대한건축학회논문집 (Journal of the Architectural Institute of Korea)

  • 제38권10호
  • /
  • Pages.231-240
  • /
  • 2022
  • /
  • 2733-6239(pISSN)
  • /
  • 2733-6247(eISSN)
대한건축학회 (Architectural Institute of Korea)
권호 표지
DOI QR코드

DOI QR Code

순환 신경망 모델에 따른 재실 인원 예측모델 개발 및 성능비교

Development of Occupancy Prediction Model and Performance Comparison According to the Recurrent Neural Network Models

  • Choi, Young Jae (Dept. of Architecture and Building Science, Chung-Ang University) ;
  • Park, Bo Rang (Dept. of Architecture and Building Science, Chung-Ang University) ;
  • Hyun, Ji Yeon (Dept. of Architecture and Building Science, Chung-Ang University) ;
  • Moon, Jin Woo (Dept. of Architecture and Building Science, Chung-Ang University)
  • 투고 : 2022.07.19
  • 심사 : 2022.09.20
  • 발행 : 2022.10.30
⟨ 이전 논문 다음 논문 ⟩

초록

An accurate occupancy prediction is essential for occupant-centric control (OCC) that saves energy while providing a comfortable indoor environment. Various machine learning-based approaches are being tried to develop an occupancy prediction model. Among these approaches, the performance of the recurrent neural network (RNN) based models, showed strength in time series forecasting and were found to be superb. However, studies related to performance comparison between RNN based models are insufficient; although the model performance had possibility for improvement through optimization. Therefore, in this study the RNN, long short-term memory (LSTM), and gated recurrent unit (GRU) models were developed to predict the number of occupants after 15, 30, and 60 minutes. The optimal models for each prediction horizon were derived through optimization and performance evaluation. As a result, the GRU model presented the best performance. The root mean squared error (RMSE) and mean absolute error (MAE) of the prediction model after 15 minutes was 0.8073, 1.5301, the prediction model after 30 minutes was 1.2841, 2.3386, and 2.0769, 3.3685, for the prediction model after 60 minutes. These results show superior performance compared to the existing RNN based models and signify that it is possible to provide accurate values for various prediction horizons. Thus, if outlier supplementation and addition of the adaptation function are implemented through an algorithm in the future, the developed models are expected to be utilized as a key element for OCC.

키워드

Acknowledgement

본 연구는 산업통상자원부(MOTIE)와 한국에너지기술평가원(KETEP)의 지원을 받아 수행한 연구 과제입니다. (No. 20212020800120)

References

  1. Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2018). State-of-the-art in artificial neural network applications: A survey, Heliyon, 4(11), e00938. https://doi.org/10.1016/j.heliyon.2018.e00938
  2. Arroyo, J., Spiessens, F., & Helsen, L. (2022). Comparison of optimal control techniques for building energy management, Frontiers in Built Environment, 8 (Artificial Intelligence Applications in Building's Thermal Management).
  3. Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult, IEEE Transactions on Neural Networks, 5(2), 157-166. https://doi.org/10.1109/72.279181
  4. Bianchini, G., Casini, M., Pepe, D., Vicino, A., & Zanvettor, G. G. (2019). An integrated model predictive control approach for optimal HVAC and energy storage operation in large-scale buildings, Applied Energy, 240, 327-340. https://doi.org/10.1016/j.apenergy.2019.01.187
  5. Chen, Z., & Soh, Y. C. (2017). Comparing occupancy models and data mining approaches for regular occupancy prediction in commercial buildings, Journal of Building Performance Simulation, 10(5-6), 545-553. https://doi.org/10.1080/19401493.2016.1199735
  6. Cho, H. U., Nam, Y., Choi, E. J., Choi, Y. J., Kim, H., Bae, S., & Moon, J. W. (2021). Comparative analysis of the optimized ANN, SVM, and tree ensemble models using bayesian optimization for predicting gshp cop, Journal of Building Engineering, 44, 103411. https://doi.org/10.1016/j.jobe.2021.103411
  7. Cho, K., Van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches, arXiv preprint arXiv, 1409-1259.
  8. Choi, Y. J., Park, B. R., Hyun, J. Y., & Moon, J. W. (2022). Development of an adaptive artificial neural network model and optimal control algorithm for a data center cyber-physical system, Building and Environment, 210, 108704. https://doi.org/10.1016/j.buildenv.2021.108704
  9. Hitimana, E., Bajpai, G., Musabe, R., Sibomana, L., & Kayalvizhi, J. (2021). Implementation of IoT framework with data analysis using deep learning methods for occupancy prediction in a building, Future Internet, 13(3), 67. https://doi.org/10.3390/fi13030067
  10. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory, Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  11. Huang, W., Lin, Y., Lin, B., & Zhao, L. (2019). Modeling and predicting the occupancy in a China hub airport terminal using Wi-Fi data, Energy and Buildings, 203, 109439. https://doi.org/10.1016/j.enbuild.2019.109439
  12. Huchuk, B., Sanner, S., & O'Brien, W. (2019). Comparison of machine learning models for occupancy prediction in residential buildings using connected thermostat data, Building and Environment, 160, 106177. https://doi.org/10.1016/j.buildenv.2019.106177
  13. Jin, Y., Yan, D., Chong, A., Dong, B., & An, J. (2021). Building occupancy forecasting: A systematical and critical review, Energy and Buildings, 251, 111345. https://doi.org/10.1016/j.enbuild.2021.111345
  14. Kim, S., Kang, S., Ryu, K. R., & Song, G. (2019). Real-time occupancy prediction in a large exhibition hall using deep learning approach. Energy and Buildings, 199, 216-222. https://doi.org/10.1016/j.enbuild.2019.06.043
  15. Kim Y. J., & Park C. S. (2008). Prediction of Occupant's Presence in Residential Apartment Buildings using Markov Chain, Korean Institute of Architectural Sustainable Environment and Building Systems Conference, 116-121.
  16. Luo, N., Wang, Z., Blum, D., Weyandt, C., Bourassa, N., Piette, M. A., & Hong, T. (2022). A three-year dataset supporting research on building energy management and occupancy analytics, Scientific Data, 9(1), 1-15. https://doi.org/10.1038/s41597-021-01104-5
  17. Ohsugi, S., & Koshizuka, N. (2018). Delivery route optimization through occupancy prediction from electricity usage, In 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC) IEEE, 1, 842-849.
  18. Panchabikesan, K., Haghighat, F., & El Mankibi, M. (2021). Data driven occupancy information for energy simulation and energy use assessment in residential buildings, Energy, 218, 119539. https://doi.org/10.1016/j.energy.2020.119539
  19. Peng, Y., Rysanek, A., Nagy, Z., & Schluter, A. (2017). Occupancy learning-based demand-driven cooling control for office spaces, Building and Environment, 122, 145-160. https://doi.org/10.1016/j.buildenv.2017.06.010
  20. Sangogboye, F. C., Arendt, K., Singh, A., Veje, C. T., Kjaergaard, M. B., & Jorgensen, B. N. (2017). Performance comparison of occupancy count estimation and prediction with common versus dedicated sensors for building model predictive control, Building Simulation, 10(6), 829-843. https://doi.org/10.1007/s12273-017-0397-5
  21. Schiele, J., Koperna, T., & Brunner, J. O. (2021). Predicting intensive care unit bed occupancy for integrated operating room scheduling via neural networks, Naval Research Logistics (NRL), 68(1), 65-88. https://doi.org/10.1002/nav.21929
  22. Snoek, J., Larochelle, H., & Adams, R. P. (2012). Practical bayesian optimization of machine learning algorithms, Advances in Neural Information Processing Systems, 25.
  23. Song, D. (2021). Green Remodeling for Carbon Neutrality in the Building Sector, Review of Architecture and Building Science, 65(6), 27-30.