With the development of Internet of Things(IoT), the world gradually moves toward the interconnection of all things. In terrestrial networks, NB-IoT(Narrow Band-Internet of Things) and LoRa(Long Rage) are used widely in the IoT industry. For low-earth-orbit(LEO) satellites, they have a lot of conspicuous advantages, like broader coverage, lower construction cost. In this letter, we place emphasis on the application of LoRa related technologies to LEO satellite communication systems, and the modulation is the prior research. Chirp Spread Spectrum(CSS) modulation is the most important technology in LoRa. Therefore, the research of CSS modulation used in the satellite IoT is imperative.

In this letter, we use squared iterative method with parameter checking to accelerate the convergence rate of Expectation/Conditional Maximization (ECM) algorithm when estimating the channel parameters blindly in flat fading non-Gaussian channels, and further, we proposed automatic modulation classification (AMC) in flat fading non-Gaussian channels based on the proposed maximum likelihood estimator. The numerical results show that the proposed method can accelerate the convergence rate of ECM algorithm, and AMC based on the proposed method is faster than that based on ECM, while the accuracy of the former shows nearly no loss compared to that of the latter.

The technology of Chirp Spread Spectrum (CSS) has been developed for decades, widely known to be used in the field of radar and sonar. In recent years, CSS is used in IEEE 802.15.4a and LoRa (Long Range) Internet of Things (IoT) called LoRa modulation. On the other hands, CSS has never been used in Low-Earth-Orbit (LEO) satellite communication systems for low-data-rate transmission (IoT). CSS applied in LoRa as a kind of successful commercial IoT technology will promote us to do research on its application in satellite communication for IoT. There are some new types of chirp signal with the same chirp rate to realize multiple access in these years. Based on these, this letter is on the research of these kinds of chirp signal in satellite multiple access communication systems.

Chirp signal has been used in some fields, like radar and sonar. In recent years, Symmetry Chirp Signal (SCS) is a kind of revised LoRa chirp signal and proposed to be used in Low-Earth-Orbit (LEO) satellite Internet of Things (IoT) for low-data-rate transmission. However, in term of the complexity and performance, traditional acquisition methods to capture SCS (time delay and frequency offset acquisition) will have some limitations in LEO satellite IoT. Thus, this letter presents a new acquisition method to balance the complexity and performance for SCS.

Spectrum sharing is a pivotal technology for integrated satellite-maritime network to improve spectrum efficiency. However, the majority of existing spectrum sharing approaches relied on time-frequency multiplexing to circumvent or suppress interference, and often overlooked the problem of incomplete observability and interference present in heterogeneous systems. This limitation hindered overall system throughput improvements. In this paper, an intelligent spectrum sharing strategy for integrated satellite-maritime heterogeneous mobile networks is firstly proposed. This strategy aims to operate co-frequency communication transmissions within the interference constraints, as derived from protocols and standards of International Telecommunication Union (ITU), to maximize the overall system throughput and spectral efficiency. Furthermore, considering the limitation that the satellite cannot fully observe channel statuses, we model the spectrum sharing process as a Partially Observable Markov Decision Process (POMDP). We employ an algorithm architecture that combines Dueling Deep Q-learning Network (DQN) and Double DQN to address this challenge, which enables satellites to efficiently evaluate the value of all channel allocation actions, thereby enhancing decision-making accuracy and algorithm convergence speed. Simulation results validate the superiority of our proposed strategy over compared methods in terms of throughput and stability.

Agile-satellite mission planning is a crucial issue in the construction of satellite constellations. The large scale of remote sensing missions and the high complexity of constraints in agile-satellite mission planning pose challenges in the search for an optimal solution. To tackle the issue, a dynamic destroy deep-reinforcement learning (D3RL) model is designed to facilitate subsequent optimization operations via adaptive destruction to the existing solutions. Specifically, we first perform a clustering and embedding operation to reconstruct tasks into a clustering graph, thereby improving data utilization. Secondly, the D3RL model is established based on graph attention networks (GATs) to enhance the search efficiency for optimal solutions. Moreover, we present two applications of the D3RL model for intensive scenes: the deep-reinforcement learning (DRL) method and the D3RL-based large-neighborhood search method (DRL-LNS). Experimental simulation results illustrate that the D3RL-based approaches outperform the competition in terms of solutions’ quality and computational efficiency, particularly in more challenging large-scale scenarios. DRL-LNS outperforms ALNS with an average scheduling rate improvement of approximately 11% in Area instances. In contrast, the DRL approach performs better in World scenarios, with an average scheduling rate that is around 8% higher than that of ALNS.