Name: IT Expo
Uploaded: 2023-04-04
Duration: 3 min 3 s
Description: IT Expo. AIDI 2005-01: Capstone Term II. Submitted by: Group No.7 Bavithra Ganesan (100900119) Jasmeet Kaur (100881373) Pritesh Dalal(100872247) Rutvik Shah(100886648).

IT Expo. AIDI 2005-01: Capstone Term II. Submitted by: Group No.7 Bavithra Ganesan (100900119) Jasmeet Kaur (100881373) Pritesh Dalal(100872247) Rutvik Shah(100886648). 

Scene 1

Submitted by: Group No.7 Bavithra Ganesan (100900119)  Jasmeet Kaur (100881373) Pritesh Dalal(100872247) Rutvik  Shah(100886648)

Problem Statement. This study aims to investigate the viability of applying data mining algorithms for energy consumption forecasting in industrial settings, specifically in the context of a South Korean steel manufacturing facility. The study uses cutting-edge methods including machine learning algorithms and artificial neural networks to forecast daily energy use patterns. The main objective of this study is to assess the precision and efficacy of these models in predicting energy consumption and to find possible areas where energy may be saved, operational efficiency can be increased, and useful insights can be provided for practical applications.. 

Scene 2

This study aims to investigate the viability of applying data mining algorithms for energy consumption forecasting in industrial settings, specifically in the context of a South Korean steel manufacturing facility. The study uses cutting-edge methods including machine learning algorithms and artificial neural networks to forecast daily energy use patterns. The main objective of this study is to assess the precision and efficacy of these models in predicting energy consumption and to find possible areas where energy may be saved, operational efficiency can be increased, and useful insights can be provided for practical applications.

Model Architecture. Graphical user interface Description automatically generated. 

Scene 3

Graphical user interface

Description automatically generated

Modelling Techniques. Linear regression models the relationship between a dependent variable (energy consumption) and independent variables using a linear equation.. 

Scene 4

Linear regression models the relationship between a dependent variable (energy consumption) and independent variables using a linear equation.

Random forest regressor uses decision trees to predict energy consumption by combining the predictions of multiple trees built on random subsets of data and features.

Artificial neural network is a complex model inspired by the human brain that can capture non-linear relationships between features and energy consumption, and learn from data without explicit programming

Linear Regression model sample illustration Download Scientific Diagram

Principle of filling random forest The bootstrap resampling technique

Applied Deep Learning Part 1 Artificial Neural Networks

Results. Chart bar chart Description automatically generated. 

Scene 5

Chart bar chart Description automatically generated

From the above graphs, it can be seen that ANN, has highest R2 score and lowest MSE among all models.  The difference in other metric MSE points out that ANN is better than other two.  There is no overfitting of data as explained above in modelling section.  It can be concluded that ANN performs better than other models and predict the energy consumption precisely.

Future Directions. E xpanding the analysis to more locations and business sectors to evaluate how well the data mining models can be applied broadly. Analysing the underlying causes of energy use more thoroughly to find areas where energy can be saved, and efficiency can be increased. A nalysing the effectiveness of the data mining models across extended time spans to determine their applicability in actual energy management scenarios.. 

Scene 6

E xpanding the analysis to more locations and business sectors to evaluate how well the data mining models can be applied broadly.  Analysing the underlying causes of energy use more thoroughly to find areas where energy can be saved, and efficiency can be increased.  A nalysing the effectiveness of the data mining models across extended time spans to determine their applicability in actual energy management scenarios.