ABSTRACT
This chapter details how modular data center technology can be used to expand an existing compute resource. It describes NASA’s requirements for supercomputing and how resources were provided prior to the integration of the Electra module-based system. NASA has increasingly relied on high-performance computing (HPC) resources for computational modeling, simulation, and data analysis to meet the science and engineering goals of its missions in space exploration, aeronautics, and Earth and space science. The High-End Computing Capability project predicts that NASA’s requirements for supercomputing capabilities will continue to grow exponentially over time, as the agency leverages HPC to pursue its challenging missions. The modular data center is controlled by the programmable logic controller, which queries sensors throughout the module and makes adjustments to maintain the internal environment within the set operating parameters. NASA Advanced Supercomputing teams have developed several processes to minimize the number of full system outages and maximize availability.
