HPE partners with NREL
16/03/2020
The National Renewable Energy Laboratory (NREL) is partnering with Hewlett Packard Enterprise (HPE) to develop artificial intelligence (AI) and machine learning (ML) technologies for efficient data centre operation.The US Department of Energy (DOE) laboratory will share more than five years’ worth of historical data from sensors within its supercomputers, Peregrine and Eagle, and also in its facility, which the company claims to be one of the world’s most efficient data centres. This information will help other organisations to optimise their own operations, claims the National Renewable Energy Laboratory.
The three-year-long AIOps reserch and development (R&D) collaboration has access to more than 16 TB of data from the Energy Systems Integration Facility (ESIF) high-performance computing (HPC) Data Center.
ESIF had an average power usage effectiveness (PUE) of just 1.032 in 2017 and currently captures 97% of the waste heat from its supercomputers to warm nearby office and laboratory space.
The Group claims that early results based on models trained with historical data were able to predict or identify events that previously occurred in NREL’s data centre. The focus is on monitoring energy usage to optimise energy efficiency and sustainability as measured by metrics such as PUE, water usage effectiveness (WUE) and carbon usage effectiveness (CUE).
The project, which was spun out of the DOE’s exascale-focused PathForward initiative, will focus on four key areas:
- Monitoring: collecting, processing and analysing vast volumes of IT and facility telemetry from disparate sources before applying algorithms to data in real time;
- Analytics: big data analytics and machine learning will be used to analyse data from various tools and devices spanning the data centre facility;
- Control: algorithms will be applied to enable machines to solve issues autonomously, as well as to intelligently automate repetitive tasks and perform predictive maintenance on both the IT and the data centre facility; and
- Data centre operations: AIOps will evolve to become a validation tool for continuous integration (CI) and continuous deployment (CD) for core IT functions that span the modern data centre facility.
