Summary
There are currently 2666 active satellites orbiting the Earth to support the world’s telecommunication, navigation, exploration, and security systems. These satellites downstream a deluge of data to the Earth where most of the processing/analysis is performed, due to the lack of reliable on-board computing capabilities at the satellites. The introduction of Artificial Intelligence (AI) at earth stations has allowed us to process such big-data in more efficient ways, overall, boosting our capabilities. Nonetheless, the key bottleneck remains – better progress cannot be realized without addressing the bandwidth constraint. Henceforth, all of these data are then relayed to the cloud servers to be processed by artificial intelligence (AI) algorithms and, hereafter, feed the end-user meaningful information. Henceforth, nowadays data transmission and governance are inefficient. Moreover, if we do not revolutionize the way we process our data, we have to continuously dependent on cloud technology, which will be a major problem in the future. Besides its technical disadvantages (risk of data confidentiality, prone to network congestion, etc.), a cloud system is power-hungry, high operational and maintenance cost, and expanding a new server will consume a large area of land. These aspects significantly contribute to the increase of carbon and silicon footprint that damage the environment. The project proposes a disruptive concept by bringing the AI itself available on the sky, where the satellites have the autonomous computation power to differentiate signal to noise before transmitting the data to Earth, directly to the end-user. This work exploits an emerging memristor technology for making AI hardware accelerator as the “computing element” on board the satellite. The architectonic of memristor not only delivers lightweight, low power, fast, and dense AI chip, but also rad-hard; these are the crucial factors that will keep the cost of deployment to space minimum.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101029535 |
| Start date: | 01-09-2021 |
| End date: | 31-08-2023 |
| Total budget - Public funding: | 212 933,76 Euro - 212 933,00 Euro |
Cordis data
Original description
There are currently 2666 active satellites orbiting the Earth to support the world’s telecommunication, navigation, exploration, and security systems. These satellites downstream a deluge of data to the Earth where most of the processing/analysis is performed, due to the lack of reliable on-board computing capabilities at the satellites. The introduction of Artificial Intelligence (AI) at earth stations has allowed us to process such big-data in more efficient ways, overall, boosting our capabilities. Nonetheless, the key bottleneck remains – better progress cannot be realized without addressing the bandwidth constraint. Henceforth, all of these data are then relayed to the cloud servers to be processed by artificial intelligence (AI) algorithms and, hereafter, feed the end-user meaningful information. Henceforth, nowadays data transmission and governance are inefficient. Moreover, if we do not revolutionize the way we process our data, we have to continuously dependent on cloud technology, which will be a major problem in the future. Besides its technical disadvantages (risk of data confidentiality, prone to network congestion, etc.), a cloud system is power-hungry, high operational and maintenance cost, and expanding a new server will consume a large area of land. These aspects significantly contribute to the increase of carbon and silicon footprint that damage the environment. The project proposes a disruptive concept by bringing the AI itself available on the sky, where the satellites have the autonomous computation power to differentiate signal to noise before transmitting the data to Earth, directly to the end-user. This work exploits an emerging memristor technology for making AI hardware accelerator as the “computing element” on board the satellite. The architectonic of memristor not only delivers lightweight, low power, fast, and dense AI chip, but also rad-hard; these are the crucial factors that will keep the cost of deployment to space minimum.Status
SIGNEDCall topic
MSCA-IF-2020Update Date
28-04-2024
Images
No images available.
Geographical location(s)
Structured mapping
