Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings DOI Creative Commons
Haidar Hosamo, Silvia Mazzetto

Buildings, Год журнала: 2024, Номер 15(1), С. 39 - 39

Опубликована: Дек. 26, 2024

This study evaluates the performance of 15 machine learning models for predicting energy consumption (30–100 kWh/m2·year) and occupant dissatisfaction (Percentage Dissatisfied, PPD: 6–90%), key metrics optimizing building performance. Ten evaluation metrics, including Mean Absolute Error (MAE, average prediction error), Root Squared (RMSE, penalizing large errors), coefficient determination (R2, variance explained by model), are used. XGBoost achieves highest accuracy, with an MAE 1.55 kWh/m2·year a PPD 3.14%, alongside R2 values 0.99 0.97, respectively. While these highlight XGBoost’s superiority, its margin improvement over LightGBM (energy MAE: 2.35 kWh/m2·year, 3.89%) is context-dependent, suggesting application in high-precision scenarios. ANN excelled at predictions, achieving lowest (1.55%) Percentage (MAPE: 4.97%), demonstrating ability to model complex nonlinear relationships. modeling advantage contrasts LightGBM’s balance speed making it suitable computationally constrained tasks. In contrast, traditional like linear regression KNN exhibit high errors (e.g., 17.56 17.89%), underscoring their limitations respect capturing complexities datasets. The results indicate that advanced methods particularly effective owing intricate relationships manage high-dimensional data. Future research should validate findings diverse real-world datasets, those representing varying types climates. Hybrid combining interpretability precision ensemble or neural be explored. Additionally, integrating techniques digital twin platforms could address real-time optimization challenges, dynamic behavior time-dependent consumption.

Язык: Английский

An Integrative Approach to Enhance Load Forecasting Accuracy in Power Systems based on Multivariate Feature Selection and Selective Stacking Ensemble Modeling DOI
Jialei Chen, Chu Zhang, Xi Li

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 136337 - 136337

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Predicting Residential Energy Consumption in South Africa Using Ensemble Models DOI Creative Commons
David Attipoe, Donatien Koulla Moulla, Ernest Mnkandla

и другие.

Applied Computational Intelligence and Soft Computing, Год журнала: 2025, Номер 2025(1)

Опубликована: Янв. 1, 2025

This study presents ensemble machine learning (ML) models for predicting residential energy consumption in South Africa. By combining the best features of individual ML models, reduce drawbacks each model and improve prediction accuracy. We present four models: by averaging (EA), stacking estimator (ESE), boosting (EB), voting (EVE). These are built on top Random Forest (RF) Decision Tree (DT). base predictor leverage historical patterns to capture temporal intricacies, including seasonal variations rolling averages. In addition, we employed feature engineering methodologies further enhance their predictive abilities. The accuracy was evaluated assessing various performance indicators, mean squared error (MSE), absolute (MAE), percentage (MAPE), coefficient determination R 2 . Overall, findings illustrate efficiency providing accurate predictions consumption. provides valuable insights researchers practitioners buildings benefits using building research domains.

Язык: Английский

Процитировано

0
Applications of Explainable Artificial Intelligence (XAI) and interpretable Artificial Intelligence (AI) in smart buildings and energy savings in buildings: A systematic review DOI
M. Haghighat,

Ehsan MohammadiSavadkoohi,

Niusha Shafiabady

и другие.

Journal of Building Engineering, Год журнала: 2025, Номер unknown, С. 112542 - 112542

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings DOI Creative Commons
Haidar Hosamo, Silvia Mazzetto

Buildings, Год журнала: 2024, Номер 15(1), С. 39 - 39

Опубликована: Дек. 26, 2024

This study evaluates the performance of 15 machine learning models for predicting energy consumption (30–100 kWh/m2·year) and occupant dissatisfaction (Percentage Dissatisfied, PPD: 6–90%), key metrics optimizing building performance. Ten evaluation metrics, including Mean Absolute Error (MAE, average prediction error), Root Squared (RMSE, penalizing large errors), coefficient determination (R2, variance explained by model), are used. XGBoost achieves highest accuracy, with an MAE 1.55 kWh/m2·year a PPD 3.14%, alongside R2 values 0.99 0.97, respectively. While these highlight XGBoost’s superiority, its margin improvement over LightGBM (energy MAE: 2.35 kWh/m2·year, 3.89%) is context-dependent, suggesting application in high-precision scenarios. ANN excelled at predictions, achieving lowest (1.55%) Percentage (MAPE: 4.97%), demonstrating ability to model complex nonlinear relationships. modeling advantage contrasts LightGBM’s balance speed making it suitable computationally constrained tasks. In contrast, traditional like linear regression KNN exhibit high errors (e.g., 17.56 17.89%), underscoring their limitations respect capturing complexities datasets. The results indicate that advanced methods particularly effective owing intricate relationships manage high-dimensional data. Future research should validate findings diverse real-world datasets, those representing varying types climates. Hybrid combining interpretability precision ensemble or neural be explored. Additionally, integrating techniques digital twin platforms could address real-time optimization challenges, dynamic behavior time-dependent consumption.

Язык: Английский

Процитировано

2