Comparasion of HVAC Energy Consumption Prediction in an Academic Building using LSTM and DNN
Abstract
Energy consumption information is a collection of information obtained from datasets that is useful for making decisions for energy conservation. In this paper, we proposed a modern approach based on LSTM and DNN. While many researchers have employed these methods for predicting energy consumption, this paper seeks to compare their efficacy to determine which is superior. The comparative analysis in question employs accuracy metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2) values. Furthermore, the accuracy metric outcomes indicate that the LSTM method surpasses the DNN approach in terms of the R-squared (R2) value, with respective scores of 0.931 and 0.782. Meanwhile, for other accuracy metrics, the DNN method outperforms LSTM. Nevertheless, the performance of the two proposed methods is excellent, as evidenced by the R-squared (R2) value exceeding 0.75, which aligns with modeling standards observed in numerous research studies.
Keywords:
Long short-term memory (LSTM); Deep neural network (DNN); Accuracy metrics; Energy consumption prediction
Downloads
Download data is not yet available.
References
[1] T. A. Nguyen and M. Aiello, “Energy intelligent buildings based on user activity: A survey,“ Energy and Buildings, vol. 56, pp. 244-257, 2013, doi:10.1016/j.enbuild.2012.09.005.,[Online]. Available: http://dx.doi.org/10.1016/j.enbuild.2012.09.005
[2] Andrea Costa, Marcus M. Keane, J. Ignacio Torrens, Edward Corry, Building operation and energy performance: monitoring, analysis and optimisation toolkit, Appl. Energy 101 (2013) 310-316, https://doi.org/10.1016/ j.apenergy.2011.10.037.
[3] Global, A. B. C. 2020 Global Status Report for Buildings and Construction. Global Alliance for Buildings and Construction. Paris, France, 2020.
[4] H. Liu, Y. Liu, X. Guo, H. Wu, H. Wang, and Y. Liu, “An energy consumption prediction method for HVAC systems using energy storage based on time series shifting and deep learning,” Energy Build., vol. 298, no. August, p. 113508, 2023, doi: 10.1016/j.enbuild.2023.113508.
[5] S. L. Zhou, A. A. Shah, P. K. Leung, X. Zhu, and Q. Liao, “A comprehensive review of the applications of machine learning for HVAC,” DeCarbon, vol. 2, no. July, p. 100023, 2023, doi: 10.1016/j.decarb.2023.100023.
[6] K. Friansa, J. Pradipta, I. N. Haq, P. H. K. Utama, M. Wasesa, and E. Leksono, “Enhancing HVAC Electricity Load Prediction Accuracy using Bi-LSTM Method based on Daily Dataset,” Proc. 2023 Int. Conf. Instrumentation, Control. Autom. ICA 2023, pp. 92–96, 2023, doi: 10.1109/ICA58538.2023.10273121.
[7] A. Abida and P. Richter, “HVAC control in buildings using neural network,” J. Build. Eng., vol. 65, no. July 2022, p. 105558, 2023, doi: 10.1016/j.jobe.2022.105558.
[8] M. Ala’raj, M. Radi, M. F. Abbod, M. Majdalawieh, and M. Parodi, “Data-driven based HVAC optimisation approaches: A Systematic Literature Review,” J. Build. Eng., vol. 46, no. August 2021, p. 103678, 2022, doi: 10.1016/j.jobe.2021.103678
[9] D. Zhao et al., “Data-driven online energy management framework for HVAC systems: An experimental study,” Appl. Energy, vol. 352, no. August, p. 121921, 2023, doi: 10.1016/j.apenergy.2023.121921.
[10] H. Zhong, J. Wang, H. Jia, Y. Mu, S. Lv, Vector field-based support vector regression for building energy consumption prediction, Appl. Energy 242 (2019) 403–414.
[11] A.T. Eseye, M. Lehtonen, Short-term forecasting of heat demand of buildings for efficient and optimal energy management based on integrated machine learning models, IEEE Trans. Ind. Inf. 16 (12) (2020) 7743–7755.
[12] Y. Wei, X. Zhang, Y. Shi, L. Xia, S. Pan, J. Wu, X. Zhao, A review of data-driven approaches for prediction and classification of building energy consumption, Renew. Sustain. Energy Rev. 82 (2018) 1027–1047.
[13] A. Afram, F. Janabi-Sharifi, Review of modeling methods for HVAC systems, Appl. Therm. Eng. 67 (1–2) (2014) 507–519.
[14] R. Tang, C. Fan, F. Zeng, and W. Feng, “Data-driven model predictive control for power demand management and fast demand response of commercial buildings using support vector regression,” Build. Simul., vol. 15, no. 3, pp. 317–331, 2022, doi:10.1007/s12273-021-0811-x.
[15] Z. Wang, T. Hong, M.A. Piette, Building thermal load prediction through shallow machine learning and deep learning, Appl. Energy 263 (2020), 114683.
[16] A. Das, M.K. Annaqeeb, E. Azar, V. Novakovic, M.B. Kjærgaard, Occupant-centric miscellaneous electric loads prediction in buildings using state-of-the-art deep learning methods, Appl. Energy 269 (2020), 115135.
[17] Salam, A., & El Hibaoui, A. (2021). Energy consumption prediction model with deep inception residual network inspiration and LSTM. Mathematics and Computers in Simulation, 190, 97–109. https://doi.org/10.1016/j.matcom.2021.05.006.
[18] Graves A. Long short-term memory. In: Supervised sequence labelling with recurrent neural networks. Springer; 2012, p. 37–45.
[19] Jiang, P., Wang, Z., Li, X., Wang, X. V., Yang, B., & Zheng, J. (2023). Energy consumption prediction and optimization of industrial robots based on LSTM. Journal of Manufacturing Systems, 70(June), 137–148. https://doi.org/10.1016/j.jmsy.2023.07.009
[20] Li, Y., Tong, Z., Tong, S., & Westerdahl, D. (2022). A data-driven interval forecasting model for building energy prediction using attention-based LSTM and fuzzy information granulation. Sustainable Cities and Society, 76(October 2021), 103481. https://doi.org/10.1016/j.scs.2021.103481
[21] Li, G., Li, F., Xu, C., & Fang, X. (2022). A spatial-temporal layer-wise relevance propagation method for improving interpretability and prediction accuracy of LSTM building energy prediction. Energy and Buildings, 271, 112317. https://doi.org/10.1016/j.enbuild.2022.112317
[22] Pandey, P. R., & Dong, B. (2023). Prediction of window opening behavior and its impact on HVAC energy consumption at a residential dormitory using Deep Neural Network. Energy and Buildings, 296(May), 113355. https://doi.org/10.1016/j.enbuild.2023.113355
[23] Alcántara, A., Galván, I. M., & Aler, R. (2022). Direct estimation of prediction intervals for solar and wind regional energy forecasting with deep neural networks. Engineering Applications of Artificial Intelligence, 114(October 2021), 105128. https://doi.org/10.1016/j.engappai.2022.105128
[24] Modeling and optimizing building hvac energy systems using deep neural networks, International Conference on Smart Grid and Clean Energy Technologies (ICSGCE) (2018), https://doi.org/10.1109/ICSGCE.2018.8556684 , 2018
[25] Vision-based individual factors acquisition for thermal comfort assessment in a built environment, 15th IEEE International Conference on Automatic Face and Gesture Recognition (2020), https://doi.org/10.1109/FG47880.2020.00057 , 2020
[26] Y. Chen, Y. Shi, B. Zhang, Modeling and Optimization of Complex Building Energy Systems with Deep Neural Networks, 2017, https://doi.org/10.1109/ ACSSC.2017.8335578.
[27] Y. P. Chandra and T. Matuska, “Intelligent data systems for building energy workflow: Data pipelines, LSTM efficiency prediction and more,” Energy Build., vol. 267, p. 112135, 2022, doi: 10.1016/j.enbuild.2022.112135.
[28] S. Han, H. S. Choi, J. Choi, J. H. Choi, and J. G. Kim, “A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations,” Comput. Methods Appl. Mech. Eng., vol. 373, p. 113480, 2021, doi: 10.1016/j.cma.2020.113480.
[2] Andrea Costa, Marcus M. Keane, J. Ignacio Torrens, Edward Corry, Building operation and energy performance: monitoring, analysis and optimisation toolkit, Appl. Energy 101 (2013) 310-316, https://doi.org/10.1016/ j.apenergy.2011.10.037.
[3] Global, A. B. C. 2020 Global Status Report for Buildings and Construction. Global Alliance for Buildings and Construction. Paris, France, 2020.
[4] H. Liu, Y. Liu, X. Guo, H. Wu, H. Wang, and Y. Liu, “An energy consumption prediction method for HVAC systems using energy storage based on time series shifting and deep learning,” Energy Build., vol. 298, no. August, p. 113508, 2023, doi: 10.1016/j.enbuild.2023.113508.
[5] S. L. Zhou, A. A. Shah, P. K. Leung, X. Zhu, and Q. Liao, “A comprehensive review of the applications of machine learning for HVAC,” DeCarbon, vol. 2, no. July, p. 100023, 2023, doi: 10.1016/j.decarb.2023.100023.
[6] K. Friansa, J. Pradipta, I. N. Haq, P. H. K. Utama, M. Wasesa, and E. Leksono, “Enhancing HVAC Electricity Load Prediction Accuracy using Bi-LSTM Method based on Daily Dataset,” Proc. 2023 Int. Conf. Instrumentation, Control. Autom. ICA 2023, pp. 92–96, 2023, doi: 10.1109/ICA58538.2023.10273121.
[7] A. Abida and P. Richter, “HVAC control in buildings using neural network,” J. Build. Eng., vol. 65, no. July 2022, p. 105558, 2023, doi: 10.1016/j.jobe.2022.105558.
[8] M. Ala’raj, M. Radi, M. F. Abbod, M. Majdalawieh, and M. Parodi, “Data-driven based HVAC optimisation approaches: A Systematic Literature Review,” J. Build. Eng., vol. 46, no. August 2021, p. 103678, 2022, doi: 10.1016/j.jobe.2021.103678
[9] D. Zhao et al., “Data-driven online energy management framework for HVAC systems: An experimental study,” Appl. Energy, vol. 352, no. August, p. 121921, 2023, doi: 10.1016/j.apenergy.2023.121921.
[10] H. Zhong, J. Wang, H. Jia, Y. Mu, S. Lv, Vector field-based support vector regression for building energy consumption prediction, Appl. Energy 242 (2019) 403–414.
[11] A.T. Eseye, M. Lehtonen, Short-term forecasting of heat demand of buildings for efficient and optimal energy management based on integrated machine learning models, IEEE Trans. Ind. Inf. 16 (12) (2020) 7743–7755.
[12] Y. Wei, X. Zhang, Y. Shi, L. Xia, S. Pan, J. Wu, X. Zhao, A review of data-driven approaches for prediction and classification of building energy consumption, Renew. Sustain. Energy Rev. 82 (2018) 1027–1047.
[13] A. Afram, F. Janabi-Sharifi, Review of modeling methods for HVAC systems, Appl. Therm. Eng. 67 (1–2) (2014) 507–519.
[14] R. Tang, C. Fan, F. Zeng, and W. Feng, “Data-driven model predictive control for power demand management and fast demand response of commercial buildings using support vector regression,” Build. Simul., vol. 15, no. 3, pp. 317–331, 2022, doi:10.1007/s12273-021-0811-x.
[15] Z. Wang, T. Hong, M.A. Piette, Building thermal load prediction through shallow machine learning and deep learning, Appl. Energy 263 (2020), 114683.
[16] A. Das, M.K. Annaqeeb, E. Azar, V. Novakovic, M.B. Kjærgaard, Occupant-centric miscellaneous electric loads prediction in buildings using state-of-the-art deep learning methods, Appl. Energy 269 (2020), 115135.
[17] Salam, A., & El Hibaoui, A. (2021). Energy consumption prediction model with deep inception residual network inspiration and LSTM. Mathematics and Computers in Simulation, 190, 97–109. https://doi.org/10.1016/j.matcom.2021.05.006.
[18] Graves A. Long short-term memory. In: Supervised sequence labelling with recurrent neural networks. Springer; 2012, p. 37–45.
[19] Jiang, P., Wang, Z., Li, X., Wang, X. V., Yang, B., & Zheng, J. (2023). Energy consumption prediction and optimization of industrial robots based on LSTM. Journal of Manufacturing Systems, 70(June), 137–148. https://doi.org/10.1016/j.jmsy.2023.07.009
[20] Li, Y., Tong, Z., Tong, S., & Westerdahl, D. (2022). A data-driven interval forecasting model for building energy prediction using attention-based LSTM and fuzzy information granulation. Sustainable Cities and Society, 76(October 2021), 103481. https://doi.org/10.1016/j.scs.2021.103481
[21] Li, G., Li, F., Xu, C., & Fang, X. (2022). A spatial-temporal layer-wise relevance propagation method for improving interpretability and prediction accuracy of LSTM building energy prediction. Energy and Buildings, 271, 112317. https://doi.org/10.1016/j.enbuild.2022.112317
[22] Pandey, P. R., & Dong, B. (2023). Prediction of window opening behavior and its impact on HVAC energy consumption at a residential dormitory using Deep Neural Network. Energy and Buildings, 296(May), 113355. https://doi.org/10.1016/j.enbuild.2023.113355
[23] Alcántara, A., Galván, I. M., & Aler, R. (2022). Direct estimation of prediction intervals for solar and wind regional energy forecasting with deep neural networks. Engineering Applications of Artificial Intelligence, 114(October 2021), 105128. https://doi.org/10.1016/j.engappai.2022.105128
[24] Modeling and optimizing building hvac energy systems using deep neural networks, International Conference on Smart Grid and Clean Energy Technologies (ICSGCE) (2018), https://doi.org/10.1109/ICSGCE.2018.8556684 , 2018
[25] Vision-based individual factors acquisition for thermal comfort assessment in a built environment, 15th IEEE International Conference on Automatic Face and Gesture Recognition (2020), https://doi.org/10.1109/FG47880.2020.00057 , 2020
[26] Y. Chen, Y. Shi, B. Zhang, Modeling and Optimization of Complex Building Energy Systems with Deep Neural Networks, 2017, https://doi.org/10.1109/ ACSSC.2017.8335578.
[27] Y. P. Chandra and T. Matuska, “Intelligent data systems for building energy workflow: Data pipelines, LSTM efficiency prediction and more,” Energy Build., vol. 267, p. 112135, 2022, doi: 10.1016/j.enbuild.2022.112135.
[28] S. Han, H. S. Choi, J. Choi, J. H. Choi, and J. G. Kim, “A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations,” Comput. Methods Appl. Mech. Eng., vol. 373, p. 113480, 2021, doi: 10.1016/j.cma.2020.113480.
Published
2024-04-29
How to Cite
[1]
H. Christian, K. Friansa, J. Pradipta, I. Haq, and E. Leksono, “Comparasion of HVAC Energy Consumption Prediction in an Academic Building using LSTM and DNN”, JurnalEcotipe, vol. 11, no. 1, pp. 84-94, Apr. 2024.
Section
Articles
Copyright (c) 2024 Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright in each article is the property of the author.
- The author acknowledges that the Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering) has the right to publish for the first time with a Creative Commons Attribution 4.0 International License.
- The author can enter the writing separately, regulate the non-exculsive distribution of manuscripts that have been published in this journal into other versions (for example: sent to the author's institution respository, publication into books, etc.), by acknowledging that the manuscript was first published in the Jurnal Ecotipe (Electronic, Control, Telecommunication, Information, and Power Engineering);
