Robust Downlink Data Transmission in LEO Satellite–Terrestrial Networks: A Rate-Splitting Multiple Access Approach

Rate-splitting multiple access (RSMA) has recently gained attention in low-Earth orbit (LEO) satellite-terrestrial networks (LSTNs), due to its ability to provide high spectral efficiency in the context of constrained energy resources of LEO satellites. However, the impracticality of acquiring perfect real-time channel state information (CSI), due to high satellite mobility and long link delay, poses significant challenges to effective utilization of RSMA in LSTNs. To tackle this challenge, we propose a location-based robust RSMA scheme for downlink data transmission in LSTNs. First, we establish an optimization problem to minimize the power consumption of LEO satellites, while meeting user requirement on the real-time data rate violation probability. Subsequently, we transfer the probability constraints of rate violation probabilities into closed-form inequalities, by utilizing Markov inequality, Jensen’s inequality, and Cauchy-Schwarz inequality. The original problem is then transformed into a Markov decision process (MDP), and a Transformer encoder-based deep reinforcement learning (TDRL) algorithm is proposed to solve the complex problem based on the real-time locations of users and the LEO satellite. Additionally, a multi time-frame location-based training dataset generation method is proposed for the training of the TDRL model, considering the mobility of LEO satellite. Simulation results demonstrate that the proposed scheme is effective in guaranteeing the rate violation probability requirement of each user, and RSMA significantly outperforms space-division multiple access (SDMA) and nonorthogonal multiple access (NOMA), with TDRL achieving faster convergence than other baselines.