In a recent survey conducted by the Ponemon Institute, 95% of data center operators surveyed admitted to experiencing an unplanned outage in the last 24 months. Of those outages, respondents indicated that a full 80% could have been prevented.
Data centers fail for a multitude of reasons, including human error, equipment failure and environmental issues. However, the majority of data center outages fall within several main categories.
Leading causes of data center outages are (ranked from most common to least common):
1. Human error
2. UPS & battery systems
3. Genset & transfer switch systems
4. Mechanical and moving parts, such as belts and pumps
5. Breaker coordination
7. Harmonic Filters
8. Water incursion
All these root causes have a common thread: Operational and equipment issues which could generally have been avoided through appropriate maintenance systems and processes. So, how can data center operators ensure that mere maintenance issues don’t spiral into outages?
ABB recently provided an insightful white paper to address this issue with five lessons learned froma major data center outages. Find the white paper embedded below.