Development of an IoT-based big data platform for day-ahead prediction of building heating and cooling demands. (August 2019)

• Record Type: Journal Article
• Authors: Luo, X.J.; Oyedele, Lukumon O.; Ajayi, Anuoluwapo O.; Monyei, Chukwuka G.; Akinade, Olugbenga O.; Akanbi, Lukman A.
• Is Part Of: Advanced engineering informatics. Volume 41(2019)
• Publication Date: 2019-08
• Subjects: Day-ahead prediction -- Clustering -- Artificial neural network -- Building heating and cooling demand -- Internet of Things -- Big data; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2019.100926
• Languages: English
• ISSNs: 1474-0346

Abstract

Graphical abstract: Highlights: A big data platform for day-ahead prediction of building heating and cooling demands using IoT sensors. Data-driven predictive model based on hybrids of k -means clustering and artificial neural network. Correlation analysis to determine input variables to data-driven predictive model. Prediction is made in each thermal zone with involvement of IoT sensors. Mean absolute percentage error is 3% and 8% for training and testing cases. Abstract: The emerging technologies of the Internet of Things (IoT) and big data can be utilised to derive knowledge and support applications for energy-efficient buildings. Effective prediction of heating and cooling demands is fundamental in building energy management. In this study, a 4-layer IoT-based big data platform is developed for day-ahead prediction of building energy demands, while the core part is the hybrid machine learning-based predictive model. The proposed energy demand predictive model is based on the hybrids of k -means clustering and artificial neural network (ANN). Due to different temperatures of walls, windows, grounds, roofs and indoor air, various IoT sensors are installed at different locations of the building. To determine the input variables to the hybrid machine learning-based predictive model, correlation analysis is adopted. Through clustering analysis, the characteristic patterns of daily weather profile are identified. Thus, the annual profile is classified into several featuring groups. Each group of weather profile, along with IoT sensor readings, building operating schedules as well as heating and cooling demands, is used to train the sub-ANN predictive models. Due to the involvement of IoT sensors, the overall prediction accuracy can be improved. It is found that the mean absolute percentage error of energy demands prediction is 3% and 8% in training and testing cases, respectively.