Visvesvaraya Technological University

“Jnana Sangama”, Belagavi-590018, Karnataka

Project Report On
“Online Remote Monitoring and Energy Prediction System for Grid
Connected Solar Power Plant At NIE(N) Campus”
Submitted in partial fulfilment for the award of degree of

Bachelor of Engineering
In

Electrical and Electronics Engineering

By

Vinay Gurumoorti Hebbar 4NN19EE025

Vinay Kumar 4NN19EE026
Manoj Nayak M 4NN19EE009
Roshan Shankar Moger 4NN19EE015
Vaishnavi Athreya 4NN19EE023

Under the Guidance of

Dr. Lokesh M
Assistant Professor
Dept. of EEE, NIEIT, Mysuru

Department of Electrical and Electronics Engineering

NIE INSTITUTE OF TECHNOLOGY

Mysuru-570018
2022-23
 NIE Institute of Technology
#50(Part), Hootagalli Industrial Area, Koorgalli, Mysuru-18

Department of Electrical and Electronics Engineering

CERTIFICATE

This is to certify that the project entitled “Online Remote Monitoring and Energy
Prediction System for Grid Connected Solar Power Plant At NIE(N) Campus” is a
Bonafede work carried out by Vinay Kumar (4NN19EE026), Vinay Gurumoorti Hebbar

(4NN19EE025), Manoj Nayak (4NN19EE009), Roshan Shankar Moger

(4NN19EE015), Vaishnavi Athreya (4NN19EE023) in partial fulfilment for the award of
Bachelor of Engineering in Department of Electrical and Electronics Engineering of
the Visvesvaraya Technological University, Belgavi-590018 during the year 2022-2023. It is
certified that all corrections/suggestion indicated for the Internal Assessment have been
incorporated in the report and is deposited in the departmental library. The project report has
been approved as it satisfies the academic requirements in respect of work prescribed for the
said degree.

Signature of guide Signature of HOD Signature of Principal

Dr. Lokesh M Dr. Sandeep Kumar K J Dr. Rohini Nagapadma
Assistant Professor Head of Department Principal
NIEIT, Mysuru NIEIT, Mysuru NIEIT, Mysuru

Examiner name Signature with

date

1.
 2.

DECLARATION

We, hereby Vinay Kumar (4NN19EE026), Vinay Gurumoorti Hebbar (4NN19EE025),

Manoj Nayak M (4NN19EE009), Roshan Shankar Moger (4NN19EE015), Vaishnavi
Athreya (4NN19EE023), student of VIII semester, Department of Electrical and Electronics
Engineering, NIE Institute of Technology, Mysuru declare that the Project report entitled
“Online Remote Monitoring and Energy Prediction System for Grid Connected Solar
Power Plant At NIE(N) Campus” has been successfully completed under the guidance of
Dr. Lokesh M, Assistant Professor ,This work is submitted to Visvesvaraya
Technological University, Belagavi -590018, in partial fulfilment of the requirements for
the award of Degree of Bachelor of Engineering in Department of Electrical and
Electronics Engineering during the academic year 2023

The work done in this report is original and it has not been submitted for any other degree in
any university.

Name USN Signature with date

Vinay Gurumoorti Hebbar 4NN19EE025

Vinay Kumar 4NN19EE026
Manoj Nayak M 4NN19EE009
Roshan Shankar Moger 4NN19EE015
Vaishnavi Athreya 4NN19EE023
 AKNOWDLEDGEMENT

This Report has been prepared showcasing our leaning and experience from April 2023
while working on the PROJECT titled “Online Remote Monitoring and Energy
Prediction System for Grid Connected Solar Power Plant At NIE(N) Campus”

We would like to express our gratitude to our college NIE INSTITUTE OF

TECHNOLOGY for providing the right environment to harness the right knowledge, skills
and opportunities.

We would like to thank our Principal Dr. Rohini Nagapadma for letting us be a part of this
prestigious institution and giving us the opportunity to explore our abilities to the fullest.

We would like to extend our sincere gratitude to our guide Dr Lokesh M Assistant Prof.
Dept. of EEE for his guidance and patience throughout the process.

We are grateful and would like to extend our sincere gratitude towards Dr. Sandeep Kumar
KJ, Associate Prof. and Head, Dept. of EEE for being a source of inspiration, instilling
enthusiasm and for their constant guidance, valuable knowledge and experience.

We are grateful for the cooperation and support that we have been extended with by our
department and fellow classmates who were truly helpful in the process of our learning and
understanding
 ABSTRACT
Solar energy prediction android application using linear regression, polynomial regression,
and XGBoost is a mobile application that helps predict solar energy production based on
certain parameters. The application can be used by solar energy producers, researchers, and
enthusiasts to estimate the amount of solar energy production they can expect to generate
based on the environmental and weather conditions of a specific location. The application
will use three different regression algorithms: Linear regression, polynomial regression, and
XGBoost. Linear regression is a basic machine learning algorithm that tries to fit a straight
line through a set of data points. It works well when there is a linear relationship between the
input and output variables. Polynomial regression is an extension of linear regression that can
capture non-linear relationships by fitting a polynomial curve to the data. XGBoost is a more
advanced machine learning algorithm that uses gradient boosting to improve the accuracy of
the model by minimizing the error. To use the application, the user will input various
environmental parameters such as temperature, humidity, wind speed, cloud coverage, and
other weather conditions of a specific location. The application will then use these inputs and
apply the three regression algorithms to predict the solar energy production for that location.
The linear regression algorithm will use a linear equation to predict the solar energy
production. It will try to find a straight line that fits the data points based on the input
parameters. The polynomial regression algorithm will use a polynomial equation to predict
the solar energy production. It can capture the non-linear relationship between the input and
output variables and provide more accurate predictions. XGBoost will use a gradient boosting
algorithm to improve the accuracy of the model by minimizing the error. The application will
display the predicted solar energy production based on the input parameters for each of the
three algorithms. This will allow the user to compare the predictions of each algorithm and
choose the most accurate one. The user can also compare the predictions of each algorithm
with the actual solar energy production data for the location to evaluate the accuracy of the
predictions. The application will also include a data visualization feature that will allow the
user to see the trends and patterns in the solar energy production data. This feature will help
the user to understand the factors that affect solar energy production and make informed
decisions about the location and design of solar energy systems.
 CONTENTS
CHAPTERS CONTENTS PAGE NO

Chapter 1 INTRODUCTION
1.1 General introduction 1
1.2 Literature Survey 2
1.3 Outcome of Literature Survey 3
1.4 Problem Statement 4
1.5 Motivation 4
1.6 Objective of the project 6
1.7 Existing System 7
1.8 Organisation of the report 8
Chapter 2 DEVELOPMENT OF ML BASED SOLAR
PREDICTION MODEL
2.1 Introduction 9
2.2 Proposed Methodology 10
2.2.1 Linear Regression 11
2.2.2 Polynomial Regression Model 14
2.2.3 XG Boost 17
2.3 Summary 19
Chapter 3 DEVELOPMENT OF APPLICATION
3.1 Introduction 20
3.2 App Development 21
3.2.1 Android Studio 22
3.2.2 SQLite 23
3.2.3 XML 23
3.2.4 System Requirement 24
3.3 Summary 25
Chapter 4 RESULTS and DISCUSSIONS
4.1 Introduction 26
4.2 Data Collection 26
4.3 Linear Regression Model 27
4.4 Polynomial Regression Model 28
4.5 XG Boost Model 29
4.6 Comparison of Three Prediction Model 30
4.7 Advantages 32
4.8 Summary 33
Chapter 5 CONCLUSION and FUTURE SCOPE
5.1 Conclusion 34
5.2 Future Scope 35
REFERENCE 36
ANNEXURE
Data Collect 37
CODE
XML sample code of ANDROID Application 40
JAVA Backend code sample 41

LIST OF FIGURES
FIGURE NO. TITLE PAGE NO.

1.0 Existing System 6

2.2 Flow chart of proposed methodology 10
2.2 Scaler plot with fitted line 12
2.2 Selecting the degree of polynomial model 14
2.2 XG Boost Prediction method 17
2.2.3 XG Boost Prediction graph 18
3.2.1 Android Studio 22
4.5 Output of Linear Regression Model 28
4.6 Output of Polynomial Regression Model 29
4.7 Output of Polynomial Regression model when 30
compared with actual data
4.8 Linear Regression Model 30
4.9 Polynomial Regression Model 30
4.10 XG Boost Model

LIST OF TABLES
TABLE NO TITLE PAGE NO
4.2 Previous data 26
4.4 Weather data 27