Low Earth Orbit (LEO) satellite constellations are crucial for global connectivity by providing extensive coverage and reduced delays. However, scheduling data transmission in these dynamic networks is challenging due to rapidly changing satellite positions. This research introduces BoostRL (boosted reinforcement learning), a novel framework integrating large language models (LLMs) with reinforcement learning (RL) for efficient scheduling in LEO satellite constellations. BoostRL leverages LLM-generated initial policies to accelerate convergence, thereby guiding the early stages of policy learning while adapting swiftly to dynamic network conditions. It employs a hybrid policy approach which transitions smoothly from LLM recommendations to autonomous RL policies. A tailored initialization of Q-value parameters and an enhanced loss function further optimize learning efficiency, by aligning the initial learning phase with LLM-generated insights. Simulations using two-line element (TLE) orbital data demonstrate that BoostRL achieves rapid convergence and improved efficiency, thereby validating its potential as a scalable, adaptive solution for managing satellite communication networks.

The increasing demand for ultra-low-latency and high-throughput communication necessitates network architectures capable of ensuring reliable real-time connectivity. To address this requirement, integrated architectures combining terrestrial networks (TN) and non-terrestrial networks (NTN)—particularly hierarchical multi-layer satellite systems composed of geostationary Earth orbit (GEO), medium Earth orbit (MEO), and low Earth orbit (LEO) satellites—have attracted considerable attention. Such hierarchical systems offer global coverage, low latency, and high capacity. However, their highly dynamic topology, fast-moving satellites, and fluctuating link quality pose significant challenges to establishing efficient end-to-end routing paths. Traditional routing methods based on static paths or centralized control lack the adaptability required for such environments. To address these challenges, this paper introduces a neural hierarchical reinforcement learning (HRL)-based routing algorithm for satellite networks. The framework exploits the layered structure of GEO, MEO, and LEO satellites, enabling gateway-assisted routing and adaptive path selection. Control responsibilities are distributed across orbital layers: the GEO layer allocates hop-count budgets, the MEO layer selects feasible LEO paths, and the LEO layer forwards data packets. When inter-satellite links are unavailable, terrestrial gateways provide alternative routes. Routing decisions further account for satellite-to-satellite and satellite-to-ground link quality, with an end-to-end delay-based reward function capturing transmission, processing, and propagation effects. Simulation results show that the proposed neural hierarchical framework, supported by integrated terrestrial and non-terrestrial networking, achieves faster convergence, greater route stability, and better adaptability than conventional routing algorithms and HRL approaches.

This paper presents a novel methodology to optimize the handover decision of mobile terminals (MTs) within a cooperative geostationary Earth orbit (GEO) and low Earth orbit (LEO) satellite network. Unlike prior research, which primarily focuses on inter-LEO satellite handovers for stationary terminals, this work addresses the handover challenges associated with MTs in a hybrid GEO-LEO satellite architecture. The proposed framework employs a convolutional neural network (CNN)-long-short-term memory (LSTM) encoder-decoder model to accurately predict the reference signal received power (RSRP) of potential handover target satellites, enabling more informed decision-making. A multi-agent double deep Q-network (MADDQN) algorithm is implemented to determine the optimal handover target, leveraging predicted RSRP data while considering factors such as network load and satellite connection duration. The proposed approach minimizes unnecessary handovers, enhances data throughput for MTs, and ensures stable connectivity and quality of service under diverse network conditions. The proposed method contributes to handover optimization in cooperative GEO-LEO satellite networks, offering valuable insights for next-generation satellite communication systems.

Low Earth orbit (LEO) satellite networks have emerged as a promising solution, offering advantages such as lower propagation delay, broader coverage, and rapid deployment capabilities. However, the dynamic topology and frequent handovers inherent in LEO satellite systems, coupled with limited onboard computational resources, necessitate the development of efficient and lightweight routing algorithms. Therefore, this paper proposes quantum reinforcement learning-based satellite routing (QRL-SR) tailored for LEO satellite networks. The QRL-SR algorithm addresses three critical considerations: (i) adapting to the dynamic and time-varying environment of LEO satellite networks; (ii) incorporating LEO satellite geometry by transforming celestial coordinate data, specifically two-line element, into orbital coordinate systems for accurate LEO satellite positioning over time; and (iii) being designed to be lightweight by leveraging QRL to reduce the number of training parameters. The proposed QRL-SR efficiently trains routing policies with fewer parameters, aligning with LEO satellites’ small-size, weight, and power (SWaP) constraints. The primary purpose of the QRL-SR-based LEO satellites is to reduce free space path loss, delay time, and the number of hops needed for routing through the inter-satellite links. Finally, experimental results demonstrate that the QRL-SR achieves routing performance comparable to or outperforms conventional algorithms while significantly reducing computational resources.

We investigate the minimum-delay multicast scheduling problem for millimeter wave (mmWave) networks. Salient characteristics of mmWave links, directionality and reflections, are considered under sectored antenna model. We first consider the model where the signal is received at a single Direction-of-Arrival (DoA) with the highest SNR at each node. We identify the property such that the optimal policy can be recursively partitioned into smaller sizes and propose an iterative method based on graphs which finds the optimal schedule in polynomial time. Next, we extend our model where a node leverages signals received at multiple DoAs through reflections. We introduce the concept of receiving direction diversity (RDD) which states that the availability of multiple receiving directions enables opportunistic reduction of multicast delay. We prove NP-hardness of the problem, and propose approximations with performance bounds and heuristics of reduced complexity. Next, we consider multicast scheduling with rateless codes (RCs) which reduces delay by flexible packet reception. For both cases of coded multicast with and without RDD, we formulate linear programming problems and propose greedy algorithms with nearly optimal performance and reduced complexity. By simulation we show the outperformance of our method over conventional ones, and numerically characterize the gain of RDD and RCs.

We investigate the minimum-delay multicast problem for millimeter wave (mmWave) networks. Salient characteristics of mmWave links, directionality and reflections, are considered under sectored antenna model. We first consider directionality only, and identify the property such that the optimal policy can be recursively partitioned into smaller sizes. Using such optimal substructure, we propose an iterative method based on graphs which finds the optimal schedule in polynomial time. Next, we extend our model to incorporate reflections. We introduce the concept of path diversity which states that the availability of reflected paths enables opportunistic reduction of multicast delay. We prove NP-hardness of the problem, and propose approximations with performance bounds and heuristics of reduced complexity. By simulation we show the outperformance of our method over conventional ones, and numerically characterize the gain of path diversity in terms of network size.

In this paper, we study a downlink band allocation game and algorithms in heterogeneous networks consisting of eNodeB (eNB) and femtocells (FC). If eNB and FC act as selfish players which compete to maximize their own utility, the resulting Nash equilibria (NE) may show poor performance due to interference. We propose an algorithm to avoid such equilibria. Specifically, we impose high prices on certain bands, which discourages FC from allocating such bands to its users. The case of 2-player 2-band is analyzed, under which our proposed scheme excels the case of full competition. Simulation results show that our algorithm prevents the players from ending up in inefficient equilibrium points, and also improves performance and fairness.