Load estimation models for the heat demand of buildings: Application of optimized Gaussian Process Regression

Yuanke  Shen

doi:10.6180/jase.202503_28(3).0010

Load estimation models for the heat demand of buildings: Application of optimized Gaussian Process Regression

Environmental Engineering

Yuanke ShenThis email address is being protected from spambots. You need JavaScript enabled to view it.

School Enterprise Cooperation and Employment Guidance Center, Zibo Vocational Institute, Zibo 255300, Shandong, China

Received: December 12, 2023
Accepted: March 14, 2024
Publication Date: May 22, 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.202503_28(3).0010

Environmental issues, energy security, thermal comfort, and economic considerations are the primary driving forces motivating research efforts to curb energy consumption and the associated greenhouse gas emissions across various sectors of the economy. Analyzing the energy performance of buildings proves to be a complex undertaking due to its reliance on numerous variables linked to building attributes, weather conditions, equipment and systems, occupant behavior, and sociological factors. This paper presents a non-parametric, Bayesian machine learning approach for analyzing and forecasting building heating load. The foundational technique in this approach is the utilization of the Gaussian Process Regression model. In pursuit of optimization goals, two meta-heuristic algorithms, namely Prairie Dog Optimization and the Arithmetic Optimization algorithm, are incorporated. This results in the development of three models: one for the singular GPR model and two for the hybridized versions of the model. Together, these models are employed to estimate the heating load of buildings. The study underscores the significance of identifying model input variables and conducts a thorough performance comparison among various machine learning methods and measured heating demand. Offering valuable insights into the forecasting of building heating loads, the research puts forth the GPAO (Combination of GPR and AOA) model as the optimal choice for achieving optimized energy production, distribution, and consumption in building systems. The obtained results show that Gaussian Process Regression, enhanced with an Arithmetic optimization algorithm, is a more suitable machine learning method with a maximum coefficient of determination of 0.991 and minimum performance errors of 0.955.

Keywords: Heating Load Demand; Prediction Models; Building Energy Consumption; Gaussian Process Regression; Metaheuristic Optimization Algorithms

[1] L. Pedersen, J. Stang, and R. Ulseth, (2008) “Load prediction method for heat and electricity demand in buildings for the purpose of planning for mixed energy distribution systems" Energy and Buildings 40: 1124–1134. DOI: 10.1016/j.enbuild.2007.10.014.
[2] 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.
[3] 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.
[4] D. Ürge-Vorsatz, L. F. Cabeza, S. Serrano, C. Barreneche, and K. Petrichenko, (2015) “Heating and cooling energy trends and drivers in buildings" Renewable and Sustainable Energy Reviews 41: 85–98. DOI: 10.1016/j.rser.2014.08.039.
[5] A. Kusiak and M. Li, (2010) “Cooling output optimization of an air handling unit" Applied Energy 87: 901– 909. DOI: 10.1016/j.apenergy.2009.06.010.
[6] N. Luo, T. Hong, H. Li, R. Jia, and W. Weng, (2017) “Data analytics and optimization of an ice-based energy storage system for commercial buildings" Applied Energy 204: 459–475. DOI: 10.1016/j.apenergy.2017.07.048.
[7] D. H. Spethmann, (1989) “Optimal control for cool storage" ASHRAE transactions 95: 1189–1193.
[8] X. Li and J. Wen, (2014) “Review of building energy modeling for control and operation" Renewable and Sustainable Energy Reviews 37: 517–537. DOI: 10.1016/j.rser.2014.05.056.
[9] J. E. Braun and N. Chaturvedi, (2002) “An inverse gray-box model for transient building load prediction" Hvac&r Research 8: 73–99. DOI: 10.1080/10789669.2002.10391290.
[10] S. Imam, D. A. Coley, and I. Walker, (2017) “The building performance gap: Are modellers literate?" Building Services Engineering Research and Technology 38: 351–375.
[11] S. Wang and X. Xu, (2006) “Simplified building model for transient thermal performance estimation using GAbased parameter identification" International journal of thermal sciences 45: 419–432. DOI: 10.1016/j.ijthermalsci.2005.06.009.
[12] D. H. Blum, K. Arendt, L. Rivalin, M. A. Piette, M. Wetter, and C. T. Veje, (2019) “Practical factors of envelope model setup and their effects on the performance of model predictive control for building heating, ventilating, and air conditioning systems" Applied Energy 236: 410–425. DOI: 10.1016/j.apenergy.2018.11.093.
[13] Z. Wang, B. Lin, and Y. Zhu, (2015) “Modeling and measurement study on an intermittent heating system of a residence in Cambridgeshire" Building and environment 92: 380–386. DOI: 10.1016/j.buildenv.2015.05.014.
[14] H. Harb, N. Boyanov, L. Hernandez, R. Streblow, and D. Müller, (2016) “Development and validation of grey-box models for forecasting the thermal response of occupied buildings" Energy and Buildings 117: 199– 207. DOI: 10.1016/j.enbuild.2016.02.021.
[15] Z. Wang, T. Hong, and M. A. Piette, (2019) “Data fusion in predicting internal heat gains for office buildings through a deep learning approach" Applied energy 240: 386–398. DOI: 10.1016/j.apenergy.2019.02.066.
[16] J. R. Forrester and W. J. Wepfer, (1984) “Formulation of a load prediction algorithm for a large commercial building" ASHRAE transactions 90: 536–551.
[17] D. H. Spethmann, (1989) “Optimal control for cool storage" ASHRAE transactions 95: 1189–1193.
[18] 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.
[19] Y. Zhao, C. Zhang, Y. Zhang, Z. Wang, and J. Li, (2020) “A review of data mining technologies in building energy systems: Load prediction, pattern identification, fault detection and diagnosis" Energy and Built Environment 1: 149–164. DOI: 10.1016/j.enbenv.2019.11.003.
[20] X. J. Luo, L. O. Oyedele, A. O. Ajayi, and O. O. Akinade, (2020) “Comparative study of machine learningbased multi-objective prediction framework for multiple building energy loads" Sustainable Cities and Society 61: 102283. DOI: 10.1016/j.scs.2020.102283.
[21] 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.
[22] M. Ahmadi, (2024) “Building energy efficiency: using machine learning algorithms to accurately predict heating load" Asian Journal of Civil Engineering: 1–11. DOI: 10.1007/s42107-023-00967-w.
[23] 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.
[24] E. Abdelkader, A. Al-Sakkaf, and R. Ahmed, (2020) “A comprehensive comparative analysis of machine learning models for predicting heating and cooling loads" Decision Science Letters 9: 409–420. DOI: 10.5267/j.dsl.2020.3.004.
[25] 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.
[26] H. X. Zhao and F. Magoulès, (2010) “Parallel support vector machines applied to the prediction of multiple buildings energy consumption" Journal of Algorithms & Computational Technology 4: 231–249. DOI: 10.1260/1748-3018.4.2.231.
[27] Y. Wei, L. Xia, S. Pan, J. Wu, X. Zhang, M. Han, W. Zhang, J. Xie, and Q. Li, (2019) “Prediction of occupancy level and energy consumption in office building using blind system identification and neural networks" Applied energy 240: 276–294. DOI: 10.1016/j.apenergy.2019.02.056.
[28] Y. Guo, J. Wang, H. Chen, G. Li, J. Liu, C. Xu, R. Huang, and Y. Huang, (2018) “Machine learning-based thermal response time ahead energy demand prediction for building heating systems" Applied energy 221: 16–27. DOI: 10.1016/j.apenergy.2018.03.125.
[29] C. Fan, F. Xiao, and S. Wang, (2014) “Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques" Applied Energy 127: 1–10. DOI: 10.1016/j.apenergy.2014.04.016.
[30] J.-S. Chou and D.-K. Bui, (2014) “Modeling heating and cooling loads by artificial intelligence for energy-efficient building design" Energy and Buildings 82: 437–446. DOI: 10.1016/j.enbuild.2014.07.036.
[31] R. E. Edwards, J. New, and L. E. Parker, (2012) “Predicting future hourly residential electrical consumption: A machine learning case study" Energy and Buildings 49: 591–603. DOI: 10.1016/j.enbuild.2012.03.010.
[32] J. Massana, C. Pous, L. Burgas, J. Melendez, and J. Colomer, (2015) “Short-term load forecasting in a nonresidential building contrasting models and attributes" Energy and Buildings 92: 322–330. DOI: 10.1016/j.enbuild.2015.02.007.
[33] Z. Wang, T. Hong, and M. A. Piette, (2019) “Data fusion in predicting internal heat gains for office buildings through a deep learning approach" Applied energy 240: 386–398. DOI: 10.1016/j.apenergy.2019.02.066.
[34] W. Wang, T. Hong, X. Xu, J. Chen, Z. Liu, and N. Xu, (2019) “Forecasting district-scale energy dynamics through integrating building network and long short-term memory learning algorithm" Applied Energy 248: 217–230. DOI: 10.1016/j.apenergy.2019.04.085.
[35] Q. Li, Q. Meng, J. Cai, H. Yoshino, and A. Mochida, (2009) “Applying support vector machine to predict hourly cooling load in the building" Applied Energy 86: 2249–2256. DOI: 10.1016/j.apenergy.2008.11.035.
[36] Y. Guo, J. Wang, H. Chen, G. Li, J. Liu, C. Xu, R. Huang, and Y. Huang, (2018) “Machine learning-based thermal response time ahead energy demand prediction for building heating systems" Applied energy 221: 16–27. DOI: 10.1016/j.apenergy.2018.03.125.
[37] C. Fan, F. Xiao, and Y. Zhao, (2017) “A short-term building cooling load prediction method using deep learning algorithms" Applied energy 195: 222–233. DOI: 10.1016/j.apenergy.2017.03.064.
[38] Z. Wang, T. Hong, and M. A. Piette, (2019) “Predicting plug loads with occupant count data through a deep learning approach" Energy 181: 29–42. DOI: 10.1016/j.energy.2019.05.138.
[39] 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.
[40] F. Masoumi, S. Najjar-Ghabel, A. Safarzadeh, and B. Sadaghat, (2020) “Automatic calibration of the groundwater simulation model with high parameter dimensionality using sequential uncertainty fitting approach" Water Supply 20: 3487–3501. DOI: 10.2166/ws.2020.241.
[41] Y. Zhou, Y. Liu, D. Wang, and X. Liu, (2021) “Comparison of machine-learning models for predicting short-term building heating load using operational parameters" Energy and Buildings 253: 111505. DOI: 10.1016/j.enbuild.2021.111505.
[42] 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.
[43] W. Pessenlehner and A. Mahdavi. Building morphology, transparence, and energy performance. Citeseer, 2003.
[44] H. I. Erdal, O. Karakurt, and E. Namli, (2013) “High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform" Engineering Applications of Artificial Intelligence 26: 1246–1254. DOI: 10.1016/j.engappai.2012.10.014.
[45] M. Ebden, (2015) “Gaussian processes: A quick introduction" arXiv preprint arXiv:1505.02965:
[46] M.-Y. Cheng, C.-C. Huang, and A. F. V. Roy, (2013) “Predicting project success in construction using an evolutionary Gaussian process inference model" Journal of Civil Engineering and Management 19: S202–S211. DOI: 10.3846/13923730.2013.801919.
[47] A. E. Ezugwu, J. O. Agushaka, L. Abualigah, S. Mirjalili, and A. H. Gandomi, (2022) “Prairie dog optimization algorithm" Neural Computing and Applications 34: 20017–20065. DOI: 10.1007/s00521-022-07530-9.
[48] L. Ngoc-Nguyen, S. Khatir, H.-Q. Nguyen, T. BuiTien, and M. A. Wahab. “A practical review of prairie dog optimization algorithm in solving damage identification problems in engineering structures”. In: Springer, 2022, 296–306. DOI: 10.1007/978-3- 031- 24041-6_24.
[49] X.-S. Yang and S. Deb. “Cuckoo search via Lévy flights”. In: Ieee, 2009, 210–214. DOI: 10.1109/NABIC.2009.5393690.
[50] M. K. Habib and A. K. Cherri, (1998) “Parallel quaternary signed-digit arithmetic operations: addition, subtraction, multiplication and division" Optics & Laser Technology 30: 515–525. DOI: 10.1016/S0030-3992(99)00004-3.
[51] L. Abualigah, A. Diabat, S. Mirjalili, M. A. Elaziz, and A. H. Gandomi, (2021) “The arithmetic optimization algorithm" Computer methods in applied mechanics and engineering 376: 113609. DOI: 10.1016/j.cma.2020.113609.
[52] 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.
[53] 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.