Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach

Abstract

Ensuring operational safety in threat-prone environments remains a critical challenge for multi-UAV networks serving as aerial base stations. This paper proposes an efficient framework to maximize global energy efficiency (EE) while promoting safe operation through threat-aware clustering and reward-based safety enforcement. The proposed framework is executed in three steps. First, a threat-aware K-means (TAKM) algorithm determines the minimum required UAVs and computes safe initial placements. Second, an optimal matching stage assigns physical UAVs to these centroids to minimize energy expenditure. Third, a threat-aware multi-agent twin delayed deep deterministic policy gradient (MATD3) algorithm dynamically optimizes trajectories, power, and user associations. Simulation results show that the proposed framework achieves zero observed safety violations in the considered scenarios while achieving superior EE and faster convergence than other learning methods and non-clustering baselines. Compared to heuristic optimization, the proposed framework outperforms the greedy particle swarm optimization (GPSO) and achieves performance comparable to that of the optimized PSO (OPSO), while incurring significantly lower online deployment computational complexity. Furthermore, the proposed framework demonstrates effective generalization to unseen user distributions, large UAV fleets, and different threat geometries, while maintaining zero safety violations.

Mathematical Characterization of Dynamic Risk Spillovers in Carbon-Energy Financial Networks with Multi-Dimensional Uncertainty: A TVP-VAR-DY Connectedness Approach via Generalized Forecast-Error Variance Decomposition
Wenxin Zhang, Rufei Zhang, Qian Zhu
Mathematics18 Oct 2026Peer-reviewedCC BY 4.0General mathematicsCrossref
Nonparametric Efficient Estimation of Dynamic Treatment Regimes with Competing Risks
Nitya Shah, Laura D. Carbone, Howard A. Fink +2
arXiv28 Aug 2026PreprintCC BY 4.0Full textStatisticsarXiv
Communication-efficient ADMM over Hierarchical Networks
Binh Nguyen, Shuangqing Wei, Truong X. Nghiem
arXiv20 Sep 2026PreprintCC BY 4.0Full textOptimisation & controlarXiv
Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control
Edoardo Caldarelli, Franco Coltraro, Adrià Colomé +2
arXiv18 May 2026PreprintCC BY 4.0Full textDynamical systems Optimisation & controlarXiv
Efficient and Accurate Lift-and-Decoupling Generalized Transferable Neural Networks for Elliptic and Moving Interface Problems
Tao Cheng, Junqing Jia, Lili Ju +1
arXiv2 Oct 2026PreprintCC BY 4.0Full textNumerical analysis & scientific computingarXiv

Cite

BibTeX RIS

BibTeX

@misc{alkamali2026threataware,
  title = {{Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach}},
  author = {Faisal Al-Kamali and Hussein A. Ammar and Francois Chan and James H. Bayes and Yasser Gadallah and Mohamed H. Ahmed},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.30690},
  eprint = {2609.30690},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.30690},
}

RIS

TY  - UNPB
TI  - Threat-Aware Energy-Efficient Deployment for Dynamic UAV Networks: A Multi-Agent RL Approach
AU  - Faisal Al-Kamali
AU  - Hussein A. Ammar
AU  - Francois Chan
AU  - James H. Bayes
AU  - Yasser Gadallah
AU  - Mohamed H. Ahmed
PY  - 2026
DA  - 2026/09/25
PB  - arXiv
DO  - 10.48550/arxiv.2609.30690
UR  - https://arxiv.org/abs/2609.30690
AB  - Ensuring operational safety in threat-prone environments remains a critical challenge for multi-UAV networks serving as aerial base stations. This paper proposes an efficient framework to maximize global energy efficiency (EE) while promoting safe operation through threat-aware clustering and reward-based safety enforcement. The proposed framework is executed in three steps. First, a threat-aware K-means (TAKM) algorithm determines the minimum required UAVs and computes safe initial placements. Second, an optimal matching stage assigns physical UAVs to these centroids to minimize energy expenditure. Third, a threat-aware multi-agent twin delayed deep deterministic policy gradient (MATD3) algorithm dynamically optimizes trajectories, power, and user associations. Simulation results show that the proposed framework achieves zero observed safety violations in the considered scenarios while achieving superior EE and faster convergence than other learning methods and non-clustering baselines. Compared to heuristic optimization, the proposed framework outperforms the greedy particle swarm optimization (GPSO) and achieves performance comparable to that of the optimized PSO (OPSO), while incurring significantly lower online deployment computational complexity. Furthermore, the proposed framework demonstrates effective generalization to unseen user distributions, large UAV fleets, and different threat geometries, while maintaining zero safety violations.
ER  -

Abstract

Related

Cite