Abstract
Heating load and cooling load forecasting are crucial for estimating energy consumption and improvement of energy performance during the design phase of buildings. Since the capacity of cooling ventilation and air-conditioning system of the building contributes to the operation cost, it is ideal to develop accurate models for heating and cooling load forecasting of buildings. This paper proposes a machine-learning technique for prediction of heating load and cooling load of residential buildings. The proposed model is deep neural network (DNN), which presents a category of learning algorithms that adopt nonlinear extraction of information in several steps within a hierarchical framework, primarily applied for learning and pattern classification. The output of DNN has been compared with other proposed methods such as gradient boosted machine (GBM), Gaussian process regression (GPR) and minimax probability machine regression (MPMR). To develop DNN model, the energy data set has been divided into training (70%) and testing (30%) sets. The performance of proposed model was benchmarked by statistical performance metrics such as variance accounted for (VAF), relative average absolute error (RAAE), root means absolute error (RMAE), coefficient of determination (R2), standard deviation ratio (RSR), mean absolute percentage error (MAPE), Nash–Sutcliffe coefficient (NS), root means squared error (RMSE), weighted mean absolute percent error (WMAPE) and mean absolute percentage Error (MAPE). DNN and GPR have produced best-predicted VAF for cooling load and heating load of 99.76% and 99.84% respectively.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Abbreviations
- DNN:
-
Deep neural network
- GBM:
-
Gradient boosted machine
- GPR:
-
Gaussian process regression
- MPMR:
-
Minimax probability machine regression
- VAF:
-
Variance accounted for (VAF)
- RAAE:
-
Relative average absolute error
- RMAE:
-
Root means absolute error
- R2 :
-
Coefficient of determination
- RSR:
-
Standard deviation ratio
- MAPE:
-
Mean absolute percentage error
- NS:
-
Nash–Sutcliffe coefficient
- RMSE:
-
Root means squared error
- WMAPE:
-
Weighted mean absolute percent error
- SVDD:
-
Support vector data description
- HVAC:
-
Heating, ventilation, and air conditioning
- MARS:
-
Multivariate adaptive regression splines
- ELM:
-
Extreme learning machine
- AHSRAE:
-
American Society of Heating, Refrigerating and Air-Conditioning Engineers
- EBP:
-
Energy performance of buildings
- GHG:
-
Greenhouse gas
- UNFCCC:
-
United Nations Framework Convention on Climate Change
- BMS:
-
Building management system
- i.i.d:
-
Independent and identically distributed
References
Ahmad MW, Mourshed M, Yuce B, Rezgui Y (2016) Computational intelligence techniques for HVAC systems: a review. Build Simul 9:359–398
Akpan GE, Akpan UF (2012) Electricity consumption, carbon emissions and economic growth in Nigeria. Int J Energy Econ Policy 2:292–306
Amiribesheli M, Bouchachia H (2018) A tailored smart home for dementia care. J Ambient Intell Hum Comput 9(6):1755–1782
Amiribesheli M, Benmansour A, Bouchachia A (2015) A review of smart homes in healthcare. J Ambient Intell Hum Comput 6(4):495–517
Andreu J, Angelov P (2013) An evolving machine learning method for human activity recognition systems. J Ambient Intell Hum Comput 4(2):195–206
Banihashemi S, Ding G, Wang J (2017) Developing a hybrid model of prediction and classification algorithms for building energy consumption. Energy Procedia 110:371–376
Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35:1798–1828. https://doi.org/10.1109/TPAMI.2013.50
British Petroleum (2013) BP statistical review of world energy, June 2014. Br Pet www.bp.com/statisticalreview. https://doi.org/10.1016/j.egypro.2013.06.172. Accessed June 2018
Chou JS, Bui DK (2014) Modeling heating and cooling loads by artificial intelligence for energy-efficient building design. Energy Build 82:437–446. https://doi.org/10.1016/j.enbuild.2014.07.036
Chung MH, Rhee EK (2014) Potential opportunities for energy conservation in existing buildings on university campus: a field survey in Korea. Energy Build 78:176–182. https://doi.org/10.1016/j.enbuild.2014.04.018
Deb C, Eang LS, Yang J, Santamouris M (2016) Forecasting diurnal cooling energy load for institutional buildings using artificial neural networks. Energy Build 121:284–297. https://doi.org/10.1016/j.enbuild.2015.12.050
Deng L, Dong Y (2014) Foundations and trends in signal processing. Signal Proces 7:3–4
European Energy Agency (2015) Final energy consumption by sector and fuel. Indic Assess | Data maps 20. CSI 027/ENER 016
Fan C, Xiao F, Zhao Y (2017) A short-term building cooling load prediction method using deep learning algorithms. Appl Energy 195:222–233. https://doi.org/10.1016/j.apenergy.2017.03.064
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press
Gul MS, Patidar S (2015) Understanding the energy consumption and occupancy of a multi-purpose academic building. Energy Build 87:155–165. https://doi.org/10.1016/j.enbuild.2014.11.027
Gunay B, Shen W, Newsham G (2017) Inverse blackbox modeling of the heating and cooling load in office buildings. Energy Build 142:200–210. https://doi.org/10.1016/j.enbuild.2017.02.064
Guo P, Cheng W, Wang Y (2017) Hybrid evolutionary algorithm with extreme machine learning fitness function evaluation for two-stage capacitated facility location problems. Expert Syst Appl 71:57–68. https://doi.org/10.1016/j.eswa.2016.11.025
Khayatian F, Sarto L, Dall’O’ G (2016) Application of neural networks for evaluating energy performance certificates of residential buildings. Energy Build 125:45–54. https://doi.org/10.1016/j.enbuild.2016.04.067
Kreider JF, Claridge DE, Curtiss P et al (1995) Building energy use prediction and system identification using recurrent neural networks. J Sol Energy Eng 117:161. https://doi.org/10.1115/1.2847757
Lechtenböhmer S, Schüring A (2011) The potential for large-scale savings from insulating residential buildings in the EU. Energy Effic 4:257–270. https://doi.org/10.1007/s12053-010-9090-6
Li Y, Li X (2015) Natural ventilation potential of high-rise residential buildings in northern China using coupling thermal and airflow simulations. Build Simul 8:51–64. https://doi.org/10.1007/s12273-014-0188-1
Lindelöf D (2017) Bayesian estimation of a building’s base temperature for the calculation of heating degree-days. Energy Build 134:154–161. https://doi.org/10.1016/j.enbuild.2016.10.038
Madadnia J, Vakiloroaya V, Samali B (2013) Modelling and performance prediction of an integrated central cooling plant for HVAC energy efficiency improvement. Build Simul 6:127–138. https://doi.org/10.1007/s12273-013-0104-0
Malkawi A, Yan B, Chen Y, Tong Z (2016) Predicting thermal and energy performance of mixed-mode ventilation using an integrated simulation approach. Build Simul 9:335–346. https://doi.org/10.1007/s12273-016-0271-x
Martínez-Molina A, Tort-Ausina I, Cho S, Vivancos JL (2016) Energy efficiency and thermal comfort in historic buildings: a review. Renew Sustain Energy Rev 61:70–85. https://doi.org/10.1016/j.rser.2016.03.018
Naji S, Keivani A, Shamshirband S et al (2016) Estimating building energy consumption using extreme learning machine method. Energy 97:506–516. https://doi.org/10.1016/j.energy.2015.11.037
Natekin A, Knoll A (2013) Gradient boosting machines, a tutorial. Front Neurorobot. https://doi.org/10.3389/fnbot.2013.00021
Nilashi M, Dalvi-Esfahani M, Ibrahim O et al (2017) A soft computing method for the prediction of energy performance of residential buildings. Measurement. https://doi.org/10.1016/j.measurement.2017.05.048
Rasmussen CE, Williams CK (2006) Gaussian processes for machine learning, vol 2. MIT Press, Cambridge, MA, p 4
Roy SS, Roy R, Balas VE (2018) Estimating heating load in buildings using multivariate adaptive regression splines, extreme learning machine, a hybrid model of MARS and ELM. Renew Sustain Energy Rev 82:4256–4268
Samuel EI, Joseph-Akwara E, Richard A (2017) Assessment of energy utilization and leakages in buildings with building information model energy. Front Archit Res 6:29–41. https://doi.org/10.1016/j.foar.2017.01.002
Sánchez-Oro J, Duarte A, Salcedo-Sanz S (2016) Robust total energy demand estimation with a hybrid variable neighborhood search—extreme learning machine algorithm. Energy Convers Manag 123:445–452. https://doi.org/10.1016/j.enconman.2016.06.050
Strohmann TR, Belitski A, Grudic GZ, DeCoste D (2004) Sparse greedy minimax probability machine classification. Adv Neural Inf Process Syst 16:105–112
Tsanas A, Xifara A (2012) Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools. Energy Build 49:560–567. https://doi.org/10.1016/j.enbuild.2012.03.003
U.S. Department of Energy (2009) Buildings energy data book. http://buildingsdatabook.eren.doe.gov/, pp 1–271. Accessed June 2018
Xu X, Taylor JE, Pisello AL, Culligan PJ (2012) The impact of place-based affiliation networks on energy conservation: an holistic model that integrates the influence of buildings, residents and the neighborhood context. Energy Build 55:637–646. https://doi.org/10.1016/j.enbuild.2012.09.013
Yang L, Yan H, Lam JC (2014) Thermal comfort and building energy consumption implications—a review. Appl Energy 115:164–173
Yu J, Lee H, Im Y et al (2010) Real-time classification of internet application traffic using a hierarchical multi-class SVM. KSII Trans Internet Inf Syst 4:859–876. https://doi.org/10.3837/tiis.2010.10.009
Zuazua-Ros A, Martín Gómez C, Ramos JC, Bermejo-Busto J (2017) Towards cooling systems integration in buildings: experimental analysis of a heat dissipation panel. Renew Sustain Energy Rev 72:73–82
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Roy, S.S., Samui, P., Nagtode, I. et al. Forecasting heating and cooling loads of buildings: a comparative performance analysis. J Ambient Intell Human Comput 11, 1253–1264 (2020). https://doi.org/10.1007/s12652-019-01317-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-019-01317-y