DNN-Based Energy-Efficient Resource Management for Beam-Hopping LEO Satellite Communications

This paper presents a deep neural network (DNN)-based resource allocation framework aimed at maximizing energy efficiency (EE) in beam-hopping (BH) low-Earth orbit (LEO) satellite communication systems. Specifically, in BH-LEO satellite systems, it is challenging to solve the joint optimization of time slot scheduling and transmit power control, due to the intrinsic complexity and non-convex nature of the original mixed-integer nonlinear programming formulation. To mitigate this issue, we propose a strategy to decompose the problem into two tractable subproblems: an integer programming model for time slot allocation and a nonlinear programming model for transmit power allocation. For the time slot allocation subproblem, we employ a dueling double deep Q-network (D3QN), combining the strengths of both dueling and double Q-learning techniques to enable stable and efficient decision-making. Then, for the power allocation subproblem, we design a novel unsupervised DNN (UDNN)-based model that estimates spectral efficiency to indirectly determine transmit power, thereby avoiding the difficulties of solving a non-convex optimization problem for EE maximization. Extensive simulation results show that the proposed D3QN and UDNN-based schemes outperform existing iterative and DNN-based approaches in terms of both EE and outage performance, while achieving a significant reduction in computational overhead.