Prediction of energy use intensity of urban buildings using the semi-supervised deep learning model. (15th June 2022)

• Record Type: Journal Article
• Authors: Jiang, Feifeng; Ma, Jun; Li, Zheng; Ding, Yuexiong
• Is Part Of: Energy. Volume 249(2022)
• Publication Date: 2022-06-15
• Subjects: Energy use intensity -- Urban buildings -- Unlabeled samples -- Neural network -- Semi-supervised learning -- Spatial analysis; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2022.123631
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Prediction of building energy performance is a critical strategy for building energy management. Extant studies established city-scale prediction models only based on buildings with energy data. However, building energy data in most cities is limited, which may impair model performance. A large number of unlabeled buildings (without energy data) may reveal important energy use knowledge, but few studies have explored their capability to improve building energy prediction. Therefore, a novel semi-supervised deep learning method, namely dynamically updated multi-fold semi-supervised learning method based on deep neural networks (DUMSL-DNN) is proposed to predict building energy use intensity (EUI) by utilizing unlabeled samples. Manhattan is selected as a case study, which contains 4854 labeled samples and 34, 456 unlabeled samples. Compared with the optimal DNN model, DUMSL-DNN can improve building EUI prediction with root-mean-square error (RMSE) reduced by 9.36% and mean absolute error (MAE) reduced by 9.43%. The DUMSL method is superior to typical semi-supervised learning methods with the lowest RMSE of 0.5207 and the lowest MAE of 0.3325. By the implementation of DUMSL-DNN, more areas with high EUI are identified in Manhattan. Specifically, commercial buildings and residential buildings built before 1965 have higher EUI. Measures are accordingly proposed to improve building energy efficiency. Highlights: This study explores how the unlabeled samples can enhance building EUI prediction. A novel semi-supervised deep learning method is proposed for building EUI prediction. Compared with DNN, DUMSL-DNN can use unlabeled samples to reduce RMSE by 9.36%. The DUMSL method is superior to typical semi-supervised learning methods. More areas with high EUI are identified in Manhattan for policy-making.