DATA SCIENCE PROJECT REPORT
(Project Semester August-December 2020)
Power Consumption in India (2019-2020)
Submitted by
P Anand Kumar Reddy
Registration No: 11807873
Computer Science and Engineering
Section: KM074
Course Code: INT217
Under the Guidance of
Ms. Komal Arora
Discipline of CSE/IT
Lovely School of Computer Science and Engineering
Lovely Professional University, Phagwara
CERTIFICATE
This is to certify that P Anand Kumar Reddy bearing Registration no.
11807873 has completed INT217 project titled, “Power Consumption in
India (2019-2020)” under my guidance and supervision. To the best of my
knowledge, the present work is the result of his/her original development,
effort and study.
Signature and Name of the Supervisor
Designation of the Supervisor
School of Computer Science and Engineering
Lovely Professional University
Phagwara, Punjab.
Date: 20-11-2020
DECLARATION
I, P Anand Kumar Reddy, student of Lovely Professional University under
CSE/IT Discipline at, Lovely Professional University, Punjab, hereby declare
that all the information furnished in this project report is based on my own
intensive work and is genuine.
Date: 20-11-2020 Signature
Registration No. 11807873 P Anand Kumar Reddy
ACKNOWLEDGEMENT
A project work is a combination of views, ideas, suggestions and contribution
of many people. Thus, one of the pleasant parts of writing the report is to
thank those who have contributed towards its fulfilment.
I consider it as great privilege to have esteemed Lecturer Ms. Komal Arora as
my project guide. I take this opportunity to express my sincere gratitude to
him through constant advice and constructive criticism nourished my interest
in the subject and provided a free and pleasant atmosphere to work against all
odd situations. I avail this opportunity to extend my heart full thanks and deep
respect to faculty member for their able guidance during this project.
My gratitude to all those, who responded to my questionnaire in a well-
defined manner and helped me acquiring knowledge.
I would like to communicate a deep sense of gratitude to all these people
without whom my project would not have been such a great learning
experience.
P Anand Kumar Reddy
KM074
Reg No. 11807873
Lovely Professional University
Table of Contents
Sr.No. Particulars
1. Introduction
2. Scope of the Analysis
3. Source of the Dataset
4. ETL Process
5. Analysis on Dataset
a. Introduction
b. Specific Requirements/Functions and Formulas
c. Analysis Results
6. List of Analysis with Results
7. References
8. Bibliography
Introduction
India is the world's third-largest producer and third-largest consumer of electricity. The na-
tional electric grid in India has an installed capacity of 370.106 GW as of 31 March 2020.
Renewable power plants, which also include large hydroelectric plants, constitute 35.86% of
India's total installed capacity. During the 2018-19 fiscal year, the gross electricity generated
by utilities in India was 1,372 TWh and the total electricity generation (utilities and non-util-
ities) in the country was 1,547 TWh. The gross electricity consumption in 2018-19 was 1,181
kWh per capita.
In 2015-16, electric energy consumption in agriculture was recorded as being the highest
(17.89%) worldwide. The per capita electricity consumption is low compared to most other
countries despite India having a low electricity tariff.
In light of the recent COVID-19 situation, when everyone has been under lockdown for the
months of April & May the impacts of the lockdown on economic activities have been faced
by every sector in a positive or a negative way.
With the electricity consumption being so crucial to the country, we came up with a plan to
study the impact on energy consumption state and region wise.
The dataset is exhaustive in its demonstration of energy consumption state wise.
Dataset
Column Definition
States All States in India
Regions Regions in India
Latitude and Longitude The Coordinates of States in India
Dates All dates between 2019 and 2020
Usage Electricity usage by different states
Scope of the Analysis
Data is in the form of a time series for a period of 17 months beginning from 2nd Jan 2019
till 23rd May 2020. Rows are indexed with dates and columns represent states. Rows and
columns put together, each datapoint reflects the power consumed in Mega Units (MU) by
the given state (column) at the given date (row). The data is divided into multiple tables like
maximum power usage states and minimum usage states. Data shows that main electricity
usage by regions and location in maps by using latitude and longitude.
Power System Operation Corporation Limited (POSOCO) is a wholly-owned Government of
India enterprise under the Ministry of Power. It was earlier a wholly-owned subsidiary of
Power Grid Corporation of India Limited. It was formed in March 2009 to handle the power
management functions of PGCIL.
Since such vast field of data present of the Power Consumption in India there is wide range
of scope of the analysis of date. For example:
a) State wise Electricity Usage
b) Date wise Electricity Usage
c) Maximum and Minimum Power Usage States
Source of the Dataset
The dataset is taken from the Kaggle with the name ‘Power Consumption in India’.
https://www.kaggle.com/twinkle0705/state-wise-power-consumption-in-india
Author of the Dataset
Twinkle Khanna
Data last Updated
June 2020
ETL Process
ETL stands for Extraction, Transformation and Loading. It is a process in data warehousing
to extract data, transform data and load data to final source. ETL covers a process of how the
data are loaded from the source system to the data warehouse. Let us briefly describe each
step of the ETL process.
Extraction: Extraction is the first step of ETL process where data from different
sources like txt file, XML file, Excel file or various sources collected.
Transformation: Transformation is the second step of ETL process where all col-
lected data is been transformed into same format i.e. format can be anything as per
our requirement before loading it to data-warehouse i.e. it may be data-type format,
data merge format, splitting format, alphabet joining format, currency format etc.
Loading: Final step of ETL process, the big chunk of data which is collected from
various sources and transformed then finally load to our data warehouse.
Analysis of Dataset
1. Tableau
a. Introduction: In this tableau, I made some changes to the data and also some
cleaning like change date and removing time.
b. Specific Requirements/Functions and Formulas:
Tableau Prep
2. Dashboard
a. Introduction: It contains all pivot tables, slicers, and hyperlinks. Here we can see
the whole data and how it performs when we click the slicers.
3. Diagram View
a. Introduction: Diagram View to connect all the tables in excel sheet and I almost
connected 4 tables and also extra 2 tables because some of the tables are not con-
necting.
4. Maximum Power Consume States:
a. Introduction: The analysis shows the top 10 maximum power consumption states
in India.
b. Specific Requirements/Functions and Formulas:
Pivot table of States
Pivot table of Usage
Stacked Bar Chart
c. Analysis Results:
Maharashtra state consume 12.7% power. It is the highest Electricity Con-
sumption State.
Maximum Power Consume States
Maharashtra
Gujarat
UP
Tamil Nadu
NR
Rajasthan SR
WR
MP
Karnataka
Telangana
Andhra Pradesh
Punjab
0 50000 100000 150000 200000 250000
5. Minimum Power Consume States:
a. Introduction: The analysis shows the top 10 minimum power consumption states
in India.
b. Specific Requirements/Functions and Formulas:
Pivot table of states
Pivot table of Usage
Stacked Bar Chart
c. Analysis Results:
Sikkim state consume 0.0379% power. It is lowest Electricity
Consumption State.
In this pandemic time over all Regions Electricity Consumption is decreas-
ing comparatively last year.
Minimum Power Consume States
6000
5000
4000
WR
3000 SR
NR
NER
ER
2000
1000
0
a
nd
y
ay
a
ar
h
ur
a ur d
es
h m im
Go al ig ip ip l an ra kk
Po nd r a n ga ad i zo Si
gh T r
e
Ch
a M Na lP M
M ha
ac
un
Ar
6. State wise Consumption:
a. Introduction: The analysis shows the power usage comparison between states in
India.
b. Specific Requirements/Functions and Formulas:
Pivot table of years
Pivot table of states
Line with Markers Chart
c. Analysis Results:
In June month usage of power is started decreasing again July month star-
ted increasing power usage
October and November are usually cloudless so that time the usage of
Electricity is low.
Again, July middle started increasing the power consumption
180000
State-wise Electricity Consumption
160000
140000
120000
100000
2019
80000 2020
60000
40000
20000
0
es
h
am g ar
h l hi a a K
ak
a tra ay
a P a b im na UP ga
l
ss De Go an J&
at sh al
M ish unja kk ga en
rad A di a ry n a h Od P S i n
P an H
Ka
r ar eg la tB
hra Ch ah M Te es
d M W
An
7. Region wise Consumption
a. Introduction: The analysis shows the relation between Regions and Sum of Power
Usage in India.
b. Specific Requirements/Functions and Formulas:
Pivot table of Regions
Pivot table of Sum of Usage
3-D Pie Chart
c. Analysis Results:
In North region UP consume maximum electricity, Chandigarh Consume
low electricity in north region.
In West Region Maharashtra State consume maximum electricity
In South region Tamil Nadu state consume maximum power and Pondy
consume minimum electricity.
In NER Assam Consume maximum electricity
Region wise Consumption
9.63% 1.27
31.61% %
ER
NER
29.61% NR
SR
WR
27.88%
8. Month wise Consumption:
a. Introduction: The analysis shows the relation between Months and Sum of Power
Usage in different years in India.
b. Specific Requirements/Functions and Formulas:
Pivot table on Months
Pivot table on Usage in different years
Doughnut Chart
c. Analysis Results:
In June month usage of power is started decreasing again July month star-
ted increasing power usage
October and November are usually cloudless so that time the usage of
Electricity is low.
Again, July middle started increasing the power consumption
Month wise Consumption
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
9. 3D Map
a. Introduction: The analysis shows the relation between Latitude and Longitude in
India.
b. Specific Requirements/Functions and Formulas:
3D Map
Longitude Data
Latitude Data
10. Hyperlinks and Slicers
a. Introduction: Hyperlinks helps to redirect to the respective excel sheet and we
have to select to which sheet it has to redirect.
Slicers helps to change the data in pivot tables like selecting data according to
our choice. In my data slicers are Year, Regions.
Hyperlinks
Slicers
List of Analysis with Results
Maharashtra state consume 12.7% power. It is the highest Electricity Consumption
State.
Sikkim state consume 0.0379% power. It is lowest Electricity Consumption State.
Over all North Region consumes high Electricity 27.3%, North east region Electricity
Consumption is 21.2 %, South Region and West Region consume almost same
Electricity 18.2%, East Region consume minimum Electricity 15.2%.
In this pandemic time over all Regions Electricity Consumption is decreasing compar-
atively last year.
In all Regions, when the summer is starting that time the usage of Electricity is started
increasing middle of February the power usage started increasing.
In June month usage of power is started decreasing again July month started increas-
ing power usage
October and November are usually cloudless so that time the usage of Electricity is
low.
In North region UP consume maximum electricity, Chandigarh Consume low electri-
city in north region.
In West Region Maharashtra State consume maximum electricity.
Again, July middle started increasing the power consumption
In South region Tamil Nadu state consume maximum power and Pondy consume
minimum electricity.
In NER Assam Consume maximum electricity.
Other state consumes very low electricity power (within 200 vol only)
References
1. www.kaggle.com
2. www.stackoverflow.com
3. www.google.com
4. www.youtube.com
5. www.github.com
Bibliography
1. Microsoft Excel 2016 Bible: The Comprehensive Tutorial Resource by John
Walkenbach, Wiley.
2. Fundamentals of Business Analytics by R.N. Prasad, Seema Acharya, Wiley.
