Developing window behavior models for residential buildings using XGBoost algorithm

•Longitudinal behavioral data were collected from six apartments, lasting for 136 days.•Window behavior models were developed for residential buildings in China.•XGBoost algorithm showed better prediction performance than logistic regression. Buildings account for over 32% of total society energy co...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Energy and buildings Ročník 205; s. 109564
Hlavní autoři: Mo, Hao, Sun, Hejiang, Liu, Junjie, Wei, Shen
Médium: Journal Article
Jazyk:angličtina
Vydáno: Lausanne Elsevier B.V 15.12.2019
Elsevier BV
Témata:
Accuracy
Air conditioners
Air conditioning
Algorithms
Artificial intelligence
Behavior
Behavior modeling
Building design
Buildings
Computer simulation
Energy consumption
Energy efficiency
Learning algorithms
Logistics regression
Machine learning
Mathematical models
Model accuracy
Regression analysis
Residential areas
Residential buildings
Ventilation
Window behavior
XGBoost algorithm
Window behavior
XGBoost algorithm
Behavior modeling
Logistics regression
Residential buildings
ISSN:0378-7788, 1872-6178
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Longitudinal behavioral data were collected from six apartments, lasting for 136 days.•Window behavior models were developed for residential buildings in China.•XGBoost algorithm showed better prediction performance than logistic regression. Buildings account for over 32% of total society energy consumption, and to make buildings more energy efficient dynamic building performance simulation has been widely adopted during the buildings’ design to help select most appropriate HVAC (Heating Ventilation and Air Conditioning) systems. Due to the lack of good behavioral models in current simulation packages, many researchers have tried to develop useful behavioral models to improve simulation accuracy, including window behavior models, using field data collected from real buildings. During this work, many mathematical and machine learning methods have been used, and some level of prediction accuracy has been achieved. XGBoost is a recently introduced machine learning algorithm, which has been proven as very powerful in modeling complicated processes in other research fields. In this study, this algorithm has been adopted to model and predict occupant window behavior, aiming to further improve the modeling accuracy from a globally accepted modeling approach, namely, Logistic Regression Analysis. Field data in terms of both occupant window behavior and relevant influential factors were collected from real residential buildings during transitional seasons. Both XGBoost and Logistic Regression Analysis were used to build window behavior models, after a feature selection work, and their prediction performances on an independent dataset were compared. The comparison revealed that XGBoost has solid advantages in modeling occupant window behavior, over Logistic Regression Analysis, and it is expecting that the same finding would be obtained for other behavioral types, such as blind control and air-conditioner operation.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0378-7788
1872-6178
DOI:10.1016/j.enbuild.2019.109564