https://orcid.org/0000-0001-5486-7214
![Sample our Computer Science journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5928/TOC-Subject-Sample-2021-Computer-Science.jpg"})
ABSTRACT
In non-air-conditioned buildings, opening or closing of windows is one of the most common behaviours that occupants tend to carry out to restore their thermal comfort. As an alternative approach to studying the occupant behaviour, particularly when it is difficult to run extensive field studies or due to limits like privacy concerns, this work explores a data-driven method to predict the window openings based on thermal comfort evaluation. The Gradient Boosting Decision Trees (GBDT) algorithm is applied to investigate the importance of selected features, including weather and main building characteristics, to the indoor thermal comfort in non-air-conditioned buildings across whole China. The training set comprises the building simulation results of 95 main cities covering all the five climate regions in China and has 828,360 groups of data in total. The predictor achieves a high accuracy of approximately 95%, and therefore enables the users to estimate the likelihood of window opening based on outdoor weather conditions and local building characteristics. As an original contribution, the study shows that conditioned upon the availability of adequate simulation data, a machine learning predictor trained solely on simulation data can accurately predict realistic window opening behaviours, without relying on any indoor measurement.
Acknowledgements
This article acknowledges the International Conference on Civil, Architecture and Marine Engineering for publishing a portion of this abstract on ‘Tongyu Zhou, Yu Fu, and Isaac Lun. A machine learning approach to predict window openings in naturally ventilated buildings. International conference on Civil, Architecture and Marine Engineering. Osaka, Japan.2019’.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
Yu Fu
Yu Fu received the B.S. degree in Architectural Environment Engineering from the University of Nottingham Ningbo China in 2019 and the M.S. degree in Spatial Data Science and Visualisation from University College London in 2020. He is currently working as a software engineer at HiSilicon Technologies Co., Ltd. His research interests include embedded systems and machine learning.
Tongyu Zhou
Dr. Tongyu Zhou is an assistant professor in building service engineering at the Department of Architecture and Built environment, the University of Nottingham Ningbo China. He has a multidisciplinary educational background and industrial experience covering computer science, HVAC systems and intelligent buildings. His research interests mainly focus on low carbon buildings, thermal energy storage systems, building energy simulation, human comfort and occupant behaviour in buildings.
Isaac Lun
Dr. Isaac Lun is an assistant professor at the University of Nottingham Ningbo China, China. He graduated with a BEng (Hons) in Aeronautical Engineering and an MPhil in Computational Fluid Dynamics from the University of Hertfordshire, UK, and a DEng in Computational Wind Engineering at the Tohoku University, Japan. He is a member of the Institution of Mechanical Engineers, Royal Aeronautical Society and Architectural Institute of Japan. His research interests include CFD applications, urban thermal environment, wind environment, building energy simulation.
Fazel Khayatian
Dr. Fazel Khayatian is a postdoctoral researcher at the Urban Energy Systems Laboratory of Empa. His research is focused on the applications of machine learning for building energy analytics.
Wu Deng
Dr. Wu Deng is an associate professor in sustainable architecture in the Department of Architecture and Built Environment at the University of Nottingham Ningbo China. His main research areas are building typology and energy efficient building technologies in hot summer and cold winter climate.
Weiguang Su
Dr. Weiguang Su is an associate professor of Mechanical & Automotive Engineering at the Qilu University of Technology (Shandong Academy of Sciences). He holds a bachelor degree in mechanical engineering, a master degree in chemical processing and mechanical engineering, and a PhD in sustainable energy technology. He had worked as an R&D engineer at Shandong Academy of Sciences (2009–2010) and a research associate at the University of Nottingham Ningbo China (2010–2012). His research interests including energy saving in buildings, microencapsulation technologies, thermal energy storage, phase change materials. He has been awarded six research projects as a project leader by the Chinese government and industry. He was also involved in three research projects as a key research member. His research outcomes include over 40 academic papers and 21 patents.