Mission goal is to build on previous success and provide the international scientific community access to an expanded scope of space-based edge computing, AI and machine learning capabilities
Hewlett Packard Enterprise (NYSE: HPE) announced it has sent a third iteration of the HPE Spaceborne Computer, built from commercial off-the-shelf (COTS) servers, to the International Space Station (ISS) via a Northrop Grumman Commercial Resupply Services mission, contracted by NASA, aboard a SpaceX Falcon 9 rocket.
The goal of HPE Spaceborne Computer-2’s latest trip is to build upon the system’s previous success while expanding the scope and complexity of data center-level processing and high performance computing (HPC) that can be done in space, including artificial intelligence (AI) and machine learning (ML) workloads. This configuration of the award-winning1 HPE Spaceborne Computer, based on HPE Edgeline and ProLiant servers, has been updated with over 130 TB of flash-based storage from KIOXIA, the most storage to ever travel to the space station on a single mission. This includes four KIOXIA 960 GB RM Series Value SAS, eight 1,024 GB XG Series NVMe and four 30.72 TB PM6 Enterprise SAS SSDs. The additional flash memory storage will make it possible to run new types of applications and conduct research using larger data sets2 through the ISS National Laboratory.
Improvements to HPE Spaceborne Computer-2 also include an updated operating system, NASA space flight support software and new system security. Once on board the space station, the health and status of these technologies will be monitored daily to assess the performance in the harsh conditions of space.
Advancing research on Earth and in space
After installation of HPE Spaceborne Computer-2 is completed on the space station, the system will be used by researchers to advance innovation and save time. Traditionally, data gathered in space was collected aboard the research outpost and sent to Earth for processing. An onboard supercomputer enables data to be evaluated in low Earth orbit in near-real time, making it possible to achieve a 30,000 times reduction in download size3 by only transmitting the data output, or insight, to Earth instead, therefore drastically reducing download times.
Research slated for HPE Spaceborne Computer-2 includes a federated learning (FL) experiment that will independently train ML models and inference engines that were originally created on the Cloud. The experiment will be collaborated on and operated by cloud service providers with the dual-intent to contribute to ML training models used on Earth and maintain an up-to-date AI inference engine in space.
HPE will once again invite the public to submit proposals to perform experiments on the HPE Spaceborne Computer-2 through the ISS National Laboratory.
Additional information about submitting proposals can be found here.
- HPE Spaceborne Computer has been awarded the NASA Group Achievement Award in March 2023, the NASA Space Flight Awareness Award in August 2022 for the EVA Glove Inspection Team, the NASA Exceptional Technology Achievement Medal in August 2019, and the ISS R&D Innovation Award for Technology Development and Demonstration in July 2018.
↩︎ - Previous workloads, including DNA sequence data, high resolution imagery and reference databases, were limited to 2TBs. ↩︎
- Based off data collected in March 2022 for the transmission of 2.8 GBs of life sciences data that took approximately 18 hours to transmit from the International Space Station to Earth via the traditional “collect-and-forward” model, compared to on-board processing via HPE Spaceborne Computer-2 that resulted in an insight file size of 92KBs that was transmitted to Earth in approximately 2 seconds. ↩︎
