Hybrid DNN-Based Flight Power Estimation Framework for Unmanned Aerial Vehicles
Unmanned Aerial Vehicles (UAVs) have been widely used in logistics and communication, though they were initially used for military purposes. However, because the motor must always be rotated, the flight range of an UAV is limited, which, in turn, restricts the scope of UAV applications. Of course, i...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/2/104 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850081256987951104 |
|---|---|
| author | Minsu Kim Minji Kim Yukai Chen Jaemin Kim Donkyu Baek |
| author_facet | Minsu Kim Minji Kim Yukai Chen Jaemin Kim Donkyu Baek |
| author_sort | Minsu Kim |
| collection | DOAJ |
| description | Unmanned Aerial Vehicles (UAVs) have been widely used in logistics and communication, though they were initially used for military purposes. However, because the motor must always be rotated, the flight range of an UAV is limited, which, in turn, restricts the scope of UAV applications. Of course, if UAV power consumption is predicted using AI, it is possible to effectively plan UAV operations by deriving optimal energy-efficient flight paths during the simulation phase. However, when using deep neural networks (DNNs) to build a UAV power consumption model, it is difficult to make accurate inferences based solely on flight velocity data. For precise predictions, random vibration acceleration data, as a result of thrust and resistance, are also required. Unfortunately, such information cannot be obtained during the simulation phase and can only be acquired through the actual flight environment. In this paper, we propose the first hybrid DNN-based power model that combines a DNN-based power consumption model and a data-driven random vibration acceleration model that derives UAV random vibration acceleration information based on flight velocity and environment. The proposed modeling framework was evaluated with flight experiments, demonstrating a 6.12% root mean squared percentage error (RMSPE), which is 39.45% more accurate when compared with a conventional DNN-only power model. In addition, we performed case studies to show that it is possible to find energy-efficient flight paths. |
| format | Article |
| id | doaj-art-fd796bbb41bc4b73b9ae539e4b42e6b1 |
| institution | DOAJ |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-fd796bbb41bc4b73b9ae539e4b42e6b12025-08-20T02:44:46ZengMDPI AGDrones2504-446X2025-01-019210410.3390/drones9020104Hybrid DNN-Based Flight Power Estimation Framework for Unmanned Aerial VehiclesMinsu Kim0Minji Kim1Yukai Chen2Jaemin Kim3Donkyu Baek4School of Semiconductor Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaSamsung Electronics, Suwon 16677, Republic of KoreaIMEC, 3001 Leuven, BelgiumDepartment of Electronic Engineering, Myongji University, Yongin 17058, Republic of KoreaSchool of Semiconductor Engineering, Chungbuk National University, Cheongju 28644, Republic of KoreaUnmanned Aerial Vehicles (UAVs) have been widely used in logistics and communication, though they were initially used for military purposes. However, because the motor must always be rotated, the flight range of an UAV is limited, which, in turn, restricts the scope of UAV applications. Of course, if UAV power consumption is predicted using AI, it is possible to effectively plan UAV operations by deriving optimal energy-efficient flight paths during the simulation phase. However, when using deep neural networks (DNNs) to build a UAV power consumption model, it is difficult to make accurate inferences based solely on flight velocity data. For precise predictions, random vibration acceleration data, as a result of thrust and resistance, are also required. Unfortunately, such information cannot be obtained during the simulation phase and can only be acquired through the actual flight environment. In this paper, we propose the first hybrid DNN-based power model that combines a DNN-based power consumption model and a data-driven random vibration acceleration model that derives UAV random vibration acceleration information based on flight velocity and environment. The proposed modeling framework was evaluated with flight experiments, demonstrating a 6.12% root mean squared percentage error (RMSPE), which is 39.45% more accurate when compared with a conventional DNN-only power model. In addition, we performed case studies to show that it is possible to find energy-efficient flight paths.https://www.mdpi.com/2504-446X/9/2/104unmanned aerial vehiclesdeep neural networkpower consumptionempirical method |
| spellingShingle | Minsu Kim Minji Kim Yukai Chen Jaemin Kim Donkyu Baek Hybrid DNN-Based Flight Power Estimation Framework for Unmanned Aerial Vehicles Drones unmanned aerial vehicles deep neural network power consumption empirical method |
| title | Hybrid DNN-Based Flight Power Estimation Framework for Unmanned Aerial Vehicles |
| title_full | Hybrid DNN-Based Flight Power Estimation Framework for Unmanned Aerial Vehicles |
| title_fullStr | Hybrid DNN-Based Flight Power Estimation Framework for Unmanned Aerial Vehicles |
| title_full_unstemmed | Hybrid DNN-Based Flight Power Estimation Framework for Unmanned Aerial Vehicles |
| title_short | Hybrid DNN-Based Flight Power Estimation Framework for Unmanned Aerial Vehicles |
| title_sort | hybrid dnn based flight power estimation framework for unmanned aerial vehicles |
| topic | unmanned aerial vehicles deep neural network power consumption empirical method |
| url | https://www.mdpi.com/2504-446X/9/2/104 |
| work_keys_str_mv | AT minsukim hybriddnnbasedflightpowerestimationframeworkforunmannedaerialvehicles AT minjikim hybriddnnbasedflightpowerestimationframeworkforunmannedaerialvehicles AT yukaichen hybriddnnbasedflightpowerestimationframeworkforunmannedaerialvehicles AT jaeminkim hybriddnnbasedflightpowerestimationframeworkforunmannedaerialvehicles AT donkyubaek hybriddnnbasedflightpowerestimationframeworkforunmannedaerialvehicles |