RL-Driven Security-Aware Resource Allocation Framework for UAV-Assisted O-RAN

TL;DR

The paper addresses the challenge of securing, low-latency, and energy-efficient UAV-assisted resource management in an O-RAN setting for SAR/disaster scenarios. It introduces a multi-objective optimization framework that jointly selects GU–O-RU associations, encryption key lengths, and UAV trajectories, and solves it with a model-free PPO-based reinforcement learning approach structured as an MDP with state $S$, action $A$, and reward $R$, incorporating a normalized objective $P1$ and a clipped surrogate objective $L^{\text{CLIP}}(\theta)$. Key contributions include the formal MOP formulation with decision variables $x_{u,g}^{t}$, $y_{u,a,g}^{t}$, $N_{u}^{t}$, $q_{a}^{t}$, the encryption-level adaptation, and an RL solution that demonstrates practical improvements in security and energy efficiency while maintaining ultra-low latency in SAR-like conditions. The findings indicate that the proposed framework can adapt in real time to network dynamics, provide robust and secure connectivity, and guide future deployments of secure, responsive UAV-supported O-RAN systems in mission-critical environments.

Abstract

The integration of Unmanned Aerial Vehicles (UAVs) into Open Radio Access Networks (O-RAN) enhances communication in disaster management and Search and Rescue (SAR) operations by ensuring connectivity when infrastructure fails. However, SAR scenarios demand stringent security and low-latency communication, as delays or breaches can compromise mission success. While UAVs serve as mobile relays, they introduce challenges in energy consumption and resource management, necessitating intelligent allocation strategies. Existing UAV-assisted O-RAN approaches often overlook the joint optimization of security, latency, and energy efficiency in dynamic environments. This paper proposes a novel Reinforcement Learning (RL)-based framework for dynamic resource allocation in UAV relays, explicitly addressing these trade-offs. Our approach formulates an optimization problem that integrates security-aware resource allocation, latency minimization, and energy efficiency, which is solved using RL. Unlike heuristic or static methods, our framework adapts in real-time to network dynamics, ensuring robust communication. Simulations demonstrate superior performance compared to heuristic baselines, achieving enhanced security and energy efficiency while maintaining ultra-low latency in SAR scenarios.

Figures (2)

• Figure 1: System Model
• Figure 2: Performance of RL-based approach