Energy Consumption Predictor

A PROJECT REPORT

Submitted by
Parth Gupta (22BAI70263)
Arshia Gulati (22BAI70415)
Vipul Sharma (22BAI70044)

in partial fulfillment for the award of the degree of

Bachelors of Engineering
IN
Computer Science with specialization in Artificial Intelligence

Chandigarh University
February - June 2023
 CHAPTER 1.

INTRODUCTION ....................................................................... 11

SNO. DESCRIPTION PAGE NO.

1. IDENTIFICATION OF CLIENT

2. IDENTIFICATION OF PROBLEM

3. IDENTIFICATION OF TASK

4. TIMELINE

5. ORGANISATION OF REPORT
List of Tables

Table 3.1………………………………………………………………………………….

Table3.2………………………………………………………………………………….

Table3.3 …………………………………………………………………………….……
List of Figures

Figure 1.1 Gantt Chart of Project Timeline

 INTRODUCTION

1.1.Identification of Client /Need / Relevant Contemporary issue

Energy consumption refers to the utilization of energy to power different processes and devices
in various sectors such as residential, industrial, and transportation. It is a crucial element of
human activity that facilitates economic growth, social development, and environmental
sustainability. However, excessive energy consumption has several adverse effects such as
climate change, air pollution, and depletion of natural resources. Thus, comprehending the
sources, patterns, and trends of energy consumption is essential in developing sustainable
energy policies, promoting energy efficiency, and reducing greenhouse gas emissions.

According to the International Energy Agency (IEA), global energy consumption increased by
2.9% in 2019, the fastest growth rate since 2010, before declining by 4.5% in 2020 due to the
COVID-19 pandemic. Most of the energy consumption comes from fossil fuels, which account
for 84% of the world's primary energy supply. However, the use of renewable energy sources
is also increasing, driven by falling costs, government policies, and public awareness of
environmental issues. In 2020, renewable energy sources accounted for 11% of global primary
energy consumption, up from 9.7% in 2010.

An energy consumption model may be required for the following reasons by a client:

• Cost Savings: Understanding energy consumption can help individuals and businesses
identify areas where energy efficiency improvements can be made, leading to cost savings
on energy bills.

• Environmental Concerns: Energy consumption is a significant contributor to greenhouse

gas emissions, which are a major cause of climate change. By understanding energy
consumption patterns, individuals and businesses can identify ways to reduce their carbon
footprint and promote environmental sustainability.

• Compliance Requirements: Many industries and countries have regulations related to

energy consumption and emissions, and understanding energy consumption is necessary to
comply with these requirements.

• Planning and Forecasting: Understanding energy consumption patterns can help

businesses and governments plan for future energy needs and develop strategies to meet
those needs.

There are several contemporary issues related to energy consumption that have been documented
in reports by various agencies. Here are some examples:
 • Climate Change: The Intergovernmental Panel on Climate Change (IPCC) has warned
that the increasing use of fossil fuels is the main driver of climate change, which has severe
consequences for the environment, economy, and human health. The IPCC reports
emphasize the need for a transition to renewable energy sources and increased energy
efficiency to reduce greenhouse gas emissions.

• Energy Poverty: The International Energy Agency (IEA) reports that around 800 million
people worldwide lack access to electricity, and many more have limited access. This
energy poverty has significant social and economic consequences, including hindering
access to healthcare, education, and economic opportunities.

• Energy Security: The United States Energy Information Administration (EIA) reports that
global energy demand is expected to increase by nearly 50% by 2050, leading to concerns
about energy security and supply disruptions. The EIA highlights the need for diversifying
energy sources and investing in infrastructure to improve energy security.

• Digitalization of Energy Systems: The International Renewable Energy Agency (IRENA)

reports that the digitalization of energy systems is transforming the energy sector, leading
to increased efficiency, flexibility, and sustainability. However, this digital transformation
also poses challenges related to cybersecurity, privacy, and data management.

Energy consumption predictors can be useful for a wide range of clients, including:

• Individuals - An energy consumption predictor can help individuals monitor their energy
usage and identify areas where they can reduce their consumption, resulting in cost savings
and a reduced environmental impact.

• Businesses - Businesses can use energy consumption predictors to optimize their energy
usage, reduce energy costs, and improve sustainability, which can enhance their reputation
and attract environmentally-conscious customers.

• Government agencies - Energy consumption predictors can help government agencies

monitor and manage energy usage across various sectors, such as transportation, buildings,
and manufacturing. This can identify opportunities for energy efficiency and emissions
reduction.

• Consumer product manufacturers - Energy consumption predictors can benefit

consumer product manufacturers by helping them analyze the energy usage patterns of
their products. This can identify areas where energy efficiency can be improved, leading
to more environmentally-friendly products and reduced energy costs for consumers.
 • Agriculture - Energy consumption predictors can help farmers optimize their energy
usage, for example, by analyzing the energy usage patterns of irrigation systems and
identifying areas where energy efficiency can be improved. This can lead to cost savings
and a reduced environmental impact.

• Utilities - In the utility sector, energy consumption prediction can help utility companies
optimize their energy generation and distribution systems. This can result in cost savings and
improved reliability of the energy grid.

• Data centers - Data centers consume vast amounts of energy to power and cool their
servers. Energy consumption predictors can help data center operators identify
opportunities for energy efficiency, such as optimizing server workloads and cooling
systems, resulting in cost savings and reduced carbon emissions.

1.2. Identification of Problem

The problem statement of an energy consumption predictor project is to develop a machine

learning model that can accurately predict energy consumption in buildings, households, or
industries. Energy consumption prediction is essential for optimizing energy usage, reducing
energy waste, and improving energy efficiency. However, accurate prediction is challenging due
to the complex and dynamic nature of energy consumption, which is influenced by various factors
such as weather, occupancy, and equipment usage. The model will be designed to predict energy
consumption in real-time or for future periods, enabling users to optimize energy usage and reduce
energy costs.

The energy consumption predictor project has significant implications for energy management,
energy conservation, and sustainability. By accurately predicting energy consumption, it is
possible to optimize energy usage, reduce energy waste, and improve energy efficiency. This, in
turn, can lead to lower energy bills, reduced carbon emissions, and improved environmental
sustainability. Therefore, the successful development of an energy consumption predictor model
can have far-reaching benefits for society, the economy, and the environment.
1.3. Identification of Tasks

• Dataset Collection: The goal of dataset collection is to obtain a comprehensive and

representative set of data that can be used to draw conclusions, make predictions, or
develop machine learning models. The dataset will include number of rooms on each level
and number of Electrical Equipements in each room alongside corridors.

• Processing the Dataset: The data collected will be used to draw various insights and be
used to forecast the energy consumption for the upcoming years. So, the data will be
processed and formatted in a way so as it is possible to achieve the desired output. Different
methods will be created to do so.

• Comparing different ML Algorithms/Literature Review: The next objective is to pass

the dataset to different machine learning algorithms. Then compare the different machine
learning algorithms based on the output generated by them. The factors to be used for
comparing the models would be accuracy and recall value.

• Problem Formulation: After formatting the data various graphical insights will be drawn
from the dataset. The insights can include energy consumption in different seasons,
different months, etc. Confusion Matrix and similar insights will also be created to make
the visualization of the model easier.

• Selecting the suitable ML model: After comparing all the models a prediction model will
be chosen with best accuracy which will help to forecast energy consumption in the
upcoming years. These predictions can be used to reduce energy costs and for other
purposes by the organization.

• Testing and training the dataset: The model will be tested and trained on the collected
dataset. Various parameters will be used to further increase the model accuracy.

• Predicting future energy consumption: The model will predict future energy
consumption, based on historical data and other factors. This can help energy suppliers and
grid operators plan for, manage energy supply, and demand, and inform pricing and other
strategic decisions.
1.4. Timeline

Figure 1.1

1.5. Organization of the Report

Chapter 1 Problem Identification: This chapter introduces the project and describes the problem
statement discussed earlier in the report.
Chapter 2 Literature Review: This chapter prevents review for various research papers which
help us to understand the problem in a better way. It also defines what has been done to already
solve the problem and what can be further done.
Chapter 3 Design Flow/ Process: This chapter presents the need and significance of the proposed
work based on literature review. Proposed objectives and methodology are explained. This
presents the relevance of the problem. It also represents logical and schematic plan to resolve the
research problem.
Chapter 4 Result Analysis and Validation: This chapter explains various performance
parameters used in implementation. Experimental results are shown in this chapter. It explains the
meaning of the results and why they matter.
Chapter 5 Conclusion and future scope: This chapter concludes the results and explain the best
method to perform this research to get the best results and define the future scope of study that
explains the extent to which the research area will be explored in the work.

Team Roles
Member Name UID Roles

Parth Gupta 22BAI70263 • COLLECTION AND MAKING

OF THE DATASET

• CLUSTERING AND
DISTRIBUTION OF THE
DATASET.

• VISUALISATION OF THE
DATASET

Arshia Gulati 22BAI70415 • COLLECTION OF DATASET

• VISUALISATION OF THE
DATASET

• TESTING AND TRAINING OF

THE DATASET

Vipul Sharma 22BAI70044 • ANALYSING THE DATASET

• APPLYING ALGORITHMS IN
THE DATASET

• SCRAPPING THE DATASET