LEO-Satellite-Assisted UAV Path Optimization for Space–Air–Ground Internet of Remote Things Networks

Given the limited ground infrastructure in remote areas such as suburbs and rural regions, Internet of Remote Things (IoRT) devices have been widely deployed to gather critical data and information. However, traditional data transmission methods struggle to directly transmit the data to data processing centers. This paper proposes a space–air–ground Internet of Remote Things (SAG-IoRT) network architecture, which leverages the extensive coverage and efficient communication capabilities of satellites as its core advantage. In the SAG-IoRT network, low Earth orbit (LEO) satellites play a crucial role, addressing communication challenges in remote areas through their global coverage. Unmanned aerial vehicles (UAVs) serve as flexible bridges between ground and space, rapidly transmitting data collected by IoRT devices to LEO satellites, thereby enhancing data transmission efficiency and reliability. Our research focuses on optimizing the flight trajectories and scheduling strategies of UAVs to maximize the utilization of satellite communication resources, aiming to boost system throughput and reduce UAV energy consumption. To tackle the challenges of data collection and transmission in the dynamic and uncertain SAG-IoRT network environment, we formulate the optimization problem as a Markov decision process and apply the multi-agent deep deterministic policy gradient (MADDPG) algorithm to plan optimal paths for UAVs. Experimental results show that compared to the single-agent DDPG algorithm, the MADDPG-based solution not only improves system throughput by approximately 25.6% but also reduces UAV energy consumption by around 24.9%. This achievement underscores the pivotal role of satellites in advancing the development of IoRT and enabling efficient space-based communications.