Traffic prediction method and device

A technology of traffic forecasting and traffic characteristics, applied in the Internet field, can solve the problem of inaccurate traffic forecasting

Active Publication Date: 2019-09-06
CHINA UNITED NETWORK COMM GRP CO LTD
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For this reason, the present invention provides a flow forecasting method and device to solve the problem of inaccurate flow forecasting caused by imperfect forecasting models in the prior art

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
  • Traffic prediction method and device
  • Traffic prediction method and device
  • Traffic prediction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0048] The traffic prediction method provided in this embodiment can be used in data exchange centers such as base stations and servers on the side of a network operator, and can also be used in clients on the user side. Traffic forecasting is based on the verification result of historical traffic data, predicting the traffic at the next moment (stage) in order to better serve users.

[0049] Such as figure 1 As shown, the traffic prediction method provided by this embodiment includes:

[0050] Step S101: Select a flow feature vector as the input of the flow prediction model; the flow feature vector is a flow feature vector N unit time before the predicted moment, where...

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 traffic prediction method and device. The method comprises the following steps: selecting a traffic feature vector as the input of a traffic prediction model, wherein the traffic feature vectors are traffic feature vectors of N unit time before a predicted moment, and N is an integer greater than or equal to 2; training the flow prediction model by utilizing a feedforwardnetwork and a feedbackward network of a recurrent neural network according to the flow feature vector so as to determine the number of the network parameters and the number of unit time before the predicted moment; and predicting the flow of the predicted object by taking the determined network parameters and the number of the unit time before the predicted moment as the network parameters and the input number of the flow prediction model. According to the method, the network structure and parameters are dynamically adjusted, and the accuracy and efficiency of the prediction model can be improved.

Description

Technical field [0001] The present invention relates to the field of Internet technology, in particular to a method and device for traffic prediction. Background technique [0002] The rapid speed of information technology makes the data traffic generated between the terminal and the base station and between the base station and the base station increase. In order to be able to allocate network resources reasonably, it is necessary to predict the data flow that needs to be transmitted in a period of time in the future based on the actual data flow information, so as to perform data transmission more effectively. [0003] The prediction model is the basis for the prediction of data flow. How to choose a suitable deep learning algorithm and design the corresponding input value has become the key to improving the accuracy and efficiency of base station flow prediction. However, the existing traffic forecasting method has the problem of low accuracy. Summary of the invention [0004] ...

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): H04W24/06H04L12/24G06N3/04G06N3/08
CPCH04W24/06H04L41/147H04L41/145G06N3/08G06N3/044G06N3/045
Inventor 刘馨靖
Owner CHINA UNITED NETWORK COMM GRP CO LTD
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