Optimizing Power Forecasting Models with Customized Features for Academic and Industrial Buildings

Power consumption prediction is a crucial component in enhancing the efficiency and sustainability of building operations. This study investigates the impact of data collection frequency and model selection on the predictive accuracy of power consumption in two distinct building types: an Academic o...

Full description

Saved in:
Bibliographic Details
Main Authors: David Cabezuelo, Izar Lopez-Ramirez, June Urkizu, Ander Goikoetxea
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Smart Cities
Subjects:
Online Access:https://www.mdpi.com/2624-6511/8/1/3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722298891763712
author David Cabezuelo
Izar Lopez-Ramirez
June Urkizu
Ander Goikoetxea
author_facet David Cabezuelo
Izar Lopez-Ramirez
June Urkizu
Ander Goikoetxea
author_sort David Cabezuelo
collection DOAJ
description Power consumption prediction is a crucial component in enhancing the efficiency and sustainability of building operations. This study investigates the impact of data collection frequency and model selection on the predictive accuracy of power consumption in two distinct building types: an Academic one with 15-min interval data and an Industrial one with hourly data. Various machine learning models, including Support Vector Machine (SVM) with Radial and Sigmoid kernels, Random Forest (RF), and Deep Neural Networks (DNNs), across different data splits and feature sets, were considered. Our analysis reveals that higher data collection frequency generally improves model performance, as indicated by lower RMSE, MAPE, and CV values, alongside higher R² scores. The inclusion of more historical power consumption features was also found to have a more significant impact on the accuracy of predictions than including climate condition features. Moreover, the SVM-Radial model consistently outperformed others, particularly in capturing complex, non-linear patterns in the data. However, the DNN model, while competent in some metrics, showed elevated MAPE values, suggesting potential overfitting issues. These findings suggest that careful consideration of data frequency, features, and model selection is essential for optimizing power prediction, contributing to more efficient power management strategies in building operations.
format Article
id doaj-art-4fca95a9ba11486db50077bc8466cfd4
institution DOAJ
issn 2624-6511
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Smart Cities
spelling doaj-art-4fca95a9ba11486db50077bc8466cfd42025-08-20T03:11:22ZengMDPI AGSmart Cities2624-65112024-12-0181310.3390/smartcities8010003Optimizing Power Forecasting Models with Customized Features for Academic and Industrial BuildingsDavid Cabezuelo0Izar Lopez-Ramirez1June Urkizu2Ander Goikoetxea3Computer and Electronics Department, Mondragon University, 20500 Mondragon, SpainComputer and Electronics Department, Mondragon University, 20500 Mondragon, SpainComputer and Electronics Department, Mondragon University, 20500 Mondragon, SpainComputer and Electronics Department, Mondragon University, 20500 Mondragon, SpainPower consumption prediction is a crucial component in enhancing the efficiency and sustainability of building operations. This study investigates the impact of data collection frequency and model selection on the predictive accuracy of power consumption in two distinct building types: an Academic one with 15-min interval data and an Industrial one with hourly data. Various machine learning models, including Support Vector Machine (SVM) with Radial and Sigmoid kernels, Random Forest (RF), and Deep Neural Networks (DNNs), across different data splits and feature sets, were considered. Our analysis reveals that higher data collection frequency generally improves model performance, as indicated by lower RMSE, MAPE, and CV values, alongside higher R² scores. The inclusion of more historical power consumption features was also found to have a more significant impact on the accuracy of predictions than including climate condition features. Moreover, the SVM-Radial model consistently outperformed others, particularly in capturing complex, non-linear patterns in the data. However, the DNN model, while competent in some metrics, showed elevated MAPE values, suggesting potential overfitting issues. These findings suggest that careful consideration of data frequency, features, and model selection is essential for optimizing power prediction, contributing to more efficient power management strategies in building operations.https://www.mdpi.com/2624-6511/8/1/3power consumption predictionmachine learning modelspredictive analyticsfeature analysisrandom forest (RF)support vector machine (SVM)
spellingShingle David Cabezuelo
Izar Lopez-Ramirez
June Urkizu
Ander Goikoetxea
Optimizing Power Forecasting Models with Customized Features for Academic and Industrial Buildings
Smart Cities
power consumption prediction
machine learning models
predictive analytics
feature analysis
random forest (RF)
support vector machine (SVM)
title Optimizing Power Forecasting Models with Customized Features for Academic and Industrial Buildings
title_full Optimizing Power Forecasting Models with Customized Features for Academic and Industrial Buildings
title_fullStr Optimizing Power Forecasting Models with Customized Features for Academic and Industrial Buildings
title_full_unstemmed Optimizing Power Forecasting Models with Customized Features for Academic and Industrial Buildings
title_short Optimizing Power Forecasting Models with Customized Features for Academic and Industrial Buildings
title_sort optimizing power forecasting models with customized features for academic and industrial buildings
topic power consumption prediction
machine learning models
predictive analytics
feature analysis
random forest (RF)
support vector machine (SVM)
url https://www.mdpi.com/2624-6511/8/1/3
work_keys_str_mv AT davidcabezuelo optimizingpowerforecastingmodelswithcustomizedfeaturesforacademicandindustrialbuildings
AT izarlopezramirez optimizingpowerforecastingmodelswithcustomizedfeaturesforacademicandindustrialbuildings
AT juneurkizu optimizingpowerforecastingmodelswithcustomizedfeaturesforacademicandindustrialbuildings
AT andergoikoetxea optimizingpowerforecastingmodelswithcustomizedfeaturesforacademicandindustrialbuildings