UAV Trajectory Planning for AoI-Minimal Data Collection in UAV-Aided IoT Networks by Transformer

TL;DR

The paper tackles AoI‑aware data collection in UAV‑assisted cluster-based IoT networks by jointly optimizing hovering locations and visiting order. It introduces a Transformer‑Weighted A* framework that treats trajectory planning as a translation problem: an encoder/decoder network proposes a visiting order, while weighted A* selects concrete hovering points from discretized disk regions. Trained with REINFORCE, the approach generalizes to different numbers of clusters and outperforms baseline methods in total AoI, oldest‑packet AoI, and energy efficiency, with reduced computation time. The work demonstrates a scalable, learning‑based solution for real‑time AoI optimization and suggests extending to multi‑UAV scenarios for broader applicability.

Abstract

Maintaining freshness of data collection in Internet-of-Things (IoT) networks has attracted increasing attention. By taking into account age-of-information (AoI), we investigate the trajectory planning problem of an unmanned aerial vehicle (UAV) that is used to aid a cluster-based IoT network. An optimization problem is formulated to minimize the total AoI of the collected data by the UAV from the ground IoT network. Since the total AoI of the IoT network depends on the flight time of the UAV and the data collection time at hovering points, we jointly optimize the selection of hovering points and the visiting order to these points. We exploit the state-of-the-art transformer and the weighted A*, which is a path search algorithm, to design a machine learning algorithm to solve the formulated problem. The whole UAV-IoT system is fed into the encoder network of the proposed algorithm, and the algorithm's decoder network outputs the visiting order to ground clusters. Then, the weighted A* is used to find the hovering point for each cluster in the ground IoT network. Simulation results show that the trained model by the proposed algorithm has a good generalization ability to generate solutions for IoT networks with different numbers of ground clusters, without the need to retrain the model. Furthermore, results show that our proposed algorithm can find better UAV trajectories with the minimum total AoI when compared to other algorithms.

Figures (8)

• Figure 1: System model of a UAV-assisted IoT network.
• Figure 2: The time sequence of data collection in the considered UAV-IoT system.
• Figure 3: The proposed algorithm framework.
• Figure 4: Multi-head self attention.
• Figure 5: Comparison when $M$ varies.