Improving Heating Load Prediction with LSSVR: Comparative Analysis of Optimized Models

Deshen  LV; Chengquan  LIANG; Xiao  LU

doi:10.6180/jase.202505_28(5).0018

Improving Heating Load Prediction with LSSVR: Comparative Analysis of Optimized Models

Deshen LV¹, Chengquan LIANG¹This email address is being protected from spambots. You need JavaScript enabled to view it., and Xiao LU²

¹School of Intelligent Manufacturing, Nanning University, Nanning 530200, China

²School of Information Science and Engineering, Guilin University of Technology, Guilin 541006, China

Received: January 30, 2023
Accepted: May 12, 2024
Publication Date: July 15, 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).0018

At present, energy usage is one of the critical components of the global economy and population growth in the construction sector. Buildings play a crucial role in global energy consumption, and it is vital to forecast the heating needs of this sector thoroughly. This necessity is driven by various significant factors, including improving energy efficiency, financial responsibility, promoting environmental health, and developing sustainable and long-lasting solutions. Accurately estimating the heating load of buildings is incredibly important. Machine learning (ML) is one of the most effective techniques among the various methods employed for this purpose. This approach involves the analysis of historical data and an evaluation of the present conditions within the building to deliver precise predictions regarding heating load requirements. This study aims to apply the Least Squares Support Vector Regression (LSSVR) method, a frequently used ML algorithm for predicting continuous numerical values for determining building heating load. The application of the Arithmetic Optimization Algorithm (AOA) and the Ebola Optimization Search Algorithm (EOSA) is geared toward improving accuracy and reducing overall losses in heating load estimation. The research provides significant insights into predicting building heating loads and recommends that employing an LSSVR+EOSA (LSEO) model is the most efficient strategy for optimizing energy consumption. This hybrid model achieved a maximum determination coefficient of 0.985 and a root mean square error of 1.223.

Keywords: Heating Load, Least Squares Support Vector Regression, Arithmetic Optimization Algorithm, Ebola Optimization Search Algorithm.

[1] I. Dadon, (2019) “Planning the Second Generation of Smart Cities: Technology to handle the pressures of urbanization" IEEE Electrification Magazine 7(3): 6–15. DOI: 10.1109/MELE.2019.2925729.
[2] B. Sadaghat, A. Javadzade Khiavi, B. Naeim, E. Khajavi, H. Sadaghat, and A. R. Taghavi Khanghah, (2023) “The utilization of a naıve bayes model for predicting the energy consumption of buildings" Journal of Artificial Intelligence and System Modelling 1(01): 73–91. DOI: 10.22034/JAISM.2023.422292.1003.
[3] R. Jing, M. Wang, R. Zhang, N. Li, and Y. Zhao, (2017) “A study on energy performance of 30 commercial office buildings in Hong Kong" Energy and Buildings 144: 117–128. DOI: 10.1016/j.enbuild.2017.03.042.
[4] G. Yang and X. Zhai, (2019) “Optimal design and performance analysis of solar hybrid CCHP system considering influence of building type and climate condition" Energy 174: 647–663. DOI: 10.1016/j.energy.2019.03.001.
[5] L. Zhang, J. Wen, Y. Li, J. Chen, Y. Ye, Y. Fu, and W. Livingood, (2021) “A review of machine learning in building load prediction" Applied Energy 285: 116452. DOI: 10.1016/j.apenergy.2021.116452.
[6] X. Zhang, R. Yan, R. Zeng, R. Zhu, X. Kong, Y. He, and H. Li, (2022) “Integrated performance optimization of a biomass-based hybrid hydrogen/thermal energy storage system for building and hydrogen vehicles" Renewable Energy 187: 801–818. DOI: 10.1016/j.renene. 2022.01.050.
[7] X.-N. Bui, H. Moayedi, and A. S. A. Rashid, (2020) “Developing a predictive method based on optimized M5Rules–GA predicting heating load of an energyefficient building system" Engineering with Computers 36: 931–940. DOI: 10.1007/s00366-019-00739-8.
[8] X. Li and R. Yao, (2020) “A machine-learning-based approach to predict residential annual space heating and cooling loads considering occupant behaviour" Energy 212: 118676. DOI: 10.1016/j.energy.2020.118676.
[9] J. Guo, S. Yun, Y. Meng, N. He, D. Ye, Z. Zhao, L. Jia, and L. Yang, (2023) “Prediction of heating and cooling loads based on light gradient boosting machine algorithms" Building and Environment 236: 110252. DOI: 10.1016/j.buildenv.2023.110252.
[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] J. Song, L. Zhang, G. Xue, Y. Ma, S. Gao, and Q. Jiang, (2021) “Predicting hourly heating load in a district heating system based on a hybrid CNN-LSTM model" Energy and Buildings 243: 110998. DOI: 10.1016/j.enbuild. 2021.110998.
[12] R. Chaganti, F. Rustam, T. Daghriri, I. d. l. T. 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(19): 7692. DOI: 10.3390/s22197692.
[13] Y. Wei, X. Zhang, Y. Shi, L. Xia, S. Pan, J. Wu, M. Han, and X. Zhao, (2018) “A review of data-driven approaches for prediction and classification of building energy consumption" Renewable and Sustainable Energy Reviews 82: 1027–1047. DOI: 10.1016/j.rser.2017.09.108.
[14] M. Rana, S. Sethuvenkatraman, and M. Goldsworthy, (2022) “A data-driven approach based on quantile regression forest to forecast cooling load for commercial buildings" Sustainable Cities and Society 76: 103511. DOI: 10.1016/j.scs.2021.103511.
[15] 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.rser. 2015.04.020.
[16] 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.
[17] Y. Feng, Q. Duan, X. Chen, S. S. Yakkali, and J. Wang, (2021) “Space cooling energy usage prediction based on utility data for residential buildings using machine learning methods" Applied energy 291: 116814. DOI: 10.1016/j.apenergy.2021.116814.
[18] 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.
[19] J. Cai, W. Yu, B. Li, R. Yao, T. Zhang, M. Guo, H. Wang, Z. Cheng, J. Xiong, Q. Meng, et al., (2019) “Particle removal efficiency of a household portable air cleaner in real-world residences: A single-blind cross-over field study" Energy and Buildings 203: 109464. DOI: 10.1016/j.enbuild.2019.109464.
[20] X. Zhou, W. Lin, R. Kumar, P. Cui, and Z. Ma, (2022) “A data-driven strategy using long short term memory models and reinforcement learning to predict building electricity consumption" Applied Energy 306: 118078. DOI: 10.1016/j.apenergy.2021.118078.
[21] G. Baasch, P. Westermann, and R. Evins, (2021) “Identifying whole-building heat loss coefficient from heterogeneous sensor data: An empirical survey of gray and black box approaches" Energy and Buildings 241: 110889. DOI: 10.1016/j.enbuild.2021.110889.
[22] H. Liu, C. Chen, Z. Guo, Y. Xia, X. Yu, and S. Li, (2021) “Overall grouting compactness detection of bridge prestressed bellows based on RF feature selection and the GA-SVM model" Construction and Building Materials 301: 124323. DOI: 10.1016/j.conbuildmat.2021. 124323.
[23] Y. Liu, H. Chen, L. Zhang, and Z. Feng, (2021) “Enhancing building energy efficiency using a random forest model: A hybrid prediction approach" Energy Reports 7: 5003–5012. DOI: 10.1016/j.egyr.2021.07.135.
[24] D. Tien Bui, H. Moayedi, D. Anastasios, and L. Kok Foong, (2019) “Predicting heating and cooling loads in energy-efficient buildings using two hybrid intelligent models" Applied Sciences 9(17): 3543. DOI: 10.3390/app9173543.
[25] V. V. Mokeev. “Prediction of heating load and cooling load of buildings using neural network”. In: 2019 International Ural Conference on Electrical Power Engineering (UralCon). IEEE. 2019, 417–421. DOI: 10.1109/URALCON.2019.8877655.
[26] P. Dai, P. Zhou, Y. Liang, et al., (2019) “Adaptive nonlinear predictive control based on multi output least squares support vector regression modeling and its application" Control theory and application 36(1): 43–52.
[27] P. Dai, P. Zhou, Y. Liang, et al., (2019) “Adaptive nonlinear predictive control based on multi output least squares support vector regression modeling and its application" Control theory and application 36(1): 43–52.
[28] G. G. Tejani, B. Sadaghat, and S. Kumar, (2023) “Predict the maximum dry density of soil based on individual and hybrid methods of machine learning" Advances in engineering and intelligence systems 2(03): 98–109. DOI: 10.22034/AEIS.2023.414188.1129.
[29] T.-L. Le, D.-N. Truong, and D. S. Nguyen. “Nature inspired based optimize combination of time series and machine learning model for predict energy consumption of a residence”. In: AIP Conference Proceedings. 2560. 1. AIP Publishing. 2023. DOI: 10.1063/5.0124782.
[30] A. Tsanas and A. Xifara, (2012) “Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools" Energy and buildings 49: 560–567. DOI: 10.1016/j.enbuild.2012.03.003.
[31] V. N. Vapnik, (1998) “The nature of statistical learning":
[32] M. Ayubi Rad and M. S. Ayubirad, (2017) “Comparison of artificial neural network and coupled simulated annealing based least square support vector regression models for prediction of compressive strength of highperformance concrete" Scientia Iranica 24(2): 487–496.
[33] Q. B. Pham, T.-C. Yang, C.-M. Kuo, H.-W. Tseng, and P.-S. Yu, (2019) “Combing random forest and least square support vector regression for improving extreme rainfall downscaling" Water 11(3): 451. DOI: 10.3390/w11030451.
[34] C.-W. Hsu, C.-C. Chang, C.-J. Lin, et al. A practical guide to support vector classification. 2003.
[35] B. G. Aiyer, D. Kim, N. Karingattikkal, P. Samui, and P. R. Rao, (2014) “Prediction of compressive strength of self-compacting concrete using least square support vector machine and relevance vector machine" KSCE Journal of Civil Engineering 18: 1753–1758. DOI: 10.1007/s12205-014-0524-0.
[36] M. K. Habib and A. K. Cherri, (1998) “Parallel quaternary signed-digit arithmetic operations: addition, subtraction, multiplication and division" Optics & Laser Technology 30(8): 515–525. DOI: 10.1016/S0030-3992(99)00004-3.
[37] F. A. Hashim, K. Hussain, E. H. Houssein, M. S. Mabrouk, and W. Al-Atabany, (2021) “Archimedes optimization algorithm: a new metaheuristic algorithm for solving optimization problems" Applied intelligence 51: 1531–1551. DOI: 10.1007/s10489-020-01893-z.
[38] O. N. Oyelade, A. E.-S. Ezugwu, T. I. Mohamed, and L. Abualigah, (2022) “Ebola optimization search algorithm: A new nature-inspired metaheuristic optimization algorithm" IEEE Access 10: 16150–16177. DOI: 10.1109/ACCESS.2022.3147821.
[39] O. N. Oyelade and A. E. Ezugwu, (2021) “Ebola Optimization Search Algorithm (EOSA): A new metaheuristic algorithm based on the propagation model of Ebola virus disease" arXiv preprint arXiv:2106.01416: DOI: 10.48550/arXiv.2106.01416.
[40] 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(11): 3829. DOI: 10.3390/app10113829.
[41] 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.
[42] 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.
[43] 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.