Abstract
Due to climate change, buildings can consume 30% more energy by 2040, with energy performance being the critical element for achieving sustainable development in the civil construction sector. One way to solve this evaluation problem is by applying Machine Learning Methods that can assist specialists in civil construction in analyzing scenarios even in the initial phase of the project. The present work evaluates the application of the Elastic Net, Extreme Learning Machine, and Extreme Gradient Boosting models for the prediction of heating and cooling loads in residential buildings. The database used has 768 samples, with eight geometric input variables and two thermal output variables. Differential Evolution optimization algorithm was applied to select method parameters to find the sets of hyperparameters that reinforce the predictive capabilities of the models. The comparisons of the results occurred using the metrics MAE, MAPE, RMSE, and R\(^2\). The results showed that the Extreme Gradient Boosting method obtained a better performance among the tested methods than the literature, presenting the lowest values for the error metrics and significant differences in the statistical tests. Thus, combining Differential Evolution and Extreme Gradient Boosting methods, thermal loads can be predicted, assisting projects that aim at energy savings and sustainability
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pérez-Lombard, L., Ortiz, J., Pout, C.: A review on buildings energy consumption information. Energy Buildings 40(3), 394–398 (2008)
Ministério de Minas e Energia do Brasil: Uso de ar condicionado no setor residencial brasileiro: Perspectivas e contribuições para o avanço em eficiência energética. Technical report (2018)
Boermans, T., Grözinger, J.: Economic effects of investing in EE in buildings - the beam2 model. Background paper for EC Workshop on Cohesion policy (2011)
Touzani, S., Granderson, J., Fernandes, S.: Gradient boosting machine for modeling the energy consumption of commercial buildings. Energy Buildings 158, 1533–1543 (2018)
Wang, Z., Srinivasan, R.S., Shi, J.: Artificial intelligent models for improved prediction of residential space heating. J. Energy Eng. 142(4), 04016006 (2016)
Jihad, A.S., Tahiri, M.: Forecasting the heating and cooling load of residential buildings by using a learning algorithm “gradient descent”, morocco. Case Stud. Thermal Eng. 12, 85–93 (2018)
Ascione, F., Bianco, N., Mauro, G.M., Napolitano, D.F.: Building envelope design: Multi-objective optimization to minimize energy consumption, global cost and thermal discomfort. application to different italian climatic zones. Energy 174, 359–374 (2019)
AlFaris, F., Juaidi, A., Manzano-Agugliaro, F.: Intelligent homes’ technologies to optimize the energy performance for the net zero energy home. Energy Buildings 153, 262–274 (2017)
Tsanas, A., Xifara, A.: Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools. Energy and Buildings 49, 560–567 (2012)
Chou, J.S., Bui, D.K.: Modeling heating and cooling loads by artificial intelligence for energy-efficient building design. Energy Buildings 82, 437–446 (2014)
Duarte, G.R., Fonseca, L., Goliatt, P., Lemonge, A.: Comparison of machine learning techniques for predicting energy loads in buildings. Ambiente Construído 17(3), 103–115 (2017)
Friedman, J., Hastie, T., Tibshirani, R.: Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33(1), 1 (2010)
Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. Roy. Stat. Soc. Ser. B (Statistical Methodology) 67(2), 301–320 (2005)
bin Huang, G., yu Zhu, Q., kheong Siew, C.: Extreme learning machine: a new learning scheme of feedforward neural networks, pp. 985–990 (2006)
Huang, G., Huang, G.B., Song, S., You, K.: Trends in extreme learning machines: A review. Neural Netw. 61, 32–48 (2015)
Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning: data mining, inference, and prediction, springer series in statistics (2009)
Friedman, J.H.: Stochastic gradient boosting. Comput. Stat. Data Anal. 38(4), 367–378 (2002)
Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, pp. 785–794. ACM (2016)
Storn, R., Price, K.: Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11(4), 341–359 (1997)
Kachitvichyanukul, V.: Comparison of three evolutionary algorithms: GA, PSO, and DE. Ind. Eng. Manage. Syst. 11(3), 215–223 (2012)
Zhu, Q.Y., Qin, A., Suganthan, P., Huang, G.B.: Evolutionary extreme learning machine. Pattern Recogn. 38(10), 1759–1763 (2005)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Cheng, M.Y., Cao, M.T.: Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines. Appl. Soft Comput. 22, 178–188 (2014)
Castelli, M., Trujillo, L., Vanneschi, L., Popovič, A.: Prediction of energy performance of residential buildings: a genetic programming approach. Energy Buildings 102, 67–74 (2015)
Goliatt, L., Capriles, P., Duarte, G.R.: Modeling heating and cooling loads in buildings using gaussian processes. In: 2018 IEEE Congress on Evolutionary Computation (CEC), pp. 1–6. IEEE (2018)
Goliatt, L., Capriles, P.V.Z., Goulart Tavares, G.: Gradient boosting ensembles for predicting heating and cooling loads in building design. In: Moura Oliveira, P., Novais, P., Reis, L.P. (eds.) EPIA 2019. LNCS (LNAI), vol. 11804, pp. 495–506. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30241-2_42
Al-Rakhami, M., Gumaei, A., Alsanad, A., Alamri, A., Hassan, M.M.: An ensemble learning approach for accurate energy load prediction in residential buildings. IEEE Access 7, 48328–48338 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Goulart Tavares, G., Capriles, P.V.Z., Goliatt, L. (2021). Automatic Evolutionary Settings of Machine Learning Methods for Buildings’ Thermal Loads Prediction. In: Marreiros, G., Melo, F.S., Lau, N., Lopes Cardoso, H., Reis, L.P. (eds) Progress in Artificial Intelligence. EPIA 2021. Lecture Notes in Computer Science(), vol 12981. Springer, Cham. https://doi.org/10.1007/978-3-030-86230-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-86230-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86229-9
Online ISBN: 978-3-030-86230-5
eBook Packages: Computer ScienceComputer Science (R0)