Deploying High-Density Pods in a

Low-Density Data Center

White Paper 134

Revision 2

by Neil Rasmussen and Victor Avelar

Contents
> Executive summary Click on a section to jump to it

The problem: unmanaged high 3

Simple and rapid deployment of self-contained, high-
density
density pods within an existing or new low-density data
center is possible with today’s power and cooling The solution: high-density 4
technology. The independence of these high-density pods
pods allow for predictable and reliable operation of
high-density equipment without a negative impact on Pod containment methods 6
the performance of existing low-density power and
cooling infrastructure. A side benefit is that these high- Additional high-density pod 12
density pods operate at much higher electrical efficien- benefits
cy than conventional designs. Guidance on planning
design, implementation, and predictable operation of In-house vs. vendor-assisted 13
high-density pods is provided. deployment

Real-time management of 16
high-density pods

Conclusion 17

Resources 18

Appendix A 19

white papers are now part of the Schneider Electric white paper library
produced by Schneider Electric’s Data Center Science Center
[email protected]
 Deploying High-Density Pods in a Low-Density Data Center

Introduction High-density equipment such as blade servers, 1U servers, and multi-core, high-end servers
provide more computing-per-watt compared to previous generation servers. However, when
consolidated, this equipment requires concentrated power and cooling resources. Data
center operators and IT executives are often uncertain about the capability of their existing
data center and whether a new data center must be built to support higher rack densities. A
simple solution exists that allows for the rapid deployment of high-density racks within a
traditional low-density data center. A high-density pod, as illustrated in Figure 1, allows data
center managers to support a mixed-density data center environment for a fraction of the cost
of building an entirely new data center.

Low-density room

Figure 1
Basic concept of a high-
density pod

High-density
pod

Hot/cool air
circulation is HEAT ENERGY OUT – to
contained within heat rejection system
the pod

• A high-density “island” in the room

• A “mini data center” with its own
cooling

> High density enables • Thermally neutral or even positive

to the rest of the room
high efficiency • Hot/cool air circulation is localized
In traditional data centers with within the pod by short air paths
and/or physical containment
room-based power and cooling,
unmanaged high-density racks
can cause destabilizing effects
such as cooling inefficiency,
loss of cooling redundancy, hot
spots, thermal shutdown, and In this paper a high-density pod is defined as one or more rows of racks containing high-
circuit overload. density equipment all clustered together with dedicated row-based cooling that is deployed as
a unit. A high-density pod resides within the borders of a larger, low-density data center.
However, with today’s new
power and cooling technologies, The high-density pod is not the same as a high-density data center, which is a data center
high-density racks offer an dedicated to supporting nothing but, or mostly, high-density racks. Managing for the deploy-
opportunity for dramatically ment and operation of a high-density data center is not the subject of this paper.
increased efficiency and
predictability, if deployed
effectively and supported by
“smart” row-based power and High-density pod compared to “spreading out” strategy
cooling.
Although today’s IT equipment operates at high power density – that is, each individual
The high-density pods
described in this paper provide server draws a high amount of power – this does not always mean such devices must be
a way to deploy high density deployed in a high-density manner by packing them together in a rack. In fact, a popular
while at the same time strategy has been to spread out high-density servers by installing fewer in each rack. If the
achieving increased overall
equipment is dispersed like this, the data center’s average power density will likely stay in the
data center efficiency by
targeted, scalable, localized range that the data center was originally designed for. In this way, a variety of technical
power and cooling. problems can be avoided.

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 2
 Deploying High-Density Pods in a Low-Density Data Center

However, the “spreading out” strategy may not be viable for a number of reasons:

• Consumption of additional floor space, which may be difficult to justify or simply not
possible
• Executive management perception that partially-filled racks are wasteful
• Increased cabling costs (because of longer runs)
• Increased cost and difficulty of maintenance – cabling and mounting may be intertwined
with other equipment in a non-standard manner, scattered throughout the room
• Reduced electrical efficiency of the data center, because cooling-system air paths are
Related resource longer and less well targeted. The longer the air path in an uncontained system, the
White Paper 135 more chance there is for hot and cold air to mix. This mixing results in the lowering of
Hot-Aisle vs. Cold Aisle the return temperature to the air conditioner which means the system will be less effi-
Containment for Data cient in removing heat energy. For more information regarding the containment of air
Centers streams, see White Paper 135, Hot-Aisle vs. Cold-Aisle Containment for Data Centers.

For these reasons, it is expected that data enter operators will begin to deploy IT equipment
at its full density capability – in pods – rather than try to stay within an overall room power
density by spreading out the load. With new power and cooling technologies, there is now a
significant efficiency entitlement from concentrating high-density equipment into pods.

This paper assumes the choice has been made to deploy high-density IT racks in a low-
Related resource density data center. Row-based cooling, as a technique to implement these high-density
White Paper 46 pods, is presented as a simple solution for addressing high-density power and cooling issues
Cooling Strategies for Ultra- in both existing and new data centers. For more information regarding alternatives for
High Density Rack and Blade deploying high-density equipment, including the option of spreading out IT equipment, see
Servers White Paper 46, Cooling Strategies for Ultra-High Density Racks and Blade Servers.

Traditional data center design uses a raised floor to distribute cooling to low-density IT
The problem: equipment (Figure 2a) and air streams are uncontained. However, when high-density
unmanaged high equipment is randomly installed throughout a low-density data center the cooling stability is
density upset and hot spots begin to appear (Figure 2b).

Low-density room Low-density room

Figures 2a (left) and 2b

2a – Low-density data
center

2b – High-density hot spots Concentrated high-

density IT equipment

Stable Unpredictable
cooling cooling

Data centers designed for low-density racks (typically 1-3 kW / rack) vary dramatically in
construction. Ceiling heights, raised floor depths, room geometry, power distribution, and
raised floor obstructions are all quite different. In addition, IT managers vary in how they
define a high-density rack. This paper defines a high-density rack as 6 kW or higher.
Regardless of which number is used to denote a high-density rack, the following deployment
issues need to be considered:

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 3
 Deploying High-Density Pods in a Low-Density Data Center

• Delayed server deployment – uncertainty of knowing which rack can cool a newly provi-
sioned server just adds to the already long delay by having to perform a cooling as-
sessment
• Unplanned downtime – due to overloaded power distribution circuits or thermal shut-
down of IT equipment
Related resource
White Paper 121 • Unpredictable cooling throughout the data center – no certainty that every high-density
server will be properly cooled after every move, add, or change (see White Paper #121,
Airflow Uniformity Through Airflow Uniformity Through Perforated Tiles in a Raised-Floor Data Center).
Perforated Tiles in a Raised-
Floor Data Center • Loss of cooling redundancy – as more high-density racks are added, air conditioning
units that were once redundant are now required to supply the concentrated airflows.
Some subsystems are extremely impractical or costly to instrument for power consump-
tion (for example, PDUs due to number of output connections, or switchgear)

The solution: Fortunately a solution exists that can neutralize these issues and is discussed in the following
sections. Placing high-density racks in an isolated, standardized, and self-contained area of
high-density the data center provides a low cost, viable solution to the challenges mentioned above. This
pods high-density pod avoids dependence on the unpredictable nature of raised floor cooling and
would not require complex computational fluid dynamics (CFD) analysis prior to installation.

Figure 3 illustrates three high-density pod implementation methodologies all of which are
capable of supporting independent power distribution, UPS, and cooling systems. This “drop-
in” solution eliminates the hot spots in Figure 2b by simply moving high-density equipment
into the pod that contains dedicated row-oriented cooling units. The heat generated from the
high-density IT equipment within this pod is rejected to the outdoors with no negative impact
to the existing data center cooling system or the surrounding low-density IT racks. In fact,
the pod acts as its own high-density data center within an existing low-density data center.
This self-sufficient pod is, at a minimum, thermally “invisible” or, more likely, is a net exporter
of cooling to the rest of the room.

Low-density room

Figure 3
Isolated, self-sufficient
High-density
high-density pod zone

Hot/cool air
circulation is HEAT OUT
localized within to building’s heat
the zone rejection system

Three basic methods

(Top view)

HOT-AISLE RACK
Uncontained
containment containment

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 4
 Deploying High-Density Pods in a Low-Density Data Center

What is thermal “visibility”?

Isolated, standardized and self-contained high-density pods operate on the idea of isolating
server exhaust heat and directing all of that heat into the air conditioner intakes, where the air
is then cooled before being redistributed to the front of the servers. By isolating both hot and
cold air streams, the high-density pod, at a minimum, neutralizes the thermal impact that
high-density IT racks would otherwise have on traditional low-density data centers. In other
words, the pod is thermally “invisible” to the existing data center cooling system. Particularly
with hot-aisle and rack containment methods, however, it is quite likely that the row-oriented
cooling in the high-density pod will have a positive effect by actually adding cooling capacity
to the rest of the room.

Although this paper focuses on the cooling of high-density pods, it is also possible to power a
pod with its own dedicated UPS and power distribution. This may be desirable in situations
where the existing data center UPS is at capacity or is being phased out due to end-of-life or
when targeted power availability is required for a specific pod.

The system in Figure 4 integrates a cluster of high-density IT racks with a high-density row-
based cooling system and high-density UPS and power distribution system in a pre-
manufactured, pre-tested pod.

Hot air is exhausted to the

Air conditioners return neutralized hot aisle and returns to the
(ambient room temperature) air to the back of the air conditioners
front of the racks

IT IT IT IT
Figure 4 rack rack rack rack
Front-view of a standardized
modular multi-rack high-
density pod (no containment
in this example)

Integrated row-based
air conditioners

Row-based cooling architecture

A row-based cooling architecture makes it possible to have a room-neutral high-density pod.
Row-based cooling is an air distribution approach in which the air conditioners are dedicated
to a specific row of racks. This is in stark contrast with room-based cooling where perimeter
air conditioners are “dedicated” to the entire room. Row-based air conditioners may be
installed above IT racks, adjacent to IT racks, or in combination. An example of a row-based
air conditioner is shown in Figure 5.

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 5
 Deploying High-Density Pods in a Low-Density Data Center

While most facilities and IT

personnel understand the basic > Row-based cooling units
idea behind high-density pods,
Compared with the traditional room-
they question how the pod can be oriented approach, the airflow paths of
“room neutral” in the midst of row-based air conditioners are shorter
constant moves, equipment and much more predictable. In addition,
all of the rated capacity of the air
additions, and changes. Consi- conditioner can be utilized, and higher
dering their past experience with power density can be achieved. At the
the variability and at times same time, the usable capacity of the
perimeter (room-based) cooling system
perplexing nature of raised-floor
increases and in some cases its cooling
cooling, skepticism toward the redundancy is restored to the original
long-term predictability of high- design as IT load is removed from this
density pods is not surprising. system and placed into the pod.
Though raised floors and high- Although not discussed in this paper,
density pods are both governed row-based cooling is also an effective
by the same laws of fluid dynam- method for entirely cooling small low-
density data rooms (1-3 rows of racks).
ics and thermodynamics, one
major aspect sets them apart –
standardization.
If raised floors were standardized so that they all had the same depth, same dimensions,
same under floor obstructions, same under floor airflow pattern, same CRAC locations, and
same air leakage from tile cutouts, they could more easily be modeled in real time so as to
predict their behavior using design and planning software tools. If this standardization
existed, IT managers would be able to predict the cooling impact of adding a blade chassis to
a particular rack and make rational decisions based on the prediction. However, these raised
floor attributes by their very nature are customized and are not conducive to standardization.
Furthermore, the variability of all these attributes would make real-time computational fluid
dynamics (CFD) modeling nearly impossible in a typical data center.

In contrast, high-density pods use standardized hot / cold aisle widths, rack height, and air
path distances to the rack. Row-based cooling also eliminates the variability introduced by
Related resource the raised floor. These simplifications make it possible to design predictable high-density
White Paper 130 pods using standardized tools. These design tools provide the confidence that any design
will capture and neutralize the expected amount of hot exhaust air. For more information on
The Advantages of Row and
Rack-Oriented Cooling the row-based cooling architecture, and how it compares to room-based cooling, see White
Architectures for Data Centers Paper 130, The Advantages of Row and Rack-Oriented Cooling Architectures for Data
Centers.

Server exhaust heat can be diverted back to the air conditioners in three ways: uncontained,
Pod hot aisle containment, and rack air containment (see Figure 5). All of these methods
containment leverage a row-based cooling concept (e.g., the air conditioner is brought within a few feet of
the IT rack).
methods

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 6
 Deploying High-Density Pods in a Low-Density Data Center

Three ways to create a room-neutral

“island” in a low density room
Low-density room

1 Uncontained

Figure 5
High-density pod
containment methods
2 HOT-AISLE
containment

Hot/cool air
circulation is
localized within
the zone

High-density zone
Room-neutral “island” 3 RACK
containment
in a low-density room

1. Uncontained
Uncontained pods rely on the standard layout and widths of the common hot aisle and cold
> Importance of aisle arrangement to keep hot and cold air streams from mixing. For this reason, uncon-
blanking panels tained pods depend on multiple racks in a row and are not effective in cooling stand-alone IT
Effective row-based cooling racks. The hot and cold aisles formed by rows of racks (and in some cases walls) are what
depends on the isolation of hot isolate the hot and cold air streams as illustrated in Figure 6. The closer an IT equipment
and cold air streams. If any of
rack is to a row-based air conditionec, the greater the amount of exhaust air that is captured
the vertical space in a rack is
not filled by equipment, the and cooled. As the distance between the IT rack and the row-based air conditioner increases
gaps between equipment allow in an uncontained system, the more the hot exhaust air mixes with the surrounding air in the
hot exhaust air to flow through data center.
the rack and to the front of
equipment such as servers.
This mixing between the hot When to use this method:
and cold air streams reduces
the effectiveness of row-based
cooling. For more information • When IT racks designated for the pod are moved and relocated frequently
see White Paper 44, Improving • When IT racks are used from a variety of different vendors
Rack Cooling Performance
Using Airflow Management™
Blanking Panels (link in Trade-offs:
Resource section)

• More row-based air conditioners required at lower densities in order to properly capture
hot exhaust air from all IT racks.

WALL or ROW to help form “hot aisle”

Figure 6
REAR
High-density pod
CRAC

CRAC

with no containment
CRAC

Rack Rack Rack Rack

Hot aisle
FRONT

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 7
 Deploying High-Density Pods in a Low-Density Data Center

2. Hot aisle containment

Hot aisle containment pods are identical to uncontained pods except for the fact that the hot
aisle in every pair of rows is contained. The hot aisle becomes the hot exhaust channel by
enclosing it with ceiling panels and a door at each end of the aisle (Figure 7). In addition, the
racks’ rear doors are removed. The hot exhaust air is physically contained and unable to mix
with the ambient data center air. A wall or another row of racks is required to form a cold
aisle in order to isolate the cold supply air.

When to use this method:

• In cases where floor space must be conserved. This method is popular because it
consumes the same space as two rows of low-density racks.
• In data centers with hot aisle / cold-aisle layouts

Trade-offs:

• Hot aisle containment panels increase capital cost

• Hot aisle containment may exceed work environment policies due to high temperature
• Incompatible with some types of cabling, power strips, labels, and other materials that
are not rated for high temperatures
• Not possible with a single row of racks
• Authority having jurisdiction (AHJ) may require fire suppression in hot aisle

FRONT

Figure 7
CRAC

CRAC

CRAC
Rack Rack Rack Rack

High-density pod
with hot aisle
containment
REAR Hot aisle
CRAC

CRAC

CRAC

Rack Rack Rack Rack

Contained
hot aisle
FRONT

3. Rack containment
Rack containment (also called rack air containment) is similar to hot aisle containment except
that the hot exhaust air is contained using the back frame of the equipment racks and a
series of panels to form a rear air channel. This channel can be attached to a single IT rack
or to a row of racks (Figure 8). The panels used to create the hot exhaust air channel
increase the depth of a normal rack by 20 cm (8 in). An optional series of front panels may
be used on rack containment arrangements that require complete containment of hot and
cold air streams as shown in Figure 9. This optional front containment adds an additional 20
cm (8 in) to the depth of the rack.

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 8
 Deploying High-Density Pods in a Low-Density Data Center

> Why NOT use When to use this method:

containment?
• In cases where hot aisle containment is the preferred method, but a single odd row is
It may appear that containment
left uncontained
would be the clear choice for
any row-based cooling scenario. • When frequent access to and easy management of communication cables is required
However, this is not always the
case. • For complete isolation in cases such as stand-alone open data center environments or
mixed layouts – only when optional front containment is used
With row-based cooling,
containment is more important • In wiring closets that lack any form of cooling, exposing high-density equipment to high
at lower densities, where the temperatures – only when optional front containment is used
ratio of IT racks to air condition-
ers is higher. The higher this • When sound attenuation is required – only when optional front containment is used
ratio the greater the distance
between IT racks and air
conditioners, with more chance Trade-offs:
for hot exhaust air to “escape.”
Higher densities, on the other
hand, mean a lower ratio of IT
• Front and rear containment panels increase capital cost
racks to air conditioners, with • In a single rack configuration, cost increases substantially when cooling redundancy is
shorter air paths and less required
chance for hot exhaust to
escape – in this case, contain-
ment is less essential because
airflow is tightly targeted and
tends to “behave” all by itself.

In addition, there may be

practical considerations that
rule out containment, such as
higher cost at certain rack
power densities, company
restrictions on hot work
environments (i.e., a contained
hot aisle), and incompatibility
with existing racks.

Figure 8 FRONT

High-density pod with rack

CRAC
CRAC

CRAC

containment Rack Rack Rack Rack

So
lid
re
ar
do
or
s
REAR

Return air contained

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 9
 Deploying High-Density Pods in a Low-Density Data Center

Solid front
doors
FRONT

Single rack

CRAC
Rack
Optional front
containment
REAR
Figure 9 Solid rear
doors
High-density pod with rack
containment plus optional
front containment

Soli
d fron
t do
or s
FRONT
Multiple racks

CRAC

CRAC

CRAC
Rack Rack Rack Rack
So
lid
re
ar
do
or
s REAR

An overall comparison of high-density pod methods is shown in Table 1.

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 10
 Deploying High-Density Pods in a Low-Density Data Center

Table 1
Comparison of pod
containment methods

Selection No Hot aisle Rack air

Comments
criteria containment containment containment
• NO containment and HOT AISLE containment provide
minimum row spacing
• RACK air containment adds 8 inches to the depth of
Minimize the rack but may be acceptable in consolidation
Good Good Moderate to poor
footprint applications
• Front AND rear containment adds 16 inches to the
depth of the rack – should be weighed against
available floor space

• Taking racks in and out of an existing row is more

Ease of change Good Moderate to poor Moderate to poor difficult when containment systems constrain the rack
management with hardware, especially with front containment

• NO containment layout is closely linked to the existing

Minimize energy Moderate Good Good data center layout which could increase the number of
consumption row-based units

• HOT AISLE containment row-based CRAC positions

Ease of are independent of redundancy
Moderate Good Moderate to poor • More row-based CRACs needed to maintain
redundancy redundancy in rack containment

• RACK air containment and RACK air containment with

front containment may be limited since not all rack air
can be shared among all row-based coolers as with
Minimize # of HOT AISLE containment
row-based Poor to • NO containment depends heavily on rack power
CRACs Good Moderate to good density where high densities require less row-based
moderate
(particularly at coolers
low density) • RACK air containment and rack air containment with
front containment highly-influenced by redundancy
(more coolers needed)

• Poor to moderate with RACK air containment only

• Good when using RACK air containment with front
Sound Poor Moderate to poor Good containment
attenuation • Will reduce the decibel level of the cooling equipment
but will not completely eliminate the noise

• Poor to moderate with RACK air containment only

Installation in
• Good when using RACK air containment with front
thermally containment
unstable or Poor Poor Good
• Examples include wiring closets, offices, and
non-data center commercial spaces
space
• Although the hot aisle containment has additional
panels that increase cost, it will require fewer row-
Cost Dependent upon variables such as rack power density and number racks based coolers than no containment, particularly at
lower rack power densities

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 11
 Deploying High-Density Pods in a Low-Density Data Center

Additional high- The decision on whether to move forward with deployment of a high-density pod should also
consider the following benefits:
density pod
benefits • Standardization of design elements
• Compatibility with any data center, new or existing
• Configurability with dedicated UPS and power distribution
• Configurability with any level of redundancy
• Configurability with any number of IT racks

Standardized design elements

In order for high-density pods to provide predictable performance they must include standard
design elements. This includes components such as air conditioners, power distribution,
UPS, and racks. In addition, standard dimensions play a key role in predictably isolating hot
and cold air flows. Standard dimensions include hot / cold aisle widths, rack height, and
standard (short) airflow travel distances.

Modularity is also a benefit of standardization and allows high-density pods to be quickly

deployed, altered over time, and even moved to another data center. Standardized compo-
Related resource
nents and dimensions greatly simplify the design process. These pre-designed standard
White Paper 116
solutions may even be re-ordered for other data centers. Data center personnel can also
Standardization and Modularity leverage standardization by deploying predictable capacity and change management
in Network-Critical Physical software that maintains the peak performance of the high-density pod (this is discussed
Infrastructure
later). For more information on standardization see White Paper 116, Standardization and
Modularity in Network-Critical Physical Infrastructure.

Compatible with any data center, new or existing

High-density pods are modular and independent of room-based cooling architectures and
existing UPS architectures. Therefore, few constraints exist to prevent their deployment in
new or existing data centers. Sufficient floor space must be available and the floor must have
enough weight-bearing capacity. All other aspects of a standardized high-density pod are
replicable in multiple types of data centers.

Configurable with dedicated UPS and power distribution

The architecture of the high-density pod allows for deployment of pod-specific UPS and PDU
configurations in cases where the existing data center UPS is at capacity or is being phased
out due to end-of-life. These systems are rack-based and designed to be modular and
scalable.

Configurable with any level of redundancy

Redundancy levels vary depending upon the criticality of the IT assets. Traditional data
center design is such that the entire physical infrastructure is built to satisfy the redundancy
requirements of the most critical set of assets. This type of design is extremely expensive
both from a capital cost and operational cost perspective. A much more cost-effective design
is to provide redundant power and cooling only where and when required. High-density pods
allow for this targeted redundancy / availability approach by including redundant power and
cooling modules when appropriate. Note that the core infrastructure such as chilled water

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 12
 Deploying High-Density Pods in a Low-Density Data Center

piping and electrical service entrance must be designed and built on day one with the highest
redundancy level required.

Configurable with any number of IT racks

High-density pods are scalable in that they accommodate the number of IT racks required at
a specific power density. These pods can range in size from a single IT rack to 20 or more
racks depending on local codes.

Combining these characteristics results in a highly flexible, high-density solution that can
extend the life of a legacy data center and postpone the capital outlay required for building a
new one.

Traditional Pod
Attribute Comments
approach approach

Positioning the data Simple economics – cost of doing

center as a source of Difficult Easier business is lower per unit of
corporate competitive computational output
advantage

Deployments are highly dependent

Just-in-time IT on modular and predictable power
Very difficult Easy
deployments and cooling which affects manage-
Table 2 ment and ability to quickly deploy
Deploying high-
density equipment:
Predictability of Strongly linked to data center
traditional vs. High Low
performance infrastructure efficiency
pod approach

Management applications insure

Likelihood of hot spots High Very low optimal placement of equipment in
pods to prevent hot spots

Room based cooling units are

oversized to overcome under-floor
Cooling efficiency Poor Excellent
obstacles, distance, air mixing,
demand fighting, etc.

Standardization / predictability
Ability to plan Poor Excellent facilitate “what-if” scenarios before
moves, adds, and changes

In-house vs. The data center owner has two options for the deployment of high-density pods: in-house
deployment or vendor-assisted deployment. In both cases a solid project plan is required.
vendor-assisted More specific information regarding data center projects and system planning is available in
deployment white papers 140, Data Center Projects: Standardized Process and 142, Data Center
Projects: System Planning.

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 13
 Deploying High-Density Pods in a Low-Density Data Center

In-house deployment
Related resource IT managers can easily deploy smaller sized pods or smaller data centers (less than 20
White Paper 140 racks) with no previous experience. A worksheet and checklist is provided in Appendix A.
Data Center Projects:
Standardized Process This worksheet can serve as a helpful guide and facilitates the collection of information
required to specify and deploy a high-density pod. The worksheet assumes the project owner
has knowledge of the IT equipment associated with the planned high-density pod (e.g. total
Related resource
power requirements, plug requirements, rack U-height requirements and communications
White Paper 142
cabling requirements).
Data Center Projects:
System Planning
If the worksheet is properly filled out, an educated decision can be made on which pod
containment method to choose. APC TradeOff Tool™, Data Center InRow™ Containment
Related resource Selector, (see Figure 10) can help select the most appropriate pod containment method.
APC TradeOff ToolTM The results generated by the tool are based on typical scenarios and in some cases the
Data Center InRowTM recommended containment option may differ from the actual final design.
Containment Selector
Once a containment type is chosen, a decision must be made on which components the pod
will include. The worksheet helps data center staff determine whether to include a dedicated
UPS, PDU, or chiller. In some cases, certain preferences and constraints dictate which
components are included in a pod and which are not. Table 3 provides a list of possible
constraints that could affect the ultimate configuration of the high-density pod.

Constraint High-density pod requirement

None Racks and row-based cooling units

No spare power Racks, row-based cooling unites, and row-

distribution positions based power distribution unit (PDU)
Table 3
No spare power capacity on existing Racks, row-based cooling units, row-based UPS
High-density pod compo-
UPS system system, and row-based PDU
nents under various
constraints
No spare cooling capacity on existing Racks, row-based cooling units, and packaged
chiller chiller

No spare power or cooling capacity Racks, row-based cooling units, row-based UPS
on existing UPS and chiller system, and packaged chiller

No spare power or cooling capacity

Racks, row-based cooling units, row-based UPS
on existing UPS and chiller or spare system, packaged chiller, and row-based PDU
power distribution positions

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 14
 Deploying High-Density Pods in a Low-Density Data Center

Figure 10
Interactive tool for
containment
method selection

Even with the constraint of no spare UPS, chiller, or power distribution capacity, it is still
possible to extend the life of an existing data center by installing a high-density pod with its
own dedicated power and cooling resources. For example, the high-density pod in
Figure 11 includes its own chiller plant, UPS, and power distribution. It is assumed that the
data center’s electrical service entrance has sufficient spare capacity to supply power to this
packaged solution. In cases where a data center has run out of spare electrical service
capacity, a decision must be made to install an additional utility feed(s) or build a new data
center. Other factors beyond the scope of this paper such as available floor space, virtualiza-
tion potential, business objectives, leasing contracts, and future growth plans factor into the
buy-or-build decision.

Cooling distribution unit

Figure 11
Packaged standalone high-
density pod

Packaged chiller

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 15
 Deploying High-Density Pods in a Low-Density Data Center

From the time a need for a high-density pod is identified, IT and facilities personnel can
expect to populate the racks in a given pod in one to three months, assuming the required
budget is approved. However, internal company processes may extend the proposed
timeline.

Vendor-assisted deployment
Although it is possible for data center staff to deploy high-density pods without outside
assistance, projects involving data centers with 20 or more racks can be considerably more
complex. In such cases consultation with design experts and project managers is recom-
mended.

Vendor-assisted deployment usually begins with an assessment of the existing data center or
the design plans for a new data center. In either case an assessment provides the design
experts with valuable information, including preferences and constraints, which allows
optimum design decisions. Assessments help answer questions such as:

• Can an existing row be retrofit with row-based air conditioners to avoid downtime?
• If spare chilled water capacity is unavailable should a self-contained air conditioning unit
be used as opposed to a packaged chiller?
• What steps can be taken to increase the speed of deployment of a future high-density
pod?

An effective assessment (such as Schneider Electric’s Blade Server Readiness Assessment)

measures spare bulk power and cooling capacity as well as spare distribution capacity. Bulk
cooling capacity is measured at the chiller while the distribution capacity is measured at the
CRAH units on the data center floor. This data provides an estimate of cooling capacity and
compares constraints against current and future requirements. Ultimately this will help
answer the question, “When will I run out of cooling capacity and require a high-density pod?”

After measuring and analyzing the data, a plan is created to meet future high-density needs.
In the end, an effective design plan for mixed-density data centers should incorporate power,
cooling and floor space utilization efficiency. An effective design plan allows a data center to
use up its power, cooling, and space resources all at the same point in the future, thereby
avoiding stranded resources.

Real-time The architecture of row-based cooling makes real-time modeling of cooling performance
possible. Design tools can configure racks, row-based air conditioners, UPS, and power
management distribution based on high-density pod specifications such as average and peak power
of high-density density per rack, containment, redundancy, and plug types. Once a high-density pod is
deployed, real-time planning and management tools allow IT personnel to maintain predicta-
pods ble operation even after moves, adds, and changes take place. Examples of appropriate
design and planning tools include InfraStruXure Designer and APC’s Capacity and Change
Manager. For more information on management and its critical role in predictable perfor-
mance, see White Paper 150, Power and Cooling Capacity Management for Data Centers.
Related resource
White Paper 150
Power and Cooling Capacity
Management for Data
Centers

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 16
 Deploying High-Density Pods in a Low-Density Data Center

In the past it was a major challenge for IT personnel to successfully deploy a mix of high-
Conclusion density and low-density equipment in the same data center space. Traditional data centers
were specified to cool a uniform rack power density and were not capable of predictably
cooling a large number of high-density racks. Now architectures such as row-based cooling
allow for the rapid deployment of high-density pods within an existing or new low-density data
center. Modular row-oriented power and cooling can be added where and when high-density
racks are required, without any negative effect on the existing room-level infrastructure. In
combination with capacity and change management systems, pods offer a high-density
deployment solution capable of maintaining predictable operation even after moves, adds,
and changes.

About the author

Neil Rasmussen is a Senior VP of Innovation for Schneider Electric. He establishes the
technology direction for the world’s largest R&D budget devoted to power, cooling, and rack
infrastructure for critical networks.

Neil holds 19 patents related to high-efficiency and high-density data center power and cooling
infrastructure, and has published over 50 white papers related to power and cooling systems,
many published in more than 10 languages, most recently with a focus on the improvement of
energy efficiency. He is an internationally recognized keynote speaker on the subject of high-
efficiency data centers. Neil is currently working to advance the science of high-efficiency,
high-density, scalable data center infrastructure solutions and is a principal architect of the APC
InfraStruXure system.

Prior to founding APC in 1981, Neil received his bachelors and masters degrees from MIT in
electrical engineering, where he did his thesis on the analysis of a 200MW power supply for a
tokamak fusion reactor. From 1979 to 1981 he worked at MIT Lincoln Laboratories on flywheel
energy storage systems and solar electric power systems.

Victor Avelar is a Senior Research Analyst at Schneider Electric. He is responsible for data
center design and operations research, and consults with clients on risk assessment and
design practices to optimize the availability and efficiency of their data center environments.
Victor holds a Bachelor’s degree in Mechanical Engineering from Rensselaer Polytechnic
Institute and an MBA from Babson College. He is a member of AFCOM and the American
Society for Quality.

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 17
 Deploying High-Density Pods in a Low-Density Data Center

Resources
Click on icon to link to resource
Hot-Aisle vs. Cold-Aisle Containment
for Data Centers
White Paper 135

Cooling Strategies for Ultra-High Density

Rack and Blade Servers
White Paper 46

The Advantages of Row and Rack-Oriented

Cooling Architectures for Data Centers
White Paper 130

Standardization and Modularity in Network-

Browse all
Critical Physical Infrastructure
white papers
White Paper 116
whitepapers.apc.com
Data Center Projects:Standardized Process
White Paper 140

Data Center Projects: System Planning

White Paper 142

Power and Cooling Capacity Management

for Data Centers
White Paper 150

Improving Rack Cooling Performance Using

Airflow ManagementTM Blanking Panels
White Paper 44

Airflow Uniformity Through Perforated Tiles

in a Raised-Floor Data Center
White Paper 121
Browse all
TradeOff Tools™
tools.apc.com

Contact us
For feedback and comments about the content of this white paper:

Data Center Science Center

[email protected]

If you are a customer and have questions specific to your data center project:

Contact your Schneider Electric representative

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 18
 Deploying High-Density Pods in a Low-Density Data Center

Appendix A: Worksheet and checklist for deployment

of a high-density pod

Data / input Value Comments

Goal for the availability and reliability of the pod,

Criticality level: consistent with the business mission. See White
1 1, 2, 3, or 4 Paper 122 for guidance and choosing an appropri-
ate criticality level.

Average IT load per rack. (The pod’s cooling will be

Average rack power density (kW)
The pod

2 designed to handle this.)

Maximum anticipated IT load in any rack of the pod.

3 Peak rack power density
(The pod’s cooling will be designed to handle this.)

Is there sufficient service entrance Electrical service entrance capacity must be able to
4 capacity to support this high-density support the incremental power load added by the
pod? (Yes / No) pod (IT load plus power/cooling infrastructure).

Type of data center floor: raised floor

5
The room

vs. hard floor

What floor-to-ceiling height is available The height available for proposed and future
for the pod’s equipment, taking service equipment, taking into consideration all applicable
6 clearances into account? service clearances per local jurisdiction. For
(indicate ft. or m.) example, sprinklers will affect available height.

Will pod include a separate dedicated

7 If no, skip to item 12.
UPS?

Whit is available source input voltage to

8 the UPS(s) or PDU(s)?

How much current is available from the Total spare current of the subpanel feeding the
9 subpanel that will power the UPS(s) or room – must be shared with cooling equipment in
PDU(s)? item 21. Electrician is best source for information.

Total number of spare 3-pole positions available to

How many 3-pole breaker positions are
Power

10 be used by UPS(s) and PUD(s). Electrician is best

available in the panel(s)?
source of this information.

What is preferred UPS runtime?

11 See White Paper 52 for guidance
(minutes)

This will determine if there is sufficient existing UPS

Total spare capacity of all existing UPS capacity to support the new high-density pod,
12 system(s) dedicated to the data center taking into consideration desired redundancy and
distribution.
How will the electrical distribution
13 cables be routed from the PDU(s) to the
racks? (overhead or underfloor)

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 19
 Deploying High-Density Pods in a Low-Density Data Center

Data / input Value Comments

Which method will this high-density pod

14 use? No containment, hot aisle con-
tainment, or rack containment?

What existing heat rejection methods Identifies the types of heat rejection systems that
15 are available at the site? Chilled water, are available at the site. This will help in designing a
glycol, refrigerant, water cooled? high-density pod with a compatible cooling system.

The total cooling capacity (in kW) available from

the existing cooling system. For chilled water
What is the total “sensible capacity”
16 systems, this will be the capacity of the chiller plant.
(kW) of the existing cooling system?
For DX systems, this will be the total of all the CRAC
units.

What is the spare “sensible capacity” of To be filled out if chilled water spare capacity will
17 the existing chilled water system? (kW) be used for this high-density pod.
Cooling

Identifies how the following are routed:

How is cooling system piping routed? DX – glycol, condenser water, humidification and
18 Overhead or underfloor? condensate lines
Chilled water – supply/return piping

How will the chilled water piping be

Routing for refrigerant, humidification, and
19 routed to the new cooling units?
condensate lines
Overhead or underfloor?

What is the source input voltage to the

20 If no, skip to item 12.
new CRAC / CRAH unit(s)? (volts)

How much current is available to power

21 the new CRAC / CRAH unit(s)? (amps)

Does the cooling solution require both

22 If NO, skip next two items.
critical and non-critical power inputs?

What voltage feeds the critical power

23 Voltage for power to fans and controls
input of the cooling unit?

What voltage feeds the non-critcal Voltage for power to compressor (DX only),
24 power input of the cooling unit? humidifier, and pump

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 20
 Deploying High-Density Pods in a Low-Density Data Center

Data / input Value Comments

What type of physical security system is

25 required for the high-density pod?
Door card, cameras, motion detectors?

What building management system

Monitoring / management

26 (BMS) does the existing data center

use? (Name of system or none used)

What network management system

27 does the existing data center use?
(Name of system or none used)

Identifies the preferred instrumentation level for

What is the preferred level of instru-
28 the high-density pod, using various sensors such as
mentation? (typical or full)
temperature, humidity, water and motion.

How is the structured cabling within the

“Structured cabling” refers to networking cables
29 data center routed? Overhead or
connecting infrastructure equipment.
underfloor?

Schneider Electric – Data Center Science Center White Paper 134 Rev 2 21