Satellite communication (SatCom) systems operations centers currently require high human intervention, which leads to increased operational expenditure (OPEX) and implicit latency in human action that causes degradation in the quality of service (QoS). Consequently, new SatCom systems leverage artificial intelligence and machine learning (AI/ML) to provide higher levels of autonomy and control. Onboard processing for advanced AI/ML algorithms, especially deep learning algorithms, requires an improvement of several magnitudes in computing power compared to what is available with legacy, radiation-tolerant, space-grade processors in space vehicles today. The next generation of onboard AI/ML space processors will likely include a diverse landscape of heterogeneous systems. This manuscript identifies the key requirements for onboard AI/ML processing, defines a reference architecture, evaluates different use case scenarios, and assesses the hardware landscape for current and next-generation space AI processors.

This paper provides a comprehensive survey on the application and development of Artificial Intelligence (AI) and Machine Learning (ML) in satellite communication (SATCOM). It explores the increasing integration of AI/ML technologies in SATCOM systems, highlighting their potential to enhance performance, efficiency, and adaptability in response to growing demands for connectivity and data processing. The survey categorizes various use cases across different layers of satellite networks, detailing conventional solutions and the advantages of employing AI/ML techniques. It discusses the challenges associated with onboard processing, including hardware constraints, radiation tolerance, and the need for efficient resource management. Furthermore, the document examines the role of neuromorphic computing and COTS (Commercial Off-The-Shelf) devices in facilitating AI applications in space environments. Finally, we discuss the long-term developments of AI in the SATCOM sector and potential research directions. Overall, the survey emphasizes the transformative impact of AI/ML on the future of SATCOM, paving the way for innovative solutions in next-generation satellite networks.

Onboard satellite communication systems generate and manage coverage beams over the Earth. Depending on data traffic requirements, the number of beams, side lobe levels, nulls, and EIRP, their beamwidth must be efficiently generated and managed. Therefore, this paper describes an approach for beam pattern synthesis applied to geostationary satellite communication systems. The beam pattern synthesis can generate beams with a beamwidth variation from 0.45° to 1.5°, which can be controlled independently for the two principal cuts. In addition, other requirements have been considered, e.g., latitude, and longitude, required EIRP, minimum and maximum side love levels for the two principal cuts, and nulling direction. The output of the synthesizer is a weight matrix with beamforming coefficients of the required beam. The direct radiating array in this contribution utilizes an open-ended waveguide antenna as unit cell elements with a period of 0.875λ ₀ designed to work in left-hand circular polarization in the frequency band from 17.7 to 20.1 GHz. Since this design is intended for high-data rates applications, the minimum beamwidth requirements are very narrow. Therefore, 36 × 36 sub-arrays of 4 × 4 unit cells with a period of 3.5λ are considered to accomplish the beamwidth requirements while maintaining reduced computational and time resources for the weight matrix calculation compared to the conventional counterpart of 144×144 unit cells. The results show that the algorithm, which uses the surrogate optimizer, can compute the weight matrix and synthesize the beam with a slight deviation from the input data.

In this paper, we consider a scenario with one unmanned aerial vehicle (UAV) equipped with a uniform linear array (ULA), which sends combined information and sensing signals to communicate with multiple ground base stations (GBSs) and, at the same time, senses potential targets placed within an interested area on the ground. We aim to jointly design the transmit beamforming with the GBSs association to optimize communication performance while ensuring high sensing accuracy. We propose a predictive beamforming framework based on a dual deep neural network (DNN) solution to solve the formulated nonconvex optimization problem. A first DNN is trained to produce the required beamforming matrix for any point of the UAV flying area in a reduced time compared to stateof- the-art beamforming optimizers. A second DNN is trained to learn the optimal mapping from the input features, power, and effective isotropic radiated power (EIRP) constraints to the GBSs association decision. Finally, we provide an extensive simulation analysis to corroborate the proposed approach and show the benefits of EIRP, Signal-to-Noise-plus-Interference Ratio (SINR) performance and computational speed.

Recent advancements in onboard satellite communication have enhanced the capability of dynamically modifying the radiation pattern of a Direct Radiating Array (DRA). This is crucial not only for conventional communication satellites like Geostationary Orbit (GEO) but also for those in lower orbits such as Low Earth Orbit (LEO). Key design factors include the number of beams, beamwidth, Effective Isotropic Radiated Power (EIRP), and Side Lobe Level (SLL) for each beam. However, a challenge arises in multibeam scenarios when trying to simultaneously meet requirements for the aforementioned design factors which are reflected as uneven power distribution. This leads to over-saturation, especially in centrally located antenna elements due to the activation times per beam, commonly referred to as activation instances. In response to this challenge, this paper presents a method to balance the activation instances across antenna elements for each required beam. Our focus is on beams operating at 19 GHz on a CubeSat positioned 500 km above the Earth’s surface. We introduce a Genetic Algorithm (GA)-based algorithm to optimize the beamforming coefficients by modulating the amplitude component of the weight matrix for each antenna element. A key constraint of this algorithm is a limit on activation instances per element, which avoids over-saturation in the Radio Frequency (RF) chain. Additionally, the algorithm accommodates beam requirements such as beamwidth, SLL, pointing direction, and total available power. With the previous key design factors, the algorithm will optimize the required genes to address the desired beam characteristics and constraints. We tested the algorithm’s effectiveness in three scenarios using an $8\times 8$ DRA patch antenna with circular polarization, arranged in a triangular lattice. The results demonstrate that our algorithm not only meets the required beam pattern specifications but also ensures a uniform activation distribution across the antenna array.

An Inductive Frequency Selective Surface (IFSS) self-standing dichroic sub-reflector is presented, which allows the transmission of two frequency bands and reflection of a third band. The operating frequency of the sub-reflector is designed to work at Ku, K and Ka frequency bands, intended for earth to space and space to earth satellite communications. The proposed unit cell is a Jerusalem cross intertwined with an Brigid’s cross. The IFSS is investigated using transmission line theory, along with equivalent-circuit model technique. It has been designed, and simulated using CST Microwave Studio and Advance Design Simulator (ADS). The cascade configuration of the IFSS is also investigated to improve frequency roll-off and bandwidth of the reflection and transmission coefficients. The IFSS has been manufactured using two-sided Photo Chemical Machining (PCM) technique, and has been experimentally characterized using an optical configuration, comprising two double ridged horn antennas connected to a VNA and a rotation system. Measured results are in good agreement with theoretical and simulation data, which validates the reliability of the design and manufacturing process.