An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular Networks
Today’s terrestrial cellular communications networks face difficulties in serving coexisting users and devices due to the enormous demands of mass connectivity. Further, natural disasters and unexpected events lead to an unpredictable amount of data traffic, thus causing congestion to the network. I...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Telecom |
Subjects: | |
Online Access: | https://www.mdpi.com/2673-4001/3/1/5 |
_version_ | 1797441504989413376 |
---|---|
author | Lefteris Tsipi Michail Karavolos Demosthenes Vouyioukas |
author_facet | Lefteris Tsipi Michail Karavolos Demosthenes Vouyioukas |
author_sort | Lefteris Tsipi |
collection | DOAJ |
description | Today’s terrestrial cellular communications networks face difficulties in serving coexisting users and devices due to the enormous demands of mass connectivity. Further, natural disasters and unexpected events lead to an unpredictable amount of data traffic, thus causing congestion to the network. In such cases, the addition of on-demand network entities, such as fixed or aerial base stations, has been proposed as a viable solution for managing high data traffic and offloading the existing terrestrial infrastructure. This paper presents an unmanned aerial vehicles (UAVs) aided offloading strategy of the terrestrial network, utilizing an unsupervised machine learning method for the best placement of UAVs in sites with high data traffic. The proposed scheme forms clusters of users located in the affected area using the k-medoid algorithm. Followingly, based on the number of available UAVs, a cluster selection scheme is employed to select the available UAVs that will be deployed to achieve maximum offloading in the system. Comparisons with traditional offloading strategies integrating terrestrial picocells and other UAV-aided schemes show that significant offloading, throughput, spectral efficiency, and sum rate gains can be harvested through the proposed method under a varying number of UAVs. |
first_indexed | 2024-03-09T12:24:02Z |
format | Article |
id | doaj.art-b5c0abfdd9ab4e6c961fb01a0c9287d1 |
institution | Directory Open Access Journal |
issn | 2673-4001 |
language | English |
last_indexed | 2024-03-09T12:24:02Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Telecom |
spelling | doaj.art-b5c0abfdd9ab4e6c961fb01a0c9287d12023-11-30T22:37:30ZengMDPI AGTelecom2673-40012022-01-01318610210.3390/telecom3010005An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular NetworksLefteris Tsipi0Michail Karavolos1Demosthenes Vouyioukas2Department 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 Information and Communication Systems Engineering, School of Engineering, University of the Aegean, 83200 Samos, GreeceToday’s terrestrial cellular communications networks face difficulties in serving coexisting users and devices due to the enormous demands of mass connectivity. Further, natural disasters and unexpected events lead to an unpredictable amount of data traffic, thus causing congestion to the network. In such cases, the addition of on-demand network entities, such as fixed or aerial base stations, has been proposed as a viable solution for managing high data traffic and offloading the existing terrestrial infrastructure. This paper presents an unmanned aerial vehicles (UAVs) aided offloading strategy of the terrestrial network, utilizing an unsupervised machine learning method for the best placement of UAVs in sites with high data traffic. The proposed scheme forms clusters of users located in the affected area using the k-medoid algorithm. Followingly, based on the number of available UAVs, a cluster selection scheme is employed to select the available UAVs that will be deployed to achieve maximum offloading in the system. Comparisons with traditional offloading strategies integrating terrestrial picocells and other UAV-aided schemes show that significant offloading, throughput, spectral efficiency, and sum rate gains can be harvested through the proposed method under a varying number of UAVs.https://www.mdpi.com/2673-4001/3/1/55Gmachine learningUAV placementoffloading |
spellingShingle | Lefteris Tsipi Michail Karavolos Demosthenes Vouyioukas An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular Networks Telecom 5G machine learning UAV placement offloading |
title | An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular Networks |
title_full | An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular Networks |
title_fullStr | An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular Networks |
title_full_unstemmed | An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular Networks |
title_short | An Unsupervised Machine Learning Approach for UAV-Aided Offloading of 5G Cellular Networks |
title_sort | unsupervised machine learning approach for uav aided offloading of 5g cellular networks |
topic | 5G machine learning UAV placement offloading |
url | https://www.mdpi.com/2673-4001/3/1/5 |
work_keys_str_mv | AT lefteristsipi anunsupervisedmachinelearningapproachforuavaidedoffloadingof5gcellularnetworks AT michailkaravolos anunsupervisedmachinelearningapproachforuavaidedoffloadingof5gcellularnetworks AT demosthenesvouyioukas anunsupervisedmachinelearningapproachforuavaidedoffloadingof5gcellularnetworks AT lefteristsipi unsupervisedmachinelearningapproachforuavaidedoffloadingof5gcellularnetworks AT michailkaravolos unsupervisedmachinelearningapproachforuavaidedoffloadingof5gcellularnetworks AT demosthenesvouyioukas unsupervisedmachinelearningapproachforuavaidedoffloadingof5gcellularnetworks |