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

Prediction method of network resource and environment coupling relationship

A technology of network resources and coupling relationship, applied in the field of prediction of the coupling relationship between network resources and the environment, can solve the problems of sudden changes in the environment and low accuracy of multi-dimensional nonlinear functions, and achieve the effects of increasing representation ability, improving utilization, and accurate learning

Active Publication Date: 2020-03-27
CHINA ELECTRONICS TECH GRP NO 7 RES INST
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to solve the current actual network communication process, due to problems such as equipment failure and environmental mutation, the environmental sensing equipment collects incomplete or inaccurate data, while the existing technology faces the situation of missing data, and directly deletes the missing data. The value method, or the missing value is filled with the previous row of data or the mean value. This conventional fitting method solves the problem of low accuracy of the prediction results of multidimensional nonlinear functions. A prediction method for the coupling relationship between network resources and the environment is proposed. It can quickly and accurately complete missing values ​​and improve prediction accuracy

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
  • Prediction method of network resource and environment coupling relationship
  • Prediction method of network resource and environment coupling relationship
  • Prediction method of network resource and environment coupling relationship

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] Such as figure 1 As shown, a prediction method for the coupling relationship between network resources and the environment, the prediction method includes the following steps:

[0071] S1: Obtain the original data through the environment sensing device, and use the missing value processing method based on multi-dimensional fuzzy mapping and the method of service expansion to preprocess the original data to obtain a preliminary parameter set;

[0072] Among them, such as figure 2 As shown, the missing value processing method based on multidimensional fuzzy mapping comprises the following steps:

[0073] S101: Select complete features other than fields to be filled as a mapping subset;

[0074] S102: Divide the training set and the test set according to the lack of fields to be filled, wherein the data with complete fields is used as a training set, and the data with missing fields is used as a test set;

[0075] S103: Train the model to learn the mapping relationship...

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 prediction method for a network resource and environment coupling relation. The method comprises the following steps: carrying out the preprocessing of an original incompleteparameter set through a missing value processing method and a service expansion method based on multi-dimensional fuzzy mapping, and obtaining a preliminary parameter set; performing feature construction on the preliminarily obtained parameter set through a feature construction method based on multi-dimensional environmental parameters to obtain data with stronger representation capability; S3, fusing forward sequence search, backward sequence search and a simulated annealing algorithm to perform dimension reduction on the features of the data obtained in the step S2, thereby reducing the variable space of each dimension and the complexity of multi-dimensional representation model training; a model training method based on a decision tree is adopted to carry out training learning prediction on data, and accurate description of network resources under complex environment constraints is realized. According to the method, the missing value can be quickly and accurately complemented, andthe purpose of improving the model efficiency can be achieved while the prediction precision is improved.

Description

technical field [0001] The present invention relates to the technical field of network communication, and more specifically, to a method for predicting the coupling relationship between network resources and the environment. Background technique [0002] In the actual network communication process, due to problems such as equipment failures and environmental mutations, environment sensing devices collect incomplete or inaccurate data, which in turn leads to abnormal representation results of network resource status. Whether the characterization of network resource status is accurate will have a great impact on the utilization of network resources. [0003] If the incomplete or inaccurate data collected by the environment sensing device is not filled, the data will be entered into the analysis model with a value of 0 by default. Whether it is in the training or testing phase, the input of 0 value will greatly affect the model's ability to Normal data response, resulting in i...

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): G01D21/02
CPCG01D21/02
Inventor 罗涛刘颖徐艳雷鹏张洁
Owner CHINA ELECTRONICS TECH GRP NO 7 RES INST
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