Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/141152
Title: Deep learing based MIMO system compare with precoding
Authors: Ye, Yuchen
Keywords: Engineering::Electrical and electronic engineering::Wireless communication systems
Issue Date: 2020
Publisher: Nanyang Technological University
Project: ISM-DISS-01843
Abstract: At the beginning of this century, the development of science and technology has made humans pursue higher data transmission rates and lower bit error rates in the field of communications. To address this issue, people invented Multiple Input Multiple Output (MIMO) system, which has higher channel capacity and low bit error rate. However, in MIMO system, people also have to face some problem such as waste of energy caused by energy radiation. Hence, people come up with precoding technology, which can pre-process signal at the transmitter when the channel status is determined. In recent years, deep learning has become a popular topic and it has achieved excellent results in many related fields. Researchers are increasingly willing to introduce deep learning in their field of research. In this report, a simulation which combines MIMO system and precoding technology is used to collect training data, and then deep learning is used to train a deep neural network (DNN) model to estimate the MIMO channel. The estimated channel is then used to test the data. The result shows that using deep learning to estimate MIMO channel can have a lower bit error rate (BER) than precoding technology, and when the signal-noise ratio (SNR) increase, the gap between deep learning and precoding technology becomes larger.
URI: https://hdl.handle.net/10356/141152
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
Dissertation_Ye Yuchen_G1902290H.pdf
  Restricted Access
1.97 MBAdobe PDFView/Open

Page view(s)

185
Updated on Jan 29, 2023

Download(s)

10
Updated on Jan 29, 2023

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.