Comparing Machine Learning Models For Predicting Fuel Consumption In Energy Generation For The Food Processing Industry In Nigeria - Applied Research Project (MSc Data Analytics)

Aug 5, 2026

Upload by Aurelia

Accurate prediction of fuel consumption is essential for energy management, cost optimization, and environmental pollution control in Nigeria’s food processing industry. This applied research, structured using the CRISP-DM methodology, compares Artificial Neural Networks, Support Vector Machines, and Random Forest models for forecasting fuel consumption in energy generation. The study uses two years of historical data from Flour Mills of Nigeria Plc, including energy generated, gas consumption, gas pressure, and related variables. Model performance is assessed with RMSE, MSE, and R-squared metrics, showing Random Forest as the strongest overall performer.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages48

Reading Time2 h 1 min

AccessFree to download

Abstract

Chapter One: Introduction

Background

Motivation

Research Questions

Research Aim and Objectives

Research Design

Chapter Two: Overview

Literature Review

Comparison of Models

Chapter Three: Main Body

Business Understanding

Data Unsonderstanding

Data Preparation

Data Modelling

Evaluation

Deployment

Chapter Four: Conclusions

Limitations

Recommendations

References

List of Figures

List of Tables

COMPARING MACHINE LEARNING MODELS FOR PREDICTING FUEL CONSUMPTION IN ENERGY GENERATION FOR THE FOOD PROCESSING INDUSTRY IN NIGERIA Chiamaka Praise Ofili Applied Research Project submitted in partial fulfilment of the requirements for the degree of MSc Data Analytics at Dublin Business School Supervised by Samuel Ogwu DECLARATION ‘I declare that this Applied Research Project that I have submitted to Dublin Business School for the award of master’s in data Analytics is the result of my own investigations, except where otherwise stated, where it is clearly acknowledged by references. Furthermore, this work has not been submitted for any other degree.’ Signed: Chiamaka Praise Ofili Student Number: 10611520 Date: 28th August 2023 ACKNOWLEDGEMENTS I would like to express my sincere gratitude to my supervisor, Samuel Ogwu, for his invaluable guidance, support, and encouragement throughout the course of my dissertation. His expertise, feedback, and continuous motivation have been instrumental in shaping the direction of my research and enhancing the quality of my work. I am also deeply grateful to my family and friends for their unwavering love and support during this journey. I couldn't have achieved this milestone without their support. I also want to acknowledge the academic community and all the resources that have contributed to the success of this dissertation. ABSTRACT Accurate prediction of fuel consumption is crucial for effective energy management, cost optimization and environmental pollution management in the food processing industry in Nigeria. Machine learning models have shown promise in various domains for predicting and optimizing fuel and energy consumption. This research under the CRISP-DM methodology, compared the performance of three machine learning models which include Artificial Neural Networks, Support Vector Machines and Random Forest in predicting fuel consumption in energy generation in a food processing industry in Nigeria. This research was conducted using historical data on fuel consumption and independent variables such as energy generated, gas consumption, gas pressure, etc. collected over 2 years from Flour Mills of Nigeria Plc. The performance of the predicted models was evaluated based on Root Mean Square Error (RMSE), Mean Square Error (MSE) and R Square evaluation metrics. The Random Forest Model performed best across most metrics, with the lowest RMSE (8124 .62 & 26061.43) and MSE (6 .6E+07 & 6.8E+08) on both training and testing data, and a relatively high R-squared value (0 .93 & 0.52) . The ANN Model performed reasonably well, but the SVM Model had a comparatively poorer performance. TABLE OF CONTENTS DECLARATION 1 ACKNOWLEDGEMENTS 2 ABSTRACT 3 CHAPTER ONE: INTRODUCTION 8 1.1 BACKGROUND 8 1.2 MOTIVATION 9 1.3 RESEARCH QUESTIONS 9 1.4 RESEARCH AIM AND OBJECTIVES 10 1.5 RESEARCH DESIGN 10 CHAPTER TWO: OVERVIEW 12 2.1 LITERATURE REVIEW 13 2.1.1 Artificial Neural Networks 14 2.1.2 Support Vector Machine 15 2.1.3 Random Forest 17 2.2 COMPARISON OF MODELS 19 CHAPTER THREE: MAIN BODY 22 3.1 BUSINESS UNDERSTANDING 22 3.2 DATA UNDESTANDING 23 3.3 DATA PREPARATION 24 3.4 DATA MODELLING 30 3.4.1 Artificial Neutral Networks 30 3.4.2 Support Vector Machines 31 3.4.3 Random Forest 32 3.5 EVALUATION 34 3.5.1 Mean Squared Error (MSE) 34 3.5.2 Root Mean Squared Error (RMSE) 34 3.5.3 R-squared (Coefficient of Determination) 35 3.5.4 Results 36 3.6 DEPLOYMENT 38 CHAPTER FOUR: CONCLUSIONS 40 4.1 LIMITATIONS 41 4.2 RECOMMENDATIONS 41 REFERENCES 43 LIST OF FIGURES Figure 1: CRISP DM Model 11 Figure 2: Research Design 22 Figure 3: Statistical Qualities of Data 25 Figure 4: Handling Null Values 26 Figure 5: Distribution of Dataset Features 26 Figure 6: Probability Distribution of Target Variable 27 Figure 7: Correlation Heat Map 27 Figure 8: Feature Selection and Scaling 28 Figure 9: Scaled Da

FAQs

Which machine learning models are compared for predicting fuel consumption?

The study compares Artificial Neural Networks, Support Vector Machines, and Random Forest models under the CRISP-DM workflow.

What data and variables are used in the research?

Historical fuel consumption data and independent variables such as energy generated, gas consumption, and gas pressure are used, collected over two years from Flour Mills of Nigeria Plc.

How is model performance evaluated and which model performs best?

Performance is measured using RMSE, MSE, and R-squared. Random Forest achieves the best results across most metrics, with the lowest RMSE and MSE on both training and testing data and relatively high R-squared values.

Aug 5, 2026

Upload by Aurelia