ABSTRACT This paper proposes a novel approach for energy‐efficient and scalable path planning in 6G‐enabled networks using drones for IoT device localization. The proposed method leverages AI‐driven path optimization and green communication techniques, including dynamic power control, energy harvesting, and sleep‐mode base stations, to achieve low‐latency, high‐throughput, and energy‐efficient performance. We evaluate the method through a series of experiments, comparing it with several state‐of‐the‐art techniques such as SEDMAG, WSA, DREAMS, and Zcurve. The experimental results demonstrate that the GPP outperforms these baseline methods in terms of energy efficiency, localization accuracy, and system scalability, especially in high‐density environments. Furthermore, we conduct an ablation study and hyperparameter analysis to assess the impact of key components and parameters on the system's performance. The results show that each component plays a critical role in optimizing the system's performance, with the AI‐driven optimization and dynamic power control being particularly important for achieving the best overall performance. This research paves the way for the deployment of efficient path planning strategies in future 6G networks.
Fan et al. (Thu,) studied this question.