A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Forecasting building occupancy: A temporal-sequential analysis and machine learning integrated approach
Graphical abstract Display Omitted
Highlights Occupancy forecasting in buildings is essential for operation and energy management. By integrating temporal-sequential analysis and machine learning method, the proposed model outperforms other baseline models. The consideration of weekly routine patterns by the TS-week-ANN model possessed better robustness and generalizability.
Abstract Building occupancy is the basis for building energy simulations, operations, and management. With the increasing need for energy conservation and the occupant-centric service of building energy systems, occupancy forecasting has become an essential input for simulations. These applications include model predictive control and demand response, with the potential to optimize the use of renewable energy sources. Based on recent research, occupancy forecasting tends to be based on occupancy data of the previous time step or continuous lagged dependent variables. Previous analysis demonstrated that building occupancy is innately temporal and sequential with seasonal features, which may be instructive for forecast research. This study proposes a temporal-sequential (TS) analysis and machine learning integrated approach for occupancy forecasting. Using hourly occupant data from 16 different buildings, we demonstrate that the proposed temporal-sequential analysis using a 1-week seasonal period with an artificial neural network structure (TS-week-ANN) outperforms other baseline methods.
Forecasting building occupancy: A temporal-sequential analysis and machine learning integrated approach
Graphical abstract Display Omitted
Highlights Occupancy forecasting in buildings is essential for operation and energy management. By integrating temporal-sequential analysis and machine learning method, the proposed model outperforms other baseline models. The consideration of weekly routine patterns by the TS-week-ANN model possessed better robustness and generalizability.
Abstract Building occupancy is the basis for building energy simulations, operations, and management. With the increasing need for energy conservation and the occupant-centric service of building energy systems, occupancy forecasting has become an essential input for simulations. These applications include model predictive control and demand response, with the potential to optimize the use of renewable energy sources. Based on recent research, occupancy forecasting tends to be based on occupancy data of the previous time step or continuous lagged dependent variables. Previous analysis demonstrated that building occupancy is innately temporal and sequential with seasonal features, which may be instructive for forecast research. This study proposes a temporal-sequential (TS) analysis and machine learning integrated approach for occupancy forecasting. Using hourly occupant data from 16 different buildings, we demonstrate that the proposed temporal-sequential analysis using a 1-week seasonal period with an artificial neural network structure (TS-week-ANN) outperforms other baseline methods.
Forecasting building occupancy: A temporal-sequential analysis and machine learning integrated approach
Jin, Yuan (author) / Yan, Da (author) / Kang, Xuyuan (author) / Chong, Adrian (author) / Sun, Hongsan-- (author) / Zhan, Sicheng (author)
Energy and Buildings ; 252
2021-08-11
Article (Journal)
Electronic Resource
English
Occupancy Forecasting for Dynamic Building Controls
| IEEE | 2023
Temporal Visualization of Building Occupancy Phase
| ASCE | 2007
Temporal Visualization of Building Occupancy Phase
| British Library Conference Proceedings | 2007
Building occupancy forecasting: A systematical and critical review
| Elsevier | 2021