Dr. Cliff Federspiel, Ph.D.
Predictive Analytics for Data Center Thermal Risk and Reliability Management . by Dr. Cliff Federspiel, Ph.D., Speaker
Real-time operational data in combination with analytics has the power to reveal previously unseen and unknown weaknesses in a data center. Specifically, high temperature events can trigger expensive, emergency truck rolls or SLA violations.
This presentation will describe a means of precisely determining the functional cooling redundancy of a facility, show statistical analysis that correlates poor redundancy with high temperature events, and share tools that identify and suggest remediation for rooms – and facilities – at risk. Use of cooling analytics is an important aspect of operational excellence, and is a competitive differentiator for datacenter operators.
By combining industry standards for design redundancy and equipment performance with data from a properly monitored data center, it is possible to determine a “score” or metric that identifies low/poor redundancy. A low score can be caused by three things: underperforming or non-performing equipment, operator issues, and IT problems. Equipment problems are flagged when cooling units aren’t responding to commands or are underperforming according to ASHRAE 90.1 or corporate standards. Operator issues usually involve manual overrides – both known and unknown - that often reduce cooling capacity in a complex environment. IT problems are identified as overloaded rooms, or rooms in which IT load is present but not accomplishing its purpose, i.e. decommissioned but still-powered IT equipment. Individually and together, these factors contribute to compromised redundancy, lower reliability, and higher risk.
The presentation will describe the science behind the metrics, stepping through a statistical analysis based on data from hundreds of facilities. The analysis projects that rooms with scores of 0-2 are likely to experience a high temperature event, while rooms with scores below zero (no redundancy) are significantly more likely to experience a high temperature event. Such events result in expensive, emergency truck rolls and painful middle-of-the-night calls. A tool showing the scoring and identifying specific issues that contribute to the score, along with methods to remediate those issues, will be demonstrated.
Choose category and click GO to search for thermal solutions
|Subscribe to Qpedia|
a subscription to qpedia monthly thermal magazine from the media partner advanced thermal solutions, inc. (ats) will give you the most comprehensive and up-to-date source of information about the thermal management of electronics
|Subscribe to coolingZONE|
|Submit Press Release|
if you have a press release and would like it to be published on coolingzone please upload your pr here
|Media Partner, Qpedia|
|Heat Transfer Calculators|