Onboard Processing in Satellite Communications Using AI Accelerators

Abstract

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.

Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing

“…After offline training, the ML payload controller can be deployed on board the satellite for real-time inference. This data-driven architecture offers the advantage of reduced processing times [33]. Table 1 provides an overview of the main characteristics of the setting under study.…”

Machine Learning-Based Solutions for Handover Decisions in Non-Terrestrial Networks

“…All of the above-mentioned handover strategies are related to terrestrial networks (TNs); however, in NTNs, the network architecture and infrastructure are dissimilar from those of conventional terrestrial networks, which might make handover more challenging. Moreover, an in-depth analysis of the current status of onboard artificial intelligence and machine learning (AI/ML) processing is provided in [32], along with a list of important factors to take into account while implementing it in communication satellites. Also, it offers a helpful framework for comparing and assessing the feasibility of various AI chipsets for onboard AI/ML processing.…”

Machine Learning and Deep Learning powered satellite communications: Enabling technologies, applications, open challenges, and future research directions

“…The newer generation satellites aim to use on-edge processing ie board processing, then transmit only the required data to the base stations. [101][102][103][104][105] The Phi-sat 1 is the first of its kind mission, that uses onboard technology for DL usage. The Phi-Sat 1 was used for remote sensing applications like cloud detection utilizing a specially designed onboard processor, Intel Movidius Myriad 2, which is a hardware AI accelerator.…”

“…101,102 The Phi-Sat 1 system consists of eyes of things (EoT) system with the Myriad 2 vision processing unit along with a HyperScout 2, which is a miniaturized spectral camera, which can be used to capture data in the near-infrared and thermal infrared regions. The Myriad 2 vision processing unit is an SoC with integrated DRAM RISC-V processors, streaming hybrid architecture vector engines, and can compute with a steady voltage supply of 2 V. [101][102][103][104]106 The NN on the Phi-SAT-1 was trained using modified data from European Space Agency's Sentinal 2 archive. The modification was done to simulate the behavior of the HyperScout 2 system.…”

“…This however used a lot of power and bandwidth resources of the satellite. The newer generation satellites aim to use on‐edge processing ie board processing, then transmit only the required data to the base stations 101–105 …”