Transforming Building Energy Management: Sparse, Interpretable, and Transparent Hybrid Machine Learning for Probabilistic Classification and Predictive Energy Modelling

The building sector, responsible for 40% of global energy consumption, faces increasing demands for sustainability and energy efficiency. Accurate energy consumption forecasting is essential to optimise performance and reduce environmental impact. This study introduces a hybrid machine learning fram...

Full description

Saved in:
Bibliographic Details
Main Authors: Yiping Meng, Yiming Sun, Sergio Rodriguez, Binxia Xue
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Architecture
Subjects:
Online Access:https://www.mdpi.com/2673-8945/5/2/24
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850156643239591936
author Yiping Meng
Yiming Sun
Sergio Rodriguez
Binxia Xue
author_facet Yiping Meng
Yiming Sun
Sergio Rodriguez
Binxia Xue
author_sort Yiping Meng
collection DOAJ
description The building sector, responsible for 40% of global energy consumption, faces increasing demands for sustainability and energy efficiency. Accurate energy consumption forecasting is essential to optimise performance and reduce environmental impact. This study introduces a hybrid machine learning framework grounded in Sparse, Interpretable, and Transparent (SIT) modelling to enhance building energy management. Leveraging the REFIT Smart Home Dataset, the framework integrates occupancy pattern analysis, appliance-level energy prediction, and probabilistic uncertainty quantification. The framework clusters occupancy-driven energy usage patterns using K-means and Gaussian Mixture Models, identifying three distinct household profiles: high-energy frequent occupancy, moderate-energy variable occupancy, and low-energy irregular occupancy. A Random Forest classifier is employed to pinpoint key appliances influencing occupancy, with a drop-in accuracy analysis verifying their predictive power. Uncertainty analysis quantifies classification confidence, revealing ambiguous periods linked to irregular appliance usage patterns. Additionally, time-series decomposition and appliance-level predictions are contextualised with seasonal and occupancy dynamics, enhancing interpretability. Comparative evaluations demonstrate the framework’s superior predictive accuracy and transparency over traditional single machine learning models, including Support Vector Machines (SVM) and XGBoost in Matlab 2024b and Python 3.10. By capturing occupancy-driven energy behaviours and accounting for inherent uncertainties, this research provides actionable insights for adaptive energy management. The proposed SIT hybrid model can contribute to sustainable and resilient smart energy systems, paving the way for efficient building energy management strategies.
format Article
id doaj-art-9a9f2c0122be478ba12c3eb95ad2d01a
institution OA Journals
issn 2673-8945
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Architecture
spelling doaj-art-9a9f2c0122be478ba12c3eb95ad2d01a2025-08-20T02:24:26ZengMDPI AGArchitecture2673-89452025-03-01522410.3390/architecture5020024Transforming Building Energy Management: Sparse, Interpretable, and Transparent Hybrid Machine Learning for Probabilistic Classification and Predictive Energy ModellingYiping Meng0Yiming Sun1Sergio Rodriguez2Binxia Xue3School of Computing, Engineering and Digital Technologies, Teesside University, Middlesbrough, Tees Valley TS1 3BX, UKSchool of Electrical and Electronic Engineering, University of Sheffield, Western Bank, Sheffield S10 2TN, UKSchool of Computing, Engineering and Digital Technologies, Teesside University, Middlesbrough, Tees Valley TS1 3BX, UKSchool of Architecture and Design, Harbin Institute of Technology, Harbin 150001, ChinaThe building sector, responsible for 40% of global energy consumption, faces increasing demands for sustainability and energy efficiency. Accurate energy consumption forecasting is essential to optimise performance and reduce environmental impact. This study introduces a hybrid machine learning framework grounded in Sparse, Interpretable, and Transparent (SIT) modelling to enhance building energy management. Leveraging the REFIT Smart Home Dataset, the framework integrates occupancy pattern analysis, appliance-level energy prediction, and probabilistic uncertainty quantification. The framework clusters occupancy-driven energy usage patterns using K-means and Gaussian Mixture Models, identifying three distinct household profiles: high-energy frequent occupancy, moderate-energy variable occupancy, and low-energy irregular occupancy. A Random Forest classifier is employed to pinpoint key appliances influencing occupancy, with a drop-in accuracy analysis verifying their predictive power. Uncertainty analysis quantifies classification confidence, revealing ambiguous periods linked to irregular appliance usage patterns. Additionally, time-series decomposition and appliance-level predictions are contextualised with seasonal and occupancy dynamics, enhancing interpretability. Comparative evaluations demonstrate the framework’s superior predictive accuracy and transparency over traditional single machine learning models, including Support Vector Machines (SVM) and XGBoost in Matlab 2024b and Python 3.10. By capturing occupancy-driven energy behaviours and accounting for inherent uncertainties, this research provides actionable insights for adaptive energy management. The proposed SIT hybrid model can contribute to sustainable and resilient smart energy systems, paving the way for efficient building energy management strategies.https://www.mdpi.com/2673-8945/5/2/24hybrid machine learningsparse interpretable transparent (SIT) modelenergy predictionuncertainty quantificationsustainable energy management
spellingShingle Yiping Meng
Yiming Sun
Sergio Rodriguez
Binxia Xue
Transforming Building Energy Management: Sparse, Interpretable, and Transparent Hybrid Machine Learning for Probabilistic Classification and Predictive Energy Modelling
Architecture
hybrid machine learning
sparse interpretable transparent (SIT) model
energy prediction
uncertainty quantification
sustainable energy management
title Transforming Building Energy Management: Sparse, Interpretable, and Transparent Hybrid Machine Learning for Probabilistic Classification and Predictive Energy Modelling
title_full Transforming Building Energy Management: Sparse, Interpretable, and Transparent Hybrid Machine Learning for Probabilistic Classification and Predictive Energy Modelling
title_fullStr Transforming Building Energy Management: Sparse, Interpretable, and Transparent Hybrid Machine Learning for Probabilistic Classification and Predictive Energy Modelling
title_full_unstemmed Transforming Building Energy Management: Sparse, Interpretable, and Transparent Hybrid Machine Learning for Probabilistic Classification and Predictive Energy Modelling
title_short Transforming Building Energy Management: Sparse, Interpretable, and Transparent Hybrid Machine Learning for Probabilistic Classification and Predictive Energy Modelling
title_sort transforming building energy management sparse interpretable and transparent hybrid machine learning for probabilistic classification and predictive energy modelling
topic hybrid machine learning
sparse interpretable transparent (SIT) model
energy prediction
uncertainty quantification
sustainable energy management
url https://www.mdpi.com/2673-8945/5/2/24
work_keys_str_mv AT yipingmeng transformingbuildingenergymanagementsparseinterpretableandtransparenthybridmachinelearningforprobabilisticclassificationandpredictiveenergymodelling
AT yimingsun transformingbuildingenergymanagementsparseinterpretableandtransparenthybridmachinelearningforprobabilisticclassificationandpredictiveenergymodelling
AT sergiorodriguez transformingbuildingenergymanagementsparseinterpretableandtransparenthybridmachinelearningforprobabilisticclassificationandpredictiveenergymodelling
AT binxiaxue transformingbuildingenergymanagementsparseinterpretableandtransparenthybridmachinelearningforprobabilisticclassificationandpredictiveenergymodelling