Pradeep n singh_praveenkyadav

Application of Business Analytics in Big Data of Power Sector
Pradeep N. Singh & Praveen K. Yadav
Department of Information Systems & Power Management,
University of Petroleum & Energy Studies (UPES), INDIA
ABSTRACT: - This paper provides how Business Analytics can be proving to be boon for Indian power
sector. It can better manage it along making the Indian power sector more financial viable thus promoting
competition in the Power Market, which is one of the prime objectives of Indian Electricity Act, 2003. Its
potential is not limited to distribution sector utilities but also has wide scope in Power Generating Utilities
and Transmission companies. This paper discusses the role of integration of Business Analytics with Big
Data of power sector, which is also an important function in power quality based services movement. It
also gives insights of Software Architecture, software requirements and software system attributes. It also
discusses the crucial role of energy efficiency and how business analytics can help in reducing the energy
intensity for India.
ARTICLE INFO: - General Terms: Energy Demand, Sustainability, Competitive edge and Analytic
Reports.
Keywords: AMR, MRD, CMRI, MIDAS, Energy Efficiency, Power Management, Data management
systems, Energy efficiency, Technical & Commercial Losses, Energy Intensity and Energy Conservation.
1. INTRODUCTION
Indian Power Sector is mainly governed by the
Ministry of Power. It consists of three major
segments – Generation, Transmission &
Distribution. Generation is further bifurcated into
three sectors namely Central, State & Private
Sector.
India is world’s sixth largest energy consumer,
accounting for 3.4% of global energy feeding.
Due to India’s economic rise, the demand for
energy has grown at an average of 3.6% per
annum over the past 30 years. At the end of
May 2013, the installed power generation
capacity of India stood at 225.133 GW, while the
per capita energy consumption stood at 778
KWh (Jan 2012).
Introduction to power quality based services and
increase in priorities towards “retail” players In
India, there is need of full-fledged retail markets
in present scenario. End-users are not
participating in the present markets. Integration
of renewable resources such as solar power and
wind power are going at one end. Upcoming
policies, regulations and standards are
encouraging the integration of small-scale
renewables to the utility grid. At this situation, it
is expected that advent of automation and Smart
Grids, SCADA (Supervisory Control & Data
Acquisition), MIDAS (Modular Integrated

Distribution Automation System), OMS (Outage
Management System), and on-line metering and
billing in India may enable retail markets for
open up competition avenues for the entry of
end-users/consumers
The integration of Business Analytics with Big
Data of power sector is also an important
function in power quality based services
movement. This requires effective metering and
billing standards with effective communication
protocols. Apart from these necessary
requirements, there will be a need for upgrading
the present power systems. In this direction, this
paper has identified the need for introduction of
power quality based services to few retail
markets as per the consumers requirements in
the respective market. The reason behind this
proposal is increasing need of reactive power at
the load end and increasing focus on power
quality services that directly increases revenue
of mini distribution franchises or Distribution
Company.
1.1. PURPOSE
Analytics uses an innovative approach whereby
user gets a complete view of all the meters
whose data is downloaded and the utility gets
the complete analytics of their business
processes and the knowledge about the areas
where improvement in terms of technology as
well as other aspects are required. The software
gives a logical view of the entire meter reading
data according to various parameters. All the
data available from the meter can be converted
into database & spreadsheet format for further
analysis & billing purpose. A flexible wizard is
being presented to the user for converting
various information on a format using which
meter data can be converted to database or
spreadsheet.
1.2. Web Application
The web application is the front end of the
software. This web application will have following
objectives:
1. Integrate the application with ISU CSS.
2. Facilitate to monitor, analysis, and control
and report various parameters of the MRD
(Meter Reading Data).
1.3. Server Application
The server application is the back end of the
software. This server application will have
following objectives:
An application server is a server that delivers
software applications with services such as
security, data services, transaction support, load
balancing, and management of large distributed
systems.
1.4. Scope
This Software helps to analyse MRD. Billing,
meter change details. It helps various
departments in various ways & indirectly helps in
loss reduction.
1. Enforcement to monitor theft activity of
consumers.
2. ONM to monitor low voltage, unbalanced
current, etc.
3. Legal court cases supporting data on basis
of MRD.
4. Meter testing labs.
2. Business Analytics Methodology
Business Analytics is a strategic initiative by
which organizations measure, analyze, drive
and evaluate the effectiveness of their
competitive strategy. Business Analytics
projects go through the following stages as
shown in Fig. 1.

Fig 1: Life cycle of BA System
2.1. Analysis
Every Business Analytics project should clearly
justify the cost and benefits of solving a
business problem. Requirement analysis is
performed including a predefined set of critical
path factor and key performance indicators.
The end users require kPIs. The analysis phase
provides a high-level design of the various
components of the solution. Because of dynamic
nature of Business Analytics projects,
modifications in objective, estimate, technology,
people, sponsors and users can influence the
success of the project.
2.2. Designing
Based on the requirements and the complexity
of the solution, appropriate Business Analytics
technologies are selected. Prototyping is best
method for analysis of the functional
deliverables. The access requirements of the
business must match with database design
schema In most case, writing extensions to the
tool capabilities and preprocessing the data
are frequently required.
2.3. Development
The life cycle of Business Analytics system
repeats with the operating methodology at a new
level of focus. The full process of flow of data or
information across the organization consisting
analysis, modification, re-evaluation,
optimization and tuning.
2.4. Deployment
Once all components of the Business Analytics
application are tested, the application is
deployed to the user ends. The success of
Business Analytics project primarily lies on the
quality of end user training and support. This
stage includes the development of predefined
reports and analyses for business users, and
laying the groundwork for advanced high-level
analytics in the future.
2.5. Evolution
Measuring the success of application, extending
the Business Analytics application across the
enterprise or organization and increasing cross-
functional information sharing are the goals of
evolution.
3. Business Analytics in Power Sector
Engineering analysis may require a full year/Half
year of available data for analysis.
3.1. Categorization of Knowledge Area
This knowledge area can be briefly
characterized into following major categories:
Analysis
Desiging
DevelopmentDeployment
Evolution

Fig 2: Business Analytics Knowledge Area
1. Operational/Analytical Data: These
operational applications are the real-time or
near real-time applications like available
customer meter data, Grid connected DG
tracking information transfer capability (ATC)
margins, spot bidding.
2. Front-end analytics: These analytics
functions help the business to operate
beyond real-time management of the grid.
Examples include forecasting methods and
models that support generation planning and
development, demand management
programs or spot market power purchases.
These data uses are typically same-hour,
same-day applications, but there is time
limitation to scrub the data and try again to
get data or information from the field.
3. Back-end analytics: These analytics
functions are the non-real-time application
that provides rate analysis (settlement
mechanisms) and decision making, based on
the processing of data from the KCC, MRD
from AMR, and CMRI to XML through API,
SCADA. The analytics transform data into
actionable or decision-making information.
This is where the planners, accountants,
engineers and standards engineers will find
the information they need to do their jobs.
3.2 Business Analytics application in Power
Sector
Utilities are using analytics to:
1. Understanding and developing customer
profiles such as length of time in business,
the type of business, number of employees,
program results and so on.
2. Understand which are the areas of high
Transmission & Distribution Losses and
analyze their causes.
3. Improve the revenue realization by
overcoming by reducing commercial losses.
4. Analyzing generating station efficiencies and
T&D Efficiencies.
5. Useful for analyzing the consumer energy
consumption pattern and load flow studies.
6. Useful for load forecasting and energy
balancing studies.
7. Useful for generating Management
Information system reports.
8. Can be very useful in analyzing the demand
and supply miss-match and to bridge the
gap between them.
9. Understanding the segments, objectives and
prioritize customers for specific energy
efficiency.
10. Generation of useful information from the
huge amount of data coming in the utilities
from diverse applications.
11. Analyzing the past data and records.
12. Useful for faster decision making based on
real time data and factual data and to review
the progress of the implemented decisions.
13. Enhancing and empowering business
processes to become more profitable.
14. Report generation as per Organizational
structure.
These are the some of the applications specified
above and much more applications of it are
developing and will be developed in future for
Indian Power Sector utilities.
Operational
Back-EndFront-End

3.3 Necessity of Business Analytics for
Indian Power Sector
Complex Environment, political, economic and
societal pressures are placing intense demands
on power sector to make smarter decisions,
deliver results and demonstrate accountability
for meeting the energy shortage issue prevailing
in the Indian Power Sector.
An unprecedented “information explosion” both
facilitates and complicates the ability of Power
utilities to achieve and influence the desirable
outcomes. A incredible opportunity exists to use
the large amount of data to make better, fact-
based decisions. Yet, the amount of data and its
increasingly diverse and interactive nature can
also paralyze power utilities as they try to
separate the noteworthy from the not-worthy.
Analytics goes beyond reporting and providing
the mechanism to sort through this turmoil of
information and the utilities respond with better
decisions.
Today, however, most power utilities are
spending more time collecting and organizing
data than to analyze it. Analyzing talent also
tends to be more concentrated within
organizations, rather than persistent across
them. This can make it more difficult to discover
useful insights which can be obtained by looking
at information across multiple agencies and
databases.
To utilize its potential power in the public sector,
analytics will have to become a core
management competency. Building competency
will require utilities to focus on four strategies –
1. Focus on the desired outcomes to move
beyond the issues.
2. Direct the management of information
around its use.
3. Use analytics-enabled insights to meet
specific objectives.
4. Model and embed analytics discipline in
management practices.
To improve the cash flows to the power
distribution companies and thus to the
transmission and generating companies, the
potential of Business Analytics can be effectively
utilized and it will also help in making this sector
financially viable and better management will be
accomplished.
4. Business Analytics in Energy
Efficiency
India currently is facing major shortage of
electricity generation capacity, even though it is
the world’s fourth leading energy consumer after
United States, China and Russia. For providing
simple access of electricity to its consumers, it
will require large capital investments. The
increasing demand for demand for power has
increased usage of fossil fuels which has led to
the greater imports of them due to shortage of
our production resources and depleting fossil
fuel reserves.
In this context, energy efficiency and
conservation both play a dominant role. It has
been estimated that nearly 25000 MW can be
saved by implementing end use energy
efficiency and demand side management
techniques throughout India.
The demand for energy can be reduced by
decreasing the energy intensity and improving
the energy efficiency.
4.1. Energy Intensity
It is the ratio of energy consumption to the Gross
Domestic Product (GDP). It is calculated as
units of energy per unit of GDP. It is a degree of
energy efficiency of a nation’s economy.

Higher the energy intensity higher will be the
price of converting energy into GDP and vice
versa. Below a certain level of progress, growth
results in increase in energy intensity. With
further growth in economy, it starts declining.
The energy intensity augmented from 0.128
KWh in 1970-71 to 0.165 KWh in 1985-86, but is
has again come down to 0.148KWh in 2011-12.
Fig 3: Trend in Energy Intensity per rupee
(1970-71 to 2011-12)
4.2. Importance of Energy Efficiency &
Conservation
Importance of Efficient use of energy and its
conservation lies in the fact that one unit of
energy saved at the consumption level reduces
the need for fresh capacity creation by 2 times to
2.5 times. Further, such saving over efficient use
of energy can be achieved at less than one-fifth
the cost of fresh capacity creation. Energy
efficiency will definitely supplement our efforts to
meet power need, apart from reducing fossil fuel
feeding.
4.3. Shift from Energy Conservation to
Energy Efficiency
The policy concepts and goals will have to be
shifted from “energy conservation” to “energy
efficiency”, and from “energy inputs” to the
“effectiveness of energy use” and “energy
service area”. Formation of new power
generation volume is costly and demands long
gestation period whereas energy efficiency
activities can make available additional power at
reasonably low investments within a short period
of time.
4.4. Drivers of Energy Efficiency growth in
India
The main drivers are –
Energy Demand
Competitive Advantage
Regulatory
Sustainability
Climate Change
Over the last 20 years, primary energy
consumption in India has increased from
1.02x108 MTOE per year to 6.15x108 MTOE
per year. Information used from US Energy
Information Administration.
4.5. Role of Analytics in Energy Efficiency
Power Utilities energy efficiency program
development considers the following aspects:
1. Potential business and customer value
2. Funding Mechanisms
3. Regulatory requirements and expectations
4. Customer Incentives
5. Integrated and multi-channel marketing and
sales plans
6. Identification of trade allies and contractor
partners
7. Comprehensive operative plans, including
plans for customer support
8. Measurement and verification
9. Accounting and financial management
Data analytics touches and provides valuable
input into all above factors. Feedback gained
from analytics around existing programs offers
useful insight. It is playing a crucial role in

reaching the participation and consumption
reduction targets.
5. High Level Framework for BA in Big
Data of Power Sector
The requirements for what type of Big Data is
capture and store must be documented in Big
Data architecture. In addition, the requirements
for delivering Big Data to the users has to be
analyzed and role based. If a Big Data
warehouse is purchased, database has to be
extended with features that are required by
Business Analytics applications. If a Big Data
warehouse is built, the database will have to be
designed based on the Big Data architecture
developed during the previous step.
At the highest and most abstract level,
the logical framework view of Simulator
application can be considered a set of
cooperating services grouped into the following
layers, as shown in figure below:
Fig 4: High-level architecture view of Analytics Software
in Power Sector
6. System Requirement for Running
Business Analytics Application
6.1. User Classes and Characteristics
There are three types of use in the application
viz. Master, Admin and User View. These user
types are defined below:
Master: A user who can manage the
user accounts, their permissions and
type.
Admin: A user who can edit and verify
device data, manage validation and
approximation rules.
User View: A user who can view data,
process and generate reports
Basic application functionalities are accessible
to all users in Super Admin, Admin and User
View. Along with this, some features are only for
Master and some are for Admin.
6.2. User Interfaces
This web application can be access through a
latest web browser. The interface will be viewed
best on 1024 x 768 pixels resolution setting. The
application will be fully compatible with following
browsers and operating systems:
 Operating System
This application is independent
of operating system.
 Browser
IE 8.0 or above
Google Chrome 12.0 or above
Firefox 4.0 or above
Latest web browser on Android
2.2 or above
User must login to access any part of the
application. Not all the modules will be
accessible to every user. Each module is visible
Data
Base
XML
AMR CMRI
Device
User
Interface
Web
Application
MRD

to only selected users that are mentioned in the
user type association.
6.3. Hardware Interfaces
The requirement of server and client side
hardware interfaces and network hard disk are
given below:
 Windows Server Side Hardware
Processor: Intel / AMD Server
Processor
RAM: 4GB or above
Hard Disk: 10 GB
 Database Server Side Hardware
Processor: Intel / AMD Server
Processor
RAM: 8GB or above
 Client Side Hardware
Processor: Pentium III or above
RAM: 256MB or above
Hard Disk: 10 GB (for OS and
Browser installation)
6.4. Software Interfaces
The requirement of server and client side
software interfaces are given below:
 Windows Server Side Software
Operating System: Windows
Server 2003
Environment: .NET Framework
4.0 or above
IIS 6.0 with latest updates
 Database Server Side Software
Database: Microsoft SQL Server
2008 r2
 Client Side Software
Operating System: OS
independent
Screen Resolution: 1024x768 or
above
Web Browser: Latest web
browser
7. Business Analytics Software System
Attributes
Fig 5: BA Software System Attributes
7.1. Security:
The application is password protected .User will
have to enter the correct id and password in
order to access the application.
7.2. Maintainability:
The application is designed in sustainable
manner. It will be easy to integrate new
requirements in the individual modules.
7.3 Portability:
The application will be easily manageable on
any windows-based system that has any internet
browser.
8. Organizations wishing to implement
Business Analytics face the following
challenges:
1. Providing controlled access to extensive
resources with limited capacity to devices.
2. Benchmarks and performance targets
Create a new information infrastructure and
model to support the development and
deployment of multiple applications.
3. Managing and connecting with multiple
networks and Integrating to existing
enterprise and legacy systems. Creating
and managing the solutions that performs in
and out of network coverage.
Security
Maintainability
Portability

4. Enforcing security levels and role-based
access to the data warehouse.
9. The following Best Practices are used
for evaluation of the adequacy and
completeness of BA infrastructure:
1. Effective data integration process to create
required Business Analytics that help in
generating report on a daily basis.
2. Continuous monitoring processes to allow
alerts and caution to be communicated
intensely.
3. Automated information delivery and
communication process.
4. Fully automated data warehouse
administration infrastructure.
5. Availability and integrity of information on
standardized dimension such as consumers,
product and geography.
6. Delivery of answers to all key performance
business questions.
7. Integrated enterprise portal infrastructure to
deliver business process report.
8. Clear help desk and training policies, higher
end user acceptance having a consistent
look and touch across different applications.
10. Conclusion
This paper discussed the role of
Business Analytics in managing and developing
the Indian power Sector through its diverse
applications. It is a useful asset for the power
utilities for reducing the transmission and
commercial losses, for improving the cash flows,
managing their operations effectively, and better
plan out and implements their projects; reduce
energy intensity in contrast with increasing
energy efficiency and so on. It helps in all round
effective management of the power sector
utilities through the enhanced utilization of
business analytics in managing and analyzing
the big data of these power utilities.
11. Acknowledgements
The authors would like to thank Dr. D. K.
Punia and Prof. Anil Kumar for their valuable
comments that improved the quality of this paper
and BSES Yamuna Power Ltd. and University of
Petroleum & Energy Studies (UPES), for their
valuable guidance.
12. References
[1] [Online]. Available: Indian Energy Exchange
Website, www.iexindia.com, June. 2013.
[2] [Online]. Available: Ministry of Power -
Government of India Website,
http://powermin.nic.in, June. 2013.
[3] [Online]. Available: Central Electricity
Authority of India Website. Available:
http://www.cea.nic.in, June. 2013.
[4] [Online]. Available: The Climate Group,
http://www.theclimategroup.org, June 2013.
[5] [Online]. Available:
http://www.encyclopedia.com/doc/1G1-
196830172.html, June. 2013.
[6] [Online]. Available: http://www.sei.cmu.edu
/library/assets/sgmm.pdf, June. 2013.
[7] [Online]. Available: North Delhi Power
Limited (NDPL) website. http://www.cea.nic.in,
June. 2013.
[8] [Online]. Available: Bangalore Electricity
Supply Company (BESCOM) website.
http://www.bescom.org/, June. 2009.
[9] [Online]. Available: www.powersector.com
[10] [Online]. Available:
http://en.wikipedia.org/wiki/Electricity_sector_in_
India

Pradeep n singh_praveenkyadav

More Related Content

What's hot (20)

Similar to Pradeep n singh_praveenkyadav (20)

More from PMI2011 (20)

Recently uploaded (20)

Pradeep n singh_praveenkyadav