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

DSE optimization method based on K-NN algorithm and device

A technology of K-NN algorithm and optimization method, which is applied in the field of DSE optimization method and device based on K-NN algorithm, can solve the problem that the percentage cannot be applied to the schedulability analysis link, etc., so as to maintain the prediction accuracy and high prediction accuracy. , the effect of reducing false positives

Pending Publication Date: 2020-07-31
STATE GRID CORP OF CHINA +3
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, in the schedulability analysis of the solution, the original traditional algorithm can be replaced by machine learning algorithm, which is used to optimize the traditional DSE algorithm and provide a faster analysis algorithm solution, but the error prediction percentage of machine learning technology will decrease. Cannot be used in schedulability analysis because it is out of acceptable range

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
  • DSE optimization method based on K-NN algorithm and device
  • DSE optimization method based on K-NN algorithm and device
  • DSE optimization method based on K-NN algorithm and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 As shown, the present invention proposes a kind of DSE optimization method based on K-NN algorithm, and this method comprises:

[0049] S1: Build a TSN network model including communication nodes, and configure scheduling priorities for traffic levels in the TSN network model;

[0050] S2: Based on the data in the training set, the K-NN algorithm that replaces the traditional algorithm in DSE to perform schedulability analysis is trained according to the configured scheduling priority, and the node ratio value that meets the requirements is obtained;

[0051] S3: compare the node proportion value with the preset threshold value, if the node proportion value is less than the preset threshold value, use the K-NN algorithm, if the node proportion value is greater than the preset threshold value, use the traditional algorithm in DSE, for the preset Adjust the size of the threshold;

[0052] S4: Repeat the content of S3 based on the adjusted preset thresho...

Embodiment 2

[0074] Such as Figure 4 As shown, the present invention proposes a DSE optimization device based on the K-NN algorithm, and the optimization device 5 includes:

[0075] Configuration unit 51: used to construct a TSN network model including communication nodes, and configure scheduling priorities for traffic levels in the TSN network model;

[0076] Algorithm training unit 52: based on the data in the training set, the K-NN algorithm that replaces the traditional algorithm in DSE to perform schedulability analysis is trained according to the configured scheduling priority to obtain a node ratio value that meets the requirements;

[0077] Decision-making unit 53: for comparing the node proportion value with a preset threshold, if the node proportion value is less than the preset threshold value, the K-NN algorithm is used, and if the node proportion value is greater than the preset threshold value, the traditional algorithm in DSE is used , to adjust the size of the preset thr...

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 DSE optimization method based on a K-NN algorithm and a device thereof. The method comprises the steps of performing scheduling priority configuration on a traffic level in aTSN network model; training a K-NN algorithm, which replaces a traditional algorithm to execute schedulability analysis, in the DSE according to the configured scheduling priority to obtain a node proportion value meeting requirements; and comparing the node proportion value with a preset threshold value, if the node proportion value is smaller than the preset threshold value, using the K-NN algorithm, and if the node proportion value is greater than the preset threshold value, using a traditional algorithm in DSE to adjust the size of the preset threshold value. The DSE optimization method isrealized by combining a K-NN algorithm. A K-NN algorithm in a machine learning algorithm is used to replace an original schedulability analysis algorithm in traditional DSE. When the K-NN algorithm is judged to be infeasible, a traditional algorithm is still used, the calculation speed of schedulability analysis is increased, meanwhile, the false alarm rate is reduced, and the DSE optimization method and device capable of keeping high prediction accuracy and reducing false alarms are provided.

Description

technical field [0001] The invention belongs to the technical field of power communication networks, and in particular relates to a DSE optimization method and device based on a K-NN algorithm. Background technique [0002] As the design and configuration of TSN networks become more and more complex, design space exploration (DSE) algorithms are usually required to optimize the selection and configuration of TSN protocols. The DSE algorithm generally consists of three steps of iterative execution: creating candidate solutions, configuring solutions and performing schedulability analysis, and simulating and evaluating the performance of the TSN network. Among them, in the schedulability analysis of the solution, the original traditional algorithm can be replaced by machine learning algorithm, which is used to optimize the traditional DSE algorithm and provide a faster analysis algorithm solution, but the error prediction percentage of machine learning technology will decrease...

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): H04L12/24H04L12/801H04L12/851H04L29/08G06K9/62G06N20/00
CPCH04L41/145H04L47/2433H04L47/29H04L67/12G06N20/00G06F18/24G06F18/24147G06F18/214
Inventor 章立宗李洋朱炳铨谢栋于佳李勇王兆旭金乃正盛海华潘武略沈健罗刚
Owner STATE GRID CORP OF CHINA
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