Satlyt, a startup building software to turn existing satellites into distributed computing networks, completed a successful orbital test earlier this month after 13 months of development work. The test, run with the University of Houston on a NASA-funded research project, showed the software spreading tasks across computers in orbit according to communication links and available compute; it used a simulated network of four computers, four users and eight services.
Founder Rama Afullo said users will only need to define permissions, priorities and operating limits while the software makes scheduling decisions inside those bounds. Satlyt's software is already running on three satellites, and this was the first demonstration of the multi-satellite sharing concept, though NASA has not selected the company for any mission or deployment.
Orbital computing is attractive because downlinking raw data is slow and expensive, so processing images and sensor data in space can cut latency and bandwidth needs. If the approach works at scale it would let satellite operators sell spare compute, putting startups like Satlyt in competition with much larger space data centre efforts.

Satlyt, a startup building software to turn existing satellites into distributed computing networks, completed a successful orbital test earlier this month after 13 months of development work. The test, run with the University of Houston on a NASA-funded research project, showed the software spreading tasks across computers in orbit according to communication links and available compute; it used a simulated network of four computers, four users and eight services.

Founder Rama Afullo said users will only need to define permissions, priorities and operating limits while the software makes scheduling decisions inside those bounds. Satlyt's software is already running on three satellites, and this was the first demonstration of the multi-satellite sharing concept, though NASA has not selected the company for any mission or deployment.

Orbital computing is attractive because downlinking raw data is slow and expensive, so processing images and sensor data in space can cut latency and bandwidth needs. If the approach works at scale it would let satellite operators sell spare compute, putting startups like Satlyt in competition with much larger space data centre efforts.

πŸ“° Source: News Source
techcrunch.com β†—
Was this article useful?