Enhancing Residential Building Heating Load Prediction with Hybrid MLP Models

Yizhe  Guan

doi:10.6180/jase.202505_28(5).0007

Enhancing Residential Building Heating Load Prediction with Hybrid MLP Models

Civil Engineering

Yizhe GuanThis email address is being protected from spambots. You need JavaScript enabled to view it.

School of Architecture and Urban Planing, Yunnan University, Kunming 650000, Yunnan, China

Received: February 15, 2024
Accepted: May 26, 2024
Publication Date: July 10, 2024

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202505_28(5).0007

Efficiently managing the heating load (HL) of residential buildings is a critical aspect of energy conservation and sustainability. This study highlights a novel approach for HL prediction employing Multi-layer Perceptron (MLP) neural networks in conjunction with two innovative optimizers: Flying Fox Optimization (FFO) and Horse Herd Optimizers (HHO). The MLP is a powerful machine learning algorithm known for its ability to capture complex relationships within data. In this study, it is utilized as the core predictive model. FFO and HHO, both inspired by nature, provide optimization techniques that complement the MLP’s capabilities. The integration of these optimizers with the MLP model leads to a hybrid approach that leverages the strengths of each component. FFO and HHO are employed to fine-tune the MLP’s weights and biases, enhancing its predictive accuracy. The combination of MLP, FFO, and HHO outperforms traditional methods and even standalone MLP models in terms of predictive accuracy and convergence speed. This method improves HL prediction in homes aids energy management, and cuts environmental impact effectively. The hybrid MLFF2 model stands out by showcasing superior accuracy compared to other proposed models with an impressive R² value of 0.997 and a remarkably low RMSE of 0.523, MLFF2 has achieved the highest level of performance. Moreover, this research opens doors to exploring the application of nature-inspired optimization techniques in conjunction with neural networks for various other complex problems. The synergistic effect of the MLP and these innovative optimizers showcases the potential of hybrid models in addressing real-world challenges.

Keywords: Heating load; Multi-layer Perceptron; Horse Herd Optimizers; Flying Fox Optimization

[1] Y. Lu, Z. Tian, Q. Zhang, R. Zhou, and C. Chu, (2021) “Data augmentation strategy for short-term heating load prediction model of residential building" Energy 235: 121328. DOI: 10.1016/j.energy.2021.121328.
[2] R. Chaganti, F. Rustam, T. Daghriri, I. de la Torre Díez, J. L. V. Mazón, C. L. Rodríguez, and I. Ashraf, (2022) “Building heating and cooling load prediction using ensemble machine learning model" Sensors 22: 7692. DOI: 10.3390/s22197692.
[3] C. Wang, J. Yuan, K. Huang, J. Zhang, L. Zheng, Z. Zhou, and Y. Zhang, (2022) “Research on thermal load prediction of district heating station based on transfer learning" Energy 239: 122309. DOI: 10.1016/j.energy. 2021.122309.
[4] M. Proti´c, S. Shamshirband, M. H. Anisi, D. Petkovi´c, D. Miti´c, M. Raos, M. Arif, and K. A. Alam, (2015) “Appraisal of soft computing methods for short term consumers’ heat load prediction in district heating systems" Energy 82: 697–704. DOI: 10.1016/j.energy.2015.01.079.
[5] J. Ling, N. Dai, J. Xing, and H. Tong, (2021) “An improved input variable selection method of the data-driven model for building heating load prediction" Journal of Building Engineering 44: 103255. DOI: 10.1016/j.jobe.2021.103255.
[6] F. Dalipi, S. Y. Yayilgan, and A. Gebremedhin, (2016) “Data-driven machine-learning model in district heating system for heat load prediction: A comparison study" Applied Computational Intelligence and Soft Computing 2016: DOI: 10.1155/2016/3403150.
[7] G. Xue, Y. Pan, T. Lin, J. Song, C. Qi, and Z. Wang, (2019) “District heating load prediction algorithm based on feature fusion LSTM model" Energies 12: 2122. DOI: 10.3390/en12112122.
[8] K. Kato, M. Sakawa, K. Ishimaru, S. Ushiro, and T. Shibano. “Heat load prediction through recurrent neural network in district heating and cooling systems”. In: IEEE, 2008, 1401–1406. DOI: 10.1109/ICSMC.2008.4811482.
[9] J. Yuan, Z. Zhou, H. Tang, C. Wang, S. Lu, Z. Han, J. Zhang, and Y. Sheng, (2020) “Identification heat user behavior for improving the accuracy of heating load prediction model based on wireless on-off control system" Energy 199: 117454. DOI: 10.1016/j.energy.2020.117454.
[10] Y. Zhang, Z. Zhou, J. Liu, and J. Yuan, (2022) “Data augmentation for improving heating load prediction of heating substation based on TimeGAN" Energy 260: 124919. DOI: 10.1016/j.energy.2022.124919.
[11] G. Xue, C. Qi, H. Li, X. Kong, and J. Song, (2020) “Heating load prediction based on attention long short term memory: A case study of Xingtai" Energy 203: 117846. DOI: 10.1016/j.energy.2020.117846.
[12] Q. Zhang, Z. Tian, Z. Ma, G. Li, Y. Lu, and J. Niu, (2020) “Development of the heating load prediction model for the residential building of district heating based on model calibration" Energy 205: 117949. DOI: 10.1016/j.energy.2020.117949.
[13] E. Guelpa, L. Marincioni, M. Capone, S. Deputato, and V. Verda, (2019) “Thermal load prediction in district heating systems" Energy 176: 693–703. DOI: 10.1016/j.rser.2015.04.020.
[14] S. Shamshirband, D. Petkovi´c, R. Enayatifar, A. H. Abdullah, D. Markovi´c, M. Lee, and R. Ahmad, (2015) “Heat load prediction in district heating systems with adaptive neuro-fuzzy method" Renewable and Sustainable Energy Reviews 48: 760–767. DOI: 10.1016/j.enbuild. 2017.11.002.
[15] Y. Ding, Q. Zhang, T. Yuan, and K. Yang, (2018) “Model input selection for building heating load prediction: A case study for an office building in Tianjin" Energy and Buildings 159: 254–270. DOI: 10.1016/j.jobe.2019. 100950.
[16] M. Gong, Y. Bai, J. Qin, J. Wang, P. Yang, and S. Wang, (2020) “Gradient boosting machine for predicting return temperature of district heating system: A case study for residential buildings in Tianjin" Journal of Building Engineering 27: 100950. DOI: 10.1016/j.jobe.2019.100950.
[17] S. S. Roy, P. Samui, I. Nagtode, H. Jain, V. Shivaramakrishnan, and B. Mohammadi-Ivatloo, (2020) “Forecasting heating and cooling loads of buildings: A comparative performance analysis" Journal of Ambient Intelligence and Humanized Computing 11: 1253–1264. DOI: 10.1007/s12652-019-01317-y.
[18] B. Sadaghat, S. Afzal, and A. J. Khiavi, (2024) “Residential building energy consumption estimation: A novel ensemble and hybrid machine learning approach" Expert Systems with Applications 251: 123934. DOI: 10.1016/j.eswa.2024.123934.
[19] A. Moradzadeh, A. Mansour-Saatloo, B. Mohammadi-Ivatloo, and A. Anvari-Moghaddam, (2020) “Performance evaluation of two machine learning techniques in heating and cooling loads forecasting of residential buildings" Applied Sciences 10: 3829. DOI: 10.3390/app10113829.
[20] G. Zhou, H. Moayedi, M. Bahiraei, and Z. Lyu, (2020) “Employing artificial bee colony and particle swarm techniques for optimizing a neural network in prediction of heating and cooling loads of residential buildings" Journal of Cleaner Production 254: 120082. DOI: 10.1016/j.jclepro.2020.120082.
[21] A. Botchkarev, (2018) “Performance metrics (error measures) in machine learning regression, forecasting and prognostics: Properties and typology" arXiv preprint arXiv:1809.03006: DOI: 10.48550/arXiv.1809.03006.
[22] F. MiarNaeimi, G. Azizyan, and M. Rashki, (2021) “Horse herd optimization algorithm: A nature-inspired algorithm for high-dimensional optimization problems" Knowledge-Based Systems 213: 106711. DOI: 10.1016/j.knosys.2020.106711.
[23] S. Kumar, G. G. Tejani, N. Pholdee, and S. Bureerat, (2021) “Multiobjecitve structural optimization using improved heat transfer search" Knowledge-Based Systems 219: 106811. DOI: 10.1016/j.knosys.2021.106811.
[24] Z. Liu, P. Jiang, J. Wang, and L. Zhang, (2021) “Ensemble forecasting system for short-term wind speed forecasting based on optimal sub-model selection and multiobjective version of mayfly optimization algorithm" Expert Systems with Applications 177: 114974. DOI: 10.1016/j.eswa.2021.114974.
[25] Y. Li, W. Lu, Z. Pan, Z. Wang, and G. Dong, (2023) “Simultaneous identification of groundwater contaminant source and hydraulic parameters based on multilayer perceptron and flying foxes optimization" Environmental Science and Pollution Research 30: 78933–78947. DOI: 10.1007/s11356-023-27574-1.
[26] R. Aalloul, A. Elaissaoui, M. Benlattar, and R. Adhiri, (2023) “Emerging Parameters Extraction Method of PV Modules Based on the Survival Strategies of Flying Foxes Optimization (FFO)" Energies 16: 3531. DOI: 10.3390/en16083531.
[27] A. G. Parlos, K. T. Chong, and A. F. Atiya, (1994) “Application of the recurrent multilayer perceptron in modeling complex process dynamics" IEEE Transactions on Neural Networks 5: 255–266. DOI: 10.1109/72.279189.
[28] H. Taud and J.-F. Mas, (2018) “Multilayer perceptron (MLP)" Geomatic approaches for modeling land change scenarios: 451–455. DOI: 10.1007/978-3-319- 60801-3_27.
[29] F. Murtagh, (1991) “Multilayer perceptrons for classification and regression" Neurocomputing 2: 183–197. DOI: 10.1016/0925-2312(91)90023-5.
[30] H. Ramchoun, Y. Ghanou, M. Ettaouil, and M. A. J. Idrissi, (2016) “Multilayer perceptron: Architecture optimization and training": DOI: 10.9781/ijimai.2016.415.
[31] L. Noriega, (2005) “Multilayer perceptron tutorial" School of Computing. Staffordshire University 4: 444.
[32] C. Deb, F. Zhang, J. Yang, S. E. Lee, and K. W. Shah, (2017) “A review on time series forecasting techniques for building energy consumption" Renewable and Sustainable Energy Reviews 74: 902–924. DOI: 10.1016/j.rser.2017.02.085.
[33] N. Xu, Y. Dang, and Y. Gong, (2017) “Novel grey prediction model with nonlinear optimized time response method for forecasting of electricity consumption in China" Energy 118: 473–480. DOI: 10.1016/j.energy.2016.10.003.
[34] C. Li, Z. Ding, D. Zhao, J. Yi, and G. Zhang, (2017) “Building energy consumption prediction: An extreme deep learning approach" Energies 10: 1525. DOI: 10.3390/en10101525.
[35] C. Robinson, B. Dilkina, J. Hubbs, W. Zhang, S. Guhathakurta, M. A. Brown, and R. M. Pendyala, (2017) “Machine learning approaches for estimating commercial building energy consumption" Applied energy 208: 889–904. DOI: 10.1016/j.apenergy.2017.09.060.
[36] J. Zhu, Z. Yang, Y. Chang, Y. Guo, K. Zhu, and J. Zhang. “A novel LSTM based deep learning approach for multi-time scale electric vehicles charging load prediction”. In: IEEE, 2019, 3531–3536. DOI: 10.1109/ISGT-Asia.2019.8881655.
[37] N. Mohammadi and J. E. Taylor, (2017) “Urban energy flux: Spatiotemporal fluctuations of building energy consumption and human mobility-driven prediction" Applied energy 195: 810–818. DOI: 10.1016/j.apenergy.2017.03.044.
[38] D. Hsu, (2015) “Comparison of integrated clustering methods for accurate and stable prediction of building energy consumption data" Applied energy 160: 153– 163. DOI: 10.1016/j.apenergy.2015.08.126.
[39] S. Naji, A. Keivani, S. Shamshirband, U. J. Alengaram, M. Z. Jumaat, Z. Mansor, and M. Lee, (2016) “Estimating building energy consumption using extreme learning machine method" Energy 97: 506–516. DOI: 10.1016/j. energy.2015.11.037.
[40] F. Zhang, C. Deb, S. E. Lee, J. Yang, and K. W. Shah, (2016) “Time series forecasting for building energy consumption using weighted Support Vector Regression with differential evolution optimization technique" Energy and Buildings 126: 94–103. DOI: 10.1016/j.enbuild. 2016.05.028.
[41] M. W. Ahmad, M. Mourshed, and Y. Rezgui, (2017) “Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption" Energy and buildings 147: 77–89. DOI: 10.1016/j.enbuild.2017.04.038.
[42] A. Moradzadeh, A. Mansour-Saatloo, B. Mohammadi-Ivatloo, and A. Anvari-Moghaddam, (2020) “Performance evaluation of two machine learning techniques in heating and cooling loads forecasting of residential buildings" Applied Sciences 10: 3829. DOI: 10.3390/app10113829.
[43] S. S. Roy, P. Samui, I. Nagtode, H. Jain, V. Shivaramakrishnan, and B. Mohammadi-Ivatloo, (2020) “Forecasting heating and cooling loads of buildings: A comparative performance analysis" Journal of Ambient Intelligence and Humanized Computing 11: 1253– 1264. DOI: 10.1007/s12652-019-01317-y.
[44] T.-Y. Kim and S.-B. Cho, (2019) “Predicting residential energy consumption using CNN-LSTM neural networks" Energy 182: 72–81. DOI: 10.1016/j.energy.2019.05.230.
[45] M. R. Akbarzadeh, H. Ghafourian, A. Anvari, R. Pourhanasa, and M. L. Nehdi, (2023) “Estimating compressive strength of concrete using neural electromagnetic field optimization" Materials 16: 4200. DOI: 10.3390/ma16114200.
[46] Z. Wang, T. Hong, and M. A. Piette, (2020) “Building thermal load prediction through shallow machine learning and deep learning" Applied Energy 263: 114683. DOI: 10.1016/j.apenergy.2020.114683.
[47] B. Sedaghat, A. J. Khiavi, B. Naeim, E. Khajavi, and A. R. T. Khanghah, (2023) “Evaluation of Object-Based and Pixel-Based Technique for Extracting Snow Cover Surface Using Landsat 8 Satellite Images (Case Study Damavand Mountain Range)" Advances in Engineering and Intelligence Systems 2: 87–100. DOI: 10.22034/AEIS.2023.427451.1147.
[48] S. Afzal, B. M. Ziapour, A. Shokri, H. Shakibi, and B. Sobhani, (2023) “Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms" Energy 282: 128446. DOI: 10.1016/j.energy.2023.128446.
[49] M. Sajjad, S. U. Khan, N. Khan, I. U. Haq, A. Ullah, M. Y. Lee, and S. W. Baik, (2020) “Towards efficient building designing: Heating and cooling load prediction via multi-output model" Sensors 20: 6419. DOI: 10.3390/s20226419.