Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings
This study evaluates the performance of 15 machine learning models for predicting energy consumption (30–100 kWh/m<sup>2</sup>·year) and occupant dissatisfaction (Percentage of Dissatisfied, PPD: 6–90%), key metrics for optimizing building performance. Ten evaluation metrics, including M...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/15/1/39 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549329792237568 |
|---|---|
| author | Haidar Hosamo Silvia Mazzetto |
| author_facet | Haidar Hosamo Silvia Mazzetto |
| author_sort | Haidar Hosamo |
| collection | DOAJ |
| description | This study evaluates the performance of 15 machine learning models for predicting energy consumption (30–100 kWh/m<sup>2</sup>·year) and occupant dissatisfaction (Percentage of Dissatisfied, PPD: 6–90%), key metrics for optimizing building performance. Ten evaluation metrics, including Mean Absolute Error (MAE, average prediction error), Root Mean Squared Error (RMSE, penalizing large errors), and the coefficient of determination (R<sup>2</sup>, variance explained by the model), are used. XGBoost achieves the highest accuracy, with an energy MAE of 1.55 kWh/m<sup>2</sup>·year and a PPD MAE of 3.14%, alongside R<sup>2</sup> values of 0.99 and 0.97, respectively. While these metrics highlight XGBoost’s superiority, its margin of improvement over LightGBM (energy MAE: 2.35 kWh/m<sup>2</sup>·year, PPD MAE: 3.89%) is context-dependent, suggesting its application in high-precision scenarios. ANN excelled at PPD predictions, achieving the lowest MAE (1.55%) and Mean Absolute Percentage Error (MAPE: 4.97%), demonstrating its ability to model complex nonlinear relationships. This nonlinear modeling advantage contrasts with LightGBM’s balance of speed and accuracy, making it suitable for computationally constrained tasks. In contrast, traditional models like linear regression and KNN exhibit high errors (e.g., energy MAE: 17.56 kWh/m<sup>2</sup>·year, PPD MAE: 17.89%), underscoring their limitations with respect to capturing the complexities of building performance datasets. The results indicate that advanced methods like XGBoost and ANN are particularly effective owing to their ability to model intricate relationships and manage high-dimensional data. Future research should validate these findings with diverse real-world datasets, including those representing varying building types and climates. Hybrid models combining the interpretability of linear methods with the precision of ensemble or neural models should be explored. Additionally, integrating these machine learning techniques with digital twin platforms could address real-time optimization challenges, including dynamic occupant behavior and time-dependent energy consumption. |
| format | Article |
| id | doaj-art-204707def5ee4c20af99fac66b99d4b0 |
| institution | Kabale University |
| issn | 2075-5309 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj-art-204707def5ee4c20af99fac66b99d4b02025-01-10T13:15:51ZengMDPI AGBuildings2075-53092024-12-011513910.3390/buildings15010039Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in BuildingsHaidar Hosamo0Silvia Mazzetto1The SALab Sustainable Architecture Lab, Department of Architecture, Prince Sultan University, Riyadh 12435, Saudi ArabiaThe SALab Sustainable Architecture Lab, Department of Architecture, Prince Sultan University, Riyadh 12435, Saudi ArabiaThis study evaluates the performance of 15 machine learning models for predicting energy consumption (30–100 kWh/m<sup>2</sup>·year) and occupant dissatisfaction (Percentage of Dissatisfied, PPD: 6–90%), key metrics for optimizing building performance. Ten evaluation metrics, including Mean Absolute Error (MAE, average prediction error), Root Mean Squared Error (RMSE, penalizing large errors), and the coefficient of determination (R<sup>2</sup>, variance explained by the model), are used. XGBoost achieves the highest accuracy, with an energy MAE of 1.55 kWh/m<sup>2</sup>·year and a PPD MAE of 3.14%, alongside R<sup>2</sup> values of 0.99 and 0.97, respectively. While these metrics highlight XGBoost’s superiority, its margin of improvement over LightGBM (energy MAE: 2.35 kWh/m<sup>2</sup>·year, PPD MAE: 3.89%) is context-dependent, suggesting its application in high-precision scenarios. ANN excelled at PPD predictions, achieving the lowest MAE (1.55%) and Mean Absolute Percentage Error (MAPE: 4.97%), demonstrating its ability to model complex nonlinear relationships. This nonlinear modeling advantage contrasts with LightGBM’s balance of speed and accuracy, making it suitable for computationally constrained tasks. In contrast, traditional models like linear regression and KNN exhibit high errors (e.g., energy MAE: 17.56 kWh/m<sup>2</sup>·year, PPD MAE: 17.89%), underscoring their limitations with respect to capturing the complexities of building performance datasets. The results indicate that advanced methods like XGBoost and ANN are particularly effective owing to their ability to model intricate relationships and manage high-dimensional data. Future research should validate these findings with diverse real-world datasets, including those representing varying building types and climates. Hybrid models combining the interpretability of linear methods with the precision of ensemble or neural models should be explored. Additionally, integrating these machine learning techniques with digital twin platforms could address real-time optimization challenges, including dynamic occupant behavior and time-dependent energy consumption.https://www.mdpi.com/2075-5309/15/1/39machine learning modelsenergy consumption predictionoccupant dissatisfactionbuilding performance optimizationevaluation metricsadvanced algorithms |
| spellingShingle | Haidar Hosamo Silvia Mazzetto Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings Buildings machine learning models energy consumption prediction occupant dissatisfaction building performance optimization evaluation metrics advanced algorithms |
| title | Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings |
| title_full | Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings |
| title_fullStr | Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings |
| title_full_unstemmed | Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings |
| title_short | Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings |
| title_sort | performance evaluation of machine learning models for predicting energy consumption and occupant dissatisfaction in buildings |
| topic | machine learning models energy consumption prediction occupant dissatisfaction building performance optimization evaluation metrics advanced algorithms |
| url | https://www.mdpi.com/2075-5309/15/1/39 |
| work_keys_str_mv | AT haidarhosamo performanceevaluationofmachinelearningmodelsforpredictingenergyconsumptionandoccupantdissatisfactioninbuildings AT silviamazzetto performanceevaluationofmachinelearningmodelsforpredictingenergyconsumptionandoccupantdissatisfactioninbuildings |