If you have seen the 2015 Matt Damon-starrer The Martian, you will remember how at one point in the movie his character tries to get in touch with Nasa after it is discovered that he was left behind, presumed dead, on Mars but is safe and sound. He uses the remaining operating parts from the famed Pathfinder probe to get in touch with the space agency. While he manages to communicate with earth, there is a significant time lag before any message reaches Nasa or comes back to Damon’s character, Mark Watney.
What this pop culture reference tells us is that computing in space and communicating back to Earth are tricky propositions. Four years ago, the Spaceborne Computer, a proof-of-concept developed by Hewlett Packard Enterprise (HPE) and launched in partnership with Nasa, was sent to operate on the International Space Station (ISS) for a one-year mission. The goal of this computing system was to test if affordable, commercial off-the-shelf servers used on earth, but equipped with purposefully-designed software-based hardening features, could withstand the stress of a rocket launch to space, and once there, seamlessly operate on the space station. The computer successfully operated for more than a year.
Now, HPE is launching the next iteration of this project, Spaceborne Computer-2 (SBC-2), an edge computing system that will offer astronauts on the ISS twice as much computing speed. “The most important benefit to delivering reliable in-space computing with Spaceborne Computer-2 is making real-time insights a reality. Space explorers can now transform how they conduct research based on readily available data and improve decision-making,” says Mark Fernandez, principal investigator for Spaceborne Computer-2 and solution architect, Converged Edge Systems at HPE.
The computer is scheduled to be launched into orbit on the 15th Northrop Grumman Resupply Mission (NG-15) on 20 February. It will be available for use on the International Space Station for the next 2-3 years. “The possibilities of on-board computers are fascinating to me… I have a saying: ‘self-sufficient computing enables self-sufficient (space) explorers’,” Fernandez said during a press call on Thursday.
So, what exactly is ‘edge computing’? It is computing that is done at or near the source of the data. For instance, if astronauts on the space station 3D-print an object, researchers back here on earth run simulations and routines to see if it’s safe to use the object. Now, with SBC-2, astronauts will be able to run these tests and routines on the ISS, saving them valuable mission time.
Fernandez explains how the new computing system, which will also have artificial intelligence and machine learning capabilities, will help astronauts with research activities both inside and outside the space station. Inside the station, the computer will help with research conducted in areas of healthcare, life sciences and manufacturing (3-D printing is a part of this). Outside, SBC-2 will help with data & image processing and remote sensing.
The space station is dotted with hundreds of sensors from Nasa and other international space organizations. These sensors collect tonnes of data, which require a significant amount of bandwidth to send to earth to be processed. With in-space edge computing, researchers can process on-board images, signals and other data on everything from air quality -- by measuring emission levels and other pollutants in the atmosphere -- to tracking objects moving in space and in the atmosphere.
Apart from that, the computer will also come equipped with graphic processing units or GPUs to process image-intensive data, which require higher image resolution such as shots of polar ice caps on earth or medical X-rays. Fernandez says SBC-2 will enable astronauts to eliminate longer latency and wait times associated with sending data to-and-from earth to tackle research in different areas.