It is an ongoing undertaking; data
centers must become more efficient, reliable and agile to support future
business growth. Yet the problems of the past—low utilization, lack of
visibility and inefficient equipment and processes—are holding many
organizations back from achieving the required transformation.
The data center infrastructure—power and cooling systems that
ensure safe and continuous operation— often represents the least agile and
scalable component of the data center. If improperly designed and maintained,
it can constrain growth and contribute to downtime. Conversely, the right
infrastructure creates a foundation for continuous availability, increased
return on capital and cost-effective growth.
Approaches
for Scalability
Heat density has been a top concern identified by the Data Center
Users Group (DCUG) in eight of the last nine years. Yet, according to DCUG
survey data, average rack power density in the data center was about the same
in 2013 as in 2006.This is the result of more efficient servers and greater
virtualization and indicates an opportunity to add capacity by increasing rack density.
Perimeter cooling systems now operate at higher levels of
efficiency and have built-in intelligence that allows them to communicate and
collaborate. Cooling has also steadily migrated closer to the heat source,
increasing efficiency and the ability to cool higher density racks. With the
proper power and cooling infrastructure in place, most data centers can double
or triple their capacity without increasing data center space.
If additional capacity is required, an aisle-based or
container-based expansion strategy can be employed in which initial capacity is
met by the required number of aisles or containers but space and power capacity
are reserved for the addition of future “modules.” When capacity is needed,
additional aisles or containers—with integrated cooling, monitoring and power
protection and distribution—can be added, enabling an easy-to-implement modular
growth strategy.
This approach has been popular with organizations that need to
expand quickly to react to market demands or opportunity, such as colocation
providers, or those delivering cloud services. With proper planning,
significant blocks of new capacity can be added in a fraction of the time it
would take to conduct a traditional build-out or build a new data center.
Because they have the ability to respond quickly, these organizations can
reduce upfront capital costs and increase operating efficiency by using a
higher percentage of their operating capacity at startup.
Alternately, capacity can be added
through cloud or colocation providers, but even in this case, infrastructure
remains an important consideration. The in-house data center infrastructure has
to adapt to varying loads without compromising efficiency. The infrastructure
of the cloud or colocation provider should be evaluated to ensure it uses
technologies and configurations proven to support high availability.
Protecting
Availability
While difficult to predict exactly what
will be expected from the data center of the future, it is hard to imagine a
scenario in which downtime isn’t a serious issue. Data centers attempting to
completely eliminate power-related downtime generally use dual-bus architecture
to eliminate single points of failure across the entire power distribution
system. This approach includes two or more independent UPS systems each capable
of carrying the entire load with N capacity after any single failure within the
electrical infrastructure. This is a proven approach for delivering Tier IV
availability, but does require custom switchgear and limits power equipment
utilization to 50 percent, impacting initial costs and operating costs.
Alternate configurations in recent years
support high availability while increasing power equipment utilization,
including distributed reserve dual-bus architecture. Static transfer switches
(STS) are used to provide redundancy across multiple UPS systems as well as the
transfer switch itself (Figure 1).
The reserve-catcher dual bus
approach is extremely attractive to organizations seeking dual-bus availability
with lower initial costs and greater efficiency. Like the distributed-reverse
dual bus, it uses STS as the power tie; however, instead of creating redundancy
through distributed primary UPS systems, it uses a secondary or reserve system
to provide dual-bus protection across multiple primary UPS systems. The result
is lower initial costs than other dual bus approaches with increased power
equipment utilization. Less critical facilities may consider a parallel
redundant configuration, such as the N + 1 architecture—in which “N” is the
number of UPS units required to support the load and “+1” is an additional unit
for redundancy. This architecture provides cost-effective scalability.
Advancing
Efficiency
For organizations seeking to optimize
data center efficiency, technology strategies that comprise a holistic
approach to improving data center energy efficiency with a comprehensive,
vendor-neutral approach to achieving meaningful reductions in data center
energy costs is needed.
Power and cooling systems
can be configured to increase efficiency. Double conversion UPS topologies
deliver better protection than other types of UPS because they completely
isolate sensitive electronics from the incoming power source, remove a wider
range of disturbances and provide a seamless transition to backup power
sources. With the combination of improved operating efficiencies and the smart use
of an active
inverter eco-mode that provides reliable
power protection and enhanced flexibility, these robust power systems
can achieve efficiencies in excess of 98 percent. In addition, intelligent paralleling can
improve the efficiency of redundant UPS systems in a parallel configuration by
deactivating UPS modules that are not required to support the load and taking
advantage of the inherent efficiency improvement available at higher loads.
Additional efficiencies can also be achieved in the distribution system by
bringing higher voltage power closer to the point of use, minimizing step down
losses.
Conclusion:
No single technology can remove all of the constraints
that prevent organizations from optimizing data center performance and
efficiency. But when technology is addressed through a systematic review and
evolution of data center management technologies each of those constraints can
be effectively overcome.