DRL-Based UAV Trajectory Planning for AoS and Energy Consumption Minimization Assisted by AoI

In edge Internet of Things (IoT) scenarios, it is important to maintain the freshness of information. The information freshness can be measured by Age of Information (AoI) and Age of Synchronization (AoS). To collect sensor node (SN) information in a flexible and efficient manner, unmanned aerial vehicles (UAVs) can be deployed. However, planning UAV trajectory, especially when SN updates are unpredictable and the energy consumption of UAV is limited, can be highly challenging. To address this issue, we propose an AoI-assisted trajectory planning for AoS and Energy minimization (AAE-TP) algorithm that leverages a deep reinforcement learning (DRL) framework. Our AAE-TP algorithm incorporates AoS in trajectory planning, allowing the UAV to obtain the AoS of the SN during information updates to compensate for the limitations of AoI. Simulation results demonstrate that the proposed algorithm can significantly improve the freshness of SN data collected by UAV while minimizing energy consumption.