Predicting Wireless MmWave Massive MIMO Channel Characteristics Using Machine Learning Algorithms

Lu Bai, Cheng-Xiang Wang, Jie Huang, Qian Xu, Yuqian Yang, George Goussetis, Jian Sun, Wensheng Zhang

Research output: Contribution to journalArticle

Abstract

This paper proposes a procedure of predicting channel characteristics based on a well-known machine learning (ML) algorithm and convolutional neural network (CNN), for three-dimensional (3D) millimetre wave (mmWave) massive multiple-input multiple-output (MIMO) indoor channels. The channel parameters, such as amplitude, delay, azimuth angle of departure (AAoD), elevation angle of departure (EAoD), azimuth angle of arrival (AAoA), and elevation angle of arrival (EAoA), are generated by a ray tracing software. After the data preprocessing, we can obtain the channel statistical characteristics (including expectations and spreads of the above-mentioned parameters) to train the CNN. The channel statistical characteristics of any subchannels in a specified indoor scenario can be predicted when the location information of the transmitter (Tx) antenna and receiver (Rx) antenna is input into the CNN trained by limited data. The predicted channel statistical characteristics can well fit the real channel statistical characteristics. The probability density functions (PDFs) of error square and root mean square errors (RMSEs) of channel statistical characteristics are also analyzed.

Original languageEnglish
Article number9783863
JournalWireless Communications and Mobile Computing
Volume2018
DOIs
Publication statusPublished - 23 Aug 2018

Fingerprint

Learning algorithms
Learning systems
Neural networks
Antennas
Ray tracing
Millimeter waves
Mean square error
Probability density function
Transmitters

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

@article{6ad448f2269d49ec8335a6c724935feb,
title = "Predicting Wireless MmWave Massive MIMO Channel Characteristics Using Machine Learning Algorithms",
abstract = "This paper proposes a procedure of predicting channel characteristics based on a well-known machine learning (ML) algorithm and convolutional neural network (CNN), for three-dimensional (3D) millimetre wave (mmWave) massive multiple-input multiple-output (MIMO) indoor channels. The channel parameters, such as amplitude, delay, azimuth angle of departure (AAoD), elevation angle of departure (EAoD), azimuth angle of arrival (AAoA), and elevation angle of arrival (EAoA), are generated by a ray tracing software. After the data preprocessing, we can obtain the channel statistical characteristics (including expectations and spreads of the above-mentioned parameters) to train the CNN. The channel statistical characteristics of any subchannels in a specified indoor scenario can be predicted when the location information of the transmitter (Tx) antenna and receiver (Rx) antenna is input into the CNN trained by limited data. The predicted channel statistical characteristics can well fit the real channel statistical characteristics. The probability density functions (PDFs) of error square and root mean square errors (RMSEs) of channel statistical characteristics are also analyzed.",
author = "Lu Bai and Cheng-Xiang Wang and Jie Huang and Qian Xu and Yuqian Yang and George Goussetis and Jian Sun and Wensheng Zhang",
year = "2018",
month = "8",
day = "23",
doi = "10.1155/2018/9783863",
language = "English",
volume = "2018",
journal = "Wireless Communications and Mobile Computing",
issn = "1530-8669",
publisher = "John Wiley and Sons Ltd",

}

Predicting Wireless MmWave Massive MIMO Channel Characteristics Using Machine Learning Algorithms. / Bai, Lu; Wang, Cheng-Xiang; Huang, Jie; Xu, Qian; Yang, Yuqian; Goussetis, George; Sun, Jian; Zhang, Wensheng.

In: Wireless Communications and Mobile Computing, Vol. 2018, 9783863, 23.08.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting Wireless MmWave Massive MIMO Channel Characteristics Using Machine Learning Algorithms

AU - Bai, Lu

AU - Wang, Cheng-Xiang

AU - Huang, Jie

AU - Xu, Qian

AU - Yang, Yuqian

AU - Goussetis, George

AU - Sun, Jian

AU - Zhang, Wensheng

PY - 2018/8/23

Y1 - 2018/8/23

N2 - This paper proposes a procedure of predicting channel characteristics based on a well-known machine learning (ML) algorithm and convolutional neural network (CNN), for three-dimensional (3D) millimetre wave (mmWave) massive multiple-input multiple-output (MIMO) indoor channels. The channel parameters, such as amplitude, delay, azimuth angle of departure (AAoD), elevation angle of departure (EAoD), azimuth angle of arrival (AAoA), and elevation angle of arrival (EAoA), are generated by a ray tracing software. After the data preprocessing, we can obtain the channel statistical characteristics (including expectations and spreads of the above-mentioned parameters) to train the CNN. The channel statistical characteristics of any subchannels in a specified indoor scenario can be predicted when the location information of the transmitter (Tx) antenna and receiver (Rx) antenna is input into the CNN trained by limited data. The predicted channel statistical characteristics can well fit the real channel statistical characteristics. The probability density functions (PDFs) of error square and root mean square errors (RMSEs) of channel statistical characteristics are also analyzed.

AB - This paper proposes a procedure of predicting channel characteristics based on a well-known machine learning (ML) algorithm and convolutional neural network (CNN), for three-dimensional (3D) millimetre wave (mmWave) massive multiple-input multiple-output (MIMO) indoor channels. The channel parameters, such as amplitude, delay, azimuth angle of departure (AAoD), elevation angle of departure (EAoD), azimuth angle of arrival (AAoA), and elevation angle of arrival (EAoA), are generated by a ray tracing software. After the data preprocessing, we can obtain the channel statistical characteristics (including expectations and spreads of the above-mentioned parameters) to train the CNN. The channel statistical characteristics of any subchannels in a specified indoor scenario can be predicted when the location information of the transmitter (Tx) antenna and receiver (Rx) antenna is input into the CNN trained by limited data. The predicted channel statistical characteristics can well fit the real channel statistical characteristics. The probability density functions (PDFs) of error square and root mean square errors (RMSEs) of channel statistical characteristics are also analyzed.

UR - http://www.scopus.com/inward/record.url?scp=85053137292&partnerID=8YFLogxK

U2 - 10.1155/2018/9783863

DO - 10.1155/2018/9783863

M3 - Article

VL - 2018

JO - Wireless Communications and Mobile Computing

JF - Wireless Communications and Mobile Computing

SN - 1530-8669

M1 - 9783863

ER -