Register / Data centre / EIR-1837
← Back to the list
Data centreUnited KingdomEIR-1837

Faulty UPS knocks out power at London Docklands data centre

Aug 2020Published 2 Oct 2026Updated 13 Oct 2026Responsible editor: Chief Editor

Estimated damageEstimated by the register's adjusterHow? Know the real figure?
Figure hidden: shown to subscribersMedium confidence
out of service for about •• daysShown in the record →Full estimate
From the recordRoot cause hiddenFailed part hidden

Companies named in the reporting of this entry (being named is not a finding of fault): Equinix

On 18 August 2020 a power outage hit Equinix's LD8 data centre in the Docklands area of London, which hosts equipment used by the London Internet Exchange (LINX) and many internet providers. Equinix said the root cause was a faulty uninterruptible power supply (UPS) system. The Register reported, citing a reader-relayed Equinix update, that the fault was an output static switch failure on a Galaxy UPS system supporting levels 1 to 4 of buildings 8 and 9, and that the resulting fire alarm led to the building being evacuated.

These details were not confirmed in an official statement. The Register reported that there was no fire. Giganet said both its A and B power feeds to one of its racks were lost. LINX reported that its equipment at the site lost power, and Giganet cited LINX's figure that around 150 of its members were affected. Equinix first publicly acknowledged the outage around midday, some eight hours after it began. Services returned unevenly through the day, and Equinix said at about 9:50pm BST that all services had been resolved.

Equinix attributed the outage to a faulty UPS system. The Register reported that a fire alarm activation led to a wider shutdown of levels 1 to 4 under safety procedures. Giganet said its equipment was dual fed from the data centre's A and B supplies yet both were lost, and it suspected a lack of power resiliency. Customers reported that the access control system was also offline, which made it harder to reach the site. Giganet also speculated that knock-on effects on carrier networks could follow as carriers restored racks and routing tables changed.

  1. Confirm that dual power feeds are genuinely independent upstream of the UPS, because a single UPS fault can remove both.
  2. Plan fire alarm and safety shutdown responses so that they do not unnecessarily power down wide areas of a facility during an electrical fault.
  3. Keep customers informed early and regularly during a major incident, since the first public statement came about eight hours after the outage began.
  4. Ensure access control and site entry systems have backup power so that engineers can reach equipment during an outage.

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

Published 2026-10-02. 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 Kingdom, by year, free with a credit (PNG).

Data centre incidents in the United Kingdom: 21 entries, with a free alert for the next one.

See UPS and battery room fires at data centres.

Browse the full register or submit an incident.