Google has launched a refrigerator-sized satellite carrying four Tensor Processing Units (TPUs) as part of Project Suncatcher, its research effort to test AI computing in space.
The satellite will run a version of Google’s Gemma AI model for about 15 minutes at a time because of heat limits. Google will test how its chips handle launch stress, radiation, and extreme temperatures in orbit.
Google Wants AI Data Centers in Space
The company eventually wants to build clusters of satellites that work together as orbital data centers powered by solar energy.
Each future satellite could carry dozens of TPUs and communicate with other satellites and Earth using lasers. Google plans to launch two more satellites next year to test those connections.
The current prototype was developed with satellite company Planet and launched aboard a SpaceX rocket. The mission is expected to operate for about a year.
Major Challenges Remain
Cooling is one of the biggest problems because traditional air- and water-based cooling does not work in space. Google is testing pipes and radiators to remove heat from the chips.
Repairs would also be much harder than in normal data centers, while launches remain expensive.
Google also says space-based data centers are unlikely to become cheaper than terrestrial facilities within the next five years.
Other companies are exploring similar ideas. Starcloud previously launched an Nvidia H100 chip into space, while SpaceX has said it could begin deploying orbital AI compute satellites as early as 2028.
Google describes Project Suncatcher as a long-term “moonshot” rather than something expected to replace Earth-based data centers soon.
The post Google Tests Running AI in Space With New Satellite appeared first on ProPakistani.
