A DNN decoding method and a decoding communication device for an SCMA system

A decoding method and decoder technology, applied in the field of DNN decoding method and decoding communication equipment, can solve problems such as low decoding efficiency, failure to meet 5G system deployment requirements, and hardware implementation difficulties

Active Publication Date: 2019-05-21
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the maximum likelihood algorithm (Maximum Likelihood, ML) detection, the algorithm complexity of the MPA decoder is reduced, but the hardware implementation is still re...

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 DNN decoding method and a decoding communication device for an SCMA system
  • A DNN decoding method and a decoding communication device for an SCMA system
  • A DNN decoding method and a decoding communication device for an SCMA system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] The present embodiment provides a DNN decoding method of an SCMA system, which includes the following steps:

[0068] S1, build a SCMA system for generating SCMA signals, and obtain a training sample data set after correlating the source code word of the SCMA signal sending device with the SCMA signal data received by the SCMA signal receiving device;

[0069] Specifically, the step S1 includes the following steps:

[0070] S1.1. Use a software radio structure platform (such as GNU Radio, etc.) to build a SCMA system for generating SCMA signals, and use software radio equipment (including USRP B210) to build an SCMA transmitter and SCMA receiver, set relevant parameters, and record and store the source code word of the SCMA transmitter, and send the SCMA signal generated by the SCMA system to the physical environment through the SCMA transmitter;

[0071] The setting related parameters include: setting the UHD sink module parameters of USRP B210, such as setting the ce...

Embodiment 2

[0115] This embodiment also provides an SCMA decoding device for implementing the decoding method in Embodiment 1, such as figure 2 shown, which includes:

[0116] Signal transmitter 1, which is used to send the SCMA signal generated in the SCMA system to the physical environment;

[0117] Signal receiver 2, which is used to receive SCMA signals in the physical environment, and record and store SCMA signal data;

[0118] Training data generation module 3, it is used for correlating the source code word of signal transmitter 1 with SCMA signal data, records and stores correlation result data, and obtains the signal data set under different signal-to-noise ratio conditions according to correlation result data, thus Obtain a training data set, and load and store the training data set into a Numpy array;

[0119] Model generation module 4, it is used to set up the SCMA decoder model based on deep neural network; Concrete, as Figure 2a As shown, it includes: an input layer bui...

Embodiment 3

[0124] This embodiment provides a wireless communication device, which includes the decoding device described in Embodiment 3.

[0125] Traditional SCMA decoding methods mostly use the MPA (Message Pass Algorithm) algorithm, whose complexity is O(X df ), where d f is the user overload, and the decoder in the present invention is a DNN-based decoder with a complexity of (See the complexity comparison in Table 1), where N L is the number of hidden layers, N HN is the number of hidden layer nodes. It can be seen from the calculation process that the complexity of the SCMA decoder based on the traditional MPA algorithm will increase exponentially with the increase of the number of users, while the complexity of the DNN-based SCMA decoder will increase slowly.

[0126] Table 1 Complexity comparison

[0127]

[0128] For example, for a specific SCMA scenario where 6 users share 4 resource blocks, it is assumed that 1 multiplication operation is equivalent to 10 addition ope...

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 DNN decoding method of an SCMA system and decoding communication equipment. The DNN decoding method of the SCMA system comprises the steps of S1, building the SCMA system, and obtaining a training sample data set; S2, establishing an SCMA decoder model based on a deep neural network; S3, training the SCMA decoder model; And S4, deploying an SCMA decoder model, and decoding the SCMA signal through the SCMA decoder model. According to the method, the SCMA decoding accuracy can be improved on the premise that the complexity of the SCMA decoder is not increased, and compared with a traditional SCMA decoder based on an MPA algorithm, the SCMA decoder based on the DNN has the advantages that the calculation complexity and the decoding bit error rate are improved.

Description

technical field [0001] The invention relates to the field of wireless communication, in particular to a DNN decoding method and decoding communication equipment of an SCMA system. Background technique [0002] The traditional SCMA (Sparse Code Multiple Access, SCMA, Sparse Code Multiple Access) decoder uses the Message Passing Algorithm (MPA), combined with the prior probability, and uses the factor graph to iteratively update between the user node and the resource node The probabilistic message is used to analyze the codeword sent by the original multi-user as accurately as possible. Compared with the maximum likelihood algorithm (Maximum Likelihood, ML) detection, the algorithm complexity of the MPA decoder is reduced, but the hardware implementation is still relatively difficult, and its complexity increases exponentially with the number of users, resulting in low decoding efficiency , cannot meet the deployment requirements of future 5G systems. Contents of the invent...

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): H04L1/00G06N3/04
CPCG06N3/04H04L1/00
Inventor 林进挚赵希敏胡金星
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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