5 ways to increase power system availability in data centers

© 2015 Eaton. All Rights Reserved..

Five ways to increase power system availability

© 2015 Eaton. All Rights Reserved.. 2

Data centers are a cornerstone of

our always-connected lives and a

strategic asset, making reliability and

uptime more important than ever.

However, businesses are vulnerable

to a variety of threats, some out of

their control.


A power system design flaw or failure

in the electric grid can bring down

even the most sophisticated data

center.

Here are five best practices to help

mitigate your exposure to power-

related downtime.


1. Focus on long-term value

Challenge: Short- and long-term priorities are often in

conflict during data center construction or renovation.

• Those building the facility are asked to hold down

costs and shorten completion times.

• Those operating the facility want quality equipment

that meets operating specifications.


Best practice: Decision makers should make sure no one

trades long-term risk for short-term savings. And they should

communicate the importance of adhering to original operating

specifications, even if it means spending a little more.

1. Focus on long-term value


2. Consider ease of repair and reliability

Challenge: Availability and reliability are sometimes used

interchangeably—but the two have distinct meanings.

Repair time is a big factor when assessing system

availability. For example, a power supply may rarely

experience downtime (highly reliable), but not be highly

available because it has a high mean time to repair.


Best practice: When evaluating power system

components, look for products that are highly reliable

and quickly repairable. In particular, investigate how

swiftly and effectively a given power system

manufacturer can service products.

2. Consider ease of repair and reliability


3. Implement monitoring and proactive diagnostics

Challenge: Few systems fail without warning, except in

disasters. It’s just that their warnings often go unheeded

since the monitoring systems in place are reactive in

nature. If facilities managers aren’t monitoring the right

performance indicators, they may know nothing about

an impending breakdown until after it happens.


Best practice: The latest enterprise management

products can help with monitoring and proactively

maintaining mission-critical equipment. Facilities

departments need to have work processes in place

for consulting the software and responding swiftly to

signs of danger.

3. Implement monitoring and proactive diagnostics


4. Adopt an appropriate power system topology

Challenge: Power system topology has a major

impact on procurement costs, operational

expenses, reliability and average repair times.

The more redundancy you incorporate into a data

center, the more it will cost you to build and run it.

But, it will also recover faster from an outage.


Best practice: There is no single

correct answer when it comes to

selecting a power system topology.

Match your power system to your

circumstances and needs, based on

the criticality of the IT applications

the data center houses.

4. Adopt an appropriate power system topology


5. Audit your power systems

Challenge: Most data center

managers think they know what

their power systems are capable of

delivering. Far fewer, actually

know. Only by auditing power

systems and the operational

processes that support them on a

regular basis can you establish

your data center’s maximum load

parameters concretely.


Best practice: Audit power systems

thoroughly and regularly. Update any

building drawings, schematics,

operating manuals, etc., as facilities

equipment is replaced or upgraded.

5. Audit your power systems


Thank you!

Learn more at Eaton.com/PowerQuality

5 ways to increase power system availability in data centers

Technology