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...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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’s College London, London, U.K.Department of Engineering, King’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 |