Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Roadmap for Utilizing Machine Learning in Building Energy Systems Applications: Case Study of Predicting Chiller Running Capacity for School Buildings Using Stacking Learning
Cooling accounts for 12-38% of total energy consumption in schools in the US, depending on the region. In this study, stacking learning is utilized to predict chiller running capacity for four school buildings (regression) and to predict the chiller status for four another schools (classification) using a collection of interval chiller data and building demand. Singular and multiple measurement periods within one or more seasons are considered. A generalized methodology for modeling building energy systems is posited that informs selection of features, data balancing to attain the best model possible, ensemble-based stacked learning in order to prevent over-fitting, and final model development based upon the results from the stacked learning. The results show that ensemble-based stacked learning improves the model performance substantially; providing the most accurate results for both regression and classification. for both classification and regression. For, classification, the balanced accuracy is 99.79% while Kappa is 99.39%. For regression, the R-squared value, the mean absolute error (MAE) error, and the root mean squared error (RMSE) are 1.78 kW, 2.77 kW, and 0.983 respectively.
Roadmap for Utilizing Machine Learning in Building Energy Systems Applications: Case Study of Predicting Chiller Running Capacity for School Buildings Using Stacking Learning
Cooling accounts for 12-38% of total energy consumption in schools in the US, depending on the region. In this study, stacking learning is utilized to predict chiller running capacity for four school buildings (regression) and to predict the chiller status for four another schools (classification) using a collection of interval chiller data and building demand. Singular and multiple measurement periods within one or more seasons are considered. A generalized methodology for modeling building energy systems is posited that informs selection of features, data balancing to attain the best model possible, ensemble-based stacked learning in order to prevent over-fitting, and final model development based upon the results from the stacked learning. The results show that ensemble-based stacked learning improves the model performance substantially; providing the most accurate results for both regression and classification. for both classification and regression. For, classification, the balanced accuracy is 99.79% while Kappa is 99.39%. For regression, the R-squared value, the mean absolute error (MAE) error, and the root mean squared error (RMSE) are 1.78 kW, 2.77 kW, and 0.983 respectively.
Roadmap for Utilizing Machine Learning in Building Energy Systems Applications: Case Study of Predicting Chiller Running Capacity for School Buildings Using Stacking Learning
Rodwan Elhashmi (Autor:in) / Kevin P. Hallinan (Autor:in) / Abdulrahman Alanezi (Autor:in)
24.02.2021
oai:zenodo.org:4560626
Journal of Energy & Technology (JET) 1(1) 35-45
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC:
690
Machine learning vs. hybrid machine learning model for optimal operation of a chiller
| Taylor & Francis Verlag | 2019
Predicting Main Characteristics of Reinforced Concrete Buildings Using Machine Learning
| DOAJ | 2024
Predicting building energy consumption in urban neighborhoods using machine learning algorithms
| DOAJ | 2024
A data-driven machine learning approach to predicting stacking faulting energy in austenitic steels
| British Library Online Contents | 2017
Predicting Energy Consumption of Office Buildings: A Hybrid Machine Learning-Based Approach
| Springer Verlag | 2018