FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
(See section 10, rule 13)
1. Title of the invention: TARGET STATE DETERMINATION FOR DATA CENTERS
HAVING HETEROGENEOUS SUBSYSTEMS
2. Applicant(s)
NAME NATIONALITY ADDRESS
TATA CONSULTANCY Indian Nirmal Building, 9th Floor, Nariman
SERVICES LIMITED Point, Mumbai, Maharashtra 400021,
India
3. Preamble to the description
COMPLETE SPECIFICATION
The following specification particularly describes the invention and the manner in which it
is to be performed.

TECHNICAL FIELD
[0001] The present subject matter relates, in general, to data centers and, particularly
but not exclusively, to determination of targets state for data centers having heterogeneous subsystems.
BACKGROUND
[0002] Data centers have become essential for enterprises to function. As is
conventionally known in the art, a data center can be considered to include one or more computing devices and associated systems. The data centers may in turn host one or more applications. These applications may be critical to ensure the business continuity of enterprises, allowing the enterprises to function round the clock.
[0003] As would also be appreciated by a person skilled in the art, different
functionalities within enterprises are increasingly being automated to address the growing needs and requirements of the associated businesses. The above mentioned automated systems rely heavily on business critical data stored in the data centers.
[0004] Furthermore, the resources which are used for implementing the data centers
may be adequate for handling the information at the time the data centers were deployed. However, with evolving businesses the extent and complexity of the associated business critical data may increase. Consequently, costs associated with maintaining data centers may also increase. In such a case, the data centers may have to be tuned to ensure that the data centers function effectively without increasing the cost of ownership. Tuning of the data centers, however, requires planning to ensure that the cost of ownership is optimum.
SUMMARY
[0005] This summary is provided to introduce concepts related to systems and methods
for determining a target state for a data center. This summary is not intended to identify essential features of the present subject matter nor is it intended for use in determining or limiting the scope of the present subject matter.
[0006] System(s) and method(s) for determining a target state for a data centre, are
described. In one implementation, configuration information associated with one or more components within the data center, is received. Subsequently, one or more transformation capabilities are determined. Based on the configuration information and the transformation

capabilities, a plurality of target configurations are generated. In one implementation, the target configurations are implementations which provide the target state of the data center.
BRIEF DESCRIPTION OF THE DRAWINGS
[0007] The detailed description is described with reference to the accompanying
figures. In the figures, the left-most digit(s) of a reference number identifies the figure in
which the reference number first appears. The same numbers are used throughout the
drawings to reference like features and components.
[0008] Figure 1 illustrates a network environment for determining a target state for a
data center, as per one implementation of the present subject matter
[0009] Figure 2 illustrates a method for determining a target state for a data center, as
per one implementation of the present subject matter.
DETAILED DESCRIPTION
[0010] The present subject matter relates to systems and methods for determining a
target state for a data center.
[0011] As mentioned previously, data centers play an important role in the functioning
of any enterprise. Data centers can be understood as computing devices hosting a plurality of applications. Such applications may be essential for performing one or more functions, many of which may be critical to the business objective of the enterprise. The applications hosted on such data centers may also operate on large amounts of data associated with the enterprise to provide various functionalities. A large number of the functionalities are being increasingly automated to ensure that different processes within such enterprises are implemented as efficiently as possible. As would be appreciated, the extent of automation is increasing rapidly to accommodate the rapidly evolving business related demands. As business evolves, data associated with such activities also increases. In some cases, the data centers may not be fully capable of inheriting the increase in the extent of information that is to be handled for ensuring the continuity of the business of the enterprise. Furthermore, in some cases the data centers may not be adequately utilized or managed. In either case, a total cost of ownership (TCO), appearing either directly or indirectly, may be present which may determine the financial impact of automation on the enterprise. For example, data centers deploying a large number of high-end servers achieving desired resource utilization may have a high TCO or total cost of ownership. On the other hand, data centers deploying a lesser

number of servers but achieving same or similar levels of resource utilization may, in turn, have a less total cost of ownership.
[0012] As mentioned above, in case where the extent of automation of one or more
functions within the enterprise has increased, it is quite likely that the associated TCO may have also increased. Besides the increase in the TCO, data centers handling data characterized by both an increased scale as well as complexity may not be efficient and reliable for ensuring the business continuity of any business enterprise. For example, data centers, associated with banking, financial services and insurance, which are not capable of handling large volumes of data associated with the clients are likely to disrupt services or at least make the data centers run in an inefficient manner.
[0013] Typically, the data centers include a plurality of subsystems or components.
Such components can also be, for the purposes of the preset description, considered as part of the subsystems within the data centers. The subsystems typically are not heterogeneous, i.e., they differ either in hardware or in terms of the functionality being implemented for which they are deployed. The subsystems may be further identifiable or characterized by way of one or more attributes. Examples of such attributes include, but are not limited to, inventory such as server racks, network ports, location of the servers within the data centers, etc. Such attributes can be considered to describe the present state or the as-is state of the data centers. Returning to the scenario as discussed above, it might be the case that the data centers need to be upgraded such that the data centers are right-sized. Right-sized data centers can be understood as data centers, which are configured to handle the processing of business critical information for implementing the functions within the enterprise. The right—sizing of data centers can be implemented by way of hardware implementations, such as utilizing new servers or similar equipment, or can be implemented by way of software, such as scheduling, by an application, the manner in which requests from one or more client devices are processed by the data centers. When different hardware or software components or subsystems are to be upgraded, they can either be replaced in their entirety or can only selected components or subsystems can be upgraded.
[0014] Transforming the data centers from the as-is state to a target state, is
conventionally implemented based on an analysis of the as-is state of the data centers. The analysis of the as-is state of the data centers may include determining the risks, benefits, constraints and/or side-effects in introducing one or more changes within the data centers as a result of the right-sizing. In such a case, proposal of changes to the data centers, such as

changes in the hardware or software, is conventionally based on either intuition or experience of the system administrator recommending such changes.
[0015] Furthermore, no standardized basis exists which prescribes the approach as to
how the data centers can be analyzed. Therefore, the basis on which the analysis is performed may differ from one data center to another. Different data centers can also include different components or subsystems, which may also necessitate customized solutions for different data centers.
[0016] Other conventional mechanisms aim at determining optimum target state for the
data centers based on only one dimension. For example, the viability of implementing a right-
sizing of a given data center may be based only on the new technology which is to be
implemented. It may also be the case that determination of target state of the data centers may
either deal with sizing an application or sizing of hardware subsystems. Such conventional
mechanisms however also fail to consider business case scenarios for planning the right-
sizing of the data centers under consideration. Furthermore, determining the appropriate
configuration for the target state of data centers including heterogeneous subsystems may be
an additional challenge as each of the subsystems within the data centers have to be
considered to determine whether such subsystems should be involved in right-sizing, or not.
[0017] Systems and methods for determining a target state for a data center are
described. Determining a target state for a data center is based on information associated with the data centers. The information associated with the data centers can be indicative of the structure of the data centers and/or the manner in which the data centers perform or behave. Based on the information associated with the data centers, one or more transformation capabilities (interchangeably referred to as transformation levers) are identified. Once identified, different transformation proposals, which can be used for affecting the right-sizing of the data centers under consideration, can be obtained.
[0018] In one implementation, determining a target state for a data center involves
determining configuration information of the as-is state of the data centers. The configuration information in relation to the data centers can be obtained either, say from a central inventory repository storing such information, or can be requested from a user by way of a manual input. The configuration information can include information associated with hardware subsystems within the data centers, as well as information indicating one or more applications which are deployed within the data centers.
[0019] In another implementation, the configuration information can be checked for
one or more errors. For example, configuration information such as the information obtained

from an inventory repository is typically manually entered by one or more data operators. In such cases, error arising due to manual entry of such information may be present. Furthermore, other information such as name of the hardware subsystems may be incomplete. In such cases, the system for determining a target state for a data center can check the configuration information for consistency, missing data, erroneous data. Once checked, the configuration information can be further standardized. In one implementation, the configuration information can be checked based on one or more rules. For example, the configuration information can be matched with one or more reference information to check whether any errors are present within the configuration information. The reference information can be obtained either from a predefined repository or can be requested from a user, such as a system administrator in real-time.
[0020] The rules can be executed to determine the extent of matching of the
configuration information with the reference information. If the extent of matching is above a threshold value, the appropriate reference information can be considered as an entry for the configuration information. For example, an incomplete server name when compared with the reference information may identify the name of the server to be X. Accordingly, the name of the server within the configuration information can be updated, i.e., would be updated as X. In such a manner, the configuration information can be standardized. In another implementation, in case the comparison fails to provide any appropriate matching information, the configuration information can be provided to the user, say a system administrator, for review. Based on the review, the system administrator can provide the appropriate information.
[0021] Besides the configuration information, various data centers related objectives
are also determined. The objectives can include aspects which contribute directly or indirectly to the efficient functioning of the data centers, and in turn contribute to the business continuity of the enterprise. Examples of such objectives can include, but are not limited to cost efficiency, improved system behavior, higher resource utilization, etc. As would also be appreciated, such objectives would be met through various implementations applied to the data centers. Such implementations or transformation capabilities include server consolidation, virtualization and cloud migration. The implementations or transformation capabilities, when implemented, would achieve the desired objectives. For example, server consolidation when implemented is likely to make the data centers more cost efficient and provide improved functioning of the data centers. It would be appreciated by persons skilled in the art that the examples provided for objectives and the transformation capabilities are

only illustrative and not exhaustive. Other objectives and transformation capabilities would also be within the scope of the present subject matter.
[0022] Once the configuration information, the objectives and the transformation
capabilities are obtained, one or more achievable target configurations are determined. The target configurations, in one implementation, indicate the manner in which the one or more transformation capabilities can be utilized. As also provided above, the transformation configurations when implemented through employing one or more obtained transformation capabilities, would result in achieving any one or more of the desired objectives. In one implementation, the transformation configurations identify a set of subsystems within the data centers upon which the transformation capabilities can be applied to obtain a right-sized data center environment.
[0023] In one implementation, the configuration information, the objectives and the
transformation capabilities can be further associated with one or more target configurations. In such a case, based on the configuration information, the specified objectives and the transformation capabilities, one or more appropriate target configurations can be determined. As described previously, the configuration information is indicative of the components or subsystems which form a part of the data center under consideration. Depending on the as-is state of the data centers as gathered based on the configuration information, the objectives specified by, say a user and the one or more transformation capabilities, the appropriate target configurations can be identified. For example, configuration information associated with subsystems which have low computational capability may be associated with one or more target configurations which prescribe subsystems with equivalent or greater computational capacities.
[0024] In one implementation, each of the target configurations, when determined, can
also be associated with one or more constraints. The constraints can either be functional, say in terms of the computational resources that can be utilized, or the cost which can be incurred for effecting the right-sizing of the data center under consideration. Based on the constraints, appropriate business scenarios can be generated. The business scenarios may indicate various impacts on utilizing certain transformation capabilities as opposed to others. For example, server virtualization may increase data security or disaster recovery but may have associated expenses or other costs. Therefore, such business scenarios can be considered before the transformation, i.e., the right sizing can be executed.
[0025] Continuing with the example as provided above, a user may specify
computational capability as a constraint. For example, the target state of the data centers may

be required to have processors which are only quad-core. Therefore, only such target configurations are determined which include subsystems having quad-core processors. Few other examples of such constraints include criticality of the applications, family of servers, etc. It would be appreciated by a person skilled in the art that the constraints as exemplified above are only illustrative and not exhaustive. The systems and methods for determining a target state for a data center can be based on other such constraints as well without limiting the scope of the present subject matter.
[0026] As can be gathered from above, the determining a target state for a data center is
based on the information associated with the system, transformation levers, desired objectives and so on. Such determination of a target state of the data centers is parametric based and allows for a business case generation. This allows for greater visibility into the inputs that would be required for attaining the target state of the data centers. Consequently, the data centers thus implemented would be more stable and efficient in their functioning ensuring business continuity for the different enterprise functions.
[0027] While aspects of described systems and methods for determining a target state
for a data center can be implemented in any number of different computing systems, environments, and/or configurations, the embodiments are described in the context of the following exemplary system(s) and methods.
[0028] Fig. 1 illustrates various components of a target state determination system 100,
for determining a target state for a data center (not shown in the figures) according to an embodiment of the present subject matter. In said embodiment, the target state determination system 100 includes one or more processor(s) 102, interfaces 104, and a memory 106 coupled to the processor(s) 102. The processor(s) 102 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor(s) 102 are configured to fetch and execute computer-readable instructions and data stored in the memory 106.
[0029] The functions of the various elements shown in the figure, including any
functional blocks labeled as “processor(s)”, may be provided through the use of dedicated hardware as well as hardware capable of executing software in association with appropriate software. When provided by a processor, the functions may be provided by a single dedicated processor, by a single shared processor, or by a plurality of individual processors, some of which may be shared. Moreover, explicit use of the term “processor” should not be construed

to refer exclusively to hardware capable of executing software, and may implicitly include, without limitation, digital signal processor (DSP) hardware, network processor, application specific integrated circuit (ASIC), field programmable gate array (FPGA), read only memory (ROM) for storing software, random access memory (RAM), non-volatile storage. Other hardware, conventional and/or custom, may also be included.
[0030] The interface(s) 104 may include a variety of software and hardware interfaces,
for example, interface for peripheral device(s), such as a keyboard, a mouse, an external memory, and a printer. Further, the interface(s) 104 may enable the target state determination system 100 to communicate over a communication network (not shown), and may include one or more ports for connecting the target state determination system 100 with other computing devices, such as web servers and external databases. The interface(s) 104 may facilitate multiple communications within a wide variety of protocols and networks, such as a network, including wired networks, e.g., LAN, cable, etc., and wireless networks, e.g., WLAN, cellular, satellite, etc.
[0031] The memory 106 may include any computer-readable medium known in the art
including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. The target state determination system 100 also includes module(s) 108 and data 110.
[0032] The module(s) 108 include routines, programs, objects, components, data
structures, etc., which perform particular tasks or implement particular abstract data types for
determining a target state for a data center. The module(s) 108 further include data
preparation module 112, target state recommendation module 114 and other module(s) 116.
[0033] The data 110 serves, amongst other things, as a repository for storing data
processed, received and generated by one or more of the modules 108. The data 110 includes configuration information 118, objectives 120, transformation capabilities 122, target configurations 124, targeting rules 126 and other data 128.
[0034] In one implementation, the data preparation module 112 receives information
associated with one or more data centers. The received information can be stored as configuration information 118. The configuration information 118 indicates various functional as well as structural aspects of the associated data centers. Data centers, in general, include one or more computing devices and other subsystems. The computing devices can be implemented using a single or multiple servers. Furthermore, other equipment may also be

utilized for enabling a communication between different computing devices within the data centers. Each of the computing devices within the data centers can further include a variety of applications performing different functions. The functions may either implement certain computational functionality to the data centers or can be used for performing business critical functions of an enterprise.
[0035] To determine a target state for a data center, the data preparation module 112
receives configuration information 118. The configuration information 118 can be received from a central inventory repository or can be manually received from a system administrator. Once received, the configuration information 118 is checked for errors. For example, the data preparation module 112 can execute one or more rules to determine whether the configuration information 118 is error-free. The configuration information 118 can be considered to be erroneous when the same is either not complete, not correct, includes missing fields and values, or is not appropriate in itself, i.e., in a format which is not conventionally used for such systems. Examples of configuration information 118 include, but are not limited to, information in relation to processes, financials, applications, resource utilization, etc.
[0036] The data preparation module 112 may check the configuration information 118
based on one or more rules stored in other data 128. For example, the data preparation
module 112 may compare the configuration information 118, say indicating one or more
server names specified incorrectly, with one or more entries of a reference database. The
reference database may in turn include a list of server names. The entries within the reference
database are in a consistent format. The format can be in conformance with the information
as required by the target state determination system 100. Furthermore, the reference database
can also include additional information which may be required by the target state
determination system 100. As would be appreciated by a person skilled in the art, the
reference information database can be based on previously defined information gathered from
numerous sources. For example, various hardware and functional attributes of one or more
subsystems may be provided by the Original Equipment Manufacturers (OEM) themselves,
or can be compiled manually based on information provided by the OEMs.
[0037] The data preparation module 112, on comparison, may determine the extent of
matching between the configuration information 118 under consideration and the entries within the reference database. In case the matching extent is above a threshold value, the entry within the reference database can be taken as the information in the configuration information 118. The present process can be repeated until appropriate server names are

obtained in the appropriate format. In case no appropriate name is determined, the system
administrator can be requested to provide the names of the server in the desired format.
[0038] As also mentioned previously, the data preparation module 112 can also
determine missing information. Continuing with the example provided above, the configuration information 118 may in some cases include the server information but may not include the appropriate socket related information. In such cases, once the appropriate entry for the server under consideration is identified in the reference database, the data preparation module 112 may obtain the socket information associated with the relevant server. In such a manner, the data preparation module 112 can also determine and provide missing information in the configuration information 118. Similarly, incorrect configuration information 118 can also be rectified. In one implementation, the suggested changes to the configuration information 118, obtained from the reference database, can be prompted to the system administrator before they can be applied.
[0039] Once the configuration information 118 is obtained, the target state
recommendation module 114 determines one or more objectives 120. The objectives 120 can include aspects which contribute directly or indirectly to the efficient functioning of the data centers, and in turn contribute to the business continuity of the enterprise. Examples of such objectives 120 include, but are not limited to cost efficiency, improved system behavior, higher resource utilization, etc. Each of the objectives 120 are further associated with one or more transformation capabilities 122. Each of such transformation capabilities 122 can be considered to be such that, when implemented over one or more subsystems, the transformation capabilities 122 achieve the desired objective. Such transformation capabilities 122 include server consolidation, virtualization and cloud migration. For example, an objective 120 intended for effective server provisioning, reducing costs due to hardware vendor lock-in, improving disaster recovery can be accomplished in one instance by a transformation capability, such as server virtualization. Similarly, other plurality of objectives 120 may be further associated with one or more transformation capabilities 122. In one implementation, the objectives 120 and the transformation capabilities 122 may be associated by way of a mapping. In such a manner, appropriate transformation capabilities 122 associated with different objectives 120 can be determined.
[0040] As described above, once the objectives 120 are determined, the target state
recommendation module 114 determines the associated transformation capabilities 122. In one implementation, the objectives 120 can be selected by a system administrator. It would be appreciated by persons skilled in the art that the examples provided for objectives and the

transformation capabilities are only illustrative and not exhaustive. Other objectives 120 and
transformation capabilities 122 would also be within the scope of the present subject matter.
[0041] Once the configuration information 118, the objectives 120 and the
transformation capabilities 122 are obtained, the target state recommendation module 114
generates one or more achievable target configurations 124. The target configurations 124, in
one implementation, indicate the manner in which the one or more transformation capabilities
can be utilized to achieve a desired target state for a given data center. As also provided
above, the transformation capabilities 122 when implemented for the data centers under
consideration would result in achieving any one or more of the desired objectives 120.
[0042] In one implementation, the target state recommendation module 114 determines
the target configurations 124 based on one or more targeting rules 126. The targeting rules
126 may include rules which, when executed, allow the target state recommendation module
114 to analyze the obtained configuration information 118 and the transformation capabilities
122. Based on the analysis, one or more target configurations 124 are obtained.
[0043] In one implementation, the targeting rules 126 are based on different parameters.
For example, some of the targeting rules 126 may be configured based on the apparent costs that would be incurred if the transformations as per the target configurations 124 are implemented. Other examples of such parameters include benefits, risks or other side effects which might result from the transformations as per the obtained target configurations 124. In yet another implementation, the target state recommendation module 114 may further analyze the configuration information 118 and the transformation capabilities 122 based on analytics such as text-based analytics, time series analysis, graph analysis, etc.
[0044] The configuration information 118, the objectives 120 and transformation
capabilities 122 can be associated with one or more target configurations 124. As also indicated previously, based on the configuration information 118, the objectives 120 and the transformation capabilities 122, one or more target configurations 124 for affecting the transformation of data centers under consideration, is determined. In such a case, the targeting rules 126 can be executed to determine which of the target configurations 124 can be selected for the associated configuration information 118, objectives 120 and the transformation capabilities 122.
[0045] For example, there may be a constraint of the computational hardware to be
quad-core processor based. Based on the constraint, the target state recommendation module 114 may obtain one or more appropriate targeting rules 126 which qualify the computational hardware requirement. Therefore, only such target configurations are determined which

include subsystems having quad-core processors. Few other examples of such constraints include criticality of the applications, family of servers, etc. It would be appreciated by a person skilled in the art that the constraints as exemplified above are only illustrative and not exhaustive. The systems and methods for determining a target state for a data center can be based on other such constraints as well without limiting the scope of the present subject matter.
[0046] On obtaining the target configurations 124, one or more subsystems, such as
servers within the data center, are identified. As mentioned previously, the target
configurations 124 when implemented on the identified subsystems would result in a right-
sized environment. The target configurations 124 can be further be subjected to a plurality of
constraints, say one or more constraints stored in other data 128. Based on the constraints one
or more business scenarios can also be generated. The business scenarios may indicate
various impacts on utilizing certain transformation capabilities as opposed to others.
[0047] In one implementation, the constraints can also be gathered from the
configuration information 118. For example, the configuration information 118 may indicate the information relating to the end of life (EOL) of a server. As would be appreciated EOL are very likely to affect business scenarios. In such a case, the subsystems under consideration can be either refreshed, i.e., replaced by new hardware, or in other cases, no changes are made to such subsystems.
[0048] The systems and methods for determining a target state for a data center are
explained in the following exemplary embodiment, which is only illustrative, and should not be considered to be limiting the scope of the present subject matter. In one implementation, objectives include, for example, rationalization and modernization of existing servers within the data centers, discarding servers that have become obsolete or have approached their EOL, server consolidation to improve resource utilization and for reducing operational costs and server virtualization. The aforementioned objectives are stored in the target state determination system 100 as objectives 120. Corresponding to the objectives 120, the associated transformation capabilities 122 are also identified.
[0049] Furthermore, the as-is state of the data center under consideration, i.e., the data
center to undergo transformation, is assessed based on configuration information 118 which includes server description, i.e., server family, server make or model, location of the server, and information as to the environment, such as production or testing, in which the server is implemented. In the present implementation, the configuration information 118 can also include information associated with one or more applications that was running in these

servers. For example, such information may indicate that the applications which are running
are functional critical or business critical. Once the above mentioned configuration
information 118 is collected, the data preparation module 112 further processes the
configuration information 118 to determine whether the data includes any errors or is not in
conformance with one or more requirements. To correct the errors and for standardizing, the
data preparation module 112 compares the configuration information 118 with reference data.
[0050] Based on the standardized configuration information 118, the objectives 120 and
the transformation capabilities 122, one or more target configurations 124 are obtained. Continuing with the present example, Table 1 (as provided below) is an exemplary configuration information 118, as obtained based on information associated with the subsystems within the data center:
Table 1

Number of locations in which the servers are distributed 4
Type and make of servers used 159 numbers of X86 based servers 105 numbers of SPARC based servers
Percentage of servers used for production 54%
Servers without any usage information or involved in non-production usage 41
Total count of physical servers 324
Total count of virtual servers 164
Pre-virtualized servers hosting 164 server images 20
Servers without its Make and Model information 40
Total servers considered for server consolidation exercise 264
[0051] Once the configuration information 118, for example as illustrated in Table 1, is
obtained, the appropriate transformation capabilities 122 are applied. In one implementation, the targeting rules 126 can be applied on the configuration information 118 and the transformation capabilities 122 to obtain one or more target configurations 124. The target configurations 124 can identify, for the present example, the appropriate server subsystems which when implemented would achieve the desired one or more objectives. In the present implementation, the target configurations 124 can specify a combination of either Dell®

PowerEdge 2950 or Dell® PowerEdge 6850 as target subsystems for X86 based servers. The
user when presented with these options can select one of the subsystems for further analysis.
[0052] In the present example, the target server, say the X86 based Dell® PowerEdge
2950 may be selected. Once selected, the target state determination system 100 determines the number of target subsystems that may be required. In one implementation, the target state determination system 100 may also determine the number of previously existing servers and determine the required target subsystems based on varying utilization. Based on the above, the target state determination system 100 may determine the number of servers that are to be replaced, as presented in Table 2 below:
Table 2: X86 based Dell PowerEdge 2950 2/6

Partition As-Is
Server
Count No. of servers
remaining
unchanged No. of servers to be optimized New Servers Compression Rate
At 40 % Utilization
Unrestricted1 159 0 20 20 7.95
Production 87 0 13 13 6.7
Non Production 72 0 7 7 10.3
At 50% Utilization
Unrestricted1 159 6 25 19 8.05
Production 87 4 17 13 6.38
Non Production 72 0 8 8 9
At 60% Utilization
Unrestricted1 159 5 23 18 8.5
Production 87 7 20 13 6.2
Non Production 72 1 10 9 7.9
Unrestricted1 All ser vers belongi ng to a family without any usage or loc ation constra int
[0053] Once the appropriate recommendations are obtained, various constraints can be
applied to the target configurations 124 to determine the appropriate business case scenarios. Depending on the requirement appropriate subsystems can be selected. For example, it may be determined that cost savings for implementing new servers with old servers at 50% utilization are most cost effective.

[0054] Fig. 2 illustrates a method 200 for determining a target state for a data center, in
accordance with an embodiment of the present subject matter. The method 200 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, etc., that perform particular functions or implement particular abstract data types. The method 200 may also be practiced in a distributed computing environment where functions are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, computer executable instructions may be located in both local and remote computer storage media, including memory storage devices.
[0055] The order in which the method 200 are described is not intended to be construed
as a limitation, and any number of the described method blocks can be combined in any order to implement the method 200, or alternative methods. Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method 200 can be implemented in any suitable hardware, software, firmware, or combination thereof.
[0056] At block 202, configuration information related to one or more subsystems in
data centers is obtained. For example, the configuration information 118 can be received from a central inventory repository or can be manually received from a system administrator. Once received, the configuration information 118 is checked for errors. In one implementation, the data preparation module 112 can execute one or more rules to determine whether the configuration information 118 is error-free.
[0057] At block 204, one or more objectives are identified. For example, the target state
recommendation module 114 determines one or more objectives 120. The objectives 120 can include aspects which contribute directly or indirectly to the efficient functioning of the data centers, and in turn contribute to the business continuity of the enterprise. Examples of such objectives 120 include, but are not limited to cost efficiency, improved system behavior, higher resource utilization, etc.
[0058] At block 206, one or more transformation capabilities are determined based on
the identified objectives. In one implementation, the objectives 120 are associated with one or more transformation capabilities 122. In one implementation, the objectives 120 and the transformation capabilities 122 may be associated by way of a mapping. Based on the mapping, the target state recommendation module 114 determines the associated

transformation capabilities 122. In such a manner, appropriate transformation capabilities 122 associated with different objectives 120 can be determined.
[0059] At block 208, a plurality of target configurations are determined based on the
configuration information and the transformation capabilities. For example, the target state recommendation module 114 generates one or more achievable target configurations 124 based on the configuration information 118 and the transformation capabilities 122. The target state recommendation module 114 determines the target configurations 124 based on one or more targeting rules 126. The targeting rules 126 may include rules which when executed allow the target state recommendation module 114 to analyze the obtained configuration information 118 and the transformation capabilities 122. Based on the analysis, one or more target configurations 124 are obtained.
[0060] At block 210, different business case scenarios are obtained based on one or
more constraints. The target configurations 124 can be further be subjected to a plurality of
constraints, say one or more constraints stored in other data 128. Based on the constraints one
or more business scenarios can also be generated. The business scenarios may indicate
various impacts on utilizing certain transformation capabilities as opposed to others.
[0061] Although embodiments for determining a target state for a data center having
one or more heterogeneous subsystems have been described in language specific to structural features and/or methods, it is to be understood that the invention is not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as exemplary implementations the claimed subject matter.

I/We claim:
1. A system (100) for determining a target state for a data center, the system (100)
comprising:
at least one processor (102); and
memory (106) coupled to the at least one processor (102), the memory (106) comprising:
a data preparation module (112) configured to:
receive configuration information (118) associated with one or more entities within the data center; and a target state recommendation module (114) configured to:
determine at least one transformation capabilities (122); and generate a plurality of target configurations (124) based on the received configuration information (118) and the at least one transformation capabilities (122), wherein the target configurations (124) when implemented provide the target state for the data center.
2. The system (100) as claimed in claim 1, wherein the one or more objectives (120) are defined based on user input.
3. The system (100) as claimed in claim 1, wherein the data preparation module (112) is further configured to check the configuration information (118) for errors based on at least one predefined rule.
4. The system (100) as claimed in claim 3, wherein the data preparation module (112) checks the configuration information (118) based on:
determining an extent of matching one or more entries within the configuration information (118) with a predefined reference information; and
on determining the extent of matching to be greater than a predefined threshold, standardizing the one or more entries based on the predefined reference information.

5. The system (100) as claimed in claim 4, wherein the standardizing the one or more entries comprises inferring missing information based on the predefined reference information.
6. The system (100) as claimed in claim 2, wherein the target state recommendation module (114) determines the at least one transformation capabilities (122) based on the determined objectives (120).
7. The system (100) as claimed in claim 1, wherein the target state recommendation module (114) generates the target configurations (124) based on one or more targeting rules (126), wherein the targeting rules (126) are based on business considerations, technical considerations and risks.
8. The system as claimed in claim 1, wherein the target state recommendation module
(114) generates the target configurations (124) based on one of text-based analytics, time
series analysis, and graph analysis.
9. A method (300) for determining target configurations (124) to obtain a target state for
a data center, the method (300) comprising:
receiving configuration information (118) associated with one or more entities within the data center;
checking the configuration information (118) for conformance with predefined reference information;
determining at least one transformation capabilities (122); and
generating a plurality of target configurations (124) based on the received configuration information (118) and the at least one transformation capabilities (122), wherein the target configurations (124) when implemented provide the target state for the data center.
10. The method (300) as claimed in claim 9, wherein the determining the at least one
transformation capabilities (122) comprises:
determining one or more objectives (120) based at least on user input; and identifying the at least one transformation capabilities (122) based on mapping between the objectives (120) and the at least one transformation capabilities (122).

11. The method (300) as claimed in claim 9, wherein each of the target configurations (124) are associated with one or more constraints, wherein the constraints include a cost for implementing any one or more of the target configurations (124).
12. The method (300) as claimed in claim 11, wherein each of the target configurations (124) are further associated with at least one constraint.
13. The method (300) as claimed in claim 12, further comprising:
receiving input from a user indicating one or more constraints; and
generating business scenarios based on the target configurations (124) and the one or more constraints.
14. A non-transitory computer-readable medium having embodied thereon a computer
readable program code for executing a method, the method comprising:
receiving configuration information (118) associated with one or more entities within the data center;
checking the configuration information (118) for conformance with predefined reference information;
determining at least one transformation capabilities (122); and
generating a plurality of target configurations (124) based on the received configuration information (118) and the at least one transformation capabilities (122), wherein the target configurations (124) when implemented provide the target state for the data center.