A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
A methodology for calibration of building energy models at district scale using clustering and surrogate techniques
Highlights A novel method based on clustering, building energy models and Bayesian techniques is presented. The approach enables the calibration of model parameters for large groups of buildings at an urban scale. Various data-driven techniques have been tested acting as proxy of the simulation engine. Three different surrogate structures have been investigated with comparison of the results. The calibrated models provide realistic results compared to current literature studies.
Abstract Prediction of building energy use, when performed at urban scale, is influenced by the choice of modelling approach, as well as the quality of available data. In the case of data scarcity, one of the main limitations of current urban scale building energy simulation models, is the use of deterministic approaches to specify modelling inputs for entire classes of buildings. This modelling approach is characterised by three major shortcomings: first, data uncertainties are not comprehensively considered; second, a rigorous method of identification of groups of buildings to be populated by similar modelling parameters is not specified; and third, strategies to calibrate the developed energy models are missing. Considering these challenges, the current paper presents a non-deterministic calibration method for groups of buildings. The methodology utilises four techniques: (i) the use of clustering to identify building groups and associated representative buildings within the urban context; (ii) the application of an automatic building energy modelling approach to simulate buildings within these groups; (iii) the application of data-driven models, used as emulators of the dynamic simulation engine, in a computationally efficient manner; and (iv) the exploitation of a non-deterministic Bayesian calibration framework to identify sets of representative parameters for the building clusters. Datasets, based on 2646 buildings from the city of Geneva, Switzerland, are used as a case study. Validation with measured data, shows that energy consumption and energy intensity predictions when considered at an aggregated scale, are within +/– 5%. On an individual building basis, the validation error is within +/– 20% for approximately 70% of the buildings.
A methodology for calibration of building energy models at district scale using clustering and surrogate techniques
Highlights A novel method based on clustering, building energy models and Bayesian techniques is presented. The approach enables the calibration of model parameters for large groups of buildings at an urban scale. Various data-driven techniques have been tested acting as proxy of the simulation engine. Three different surrogate structures have been investigated with comparison of the results. The calibrated models provide realistic results compared to current literature studies.
Abstract Prediction of building energy use, when performed at urban scale, is influenced by the choice of modelling approach, as well as the quality of available data. In the case of data scarcity, one of the main limitations of current urban scale building energy simulation models, is the use of deterministic approaches to specify modelling inputs for entire classes of buildings. This modelling approach is characterised by three major shortcomings: first, data uncertainties are not comprehensively considered; second, a rigorous method of identification of groups of buildings to be populated by similar modelling parameters is not specified; and third, strategies to calibrate the developed energy models are missing. Considering these challenges, the current paper presents a non-deterministic calibration method for groups of buildings. The methodology utilises four techniques: (i) the use of clustering to identify building groups and associated representative buildings within the urban context; (ii) the application of an automatic building energy modelling approach to simulate buildings within these groups; (iii) the application of data-driven models, used as emulators of the dynamic simulation engine, in a computationally efficient manner; and (iv) the exploitation of a non-deterministic Bayesian calibration framework to identify sets of representative parameters for the building clusters. Datasets, based on 2646 buildings from the city of Geneva, Switzerland, are used as a case study. Validation with measured data, shows that energy consumption and energy intensity predictions when considered at an aggregated scale, are within +/– 5%. On an individual building basis, the validation error is within +/– 20% for approximately 70% of the buildings.
A methodology for calibration of building energy models at district scale using clustering and surrogate techniques
Tardioli, Giovanni (author) / Narayan, Aditya (author) / Kerrigan, Ruth (author) / Oates, Michael (author) / O’Donnell, James (author) / Finn, Donal P. (author)
Energy and Buildings ; 226
2020-07-12
Article (Journal)
Electronic Resource
English
A methodology for auto-calibrating urban building energy models using surrogate modeling techniques
| Taylor & Francis Verlag | 2019
Building energy model calibration using a surrogate neural network
| Elsevier | 2023
| Taylor & Francis Verlag | 2024
A building energy models calibration methodology based on inverse modelling approach
| Springer Verlag | 2022
Using Bayesian deep learning approaches for uncertainty-aware building energy surrogate models
| DOAJ | 2021