A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Baseline Estimation of Heating Consumption for Different House Archetypes Through a Data-Driven Clustering Methodology
This paper presents a methodology to analyze data from smart thermostats aiming at proposing a black-box prediction model of energy consumption for three common house archetypes (bungalow, split, and two-storey building) in Québec. Through a multi-step data clustering approach, based on a combination of Gaussian mixture model (GMM) and partition-based method (k-Means), hidden patterns and outlier values in the dataset can be identified. The purpose of this paper is to create a general methodology able to assess the reference consumption profiles of housing joining a grid-interactive program with dynamic pricing of electricity. The results of the proposed methodology identify demand-response (DR) events during the considered winter period and reference energy profile evaluating different combinations of external temperature and global horizontal irradiation. The final data calibration, performed in MATLAB, evaluates the macro-parameters related to occupant behaviour and passive solar gain for each house archetype. The proposed model has been compared to the business as usual (BAU) procedure in terms of accuracy in prediction, showing CV-RMSE of 9–16% compared to 21–40% of reference.
Baseline Estimation of Heating Consumption for Different House Archetypes Through a Data-Driven Clustering Methodology
This paper presents a methodology to analyze data from smart thermostats aiming at proposing a black-box prediction model of energy consumption for three common house archetypes (bungalow, split, and two-storey building) in Québec. Through a multi-step data clustering approach, based on a combination of Gaussian mixture model (GMM) and partition-based method (k-Means), hidden patterns and outlier values in the dataset can be identified. The purpose of this paper is to create a general methodology able to assess the reference consumption profiles of housing joining a grid-interactive program with dynamic pricing of electricity. The results of the proposed methodology identify demand-response (DR) events during the considered winter period and reference energy profile evaluating different combinations of external temperature and global horizontal irradiation. The final data calibration, performed in MATLAB, evaluates the macro-parameters related to occupant behaviour and passive solar gain for each house archetype. The proposed model has been compared to the business as usual (BAU) procedure in terms of accuracy in prediction, showing CV-RMSE of 9–16% compared to 21–40% of reference.
Baseline Estimation of Heating Consumption for Different House Archetypes Through a Data-Driven Clustering Methodology
Environ Sci Eng
Wang, Liangzhu Leon (editor) / Ge, Hua (editor) / Zhai, Zhiqiang John (editor) / Qi, Dahai (editor) / Ouf, Mohamed (editor) / Sun, Chanjuan (editor) / Wang, Dengjia (editor) / Petrucci, Andrea (author) / Athienitis, Andreas K. (author) / Ayevide, Follivi Kloutse (author)
International Conference on Building Energy and Environment ; 2022
Proceedings of the 5th International Conference on Building Energy and Environment ; Chapter: 101 ; 949-957
2023-09-05
9 pages
Article/Chapter (Book)
Electronic Resource
English
| Wiley | 2012
| UB Braunschweig | 1987
Archetypes du patrimoine hospitalier Archetypes of the hospital heritage
| British Library Online Contents | 2002