- Community Home
- >
- Company
- >
- Advancing Life & Work
- >
- HPE announces 3-year project to use AI and predict...
Categories
Company
Local Language
Forums
Discussions
Forums
- Data Protection and Retention
- Entry Storage Systems
- Legacy
- Midrange and Enterprise Storage
- Storage Networking
- HPE Nimble Storage
Discussions
Discussions
Discussions
Forums
Forums
Discussions
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
- BladeSystem Infrastructure and Application Solutions
- Appliance Servers
- Alpha Servers
- BackOffice Products
- Internet Products
- HPE 9000 and HPE e3000 Servers
- Networking
- Netservers
- Secure OS Software for Linux
- Server Management (Insight Manager 7)
- Windows Server 2003
- Operating System - Tru64 Unix
- ProLiant Deployment and Provisioning
- Linux-Based Community / Regional
- Microsoft System Center Integration
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Community
Resources
Forums
Blogs
- Subscribe to RSS Feed
- Mark as New
- Mark as Read
- Bookmark
- Receive email notifications
- Printer Friendly Page
- Report Inappropriate Content
HPE announces 3-year project to use AI and predictive analysis for smarter, greener data centers
By Curt Hopkins, Managing Editor, Hewlett Packard Labs
Hewlett Packard Enterprise, with the help of Hewlett Packard Labs, is entering into a three-year collaboration with U.S. Department of Energyโs National Renewable Energy Laboratory (NREL) to optimize power, cooling, and IT operations for smarter and greener datacenters for the exascale era.
This AI Ops R&D collaboration will focus on developing artificial intelligence and specifically machine learning tech to automate and improve operational efficiency, including resiliency and energy usage in data centers.
The project is part of a three-year collaboration that introduces monitoring and predictive analytics to power and cooling systems in NRELโs Energy Systems Integration Facility HPC Data Center.
According to the press release, HPE and NREL are using more than five yearsโ worth of historical data, which total more than 16 terabytes of data, collected from sensors in NRELโs supercomputers, Peregrine and Eagle, and its facility, to train models for anomaly detection to predict and prevent issues before they occur.
โWe 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 datacenters as they continue to scale power and performance,โ says Mike Vildibill, vice president of Advanced Technologies Group at HPE.
The collaboration will also deal with future water and energy consumption in data centers, which in the U.S. alone will reach approximately 73 billion kilowatt hours and 174 billion gallons of water by 2020. Early results based on models trained with historical data have successfully predicted or identified events that previously occurred in NRELโs data center, demonstrating the promise of using predictive analytics in future datacenters.
Labsโ role will be to apply machine learning algorithms to the NREL data center, combining the data collected from the IT equipment with the facilities information drawn from the center's power and cooling infrastructure. This will produce a comprehensive view of the entire supercomputer datacenter ecosystem
โLabs has a long history of research in the use of disparate sources of data for anomaly detection and system optimization," says Cullen Bash, vice president of R&D for the organization.. "Partnering with NREL on AI Ops affords us a great opportunity to explore the application of this research to solving important problems like improving the efficiency, resiliency, and sustainability of data centers."
The AI Ops project issues from HPEโs R&D work on PathForward, an exascale computing program backed by the DOE. Applying AI-driven operations to an exascale supercomputer, which will run at a thousand times the speed of todayโs systems.
To take a closer look, visit HPE booth 1325 at Supercomputing 2019 in Denver, Colorado, November 17-22.
For additional information on this collaboration, read the official press release.
- Back to Blog
- Newer Article
- Older Article
- MandyLott on: HPE Learning Partners share how to make the most o...
- thepersonalhelp on: Bridging the Gap Between Academia and Industry
- Karyl Miller on: How certifications are pushing women in tech ahead...
- Drew Lietzow on: IDPD 2021 - HPE Celebrates International Day of Pe...
- JillSweeneyTech on: HPE Tech Talk Podcast - New GreenLake Lighthouse: ...
- Fahima on: HPE Discover 2021: The Hybrid Cloud sessions you d...
- Punit Chandra D on: HPE Codewars, India is back and it is virtual
- JillSweeneyTech on: An experiment in Leadership โ Planning to restart ...
- JillSweeneyTech on: HPE Tech Talk Podcast - Growing Up in Tech, Ep.13
- Kannan Annaswamy on: HPE Accelerating Impact positively benefits 360 mi...