FRANCESCO VALENTE

Dottore di ricerca

ciclo: XXXVI


Titolo della tesi: Design and evaluation of strategies to minimize operating costs and support in-orbit Distributed Learning within satellite networks for Earth Observation

Earth Observation (EO) satellites currently acquire images to be then stored in their on-board memory, until they fly over a ground station, when they shall transmit a high amount of data in a short time. Thus, a high data rate is requested, but this is constrained by the power available on-board, in turn limited by the dimensions and masses of solar panels and batteries. However, not all data transmitted to ground are actually useful to the application. A solution can be obtained by endowing satellites with on-board processing capacity and Inter-Satellite Links (ISLs) to make them able to offload data processing to other satellites whenever they have not enough resources to accomplish the processing task. This would allow for an on-board extraction of the useful information from acquired images, leading to an increased efficiency in bandwidth usage and to a reduction of both the time needed to deliver information to the ground station and of the energy to be used by ground stations to process information. However, transmission, storage, and computational capacity available for in-orbit processing are valuable resources and could be not always available. For this reason, it is necessary to design strategies to appropriately allocate bandwidth and processing resources on satellites and to leverage the possibilities opened by the network of satellites made possible by ISLs, while optimizing a desired metric. In this thesis, I propose strategies to minimize operating costs of EO satellite networks, to save energy due to image processing on ground stations, and to support in-orbit training of machine learning models in a distributed manner to allow for faster accuracy convergence while reducing both the bandwidth and on-ground energy consumption with respect to centralized learning solutions. In particular, I first introduce and solve an optimization problem to allocate transmission, memory and processing resources to minimize the total operating cost to be paid for transferring, elaborating and storing EO data. Furthermore, since the proposed optimal strategy is NP-hard, I also define and evaluate two heuristics to be applied in real orbital scenarios, proving that they outperform benchmark solutions. Second, I introduce two optimal strategies to maximize energy saving on ground stations by leveraging at most in-orbit EO image processing. In particular, in the first strategy I do not take into account any constraint on the level of usage of on-board batteries to optimize operative life. Since this strategy results to be NP-complete, I also introduce a heuristic to be applied in real orbital scenarios. Instead, the second optimal strategy aims to maximize ground station energy saving while also optimizing satellite operative life by assuring that batteries are not discharged under a certain threshold. Results obtained with all the proposed strategies also provide useful insights on how the on-board CPU clock frequency has to be chosen to obtain optimal results, given limitations on energy available on satellites. Finally, I propose a communication strategy to support in-orbit distributed training of deep learning models by leveraging the satellite network made of both intra-orbital and inter-orbital ISLs. In particular, the proposed distributed learning strategy provides for satellites exchanging locally trained models within themselves, without having to lean on a central parameter server as it happens in federated learning schemes available in literature. Obtained results show that such strategy allows for reaching model convergence in a shorter time if compared to federated learning-based schemes.

Produzione scientifica

11573/1700793 - 2024 - Proposal and Investigation of a Lite Time Sensitive Networking solution for the support of Real Time Services in Space Launcher Networks
Fiori, T.; Lavacca, F. G.; Valente, F.; Eramo, V. - 01a Articolo in rivista
rivista: IEEE ACCESS (Piscataway NJ: Institute of Electrical and Electronics Engineers) pp. 10664-10680 - issn: 2169-3536 - wos: (0) - scopus: 2-s2.0-85182940882 (3)

11573/1706749 - 2023 - High-bandwidth technologies for next-generation launcher networks: a comparative analysis between TTethernet and Time Sensitive Networking (TSN)
Eramo, V.; Fiori, T.; Lavacca, F. G.; Valente, F. - 04b Atto di convegno in volume
congresso: 74th International Astronautical Congress, IAC 2023 (Baku (Azerbaijan))
libro: Proceedings of the International Astronautical Congress, IAC - ()

11573/1686907 - 2023 - Performance comparisons of flexible time triggered ethernet and TTEthernet technologies for space launcher networks
Eramo, V.; Fiori, T.; Lavacca, F. G.; Valente, F.; Albano, M.; Ciabuschi, S.; Cavallini, E. - 04b Atto di convegno in volume
congresso: 10th IEEE International Workshop on Metrology for AeroSpace, MetroAeroSpace 2023 (Milan; Italy)
libro: 2023 IEEE 10th International Workshop on Metrology for AeroSpace, MetroAeroSpace 2023 - Proceedings - (978-1-6654-5690-6)

11573/1682292 - 2023 - Performance Evaluation of a Launcher Network based on Commercial-Off-The-Shelf Ethernet Technology
Eramo, V.; Fiori, T.; Lavacca, F. G.; Valente, F.; Baiocchi, A.; Ciabuschi, S.; Albano, M.; Cavallini, E. - 04b Atto di convegno in volume
congresso: 2023 IEEE Aerospace Conference, AERO 2023 (usa)
libro: IEEE Aerospace Conference Proceedings - (978-1-6654-9032-0)

11573/1687679 - 2023 - Neural Graphs: An Effective Solution for the Resource Allocation in NFV Sites interconnected by Elastic Optical Networks
Eramo, V.; Lavacca, F. G.; Valente, F.; Filippetti, V.; Rosato, A.; Verdone, A.; Panella, M. - 04b Atto di convegno in volume
congresso: 23rd International Conference on Transparent Optical Networks, ICTON 2023 (rou)
libro: International Conference on Transparent Optical Networks - (979-8-3503-0303-2)

11573/1706556 - 2023 - Proposal and investigation of a next generation launcher communication system based on time sensitive networking technology
Favilli, L.; Modroño Maeztu, D.; Uribe, D.; Caramia, M.; Sagnelli, S.; Lavacca, F. G.; Fiori, T.; Valente, F.; Eramo, V. - 04b Atto di convegno in volume
congresso: 2023 European Data Handling and Data Processing Conference for Space, EDHPC 2023 (Juan Les Pins (France))
libro: Proceedings of the 2023 European Data Handling and Data Processing Conference for Space, EDHPC 2023 - ()

11573/1684398 - 2023 - Optimal bandwidth and computing resource allocation in low earth orbit satellite constellation for earth observation applications
Valente, F.; Eramo, V.; Lavacca, F. G. - 01a Articolo in rivista
rivista: COMPUTER NETWORKS (Elsevier BV:PO Box 211, 1000 AE Amsterdam Netherlands:011 31 20 4853757, 011 31 20 4853642, 011 31 20 4853641, EMAIL: nlinfo-f@elsevier.nl, INTERNET: http://www.elsevier.nl, Fax: 011 31 20 4853598) pp. 1-17 - issn: 1389-1286 - wos: WOS:001023332600001 (1) - scopus: 2-s2.0-85162072830 (2)

11573/1694157 - 2023 - Proposal and investigation of a processing and bandwidth resource allocation strategy in LEO satellite networks for earth observation applications
Valente, F.; Lavacca, F. G.; Eramo, V. - 04b Atto di convegno in volume
congresso: 2023 IEEE International Conference on Communications, ICC 2023 (Rome; Italy)
libro: IEEE International Conference on Communications - (978-1-5386-7462-8)

11573/1706657 - 2023 - A resource allocation strategy in earth observation orbital edge computing-enabled satellite networks to minimize ground station energy consumption
Valente, F.; Lavacca, F. G.; Eramo, V. - 04b Atto di convegno in volume
congresso: 36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023 (Miami (Florida))
libro: Proceedings of IEEE/IFIP Network Operations and Management Symposium 2023, NOMS 2023 - ()

11573/1706748 - 2023 - A resource allocation strategy in orbital edge Computing Earth observation satellite constellations to jointly save energy on ground and balance on-board energy consumption
Valente, F.; Lavacca, F. G.; Polverini, M.; Eramo, V. - 04b Atto di convegno in volume
congresso: 74th International Astronautical Congress, IAC 2023 (Baku (Azerbaijan))
libro: Proceedings of the International Astronautical Congress, IAC - ()

11573/1661990 - 2022 - A max plus algebra based scheduling algorithm for supporting time triggered services in ethernet networks
Eramo, V.; Fiori, T.; Lavacca, F. G.; Valente, F.; Baiocchi, A.; Ciabuschi, S.; Albano, M.; Cavallini, E. - 01a Articolo in rivista
rivista: COMPUTER COMMUNICATIONS (Butterworth Heinemann Publishers:Linacre House Jordan Hill, Oxford OX2 8DP United Kingdom:011 44 1865 314569, EMAIL: bhmarketing@repp.co.uk, INTERNET: http://www.laxtonsprices.co.uk, Fax: 011 44 1865 314569) pp. 85-97 - issn: 0140-3664 - wos: WOS:000910853600006 (2) - scopus: 2-s2.0-85142910470 (4)

11573/1655410 - 2022 - Flexible Time Triggered Ethernet: A Cost Efficient COTS-Based Technology for the Development of Launcher Networks
Eramo, V.; Valente, F.; Lavacca, F. G.; Fiori, T.; Papandrea, V.; Albano, M.; Ciabuschi, S. - 04b Atto di convegno in volume
congresso: 9th IEEE International Workshop on Metrology for AeroSpace, MetroAeroSpace 2022 (ita)
libro: 2022 IEEE 9th International Workshop on Metrology for AeroSpace, MetroAeroSpace 2022 - Proceedings - (978-1-6654-1076-2)

11573/1662851 - 2022 - Extension of the FTT-Ethernet Architecture for the support of Telemetry Messages in Launcher Networks
Eramo, V.; Valente, F.; Lavacca, F. G.; Fiori, T.; Papandrea, V.; Albano, M.; Ciabuschi, S.; Cavallini, E. - 04b Atto di convegno in volume
congresso: 2022 AEIT International Annual Conference, AEIT 2022 (ita)
libro: 2022 AEIT International Annual Conference, AEIT 2022 - (978-88-87237-55-9)

11573/1651010 - 2022 - Perspectives on AI-based Algorithms Applied to C-RAN Functional Splitting and Advanced Antenna System Problem
Lavacca, F. G.; Eramo, V.; Cianfrani, A.; Listanti, M.; Valente, F. - 04b Atto di convegno in volume
congresso: 2022 IEEE/IFIP Network Operations and Management Symposium, NOMS 2022 (Budapest; Hungary)
libro: 2022 IEEE/IFIP Network Operations and Management Symposium, NOMS 2022 - (978-1-6654-0601-7)

11573/1599940 - 2021 - Proposal and investigation of a convolutional and lstm neural network for the cost-aware resource prediction in softwarized networks†
Eramo, V.; Valente, F.; Catena, T.; Lavacca, F. G. - 01a Articolo in rivista
rivista: FUTURE INTERNET (Basel : MDPI) pp. 1-16 - issn: 1999-5903 - wos: WOS:000737187800001 (0) - scopus: 2-s2.0-85121477331 (0)

11573/1606034 - 2021 - AI-based resource prediction in network function vrtualization architectures
Eramo, V.; Valente, F.; Lavacca, F. G.; Catena, T. - 04b Atto di convegno in volume
congresso: 12th International Conference on Information and Communication Technology Convergence, ICTC 2021 (Jeju Island; Republic of Korea)
libro: International Conference on ICT Convergence - (978-1-6654-2383-0)

11573/1608803 - 2021 - Cost-aware and aI-based resource prediction in softwarized networks
Eramo, V.; Valente, F.; Lavacca, F. G.; Catena, T. - 04b Atto di convegno in volume
congresso: 2021 AEIT International Annual Conference, AEIT 2021 (Milan; Italy)
libro: 2021 AEIT International Annual Conference, AEIT 2021 - (978-88-87237-50-4)

11573/1159441 - 2018 - Simulation and experimental evaluation of a flexible time triggered ethernet architecture applied in satellite nano/micro launchers
Eramo, V.; Lavacca, F. G.; Valente, F.; Pisculli, A.; Caporossi, S. - 01a Articolo in rivista
rivista: AEROSPACE (Basel : MDPI) pp. 1-19 - issn: 2226-4310 - wos: WOS:000448392600018 (7) - scopus: 2-s2.0-85053753250 (12)

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma