EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reinforcement Learning for Energy-Efficient UAV-LoRa Networks Under Vegetation Propagation Constraints

Caio Mateus Machado Cardoso, Walid Saad, Fabricio J. B. Barros, Jasmine Priscyla Leite De Araújo

IEEE Open Journal of the Communications Society · 2026 · 7 · 5107-5117

DOI: 10.1109/ojcoms.2026.3691619 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Open Journal of the Communications Society, 2026. Verfasst von Caio Mateus Machado Cardoso und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), Brazil, under Finance Code 001, Article Processing Fee through CAPES.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reinforcement learning for uncrewed aerial vehicle (UAV)-assisted long range (LoRa) networks currently relies on model-free approaches utilizing generic propagation models. However, these studies leave model-based methods unexplored and frequently omit vegetation effects, which are essential for accurate forest deployments. This work compares the proximal policy optimization (PPO) (model-free) and DreamerV3 (model-based) algorithms for optimizing UAV-LoRa networks with vegetation-aware propagation. This study formulates the network optimization as a centralized control problem that integrates empirically-validated attenuation coefficients from Amazonian forest measurements, dynamic UAV positioning, and realistic payload constraints. Simulation results reveal fundamental tradeoffs: DreamerV3 achieves approximately $1.6\times $ sample efficiency (150k vs 250k steps), reducing costly UAV testing, while PPO delivers $4\times $ energy efficiency ( ${4}\cdot {10}^{{7}}$ vs ${1}\cdot {10}^{{7}}$ bits/Joule), and exhibits lower variance. DreamerV3’s higher coverage advantage comes at substantial energy cost. The results demonstrate the importance of vegetation-aware systems and provide deployment guidance for UAV-assisted networks in dense forest environments.

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), Brazil, under Finance Code 001
  • Article Processing Fee through CAPES

Zitieren

APA

Cardoso, C. M. M., Saad, W., Barros, F. J. B., & Araújo, J. P. L. D. (2026). Reinforcement Learning for Energy-Efficient UAV-LoRa Networks Under Vegetation Propagation Constraints. IEEE Open Journal of the Communications Society, 7, 5107-5117. https://doi.org/10.1109/ojcoms.2026.3691619

Vancouver

Cardoso CMM, Saad W, Barros FJB, Araújo JPLD. Reinforcement Learning for Energy-Efficient UAV-LoRa Networks Under Vegetation Propagation Constraints. IEEE Open Journal of the Communications Society. 2026;7:5107-5117. doi:10.1109/ojcoms.2026.3691619

BibTeX
@article{Cardoso2026,
  author = {Cardoso, Caio Mateus Machado and Saad, Walid and Barros, Fabricio J. B. and Araújo, Jasmine Priscyla Leite De},
  title = {Reinforcement Learning for Energy-Efficient UAV-LoRa Networks Under Vegetation Propagation Constraints},
  journal = {IEEE Open Journal of the Communications Society},
  year = {2026},
  volume = {7},
  pages = {5107--5117},
  doi = {10.1109/ojcoms.2026.3691619}
}
Kostenlos starten →