Joint Optimization Strategy for UAV Trajectory and Communication Offloading in Dynamic Post-disaster Scenarios

With the increasing frequency of natural disasters, terrestrial communication infrastructure is often severely damaged, leading to interruptions in edge computing and data delivery. This paper proposes a Post-Disaster Adaptive Deep Deterministic Policy Gradient algorithm (PD-DDPG) to jointly optimize the Unmanned Aerial Vehicle (UAV)'s trajectory and vehicle task offloading in such disrupted environments. The PD-DDPG framework enhances traditional DDPG by incorporating a probabilistic Roadside Unit (RSU) failure model and real-time UAV-vehicle communication constraints into the environment state, enabling informed decision-making in uncertain post-disaster conditions. The proposed model employs a multi-objective reward function that simultaneously minimizes Age of Information (AoI), transmission delay, and system-wide energy consumption. To improve exploration and convergence under non-stationary dynamics, PD-DDPG uses an adaptive noise mechanism during training. Simulation experiments across different RSU damage rates validate the robustness and generalization ability of the proposed method. Comparative evaluations with Twin Delayed Deep Deterministic Policy Gradient (TD3) and random baseline strategies demonstrate that PD-DDPG achieves lower delay and energy costs while maintaining comparable AoI levels. In addition, the UAV trained via PD-DDPG autonomously adjusts its trajectory to compensate for RSU outages and maximize service coverage. This study provides an effective framework for emergency offloading coordination and offers insights into UAV-assisted edge computing in post-disaster scenarios.