This paper focuses on the research of anti-jamming issues for Low Earth Orbit (LEO) satellite constellations. Initially, the anti-jamming problem is modeled as a Local Interaction Markov Game (LIMG) and proven to be an Exact Potential Game (EPG), with at least one pure strategy Nash Equilibrium (NE) existing. Secondly, based on the theoretical analysis and the ”offline training and online execution” architecture, a Distributed Multi-Agent Deep Reinforcement Learning-based anti-jamming (DMDRLA) scheme is proposed, and its convergence and asymptotic optimality are theoretically analyzed. Finally, simulations validate that the proposed DM-DRLA scheme can effectively balance the training costs and performance optimization of the anti-jamming model, making it suitable for anti-jamming issues in resource-constrained LEO satellite networks.

The agile Earth observation satellite scheduling problem (AEOSSP) with time-dependent transition time is a combinatorial optimization challenge. Due to its NP-hardness, problem-tailored methods are sensitive to instances and require massive computational overhead. Recently, deep reinforcement learning (DRL) models have shown promise in efficiently addressing the AEOSSP. However, these models may make decision mistakes in specific scenarios due to prioritizing maximizing average reward expectation over individual decision accuracy during DRL training, directly leading to resource wastage. To address these issues, we propose a reconstruction model (RCM), which is a DRL-based two-stage construction model (CM), including a CM and a reconstruction mechanism (RM). RCM constructs solutions initially using a DRL-trained CM, which are subsequently refined by RM. CM utilizes a more efficient network for policy representation to make decisions. RM applies two operators, "repair" and "removal," with a "repair-removal-repair" solution reconstruction process to identify and rectify decision mistakes from CM, offering a modular component to enhance the stability and solution quality. Experimental results demonstrate that the proposed RCM outperforms the state-of-the-art AEOSSP iterative search method, achieving such performance within a computational time of 0.1 s. Additionally, CM surpasses the state-of-the-art DRL policy model and RM can effectively rectify decision errors or suboptimalities, underscoring its effectiveness in enhancing DRL outcomes.

This paper presents a multi-satellite scheduling problem for very large area observation in response to various requests. It is assumed that the profit was proportional to the coverage of the acquired area, and the objective is therefore to maximize the total profits of generated observation schedule. To address the satellite scheduling problem, we first demonstrate a detailed problem description and then transform the problem into set covering problem within several criteria and constraints. Based on that, a mathematical model is established. To solve the problem, a new three-phase solving framework is proposed. In the discretizing phase, an area discretization method is adopted to establish the evaluation system. In the target decomposing phase, area target is decomposed into strips and corresponding visible time windows are calculated. In the scheduling phase, with crossover, mutation and feasibility operators, a genetic algorithm is introduced to generate an optimal observation schedule. Through extensive computational experiments on realistically generated problems in various scenarios including real-world data from China's satellite platform, the effectiveness and reliability of the proposed solving framework are verified.