Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity
Unmanned Aerial Vehicle (UAV) networks are an emerging technology, useful not only for the military, but also for public and civil purposes. Their versatility provides advantages in situations where an existing network cannot support all requirements of its users, either because of an exceptionally...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4618 |
| _version_ | 1797527837092085760 |
|---|---|
| author | Francisco Oliveira Miguel Luís Susana Sargento |
| author_facet | Francisco Oliveira Miguel Luís Susana Sargento |
| author_sort | Francisco Oliveira |
| collection | DOAJ |
| description | Unmanned Aerial Vehicle (UAV) networks are an emerging technology, useful not only for the military, but also for public and civil purposes. Their versatility provides advantages in situations where an existing network cannot support all requirements of its users, either because of an exceptionally big number of users, or because of the failure of one or more ground base stations. Networks of UAVs can reinforce these cellular networks where needed, redirecting the traffic to available ground stations. Using machine learning algorithms to predict overloaded traffic areas, we propose a UAV positioning algorithm responsible for determining suitable positions for the UAVs, with the objective of a more balanced redistribution of traffic, to avoid saturated base stations and decrease the number of users without a connection. The tests performed with real data of user connections through base stations show that, in less restrictive network conditions, the algorithm to dynamically place the UAVs performs significantly better than in more restrictive conditions, reducing significantly the number of users without a connection. We also conclude that the accuracy of the prediction is a very important factor, not only in the reduction of users without a connection, but also on the number of UAVs deployed. |
| first_indexed | 2024-03-10T09:49:28Z |
| format | Article |
| id | doaj.art-02378d433b8f4a34af5f68a98e8a933a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:49:28Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-02378d433b8f4a34af5f68a98e8a933a2023-11-22T02:52:13ZengMDPI AGSensors1424-82202021-07-012113461810.3390/s21134618Machine Learning for the Dynamic Positioning of UAVs for Extended ConnectivityFrancisco Oliveira0Miguel Luís1Susana Sargento2Department of Electronics, Telecommunications and Informatics (DETI), University of Aveiro, 3810-193 Aveiro, PortugalInstituto de Telecomunicações, 3810-193 Aveiro, PortugalDepartment of Electronics, Telecommunications and Informatics (DETI), University of Aveiro, 3810-193 Aveiro, PortugalUnmanned Aerial Vehicle (UAV) networks are an emerging technology, useful not only for the military, but also for public and civil purposes. Their versatility provides advantages in situations where an existing network cannot support all requirements of its users, either because of an exceptionally big number of users, or because of the failure of one or more ground base stations. Networks of UAVs can reinforce these cellular networks where needed, redirecting the traffic to available ground stations. Using machine learning algorithms to predict overloaded traffic areas, we propose a UAV positioning algorithm responsible for determining suitable positions for the UAVs, with the objective of a more balanced redistribution of traffic, to avoid saturated base stations and decrease the number of users without a connection. The tests performed with real data of user connections through base stations show that, in less restrictive network conditions, the algorithm to dynamically place the UAVs performs significantly better than in more restrictive conditions, reducing significantly the number of users without a connection. We also conclude that the accuracy of the prediction is a very important factor, not only in the reduction of users without a connection, but also on the number of UAVs deployed.https://www.mdpi.com/1424-8220/21/13/4618unmanned aerial vehicleUAV positioningmachine learningwireless communications |
| spellingShingle | Francisco Oliveira Miguel Luís Susana Sargento Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity Sensors unmanned aerial vehicle UAV positioning machine learning wireless communications |
| title | Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity |
| title_full | Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity |
| title_fullStr | Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity |
| title_full_unstemmed | Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity |
| title_short | Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity |
| title_sort | machine learning for the dynamic positioning of uavs for extended connectivity |
| topic | unmanned aerial vehicle UAV positioning machine learning wireless communications |
| url | https://www.mdpi.com/1424-8220/21/13/4618 |
| work_keys_str_mv | AT franciscooliveira machinelearningforthedynamicpositioningofuavsforextendedconnectivity AT miguelluis machinelearningforthedynamicpositioningofuavsforextendedconnectivity AT susanasargento machinelearningforthedynamicpositioningofuavsforextendedconnectivity |