Unlock instant, AI-driven research and patent intelligence for your innovation.

A Neural Network Based Wireless Channel Modeling Method

A technology of neural network and modeling method, applied in radio transmission system, transmission monitoring, electrical components, etc., can solve the problems of insufficient description of physical environment and high complexity of channel model

Active Publication Date: 2020-12-29
SOUTHEAST UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It solves the problem of insufficient description of the physical environment by the traditional statistical channel model and the high complexity of determining the channel model and the need for accurate environmental information

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 Neural Network Based Wireless Channel Modeling Method
  • A Neural Network Based Wireless Channel Modeling Method
  • A Neural Network Based Wireless Channel Modeling Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further illustrated below in conjunction with specific embodiments, and it should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0047] The present invention proposes a channel modeling method based on deep learning, and uses a ULA (Uniform Linear Array) antenna array for both the BS and the MS, and provides an embodiment as an example where the carrier frequency is below 6 GHz. Such as image 3 shown, including the following steps:

[0048] Step 1: Collect channel environment: detect the number M of mobile terminals (MobileStation, MS) in the network through the base station, and record the shape, placement method, and number of antenna elements of the large-scale antenna array on the base station (BaseStation, BS) through geographic measurement. The number N, the shape of the antenna array on the MS, the pla...

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 wireless channel modeling method based on a neural network. The method comprises the following steps of firstly, processing a received signal fed back by a user in order to obtain estimated channel parameters; secondly, obtaining three-dimensional geographic information of a diffuser according to a two-dimensional image, and carrying out clustering on the three-dimensional geographic information; and lastly, taking the channel parameters and the geographic information as the inputs of the neural network and the received signal as the output, and training to obtain a nonlinear time-varying neural network model. According to the method, the more accurate channel model can be obtained in acceptable complexity, and the requirements for channel modelling in scenes suchas a large-scale MIMO technology, band spreading, high mobility and the like in a future 5G communication system are met.

Description

Technical field: [0001] The invention relates to a neural network-based wireless channel modeling method, which belongs to the technical field of channel modeling in mobile communication. Background technique: [0002] The 5G-oriented New Radio (NR) system access technology can support the three major application scenarios and requirements of 5G: enhanced mobile broadband (eMBB), massive machine-type-communications (mMTC) and Ultra reliable and low latency communications (URLLC), channel propagation characteristics and models are the prerequisites for the design, evaluation and deployment of the entire communication system, and the existing channel model cannot accurately describe the 5G channel, so it is necessary to Adopt a new channel modeling method. [0003] The Geometry Based Stochastic Model (GBSM) considers the statistical characteristics of delay, amplitude and angle in different scenarios. On this basis, the 3GPP organization established the SCM (Spatial Channel ...

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 Patents(China)
IPC IPC(8): H04B17/391H04B7/0413
CPCH04B7/0413H04B17/3912
Inventor 杨锦吴炳洋崔梦佳
Owner SOUTHEAST UNIV