PQ-FRL: A Privacy-Preserving and Quality-Aware Federated Reinforcement Learning for UAV-Assisted Edge Computing
IEEE Internet of Things Journal · 2026-08 · 13 (15) · 33914-33926
DOI: 10.1109/jiot.2026.3695149 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, 2026-08. Verfasst von Zifeng Dai und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Optimizing service performance in UAV-assisted mobile edge computing (MEC) systems often relies on effective cooperative trajectory and resource allocation. Federated reinforcement learning (FRL) provides a distributed paradigm to collaboratively learn these policies without sharing raw observations. However, practical deployments face severe coupled challenges: the model quality degradation caused by differential privacy (DP) noise injection, heterogeneous environments (non-independent and identically distributed (Non-IID) data), and complex physical constraints. To mitigate these issues, we propose PQ-FRL, a privacy-preserving and quality-aware (QA) FRL framework. Our approach utilizes an output perturbation DP mechanism to provide strict per-round protection for uploaded policy updates, representing a pragmatic engineering tradeoff between securing immediate operational privacy and maintaining continuous-control DRL convergence. To address the mixed-action space, we incorporate a straight-through estimator (STE) for differentiable offloading decisions, guided by a conditionally shaped reward to prevent suboptimal local equilibria. Furthermore, a novel QA aggregation mechanism dynamically assigns weights based on explicitly DP-protected local reward signals, helping to disentangle noise from inherently poor performance. Simulation results indicate that PQ-FRL can effectively balance realistic nonlinear energy and latency constraints. Under the evaluated heterogeneous scenarios and strict privacy budgets, our method demonstrates robust utility preservation and exhibits graceful degradation as physical airspace congestion increases with larger swarm sizes, offering a stable and practical solution for privacy-sensitive UAV edge computing.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Dai, Z., Xie, H., Wei, S., & Hu, C. (2026). PQ-FRL: A Privacy-Preserving and Quality-Aware Federated Reinforcement Learning for UAV-Assisted Edge Computing. IEEE Internet of Things Journal, 13(15), 33914-33926. https://doi.org/10.1109/jiot.2026.3695149
Vancouver
Dai Z, Xie H, Wei S, Hu C. PQ-FRL: A Privacy-Preserving and Quality-Aware Federated Reinforcement Learning for UAV-Assisted Edge Computing. IEEE Internet of Things Journal. 2026;13(15):33914-33926. doi:10.1109/jiot.2026.3695149
BibTeX
@article{Dai2026,
author = {Dai, Zifeng and Xie, Hui and Wei, Shengjun and Hu, Changzhen},
title = {PQ-FRL: A Privacy-Preserving and Quality-Aware Federated Reinforcement Learning for UAV-Assisted Edge Computing},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {15},
pages = {33914--33926},
doi = {10.1109/jiot.2026.3695149}
}
EUVIMED