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

The latest Satellite Communication (SatCom) missions are characterized by a fully reconfigurable on-board software-defined payload, capable of adapting radio resources to the temporal and spatial variations of the system traffic. As pure optimization-based solutions have shown to be computationally...

Full description

Saved in:
Bibliographic Details
Main Authors: Flor Ortiz, Nicolas Skatchkovsky, Eva Lagunas, Wallace A. Martins, Geoffrey Eappen, Saed Daoud, Osvaldo Simeone, Bipin Rajendran, Symeon Chatzinotas
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Transactions on Machine Learning in Communications and Networking
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10387580/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850051560091942912
author Flor Ortiz
Nicolas Skatchkovsky
Eva Lagunas
Wallace A. Martins
Geoffrey Eappen
Saed Daoud
Osvaldo Simeone
Bipin Rajendran
Symeon Chatzinotas
author_facet Flor Ortiz
Nicolas Skatchkovsky
Eva Lagunas
Wallace A. Martins
Geoffrey Eappen
Saed Daoud
Osvaldo Simeone
Bipin Rajendran
Symeon Chatzinotas
author_sort Flor Ortiz
collection DOAJ
description The latest Satellite Communication (SatCom) missions are characterized by a fully reconfigurable on-board software-defined payload, capable of adapting radio resources to the temporal and spatial variations of the system traffic. As pure optimization-based solutions have shown to be computationally tedious and to lack flexibility, Machine Learning (ML)-based methods have emerged as promising alternatives. We investigate the application of energy-efficient brain-inspired ML models for on-board radio resource management. Apart from software simulation, we report extensive experimental results leveraging the recently released Intel Loihi 2 chip. To benchmark the performance of the proposed model, we implement conventional Convolutional Neural Networks (CNN) on a Xilinx Versal VCK5000, and provide a detailed comparison of accuracy, precision, recall, and energy efficiency for different traffic demands. Most notably, for relevant workloads, Spiking Neural Networks (SNNs) implemented on Loihi 2 yield higher accuracy, while reducing power consumption by more than <inline-formula> <tex-math notation="LaTeX">$100\times $ </tex-math></inline-formula> as compared to the CNN-based reference platform. Our findings point to the significant potential of neuromorphic computing and SNNs in supporting on-board SatCom operations, paving the way for enhanced efficiency and sustainability in future SatCom systems.
format Article
id doaj-art-9fc2d59a524e48aa8ede95336d57c2d4
institution DOAJ
issn 2831-316X
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Machine Learning in Communications and Networking
spelling doaj-art-9fc2d59a524e48aa8ede95336d57c2d42025-08-20T02:53:06ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2024-01-01216918910.1109/TMLCN.2024.335256910387580Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic ComputingFlor Ortiz0https://orcid.org/0000-0002-2280-4689Nicolas Skatchkovsky1Eva Lagunas2https://orcid.org/0000-0002-9936-7245Wallace A. Martins3https://orcid.org/0000-0002-3788-2794Geoffrey Eappen4https://orcid.org/0000-0002-4065-3626Saed Daoud5Osvaldo Simeone6https://orcid.org/0000-0001-9898-3209Bipin Rajendran7https://orcid.org/0000-0002-2960-6909Symeon Chatzinotas8https://orcid.org/0000-0001-5122-0001Interdisciplinary Centre for Security, Reliability, and Trust (SnT), Luxembourg City, LuxembourgFrancis Crick Institute, London, U.K.Interdisciplinary Centre for Security, Reliability, and Trust (SnT), Luxembourg City, LuxembourgInterdisciplinary Centre for Security, Reliability, and Trust (SnT), Luxembourg City, LuxembourgInterdisciplinary Centre for Security, Reliability, and Trust (SnT), Luxembourg City, LuxembourgInterdisciplinary Centre for Security, Reliability, and Trust (SnT), Luxembourg City, LuxembourgDepartment of Engineering, King&#x2019;s College London, London, U.K.Department of Engineering, King&#x2019;s College London, London, U.K.Interdisciplinary Centre for Security, Reliability, and Trust (SnT), Luxembourg City, LuxembourgThe latest Satellite Communication (SatCom) missions are characterized by a fully reconfigurable on-board software-defined payload, capable of adapting radio resources to the temporal and spatial variations of the system traffic. As pure optimization-based solutions have shown to be computationally tedious and to lack flexibility, Machine Learning (ML)-based methods have emerged as promising alternatives. We investigate the application of energy-efficient brain-inspired ML models for on-board radio resource management. Apart from software simulation, we report extensive experimental results leveraging the recently released Intel Loihi 2 chip. To benchmark the performance of the proposed model, we implement conventional Convolutional Neural Networks (CNN) on a Xilinx Versal VCK5000, and provide a detailed comparison of accuracy, precision, recall, and energy efficiency for different traffic demands. Most notably, for relevant workloads, Spiking Neural Networks (SNNs) implemented on Loihi 2 yield higher accuracy, while reducing power consumption by more than <inline-formula> <tex-math notation="LaTeX">$100\times $ </tex-math></inline-formula> as compared to the CNN-based reference platform. Our findings point to the significant potential of neuromorphic computing and SNNs in supporting on-board SatCom operations, paving the way for enhanced efficiency and sustainability in future SatCom systems.https://ieeexplore.ieee.org/document/10387580/Energy-efficientneuromorphic computingradio resource managementsatellite communicationspiking neural networks
spellingShingle Flor Ortiz
Nicolas Skatchkovsky
Eva Lagunas
Wallace A. Martins
Geoffrey Eappen
Saed Daoud
Osvaldo Simeone
Bipin Rajendran
Symeon Chatzinotas
Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing
IEEE Transactions on Machine Learning in Communications and Networking
Energy-efficient
neuromorphic computing
radio resource management
satellite communication
spiking neural networks
title Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing
title_full Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing
title_fullStr Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing
title_full_unstemmed Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing
title_short Energy-Efficient on-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing
title_sort energy efficient on board radio resource management for satellite communications via neuromorphic computing
topic Energy-efficient
neuromorphic computing
radio resource management
satellite communication
spiking neural networks
url https://ieeexplore.ieee.org/document/10387580/
work_keys_str_mv AT florortiz energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing
AT nicolasskatchkovsky energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing
AT evalagunas energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing
AT wallaceamartins energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing
AT geoffreyeappen energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing
AT saeddaoud energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing
AT osvaldosimeone energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing
AT bipinrajendran energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing
AT symeonchatzinotas energyefficientonboardradioresourcemanagementforsatellitecommunicationsvianeuromorphiccomputing