H2020Индивидуална стипендия2021–2023

MENESIS · Memristor-Enabled NEuromorphic System for Intelligence in Space

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2021-09-01 → 2023-08-31
Финансиране от ЕС: 212 934 €
Участници: 1
Схема: MSCA-IF

Линиите свързват координатора с партньорите.

Накратко на български

Мемристорите са ултратънки електронни компоненти, които позволяват работата на изкуствен интелект директно в космоса. Те са устойчиви на радиация, което намалява зависимостта на сателитите от наземни сървъри и ограничава разходите за енергия и поддръжка.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Memristor-Enabled NEuromorphic System for Intelligence in Space

Today's technology relies on transistor-based devices for all kinds of computation power. However, the transistor is not a rad-hard element due to its bulky architecture, allowing a huge amount of dose to be deposited into it; this results in electrical failure in computing systems. Hence, up to now, we do not have reliable artificial intelligence (A) accelerators deployed to space due to this reliability reason. This challenge makes us rely a lot on the ground station (cloud server) to compute the data streamed from the satellite. Cloud servers are power-hungry installations with high costs of operation and maintenance; the increased need for AI computation would make us keep relying on building new servers in the future, and this will eventually increase carbon and silicon footprint. The project aims to design rad-hard ultra-thin memristor devices as a novel computing element enabling AI computation in space for an efficient data stream. The architecture of the device is so thin that most of the high-energy radiation passes through the device, limiting the undesired energy deposition.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

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.

Оригинален текст от CORDIS (на английски).

Участници

UNIVERSITY OF SOUTHAMPTON · SOUTHAMPTONКоординаторОбединеното кралство