Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks
The cooperative aerial and device-to-device (D2D) networks employing non-orthogonal multiple access (NOMA) are expected to play an essential role in next-generation wireless networks. Moreover, machine learning (ML) techniques, such as artificial neural networks (ANN), can significantly enhance netw...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/6/3014 |
_version_ | 1797609055412289536 |
---|---|
author | Lefteris Tsipi Michail Karavolos Petros S. Bithas Demosthenes Vouyioukas |
author_facet | Lefteris Tsipi Michail Karavolos Petros S. Bithas Demosthenes Vouyioukas |
author_sort | Lefteris Tsipi |
collection | DOAJ |
description | The cooperative aerial and device-to-device (D2D) networks employing non-orthogonal multiple access (NOMA) are expected to play an essential role in next-generation wireless networks. Moreover, machine learning (ML) techniques, such as artificial neural networks (ANN), can significantly enhance network performance and efficiency in fifth-generation (5G) wireless networks and beyond. This paper studies an ANN-based unmanned aerial vehicle (UAV) placement scheme to enhance an integrated UAV-D2D NOMA cooperative network.The proposed placement scheme selection (PSS) method for integrating the UAV into the cooperative network combines supervised and unsupervised ML techniques. Specifically, a supervised classification approach is employed utilizing a two-hidden layered ANN with 63 neurons evenly distributed among the layers. The output class of the ANN is utilized to determine the appropriate unsupervised learning method—either k-means or k-medoids—to be employed. This specific ANN layout has been observed to exhibit an accuracy of 94.12%, the highest accuracy among the ANN models evaluated, making it highly recommended for accurate PSS predictions in urban locations. Furthermore, the proposed cooperative scheme allows pairs of users to be simultaneously served through NOMA from the UAV, which acts as an aerial base station. At the same time, the D2D cooperative transmission for each NOMA pair is activated to improve the overall communication quality. Comparisons with conventional orthogonal multiple access (OMA) and alternative unsupervised machine-learning based-UAV-D2D NOMA cooperative networks show that significant sum rate and spectral efficiency gains can be harvested through the proposed method under varying D2D bandwidth allocations. |
first_indexed | 2024-03-11T05:56:10Z |
format | Article |
id | doaj.art-5535fb13da0f4e2abfcb8845c04ca449 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T05:56:10Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-5535fb13da0f4e2abfcb8845c04ca4492023-11-17T13:44:45ZengMDPI AGSensors1424-82202023-03-01236301410.3390/s23063014Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative NetworksLefteris Tsipi0Michail Karavolos1Petros S. Bithas2Demosthenes Vouyioukas3Department of Information and Communication Systems Engineering, School of Engineering, University of the Aegean, 83200 Samos, GreeceDepartment of Information and Communication Systems Engineering, School of Engineering, University of the Aegean, 83200 Samos, GreeceDepartment of Digital Industry Technologies, National and Kapodistrian University of Athens, Thesi Skliro, 34400 Evia, GreeceDepartment of Information and Communication Systems Engineering, School of Engineering, University of the Aegean, 83200 Samos, GreeceThe cooperative aerial and device-to-device (D2D) networks employing non-orthogonal multiple access (NOMA) are expected to play an essential role in next-generation wireless networks. Moreover, machine learning (ML) techniques, such as artificial neural networks (ANN), can significantly enhance network performance and efficiency in fifth-generation (5G) wireless networks and beyond. This paper studies an ANN-based unmanned aerial vehicle (UAV) placement scheme to enhance an integrated UAV-D2D NOMA cooperative network.The proposed placement scheme selection (PSS) method for integrating the UAV into the cooperative network combines supervised and unsupervised ML techniques. Specifically, a supervised classification approach is employed utilizing a two-hidden layered ANN with 63 neurons evenly distributed among the layers. The output class of the ANN is utilized to determine the appropriate unsupervised learning method—either k-means or k-medoids—to be employed. This specific ANN layout has been observed to exhibit an accuracy of 94.12%, the highest accuracy among the ANN models evaluated, making it highly recommended for accurate PSS predictions in urban locations. Furthermore, the proposed cooperative scheme allows pairs of users to be simultaneously served through NOMA from the UAV, which acts as an aerial base station. At the same time, the D2D cooperative transmission for each NOMA pair is activated to improve the overall communication quality. Comparisons with conventional orthogonal multiple access (OMA) and alternative unsupervised machine-learning based-UAV-D2D NOMA cooperative networks show that significant sum rate and spectral efficiency gains can be harvested through the proposed method under varying D2D bandwidth allocations.https://www.mdpi.com/1424-8220/23/6/3014machine learningUAV placementartificial neural network (ANN)deep neural network (DNN)NOMAcooperative communications |
spellingShingle | Lefteris Tsipi Michail Karavolos Petros S. Bithas Demosthenes Vouyioukas Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks Sensors machine learning UAV placement artificial neural network (ANN) deep neural network (DNN) NOMA cooperative communications |
title | Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks |
title_full | Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks |
title_fullStr | Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks |
title_full_unstemmed | Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks |
title_short | Machine Learning-Based Methods for Enhancement of UAV-NOMA and D2D Cooperative Networks |
title_sort | machine learning based methods for enhancement of uav noma and d2d cooperative networks |
topic | machine learning UAV placement artificial neural network (ANN) deep neural network (DNN) NOMA cooperative communications |
url | https://www.mdpi.com/1424-8220/23/6/3014 |
work_keys_str_mv | AT lefteristsipi machinelearningbasedmethodsforenhancementofuavnomaandd2dcooperativenetworks AT michailkaravolos machinelearningbasedmethodsforenhancementofuavnomaandd2dcooperativenetworks AT petrossbithas machinelearningbasedmethodsforenhancementofuavnomaandd2dcooperativenetworks AT demosthenesvouyioukas machinelearningbasedmethodsforenhancementofuavnomaandd2dcooperativenetworks |