Optimizing Smart Wireless Charging and Data Acquisition for UAVs With Battery Life Prediction

作者：Haiyan Chen, Junyu He, Yangfan Li, Ming Zhao, Fengxiao Tang, Nei Kato · 发表于：IEEE Transactions on Vehicular Technology · 年份：2025 · DOI：10.1109/tvt.2025.3598601 · 被引用次数：2 · 研究领域：UAV Applications and Optimization、Energy Harvesting in Wireless Networks、Advanced Battery Technologies Research

As network technology advances rapidly, the use of unmanned aerial vehicles (UAVs) is rapidly growing across diverse applications, revealing unprecedented potential for widespread deployment. However, these UAVs often encounter the challenge of insufficient power during their missions. To overcome this problem, this study addresses mission interruption and energy wastage due to insufficient power by charging UAVs with a Charging UAV (CUAV). Traditional research in this area is mostly based on one key assumption: constant battery capacity. However, the battery capacity actually decreases gradually with the usage time, a fact that imposes constraints on the operational range and duration of UAVs. To address this issue, this paper proposes a wireless energy charging strategy for UAVs based on battery life prediction. The strategy first predicts the remaining lifetime of the UAV battery, and then based on this, a charging UAV is deployed to charge the UAV on mission to ensure that it can continue to fulfill its mission without having to return to the base station to recharge or replace the battery. This paper further explores a practical application scenario where multiple UAVs perform data collection from multiple sensor nodes, and these UAVs are charged by CUAVs. To achieve efficient task scheduling, this study proposes and implements a UAV scheduling algorithm based on Deep Reinforcement Learning (DRL). Through large-scale simulation evaluation, we demonstrate that the propose...