feature data, and to fill missing data and normalize data;

[0067] The training data model module is used to train the data generation model;

[0068] The model evaluation module is used to evaluate the model using the verification set according to the evaluation indicators of different machine learning models;

[0069] The model tuning module is used to automatically tune the model and adjust the hyperparameters of the model;

[0070] The model prediction module is used to predict the model, which is divided into offline prediction and online prediction; ...

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 system and method for evaluating database performance load based on machine learning, the method comprises the following steps: Using machine learning algorithm training datato generate performance load learning model, after data processing, these massive data as a training set and use machine learning technology to train, and finally generating performance and load learning model, using this model to predict the new generated feature data, and evaluating the performance and load of the database. On the one hand, the conclusion of the evaluation system is more reasonable than the analysis of the expert model, and it will not miss the important performance load index, and the problem location of database performance and load is more accurate; On the other hand, reducing the knowledge and ability requirements of database operators can greatly save human cost and provide work efficiency.

Description

technical field [0001] The invention is a machine learning-based database performance load evaluation system and method, which belongs to the field of artificial intelligence machine learning and relates to database operation and maintenance. Background technique [0002] Database applications require low response time and high performance, so performance load testing is performed before deploying database applications. However, with the continuous operation of database applications, there are more and more users, and the amount of data is increasing, which leads to an increase in the performance and load of the database. If it is not intervened and processed in time, it may lead to system downtime and other failures of varying degrees. . Therefore, real-time monitoring of data performance and load is now very important. [0003] At present, there are many performance load monitoring tools for databases, but these tools usually simply display some key operating indicators,...

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): G06F16/27G06F16/21G06F9/50
CPCG06F9/505
Inventor 张明明钱琳俞俊朱广新邵星星
Owner INFORMATION & COMM BRANCH OF STATE GRID JIANGSU ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap