Konut Yapılarında Enerji Performansının Tahmininde Regresyon Öğrenme Yöntemlerinin Karşılaştırmalı Analizi

Öz

Özel ve ticari binalar için enerji verimliliği birinci önceliktir. Bu çalışma, konut binalarının ısıtma ve soğutma yüklerini tahmin etmek için Lineer Regresör, MLP Regresörü, RBF Regresörü, SVM Regresörü, Gauss İşlemleri ve ANFIS Regresörü dahil olmak üzere altı regresyon öğrenme yönteminin performansını değerlendirmektedir. 768 bina, ısıtma yükü ve soğutma yükünü tahmin etmek için nispi yoğunluk, yüzey alanı, duvar alanı, çatı alanı, toplam yükseklik, yönlendirme, cam alanı ve cam alanı dağılımı gibi etkili parametrelere dayanarak düşünülmüş ve analiz edilmiştir. Bu çalışmada kullanılan regresyon yöntemlerinin potansiyelini değerlendirmek için korelasyon katsayısı (R), ortalama mutlak hata (MAE) ve kök ortalama kare hatası (RMSE) gibi üç istatistiksel kriter kullanılmıştır. En iyi tahmin sonuçları ANFIS regresyon modeli ile; HL için 0.998, MAE 0.46 ve RMSE için 0.68; ve CL için 0.990 R, MAE 1.26 ve RMSE 1.60'tır

Anahtar Kelimeler

• Enerji verimliliği
• ısıtma ve soğutma yükleri
• regresyon öğrenme
• ANFIS

Comparative Analysis of Regression Learning Methods for Estimation of Energy Performance of Residential Structures

Öz

Energy efficiency is a top priority for private and commercial buildings. This study evaluates the performance of six regression learning methods, including Linear Regressor, MLP Regressor, RBF Regressor, SVM Regressor, Gaussian Processes, and ANFIS Regressor to predict the heating and cooling loads of residential buildings. 768 buildings were considered and analyzed based on the influential parameters, such as relative density, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution for predicting heating load and cooling load. Three statistical criteria such as correlation coefficient (R), mean absolute error (MAE) and root mean square error (RMSE) were used to assess the potential of the regression methods used in this study. The best estimation results were obtained with the ANFIS regression model, with R of 0.998, MAE of 0.46 and RMSE of 0.68 for HL; and with R of 0.990, MAE of 1.26 and RMSE of 1.60 for CL.

Anahtar Kelimeler

• Energy efficiency
• heating and cooling loads
• regression learning
• ANFIS

Kaynakça

1. Bezdek, J.C. 1973. "Fuzzy Mathematics in Pattern Classification. Ph.D. dissertation", Cornell University, Ithaca, NY.
2. Castelli, M., Trujillo, L., Vanneschi, L. and Popoviˇc, A. 2015. “Prediction of energy performance of residential buildings: A genetic programming approach” Energy Build, 102, 67–74.
3. Cheng, M.Y. and Cao, M.T. 2014. “Accurately predicting building energy performance using evolutionary multivariate adaptive regression splines” Appl. Soft Comput, 22, 178–188.
4. Directive 2002/91/EC of The European Parliament and of The Council of 16 December 2002 on the energy performance of buildings.
5. Duarte, G.R. Fonseca, L.G., Goliatt, P.V.Z.C. and Lemonge, A.C.C. 2017. “Uma comparação de técnicas de aprendizado de máquina para a previsão de cargas energéticas em edifícios”, Ambiente Construído, 17(3), 103-115.
6. Ekici, B.B. 2016. “Building energy load prediction by using LS-SVM”, International Journal of Advances in Mechanical and Civil Engineering, vol. 3, No. 3, p.p. 163-166.
7. Fan, H., MacGill, I.F. and Sproul, A.B. 2016. “Statistical analysis of driving factors of residential energy demand in the greater Sydney region, Australia”, Energy and Buildings , vol.105, p.p.: 9–25.
8. Haykin, S. 1999. “Neural Networks A Comprehensive Foundation, second ed”, Prentice Hall, New Jersey.

9. Jang, J.S. 1993. “ANFIS: adaptive-network-based fuzzy inference system”, Systems, Man and Cybernetics, IEEE Transactions on 23: 665–685.
10. Jeon, Y.K., Kim, T., Nam, H.S. and Lee, II.W. 2016. “Implementation of energy performance assessment system for existing building”, International Conference on Information and Communication Technology Convergence (ICTC), Jeju, South Korea, p.p.:393-395.
11. Le, L.T., Nguyen, H., Dou, J. and Zhou, J. 2019. “A Comparative Study of PSO-ANN, GA-ANN, ICA-ANN, and ABC-ANN in Estimating the Heating Load of Buildings’ Energy Efficiency for Smart City Planning” Appl. Sci, 9, 2630.
12. Lee, M-W. and Kwak, K-Ch. 2016. “An Incremental Radial Basis Function Network Based on Information Granules and Its Application”, Computational Intelligence and Neuroscience . Vol. 16, p.p.:1-6.
13. Mehrabi, M., Sharifpur, M. and Meyer, J.P. 2012. “Application of the FCM-Based Neuro-Fuzzy Inference System and Genetic Algorithm-Polynomial Neural Network Approaches to Modelling the Thermal Conductivity of Alumina–Water Nanofluids”, International Communications in Heat and Mass Transfer, vol. 39, pp. 971–997.
14. Pérez-Lombard, L., Ortiz, J., and Pout, C. 2008. “A review on buildings energy consumption information”, Energy and Buildings, vol. 40, no. 3, pp. 394–398.
15. Sholahudin, S., Alam, A.G., Baek, C. and Han, H. 2014. “Prediction and analysis of building energy efficiency using artificial neural networks and design of experiments”, Jurnal Mekanikal, vol. 37, no. 2, pp. 37– 41.
16. Smola, A.J. and Schölkopf, B. 1998. “On a kernel-based method for pattern recognition, regression, approximation and operator inversion”, Algorithmica 22, 211–231.
17. Tsanas, A. and Xifara, A. 2012. "Accurate quantitative estimation of the energy performance of residential buildings using statistical machine learning tools," Energy and Buildings, vol. 49, pp. 560–567.
18. Wilkinson, G.N. and Rogers, C.E. 1973. “Symbolic descriptions of factorial models for analysis of variance”, Applied Statistics 22, 392–399.
19. Williams, C.K.I. 1998. “Prediction with Gaussian processes: From linear regression to linear prediction and beyond”, In: M.I. Jordan, editor, Learning in Graphical Models, Kluwer, pp. 599–621.
20. Yang, L., He, B.J. and Ye, M. 2014. “Application Research of Ecotect in Residential Estate Planning”, Energy and Buildings, v. 72, p. 195–202.
21. Yu, Z., Haghighat, F., Fung, B.C., and Yoshino H. 2010. “A decision tree method for building energy demand modeling”, Energy Build, vol. 42, no. 10,p.p.: 1637–1646.