2019
DOI: 10.17148/ijireeice.2019.7506
|View full text |Cite
|
Sign up to set email alerts
|

Machine Learning Based Prediction of Energy Consumption

Abstract: The prediction of energy consumption on a national or regional scale has become extremely important to researchers in recent years, especially in the light of the rate of depletion of primary energy sources combined with the rate of increase in the demand of the same resources on a global scale. The present paper deals with a simple machine learning based approach, using regression, for accurate prediction of energy consumption using the fossil fuel and energy consumption data of India as a representative coun… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 4 publications
0
2
0
Order By: Relevance
“…Due to the importance of optimizing energy consumption, many researchers are exploring the use of different types of ML algorithms to forecast energy consumption. Some examples are Decision trees and Random Forest, Linear and non-linear regression and Artificial Neural Networks (ANN) [21]. For example, the authors in [22] studied various models to predict energy consumption for a smart small-scale steel industry, namely: general linear regression, decision tree-based classification and regression trees, Random Forest, Support Vector Machine with a radial basis kernel, K-nearest neighbors and CUBIST.…”
Section: Machine Learning For Energy Consumption Prediction and Manag...mentioning
confidence: 99%
See 1 more Smart Citation
“…Due to the importance of optimizing energy consumption, many researchers are exploring the use of different types of ML algorithms to forecast energy consumption. Some examples are Decision trees and Random Forest, Linear and non-linear regression and Artificial Neural Networks (ANN) [21]. For example, the authors in [22] studied various models to predict energy consumption for a smart small-scale steel industry, namely: general linear regression, decision tree-based classification and regression trees, Random Forest, Support Vector Machine with a radial basis kernel, K-nearest neighbors and CUBIST.…”
Section: Machine Learning For Energy Consumption Prediction and Manag...mentioning
confidence: 99%
“…Linear Regression was used as a baseline and Random Forest was chosen since it represents a general-purpose ensemble approach (multiple decision trees), which is generally more robust, less prone to Two ML regression models were trained with the intention of creating the desired energy profiles: Linear Regression and Random Forest. Linear Regression was used as a baseline and Random Forest was chosen since it represents a general-purpose ensemble approach (multiple decision trees), which is generally more robust, less prone to overfitting and can handle larger datasets more efficiently, often being used in the literature for predicting energy consumption [21]. tradeoff in this case is that it may require more computational power and resources; however, this was not a constraint for the use case at hand.…”
Section: Machine Learning-creating the Predictive Modelsmentioning
confidence: 99%