Register / Data centre / EIR-2296
← Back to the list
Data centreUnited StatesEIR-2296

Utility cable fault drains UPS and blacks out National Park Service data centre in Denver

Jan 2014Published 12 Oct 2026Responsible editor: Chief Editor

Estimated damageModelled by the register's adjusterHow? Know the real figure?
Figure hidden: shown to subscribersLow confidence
out of service for about •• daysShown in the record →Full estimate

Companies named in this entry: Microsoft, Xcel Energy

On 1 January 2014, at about 3pm, the National Park Service data centre in Denver, Colorado, lost utility power and went completely dark. According to a note posted on the agency's website, the outage was caused by an underground cable that had either suffered water seepage or been affected by rodents. The agency's note blamed the local power provider, Xcel Energy. The building's uninterruptible power supplies (UPS) kept the facility running for about 30 minutes after utility power was lost.

The note made no mention of backup generators. Power was restored about two hours after the building went dark. The agency's note said the hardware in the data centre had been damaged and that about a third of the data had been corrupted. The note also said Microsoft had advised that restoring from backup tapes alone would not resolve the problem and that, in most cases, the environment would need to be rebuilt.

The agency's note attributed the utility outage to an underground cable affected by water seepage or rodent invasion. The way the two utility power feeds were re-energised was cited in the note as one reason for the damage. An automatic shutdown process was cited by the agency as a cause of file corruption. High temperature in the data centre before shutdown was cited as a further reason for the damage. The UPS gave only about 30 minutes of runtime, and no backup generators were mentioned.

  1. Test and document how facility loads transfer between utility feeds and UPS, and how feeds are re-energised after an outage, so that restoration does not add damage.
  2. Confirm that backup generation exists and is fuelled where UPS runtime, here about 30 minutes, would not cover a utility outage of this length.
  3. Set and test automatic shutdown and temperature thresholds so that equipment and data are protected in an orderly way, and keep backups that can restore a system without a full rebuild.

More lessons on outages, backup supply and restoration, from every incident on the register.

Published 2026-10-12. Written from public reporting. Descriptive, not investigative. See the data accuracy disclaimer.

See the register's stories first in Google: add it as a preferred source.

Chart to reuse with this story: Data centre incidents in the United States, by year, free with a credit (PNG).

Data centre incidents in the United States: 50 entries, with a free alert for the next one.

Browse the full register or submit an incident.