Hewlett Packard Enterprise (HPE) introduced a collaboration with the U.S. Department of Energy’s National Renewable Energy Laboratory (NREL) intending to develop Artificial Intelligence (AI) and Machine Learning (ML) technologies. It helps automation and improving operational efficiency, including resiliency and energy usage, in data centers for the exascale era. This 3-year project covers monitoring and predictive analytics to power and cooling systems in NREL’s Energy Systems Integration Facility (ESIF) HPC Data Center.
Main goal is to reduce energy consumption
NREL aims to create and implement new approaches that reduce energy consumption and lower operating costs as a world leader in advancing energy efficiency and renewable energy technologies. HPE and NREL are partners for more than five years’ worth of historical data collected from sensors in NREL’s supercomputers, Peregrine, and Eagle.
The project will use open source software and libraries such as TensorFlow, NumPy, and Sci-kit to develop machine learning algorithms. The project will focus on monitoring, analytics, control, data center operations. To optimize energy efficiency and sustainability, they will use in monitoring key metrics such as Power Usage Effectiveness (PUE), Water Usage Effectiveness (WUE), and Carbon Usage Effectiveness (CUE).
Maintaining more efficient supercomputing data centers
“We are passionate about architecting new technologies that are impactful to powering the next era of innovation with exascale computing and its extent of operational needs. We believe our journey to develop and test AI Ops with NREL, one of our longstanding and innovative partners, will allow the industry to build and maintain smarter and more efficient supercomputing data centers as they continue to scale power and performance.”
Manager for Data, Analysis and Visualization Group, NREL, Kristin Munch talked about the collaboration:
“Our research collaboration will span the areas of data management, data analytics and AI/ML optimization for both manual and autonomous intervention in data center operations. We’re excited to join HPE in this multi-year, multi-staged effort and we hope to eventually build capabilities for an advanced smart facility after demonstrating these techniques in our existing data center.”