Abstract
The significance of energy efficiency in the development of smart cities cannot be overstated. It is essential to have a clear understanding of the current energy consumption (EC) patterns in both public and private buildings. One way to achieve this is by employing machine learning classification algorithms, which offer a broader perspective on the factors influencing EC. These algorithms can be applied to real data from databases, making them valuable tools for smart city applications. In this paper, our focus is specifically on the EC of public schools in a Portuguese city, as this plays a crucial role in designing a Smart City. By utilizing a comprehensive dataset on school EC, we thoroughly evaluate multiple ML algorithms. The objective is to identify the most effective algorithm for classifying average EC patterns. The outcomes of this study hold significant value for school administrators and facility managers. By leveraging the predictions generated from the selected algorithm, they can optimize energy usage and, consequently, reduce costs. The use of a comprehensive dataset ensures the reliability and accuracy of our evaluations of various ML algorithms for EC classification.
Links
BibTeX (Download)
@article{machado2024behaviour,
title = {Behaviour of Machine Learning algorithms in the classification of energy consumption in school buildings},
author = {José Machado and António Chaves and Larissa Montenegro and Carlos Alves and Dalila Durães and Ricardo Machado and Paulo Novais},
doi = {https://doi.org/10.1093/jigpal/jzae058},
year = {2024},
date = {2024-05-18},
urldate = {2024-05-18},
journal = {Logic Journal of the IGPL},
publisher = {Oxford University Press},
abstract = {The significance of energy efficiency in the development of smart cities cannot be overstated. It is essential to have a clear understanding of the current energy consumption (EC) patterns in both public and private buildings. One way to achieve this is by employing machine learning classification algorithms, which offer a broader perspective on the factors influencing EC. These algorithms can be applied to real data from databases, making them valuable tools for smart city applications. In this paper, our focus is specifically on the EC of public schools in a Portuguese city, as this plays a crucial role in designing a Smart City. By utilizing a comprehensive dataset on school EC, we thoroughly evaluate multiple ML algorithms. The objective is to identify the most effective algorithm for classifying average EC patterns. The outcomes of this study hold significant value for school administrators and facility managers. By leveraging the predictions generated from the selected algorithm, they can optimize energy usage and, consequently, reduce costs. The use of a comprehensive dataset ensures the reliability and accuracy of our evaluations of various ML algorithms for EC classification.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}