Joint optimization of energy consumption and age of information for multi-agent UAV-assisted edge computing in disaster relief scenarios

BMC Bioinformatics · Springer Nature · 2026-11-15 · DOI: 10.1007/s11235-026-01545-6

Аннотация

In disaster relief scenarios, traditional communication infrastructures are often destroyed, leaving rescue personnel with limited computation capability and energy on their end devices. These devices generate continuous information and computing tasks that need to be collected and processed in a timely manner, which challenges the limited local resources. To tackle that, we employ Unmanned Aerial Vehicles (UAVs) as mobile edge servers to perform information collection and task offloading for these devices under disaster relief scenarios. Considering the critical need for real-time information in rescue operations, we first formulate a joint optimization problem to minimize the Age of Information (AoI) of user data and UAV energy consumption, and then propose a UAV trajectory planning algorithm based on Multi-Agent Twin Delayed Deep Deterministic Policy Gradient. Taking into account the limited battery endurance of UAVs, we incorporate a charging strategy of the UAVs to trajectory planning to guarantee persistent service, given a set of pre-deployed charging stations on ground. Simulation results demonstrate that compared with DDPG, DQN, and MAPPO, our approach reduces the average total AoI by approximately 3.90%, 12.30%, and 5.89%, respectively, and the average energy consumption by approximately 3.26%, 9.93%, and 3.40%, respectively.

Читать у издателя →

Похожие статьи