This paper delves into the application of Machine Learning (ML) techniques in the realm of 5G Non-Terrestrial Networks (5G-NTN), particularly focusing on symbol detection and equalization for the Physical Broadcast Channel (PBCH). As 5G-NTN gains prominence within the 3GPP ecosystem, ML offers significant potential to enhance wireless communication performance. To investigate these possibilities, we present ML-based models trained with both synthetic and real data from a real 5G over-the-satellite testbed. Our analysis includes examining the performance of these models under various Signal-to-Noise Ratio (SNR) scenarios and evaluating their effectiveness in symbol enhancement and channel equalization tasks. The results highlight the ML performance in controlled settings and their adaptability to real-world challenges, shedding light on the potential benefits of the application of ML in 5G-NTN.
This paper presents a study of an integrated satellite-terrestrial network, where Low-Earth-Orbit (LEO) satellites are used to provide the backhaul link between base stations (BSs) and the core network. The mobility of LEO satellites raises the challenge of determining the optimal association between LEO satellites, BSs, and users (UEs). The goal is to satisfy the UE demand while ensuring load balance and optimizing the capacity of the serving link between the BS and the LEO satellite. To tackle this complex optimization problem, which involves mixed-integer non-convex programming, we propose an iterative algorithm that leverages approximation and relaxation methods. The proposed solution aims to find the optimal two-tier satellite-BS-UE association, sub-channel assignment, power and bandwidth allocation in the shortest possible time, fulfilling the requirements of the integrated satellite-terrestrial network.
This paper presents a centralized framework for optimizing the joint design of beam placement, power, and bandwidth allocation in an MEO satellite constellation to fulfill the heterogeneous traffic demands of a large number of global users. The problem is formulated as a mixed integer programming problem, which is computationally complex in large-scale systems. To overcome this challenge, a three-stage solution approach is proposed, including user clustering, cluster-based bandwidth and power estimation, and MEO-cluster matching. A greedy algorithm is also included as a benchmark for comparison. The results demonstrate the superiority of the proposed algorithm over the benchmark in terms of satisfying user demands and reducing power consumption.
This paper aims to develop satellite-user association and resource allocation mechanisms to minimize the total transmit power for integrated terrestrial and non-terrestrial networks wherein a constellation of LEO satellites provides the radio access services to both terrestrial base stations (BSs) and the satellite-enabled users (SUEs). In this work, beside maintaining the traditional SatCom connection for SUEs, the LEO satellites provide backhaul links to the BSs to upload the data received from their ground customers. Taking the individual SUE traffic demands and the aggregated BS demands, we formulate a mixed integer programming which consists of the binary variables due to satellite association selection, power control and bandwidth allocation related variables. To cope with this challenging problem, an iterative optimization-based algorithm is proposed by relaxing the binary components and alternating updating all variables. A greedy mechanism is also presented for comparison purpose. Then, numerical results are presented to confirm the effectiveness of our proposed algorithms.