Machine learning model for predicting long-term energy consumption in buildings

Aug 3, 2026

Upload by Miles

The rapid growth in construction increases energy demand and carbon emissions, making accurate prediction of building energy use essential for energy security and sustainable development. The study investigates machine learning algorithms to forecast long-term energy consumption for buildings, supporting energy optimization and sustainable design. Three models are implemented—XGBoost, Support Vector Regression, and Long-Short-Term Memory—to capture interactions among building characteristics, environmental conditions, and energy patterns. Results identify LSTM as the most effective model, achieving R-squared of 0.993 and mean squared error of 0.004, outperforming SVM (R-squared 0.462) and XGBoost (R-squared 0.94).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Introduction

Energy conservation and global emissions

Role of machine learning in energy prediction

Study aim and modeling direction

Research Machine learning model for predicting long‑term energy consumption in buildings Aseel Hussien1 · Aref Maksoud1 · Aisha Al‑Dahhan2 · Ahmed Abdeen3 · Thar Baker4 Received: 26 October 2024 / Accepted: 24 February 2025 © The Author(s) 2025 OPEN Abstract The rapid growth in the construction sector has led to increased energy consumption and carbon emissions. Calculating energy usage and emissions is essential to energy security and promoting sustainable sector development. Therefore, the study objective is to investigate the utilazation of machine learning algorithm to predict long-term energy consumption in buildings sector, aiming to improve sustainable design and energy optimization, via the implementation of three machine learning models, XGBoost, Support Vector Regression, and Long-Short-Term Memory networks, to predict energy consumption. These models are adept at capturing complex interactions between building characteristics, environmental factors, and energy patterns. Although previous studies have explored various machine learning techniques for energy efficiency, limited research links these models to practical applications in building performance simulation. Furthermore, there is a lack of comparative evaluation of advanced machine learning models such as XGBoost, Support Vector Regression, and Long-Short-Term Memory to predict the energy consumption of building envelopes, particularly in hot climates such as the UAE. This research aims to fill this gap by providing a detailed comparison of these models against alternative approaches mentioned in the literature. The findings position Long-Short-Term Memory as a transformative force in predictive modeling, demonstrating exceptional precision with an R-squared value of 0.993 and a Mean Squared Error of 0.004. In contrast, Support Vector Regression and XGBoost showed limited predictive capabilities, with R-squared values of 0.462 and 0.94, respectively. This study establishes a solid data-driven foundation for architects and engineers to inform decisions on energy-efficient building designs, advocating Long-Short-Term Memory as the superior model for predicting energy performance. Highlights • Machine learning models enhance energy predictions, aiding sustainable building design and decision-making. • LSTM outperforms other models in forecasting energy efficiency of wall materials in hot climates. • Practical insights link ML theory to real-world applications, improving construction sustainability practices. Keywords Machine learning · Energy consumption · Building envelop · Indoor environment quality * Aseel Hussien, [ahussien@sharjah.ac.ae](ahussien@sharjah.ac.ae); Aref Maksoud, [amaksoud@sharjah.ac.ae](amaksoud@sharjah.ac.ae); Aisha Al-Dahhan, [u18103760@sharjah.ac.ae](u18103760@sharjah.ac.ae); Ahmed Abdeen, [ahmed_saleem@uow.edu.au](ahmed_saleem@uow.edu.au); Thar Baker, [t.shamsa@brighton.ac.uk |](t.shamsa@brighton.ac.uk |1Department of Architectural)[1](t.shamsa@brighton.ac.uk |1Department of Architectural)[Department of Architectural](t.shamsa@brighton.ac.uk |1Department of Architectural) Engineering, University of Sharjah, Sharjah, UAE. 2Department of Computer Science, University of Sharjah, Sharjah, UAE. 3Civil, Mining, Environmental, and Architectural Engineering, University of Wollongong, Wollongong, Australia. 4School of Architecture, Technology and Engineering, University of Brighton, Brighton, UK. Discover Internet of Things (2025) 5:18 | [https://doi.org/10.1007/s43926-025-001](https://doi.org/10.1007/s43926-025-001)15-7 1 Introduction Energy conservation in the construction sector has become a critical area of focus due to the sector’s significant energy consumption worldwide [1, 2]. Construction processes and building operations are responsible for approximately onethird of global greenhouse gas (GHG) emissions, making the sector a substantial contributor to global warming [3, 4]. This stresses the urgent need

FAQs

What is the main objective of the research?

To investigate machine learning algorithms for predicting long-term energy consumption in buildings and support sustainable design and energy optimization decisions.

Which machine learning models are compared in the study?

XGBoost, Support Vector Regression, and Long-Short-Term Memory (LSTM) are implemented and evaluated for energy consumption prediction.

How does LSTM perform compared with the other models?

LSTM delivers the highest predictive accuracy, with an R-squared value of 0.993 and mean squared error of 0.004, while Support Vector Regression and XGBoost show weaker or lower performance.

Aug 3, 2026

Upload by Miles