國立虎尾科技大學 |

Energy Optimization on UAV Assisted Communications by Machine Learning.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Energy Optimization on UAV Assisted Communications by Machine Learning./
作者:	Ravi, Prakash.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	74 p.
附註:	Source: Masters Abstracts International, Volume: 84-02.
Contained By:	Masters Abstracts International84-02.
標題:	Electrical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29373754
ISBN:	9798837538407

Energy Optimization on UAV Assisted Communications by Machine Learning.
Ravi, Prakash.

Energy Optimization on UAV Assisted Communications by Machine Learning. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 74 p.

Source: Masters Abstracts International, Volume: 84-02.

Thesis (M.S.)--Miami University, 2022.

This item must not be sold to any third party vendors.

Unmanned Aerial Vehicles (UAVs) based Base Stations(BSs) are currently considered devices that help improve network performances in wireless communication networks. They have unique features such as flexible deployment and adaptive altitude to provide communication support for ground users. Although UAVs have the above advantages, deploying UAVs in real-time has some challenges. The biggest concern is energy limitations due to the limited size of batteries. In this thesis, solar-powered UAVs are considered to support ground user communications by providing a stable connection and overcoming energy limitations. Therefore, the transmission power of the communication unit in each UAV is adaptively adjusted to support ground users. Compared to the constant power consumption, the adaptive power allocation has increased the UAV flying time by 5%. Furthermore, to extend the UAV power allocation in more realistic scenarios, the vehicle density of the ground users is predicted using Long Short-Term Memory (LSTM) neural networks. With the predicted vehicle density, linear and nonlinear optimization functions are further devised to allocate the minimum number of UAVs to support ground communications. Finally, the simulation results demonstrate that the proposed nonlinear optimization approach can reduce the required number of UAVs by 20% compared to linear optimization.

ISBN: 9798837538407Subjects--Topical Terms:

596380
Electrical engineering.
Subjects--Index Terms:

Unmanned aerial vehicles

Energy Optimization on UAV Assisted Communications by Machine Learning.
LDR:02599nam a2200409 4500 001 1104663
005 20230619080114.5
006 m o d
007 cr#unu||||||||
008 230907s2022 ||||||||||||||||| ||eng d
020 $a 9798837538407
035 $a (MiAaPQ)AAI29373754
035 $a (MiAaPQ)OhioLINKmiami1657151095245759
035 $a AAI29373754
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ravi, Prakash. $3 1413603
245 1 0 $a Energy Optimization on UAV Assisted Communications by Machine Learning.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 74 p.
500 $a Source: Masters Abstracts International, Volume: 84-02.
500 $a Advisor: Wang, Miao.
502 $a Thesis (M.S.)--Miami University, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Unmanned Aerial Vehicles (UAVs) based Base Stations(BSs) are currently considered devices that help improve network performances in wireless communication networks. They have unique features such as flexible deployment and adaptive altitude to provide communication support for ground users. Although UAVs have the above advantages, deploying UAVs in real-time has some challenges. The biggest concern is energy limitations due to the limited size of batteries. In this thesis, solar-powered UAVs are considered to support ground user communications by providing a stable connection and overcoming energy limitations. Therefore, the transmission power of the communication unit in each UAV is adaptively adjusted to support ground users. Compared to the constant power consumption, the adaptive power allocation has increased the UAV flying time by 5%. Furthermore, to extend the UAV power allocation in more realistic scenarios, the vehicle density of the ground users is predicted using Long Short-Term Memory (LSTM) neural networks. With the predicted vehicle density, linear and nonlinear optimization functions are further devised to allocate the minimum number of UAVs to support ground communications. Finally, the simulation results demonstrate that the proposed nonlinear optimization approach can reduce the required number of UAVs by 20% compared to linear optimization.
590 $a School code: 0126.
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer science. $3 573171
650 4 $a Computer engineering. $3 569006
650 4 $a Engineering. $3 561152
650 4 $a Communication. $3 556422
653 $a Unmanned aerial vehicles
653 $a Base stations
653 $a Long short-term memory
690 $a 0984
690 $a 0459
690 $a 0464
690 $a 0544
690 $a 0537
710 2 $a Miami University. $b Computational Science and Engineering. $3 1413604
773 0 $t Masters Abstracts International $g 84-02.
790 $a 0126
791 $a M.S.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29373754