Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Developing Urban-Scale Markovian Occupancy Profiles for Residential Buildings Using Smart Thermostat Data
The accuracy of building energy modelling (BEM) is challenged by the highly variable occupancy schedules, especially for residential buildings. In current practice, these models assume the same standard profile to represent occupancy in residential buildings regardless of the weekday, season, and household characteristics. To overcome these limitations, a larger dataset is required to develop dynamic, scalable occupancy models that can empower BEM tools and improve their reliability of modelling energy demand. To this end, this paper presents a methodology to use smart thermostat datasets to develop stochastic annual occupancy schedules for residential buildings. The proposed model is based on a duration probabilistic model integrated with the Markov-chain model to generate occupancy schedules that reflect the impact of time of day, day of the week, and seasons on the occupancy of residential buildings. The model showed an average accuracy of 71% and that the number of occupants in a given house has the most significant impact on the generated occupancy schedules.
Developing Urban-Scale Markovian Occupancy Profiles for Residential Buildings Using Smart Thermostat Data
The accuracy of building energy modelling (BEM) is challenged by the highly variable occupancy schedules, especially for residential buildings. In current practice, these models assume the same standard profile to represent occupancy in residential buildings regardless of the weekday, season, and household characteristics. To overcome these limitations, a larger dataset is required to develop dynamic, scalable occupancy models that can empower BEM tools and improve their reliability of modelling energy demand. To this end, this paper presents a methodology to use smart thermostat datasets to develop stochastic annual occupancy schedules for residential buildings. The proposed model is based on a duration probabilistic model integrated with the Markov-chain model to generate occupancy schedules that reflect the impact of time of day, day of the week, and seasons on the occupancy of residential buildings. The model showed an average accuracy of 71% and that the number of occupants in a given house has the most significant impact on the generated occupancy schedules.
Developing Urban-Scale Markovian Occupancy Profiles for Residential Buildings Using Smart Thermostat Data
Environ Sci Eng
Wang, Liangzhu Leon (Herausgeber:in) / Ge, Hua (Herausgeber:in) / Zhai, Zhiqiang John (Herausgeber:in) / Qi, Dahai (Herausgeber:in) / Ouf, Mohamed (Herausgeber:in) / Sun, Chanjuan (Herausgeber:in) / Wang, Dengjia (Herausgeber:in) / Doma, Aya (Autor:in) / Ouf, Mohamed (Autor:in)
International Conference on Building Energy and Environment ; 2022
Proceedings of the 5th International Conference on Building Energy and Environment ; Kapitel: 96 ; 897-905
05.09.2023
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Developing a residential occupancy schedule generator based on smart thermostat data
| Elsevier | 2024