Bandwidth prediction method based on neural network

A prediction method and neural network technology, applied in the field of network communication, can solve problems such as long bandwidth measurement interval, bandwidth cannot reflect the bandwidth change trend, etc., to make up for the inaccuracy of predicted bandwidth, reduce errors, and adjust network strategies.

Active Publication Date: 2020-07-03
NANJING UNIV +1
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the technical defects that the existing bandwidth measurement interval is long and the measured bandwidth cannot reflect the future bandwidth change trend, the present invention provides a bandwidth prediction method based on neural network

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
  • Bandwidth prediction method based on neural network
  • Bandwidth prediction method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be described in further detail below in conjunction with examples. It must be pointed out that the following examples are only used to further illustrate the present invention and cannot be interpreted as limiting the protection scope of the present invention. The specific implementation of the invention with some non-essential improvements and adjustments should still belong to the protection scope of the present invention.

[0018] figure 1 A flow chart of the neural network-based bandwidth prediction method of the present invention is shown. The specific steps are as follows:

[0019] Step 1, establish a four-layer neural network model, the network structure is as follows figure 2 shown.

[0020] The first layer of network acts on the input data, uses the LSTM layer (Long-Short-Memory) to extract the features of the input time series, and stores some long-term and short-term features into the network. The length of the input time series...

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 bandwidth prediction method based on a neural network. The method comprises the steps that (1) a neural network model is established and trained, the input of the neural network model is the bandwidth change characteristic of a historical moment, and the output of the neural network model is the bandwidth prediction value of a future moment; (2) recording real-time bandwidth data of a user and sorting according to time; sampling the real-time bandwidth data according to a set sampling interval; (3) extracting time sequence characteristics of the bandwidth; (4) inputting the time sequence characteristics of the bandwidth into a trained neural network model, and calculating a bandwidth quantization factor at a future moment; and (5) converting the calculated bandwidth quantization factor into a predicted future moment bandwidth. According to the method for quantitatively reflecting the future network state change, the future bandwidth is predicted on the basis of bandwidth measurement, the defect that the bandwidth measurement consumes long time is overcome, and the internet application can be effectively guided to cope with the network change.

Description

technical field [0001] The invention relates to the technical field of network communication, in particular to a network condition prediction method, in particular to a neural network-based bandwidth prediction method. Background technique [0002] With the gradual popularization of the Internet and the continuous improvement of network communication technology, users' demand for high-quality networks is increasing. Many daily Internet applications depend on the stability of bandwidth. In order to improve the user's actual experience, it is necessary to know the user's real-time available bandwidth. For example, when a user watches a video, if the available bandwidth is less than the size of video frames per second, the video will freeze and the user experience will be degraded. Developers consider bandwidth fluctuations when developing live video software, and will add video bit rate and resolution adjustment strategies to reduce bandwidth requirements and achieve smooth v...

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): H04L12/24H04L12/26G06N3/08
CPCH04L41/147H04L41/145H04L43/0894G06N3/08
Inventor 张旭张欣宇薛雨马展
Owner NANJING UNIV
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