Performance Evaluation of Neuromorphic Hardware for Onboard Satellite Communication Applications

January 1, 2024·
Eva Lagunas
,
Flor Ortiz
,
Geoffrey Eappen
,
Saed Daoud
,
Wallace Alves Martins
,
Jorge Querol
,
Symeon Chatzinotas
,
Nicolas Skatchkovsky
,
Bipin Rajendran
,
Osvaldo Simeone
· 1 min read
Abstract
Spiking neural networks (SNNs) implemented on neuromorphic processors (NPs) can enhance the energy efficiency of deployments of artificial intelligence (AI) for specific workloads. As such, NPs represent an interesting opportunity for implementing AI tasks power-limited onboard satellite communication spacecraft. In this article, we disseminate the findings of a recently completed study which targeted the comparison, in terms of performance and power-consumption, of different satellite communication use cases implemented on standard AI accelerators and on NPs. In particular, the article describes three prominent use cases, namely payload resource optimization, onboard interference detection and classification, and dynamic receive beamforming; and compares the performance of conventional convolutional neural networks (CNNs) implemented on Xilinx’s VCK5000 Versal development card, and SNNs on Intel’s neuromorphic chip Loihi 2.
Type
Publication
arXiv preprint arXiv:2401.06911
publication

Abstract & Overview

Spiking neural networks (SNNs) implemented on neuromorphic processors (NPs) can enhance the energy efficiency of deployments of artificial intelligence (AI) for specific workloads. As such, NPs represent an interesting opportunity for implementing AI tasks power-limited onboard satellite communication spacecraft. In this article, we disseminate the findings of a recently completed study which targeted the comparison, in terms of performance and power-consumption, of different satellite communication use cases implemented on standard AI accelerators and on NPs. In particular, the article describes three prominent use cases, namely payload resource optimization, onboard interference detection and classification, and dynamic receive beamforming; and compares the performance of conventional convolutional neural networks (CNNs) implemented on Xilinx’s VCK5000 Versal development card, and SNNs on Intel’s neuromorphic chip Loihi 2.

Publication Metadata

  • Authors: Eva Lagunas, Flor Ortiz, Geoffrey Eappen, Saed Daoud, Wallace Alves Martins, Jorge Querol, Symeon Chatzinotas, Nicolas Skatchkovsky, Bipin Rajendran, Osvaldo Simeone
  • Venue: arXiv preprint arXiv:2401.06911 (2024)
  • Research Areas: Satellite Communications, AI & Neuromorphic SatCom, SDR & Experimental Testbeds
  • DOI: 10.1109/mwc.016.2300560
  • Open Access Repository: ORBiLu – University of Luxembourg
Satellite Communications AI & Neuromorphic SatCom SDR & Experimental Testbeds