August 6, 2022

Amazon sent an AWS Snowcone device into orbit aboard the ISS

Amazon.com Inc. revealed today at its re:Mars conference that it has launched one of its AWS Snowcone compute and storage devices into orbit, as part of Axiom Space Inc’s latest mission to the International Space Station.

Snowcones are special devices designed to work in rugged, mobile and disconnected environments, bringing on-premises processing capabilities with multiple layers of encryption. Amazon said the one sent into space was a standard off-the-shelf device that had gone through months of testing by the National Aeronautics and Space Administration to get it certified.

Amazon said the Snowcone underwent five months of NASA thermal, vacuum, acoustic and vibration testing before it could be approved for the mission. However, no radiation test was necessary, as the Snowcone was deployed in a shielded environment within the ISS.

Once the device was delivered to the space station, it was then connected to the ISS systems. Later, the team behind the project downloaded an object detection machine learning model and ran it for the duration of Axiom’s mission.

The Snowcone experiment was just one of 25 carried out by Axiom as part of its mission. Clint Crosier, director of aerospace and satellites at AWS, explained that as part of the mission, astronauts had to take photos of all the new equipment on board the ISS, as well as everything that was returned to Earth. The object detection model played a role in cataloging each of these items.

The mission was more of a demonstration, but the results are useful. In space, bandwidth is limited because the ISS has minimal infrastructure. Amazon explained that traditional computing resources are bound by human spaceflight conditions, while data transport lanes are heavily congested.

This means that astronauts usually have to send the data and images they collect back to Earth for processing. It’s not so bad in near-Earth orbit, but on future missions to the Moon and Mars there will be significant delays in sending data home given the huge distances involved.

As such, having state-of-the-art computing capability on board could prove extremely useful. Thus, lessons learned from this mission can be applied to subsequent missions, Amazon said.

“AWS is committed to eliminating traditional barriers encountered in a space environment, including latency and bandwidth limitations,” Crosier said. “Performing image analysis close to the source of the data, in orbit, is a huge benefit as it can improve response times and allow the crew to focus on other critical tasks. This demonstration will help our teams assess how we can make edge processing available to crews for future space missions.

Photos: SpaceX-Imagery/Pixabay, Amazon

Show your support for our mission by joining our Cube Club and our Cube Event community of experts. Join the community that includes Amazon Web Services and Amazon.com CEO Andy Jassy, ​​Dell Technologies Founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many other luminaries and experts.