Q-Learning Enabled Ant Colony (Q-ANT)-Based Navigation Optimization Framework for UAVs
IEEE Transactions on Consumer Electronics · 2025-05 · 71 (2) · 3903-3912
DOI: 10.1109/tce.2025.3570746 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-05. Verfasst von Xing Wei und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: Guangxi Natural Science Foundation, Guilin University of Aerospace Technology Special Research Project on the Strategic Development of Distinctive Interdisciplinary Fields.
Abstract (Originalsprache)
Flying ad-hoc networks (FANETs) composed of unmanned aerial vehicles (UAVs) which are serving in both military as well as civilian domains. The environmental changes and alterations in network topology present considerable challenges to communication among drone swarms. Consequently, there is an imperative need to investigate a high-performance routing scheme for UAV based FANETs. In this study, a routing scheme is introduced that employs the reinforcement Q-learning algorithm to enhance the ant colony optimization routing protocol (Q-ANT). The primary innovation of this scheme lies in the implementation of a neighborhood link selection mechanism that incorporates link residual time and link signal strength. This approach addresses the inadequacy of relying solely on a single indicator for assessing link residual survival time and expedites the convergence velocity of the ant colony routing algorithm. Q-ANT possesses the capability to optimize its routing strategy in accordance with the prevailing network environment by utilizing the Q-learning algorithm to attain the ideal option strategy in response to environmental fluctuations. The proposed scheme is implemented within the NS3 simulation environment and scenario-based simulation experiments have been conducted on three critical network metrics: network lifetime, end-to-end delay, and packet delivery rate. The experimental results exhibit the superiority of Q-ANT in terms of minimal energy consumption, minimal latency, and an enhanced packet delivery rate to the existing approaches such as FAnt-HocNet and Q-learning based QRF.
Förderung
- Guangxi Natural Science Foundation
- Guilin University of Aerospace Technology Special Research Project on the Strategic Development of Distinctive Interdisciplinary Fields
Zitieren
APA
Wei, X., Li, N., Yang, H., & Qu, B. (2025). Q-Learning Enabled Ant Colony (Q-ANT)-Based Navigation Optimization Framework for UAVs. IEEE Transactions on Consumer Electronics, 71(2), 3903-3912. https://doi.org/10.1109/tce.2025.3570746
Vancouver
Wei X, Li N, Yang H, Qu B. Q-Learning Enabled Ant Colony (Q-ANT)-Based Navigation Optimization Framework for UAVs. IEEE Transactions on Consumer Electronics. 2025;71(2):3903-3912. doi:10.1109/tce.2025.3570746
BibTeX
@article{Wei2025,
author = {Wei, Xing and Li, Ning and Yang, Hua and Qu, Bin},
title = {Q-Learning Enabled Ant Colony (Q-ANT)-Based Navigation Optimization Framework for UAVs},
journal = {IEEE Transactions on Consumer Electronics},
year = {2025},
volume = {71},
number = {2},
pages = {3903--3912},
doi = {10.1109/tce.2025.3570746}
}
EUVIMED