TY - JOUR
T1 - Forecasting district-scale energy dynamics through integrating building network and long short-term memory learning algorithm
AU - Wang, Wei
AU - Hong, Tianzhen
AU - Xu, Xiaodong
AU - Chen, Jiayu
AU - Liu, Ziang
AU - Xu, Ning
PY - 2019/8/15
Y1 - 2019/8/15
N2 - With the development of data-driven techniques, district-scale building energy prediction has attracted increasing attention in recent years for revealing energy use patterns and reduction potentials. However, data acquisition in large building groups is difficult and adjacent buildings also interact with each other. To reduce data cost and incorporate the inter-building impact with the data-driven building energy model, this study proposes a deep learning predictive approach that fuses the building network model with a long short-term memory learning model for district-scale building energy modeling. The building network was constructed based on correlations between the energy use intensity of buildings, which can significantly reduce the computational complexity of the deep learning models for energy dynamic prediction. Five typical building groups with energy use data from 2015 to 2018 on two institutional campuses were selected to perform the validation experiment with TensorFlow. Based on the prediction error assessments, the results suggest that for total building energy use intensity prediction, the proposed model can achieve a mean absolute percentage error of 6.66% and a root mean square error of 0.36 kWh/m2, compared to 12.05% and 0.63 kWh/m2 of the conventional artificial neural network model and to 11.06% and 0.89 kWh/m2 for the support vector regression model.
AB - With the development of data-driven techniques, district-scale building energy prediction has attracted increasing attention in recent years for revealing energy use patterns and reduction potentials. However, data acquisition in large building groups is difficult and adjacent buildings also interact with each other. To reduce data cost and incorporate the inter-building impact with the data-driven building energy model, this study proposes a deep learning predictive approach that fuses the building network model with a long short-term memory learning model for district-scale building energy modeling. The building network was constructed based on correlations between the energy use intensity of buildings, which can significantly reduce the computational complexity of the deep learning models for energy dynamic prediction. Five typical building groups with energy use data from 2015 to 2018 on two institutional campuses were selected to perform the validation experiment with TensorFlow. Based on the prediction error assessments, the results suggest that for total building energy use intensity prediction, the proposed model can achieve a mean absolute percentage error of 6.66% and a root mean square error of 0.36 kWh/m2, compared to 12.05% and 0.63 kWh/m2 of the conventional artificial neural network model and to 11.06% and 0.89 kWh/m2 for the support vector regression model.
KW - Building network
KW - Data-driven prediction
KW - District-scale building energy modeling
KW - Long short-term memory networks
UR - http://www.scopus.com/inward/record.url?scp=85064623389&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85064623389&origin=recordpage
U2 - 10.1016/j.apenergy.2019.04.085
DO - 10.1016/j.apenergy.2019.04.085
M3 - 21_Publication in refereed journal
VL - 248
SP - 217
EP - 230
JO - Applied Energy
JF - Applied Energy
SN - 0306-2619
ER -