Makina öğrenmesi ile pencere parametrelerinin bina performansına etkisinin iklim değişikliği gözetilerek incelenmesi

Yıl 2023, Cilt: 38 Sayı: 4, 2069 - 2084, 12.04.2023

Gizem Akköse Ayça Duran İpek Gürsel Dino , Çağla Meral Akgül

https://doi.org/10.17341/gazimmfd.1069164

Cited By: 1

Öz

İklim ve yapılı çevre, güçlü ve dinamik bir ilişki içindedir. Bu ilişki, iklim değişikliği krizi ile son yıllarda daha da önem kazanmıştır. Bu bağlamda, binaların çevresel yüklerinin azaltılması ve bina kullanıcılarının ısıl konforunun ve sağlığının korunması daha da kritik bir hale gelmiştir. İklim değişikliği araştırmalarında eğitim binaları yüksek iç yükleri, kendine özgü bina kullanım profilleri ve ana kullanıcılarının öğrenciler olması sebebi ile diğer bina tipolojilerinden ayrılır. Ayrıca, öğrenciler yaşları, vücutları ve metabolizmalarındaki farklılıklar sebebi ile ısıl konfor ve iç ortam hava kalitesine karşı daha hassastır. Bu sebepler ile, eğitim binalarında iklim değişikliği çerçevesinde performans iyileştirmesi gerekli hale gelmektedir. Enerji kaybını azaltmak ve ısıl konfor dengesini sağlamak için en etkili yöntemlerden biri, pencerelerin parametrelerini optimize etmektir. Bu çalışma, iklim değişikliğinin eğitim binası enerji ve ısıl performansı üzerindeki etkilerini ve pencere performansına dayalı pasif iyileştirme senaryolarının etkinliğini makine öğrenmesi ve istatistiksel analizler ile incelemektedir. Araştırma bina simülasyonlarına dayalı, dört aşamalı bir yaklaşıma dayanmaktadır ve sırasıyla (i) iklim değişikliği senaryosu ile modifiye edilmiş iklim veri setlerinin oluşturulması ve analizi, (ii) mevcut bina üzerinde iklim değişikliği etki analizi, (iii) iyileştirme senaryolarının karşılaştırmalı analizi ve (iv) makine öğrenmesine dayalı tahmin modelleri analizi adımlarını takip eder. Seçilen performans göstergelerinin (bina enerji tüketimi ve kullanıcı ısıl konforu) değerlendirilmesi için Ankara'daki mevcut bir ortaokul binası örnek vaka olarak seçilmiştir. Farklı pencere parametreleriyle, olası 2025 farklı iyileştirme senaryosu parametrik olarak modellenmiştir. Performans simülasyonları sonucunda üretilen tüm veri betimsel istatistik yöntemleriyle incelendikten sonra, verinin bir alt kümesi ile Rastgele Orman (RO) tahmin modelleri eğitilmiştir. Her bir performans göstergesi için farklı pencere parametrelerinin önemi, 10 kat çapraz doğrulama yöntemiyle RO modelleri öznitelik önemleri hesaplanarak sıralanmıştır. RO modelleriyle yapılan performans tahminleri gerçek değerlerinden sadece ortalama %2 sapmakta ve yüksek tahmin kapasitesi göstermektedir. Öznitelik önem değerleri inceliğinde pencere SHGC değerinin test edilen değişkenler arasında performansa dayalı iyileştirme senaryolarının en önemli parametresi olduğu gözlemlenmiştir. Ayrıca güçlendirme senaryoları ile toplam enerji tüketimi %50'ye varan azalma gösterirken, iç mekan ısıl konforunda önemli bir iyileşme gözlemlenmektedir. Bu çalışmanın sonuçları, mevcut eğitim binalarında maksimum etki için cam performans kriterlerinin ve en etkili kombinasyon seçiminin önemini vurgulamaktadır. Sonuçlar, binaların iklim değişikliğine adaptasyonu süreçlerinde makine öğrenmesinin etkin bir şekilde kullanılabileceğini göstermektedir. Çalışmada kullanılan yöntem farklı bina parametrelerini ve bina teknolojilerini kapsayacak şekilde genişletilebilir.

Anahtar Kelimeler

Makine öğrenmesi, İklim değişikliği, Bina enerji verimliliği, Retrofit, Isıl konfor, Öznitelik önemi

Destekleyen Kurum

Orta Doğu Teknik Üniversitesi

Proje Numarası

GAP-303-2021-10674

Teşekkür

Bu araştırma, Orta Doğu Teknik Üniversitesi GAP-303-2021-10674 kodlu bilimsel araştırma projesi ödeneği ile desteklenmiştir.

Kaynakça

• NASA, Global Climate Change: Vital Signs of the Planet, (2021).
• P.F. Smith, Architecture in a climate of change : a guide to sustainable design, Routledge, 2005.
• M. Altun, Ç. Meral Akgül, A. Akçamete, Effect of envelope insulation on building heating energy requirement, cost and carbon footprint from a life cycle perspective, J. Fac. Eng. Archit. Gazi Univ. 35 (2020) 147–164. https://doi.org/10.17341/gazimmfd.445751.
• Philipp Rode, Ricky Burdett, Joana Carla Soares Gonçalves, Buildings: investing in energy and resource efficiency, in: Towar. a Green Econ. Pathways to Sustain. Dev. Poverty Erad., United Nations Environment Programme, 2011: pp. 331–373.
• IEA, World Energy Outlook 2021, IEA, Paris, 2021.
• P. de Wilde, D. Coley, The implications of a changing climate for buildings, Build. Environ. 55 (2012) 1–7. https://doi.org/10.1016/j.buildenv.2012.03.014.
• I. Gürsel Dino, Ç. Meral Akgül, Impact of climate change on the existing residential building stock in Turkey: An analysis on energy use, greenhouse gas emissions and occupant comfort, Renew. Energy. 141 (2019) 828–846. https://doi.org/10.1016/j.renene.2019.03.150.
• IEA, The Future of Cooling: Opportunities for energy-efficient air conditioning, 2018.
• Ç. Meral Akgül, İ. Gürsel Dino, Climate change impact assessment in residential buildings utilizing RCP4.5 and RCP8.5 scenarios, J. Fac. Eng. Archit. Gazi Univ. 3 (2020) 1665–1683. https://doi.org/10.17341/gazimmfd.534970.
• S. Grynning, A. Gustavsen, B. Time, B.P. Jelle, Windows in the buildings of tomorrow: Energy losers or energy gainers?, Energy Build. 61 (2013) 185–192. https://doi.org/10.1016/j.enbuild.2013.02.029.
• E. Cuce, S.B. Riffat, A state-of-the-art review on innovative glazing technologies, Renew. Sustain. Energy Rev. 41 (2015) 695–714. https://doi.org/10.1016/j.rser.2014.08.084.
• M.N. Inanici, F.N. Demirbilek, Thermal performance optimization of building aspect ratio and south window size in five cities having different climatic characteristics of Turkey, Build. Environ. 35 (2000) 41–52. https://doi.org/10.1016/S0360-1323(99)00002-5.
• A.R. Amaral, E. Rodrigues, A.R. Gaspar, Á. Gomes, A thermal performance parametric study of window type, orientation, size and shadowing effect, Sustain. Cities Soc. 26 (2016) 456–465. https://doi.org/10.1016/j.scs.2016.05.014.
• İ. Gürsel Di̇no, Binalarda Güneş Kontrol Yöntemlerinin Optimizasyon Temelli Performans Değerlendirilmesi, 5 (2017) 71–87.
• Y. Yildiz, T.G. Özbalta, Z. Durmuş Arsan, Impact of Window-to-Wall Surface Area for Different Window Glass Types and Wall Orientations on Building Energy Performance: A Case Study for a School Building Located in Izmir, Turkey, MEGARON / Yıldız Tech. Univ. Fac. Archit. E-Journal. 6 (2011) 30–38.
• M. Bojić, F. Yik, Application of advanced glazing to high-rise residential buildings in Hong Kong, Build. Environ. 42 (2007) 820–828. https://doi.org/10.1016/j.buildenv.2005.09.021.
• G. Akkose, C. Meral Akgul, I.G. Dino, Educational building retrofit under climate change and urban heat island effect, J. Build. Eng. 40 (2021) 102294. https://doi.org/10.1016/j.jobe.2021.102294.
• G. Feng, D. Chi, X. Xu, B. Dou, Y. Sun, Y. Fu, Study on the Influence of Window-wall Ratio on the Energy Consumption of Nearly Zero Energy Buildings, in: Procedia Eng., Elsevier Ltd, 2017: pp. 730–737. https://doi.org/10.1016/j.proeng.2017.10.003.
• S. Kim, P.A. Zadeh, S. Staub-French, T. Froese, B.T. Cavka, Assessment of the Impact of Window Size, Position and Orientation on Building Energy Load Using BIM, in: Procedia Eng., Elsevier Ltd, 2016: pp. 1424–1431. https://doi.org/10.1016/j.proeng.2016.04.179.
• M.C. Singh, S.N. Garg, R. Jha, Different glazing systems and their impact on human thermal comfort-Indian scenario, Build. Environ. 43 (2008) 1596–1602. https://doi.org/10.1016/j.buildenv.2007.10.004.
• Y.V. Perez, I.G. Capeluto, Climatic considerations in school building design in the hot-humid climate for reducing energy consumption, Appl. Energy. 86 (2009) 340–348. https://doi.org/10.1016/j.apenergy.2008.05.007.
• Y. Allab, M. Pellegrino, X. Guo, E. Nefzaoui, A. Kindinis, Energy and comfort assessment in educational building: Case study in a French university campus, Energy Build. 143 (2017) 202–219. https://doi.org/10.1016/j.enbuild.2016.11.028.
• L. Pérez-Lombard, J. Ortiz, C. Pout, A review on buildings energy consumption information, Energy Build. 40 (2008) 394–398. https://doi.org/10.1016/j.enbuild.2007.03.007.
• Z.S. Zomorodian, M. Tahsildoost, M. Hafezi, Thermal comfort in educational buildings: A review article, Renew. Sustain. Energy Rev. 59 (2016) 895–906. https://doi.org/10.1016/j.rser.2016.01.033.
• M.C. Katafygiotou, D.K. Serghides, Thermal comfort of a typical secondary school building in Cyprus, Sustain. Cities Soc. 13 (2014) 303–312. https://doi.org/10.1016/j.scs.2014.03.004.
• F. Ascione, N. Bianco, R.F. De Masi, G.M. Mauro, G.P. Vanoli, Energy retrofit of educational buildings: Transient energy simulations, model calibration and multi-objective optimization towards nearly zero-energy performance, Energy Build. 144 (2017) 303–319. https://doi.org/10.1016/j.enbuild.2017.03.056.
• M. Tahsildoost, Z.S. Zomorodian, Energy retrofit techniques: An experimental study of two typical school buildings in Tehran, Energy Build. 104 (2015) 65–72. https://doi.org/10.1016/j.enbuild.2015.06.079.
• F. Ascione, N. Bianco, R.F. De Masi, F. De’Rossi, G.P. Vanoli, Energy retrofit of an educational building in the ancient center of Benevento. Feasibility study of energy savings and respect of the historical value, Energy Build. 95 (2015) 172–183. https://doi.org/10.1016/j.enbuild.2014.10.072.
• T. Niemelä, R. Kosonen, J. Jokisalo, Cost-optimal energy performance renovation measures of educational buildings in cold climate, Appl. Energy. 183 (2016) 1005–1020. https://doi.org/10.1016/j.apenergy.2016.09.044.
• P. de Wilde, W. Tian, Predicting the performance of an office under climate change: A study of metrics, sensitivity and zonal resolution, Energy Build. 42 (2010) 1674–1684. https://doi.org/10.1016/j.enbuild.2010.04.011.
• T. Berger, C. Amann, H. Formayer, A. Korjenic, B. Pospischal, C. Neururer, R. Smutny, Impacts of climate change upon cooling and heating energy demand of office buildings in Vienna, Austria, Energy Build. 80 (2014) 517–530. https://doi.org/10.1016/j.enbuild.2014.03.084.
• T. Kershaw, D. Lash, Investigating the productivity of office workers to quantify the effectiveness of climate change adaptation measures, Build. Environ. 69 (2013) 35–43. https://doi.org/10.1016/j.buildenv.2013.07.010.
• S. Patidar, D. Jenkins, P. Banfill, G. Gibson, Simple statistical model for complex probabilistic climate projections: Overheating risk and extreme events, Renew. Energy. 61 (2014) 23–28. https://doi.org/10.1016/j.renene.2012.04.027.
• D.A. Waddicor, E. Fuentes, L. Sisó, J. Salom, B. Favre, C. Jiménez, M. Azar, Climate change and building ageing impact on building energy performance and mitigation measures application: A case study in Turin, northern Italy, Build. Environ. 102 (2016) 13–25. https://doi.org/10.1016/j.buildenv.2016.03.003.
• M. Dolinar, B. Vidrih, L. Kajfež-Bogataj, S. Medved, Predicted changes in energy demands for heating and cooling due to climate change, Phys. Chem. Earth. 35 (2010) 100–106. https://doi.org/10.1016/j.pce.2010.03.003.
• M. Hamdy, L.M. Jan Hensen, Ranking of dwelling types in terms of overheating risk and sensitivity to climate change, 14th Int. Conf. IBPSA - Build. Simul. 2015, BS 2015, Conf. Proc. 15 (2015) 2142–2149.
• T. Van Hooff, B. Blocken, J.L.M. Hensen, H.J.P. Timmermans, Reprint of: On the predicted effectiveness of climate adaptation measures for residential buildings, Build. Environ. 83 (2015) 142–158. https://doi.org/10.1016/j.buildenv.2014.10.006.
• L. Guan, The influence of internal load density on the energy and thermal performance of air-conditioned office buildings in the face of global warming, Archit. Sci. Rev. 58 (2015) 162–173. https://doi.org/10.1080/00038628.2014.979395.
• L. Pierangioli, G. Cellai, R. Ferrise, G. Trombi, M. Bindi, Effectiveness of passive measures against climate change: Case studies in Central Italy, Build. Simul. 10 (2017) 459–479. https://doi.org/10.1007/s12273-016-0346-8.
• M. Cellura, G. Francesco, S. Longo, M. Mistretta, G. Tumminia, Effect of Climate Change on Building Performance: the Role of Ventilative Cooling, in: Int. Build. Perform. Simul. Assoc. Conf., San Francisco, CA, 2017.
• Z. Tian, X. Zhang, S. Wei, S. Du, X. Shi, A review of data-driven building performance analysis and design on big on-site building performance data, J. Build. Eng. 41 (2021) 2352–7102. https://doi.org/10.1016/j.jobe.2021.102706.
• P. van den Brom, A. Meijer, H. Visscher, Actual energy saving effects of thermal renovations in dwellings—longitudinal data analysis including building and occupant characteristics, Energy Build. 182 (2019) 251–263. https://doi.org/10.1016/j.enbuild.2018.10.025.
• M. Fowlie, M. Greenstone, C. Wolfram, Do energy efficiency investments deliver? Evidence from the Weatherization Assistance Program, Q. J. Econ. 133 (2018) 1597–1644. https://doi.org/10.1093/QJE/QJY005.
• J. Liang, Y. Qiu, T. James, B.L. Ruddell, M. Dalrymple, S. Earl, A. Castelazo, Do energy retrofits work? Evidence from commercial and residential buildings in Phoenix, J. Environ. Econ. Manage. 92 (2018) 726–743. https://doi.org/10.1016/j.jeem.2017.09.001.
• D.E. Marasco, C.E. Kontokosta, Applications of machine learning methods to identifying and predicting building retrofit opportunities, Energy Build. 128 (2016) 431–441. https://doi.org/10.1016/j.enbuild.2016.06.092.
• E. Thrampoulidis, G. Mavromatidis, A. Lucchi, K. Orehounig, A machine learning-based surrogate model to approximate optimal building retrofit solutions, Appl. Energy. 281 (2021). https://doi.org/10.1016/j.apenergy.2020.116024.
• J.C. Wang, A study on the energy performance of school buildings in Taiwan, Energy Build. 133 (2016) 810–822. https://doi.org/10.1016/j.enbuild.2016.10.036.
• M.M. Ouf, M.H. Issa, Energy consumption analysis of school buildings in Manitoba, Canada, Int. J. Sustain. Built Environ. 6 (2017) 359–371. https://doi.org/10.1016/j.ijsbe.2017.05.003.
• T. Walter, M.D. Sohn, A regression-based approach to estimating retrofit savings using the Building Performance Database, Appl. Energy. 179 (2016) 996–1005. https://doi.org/10.1016/j.apenergy.2016.07.087.
• I.G. Hamilton, A.J. Summerfield, D. Shipworth, J.P. Steadman, T. Oreszczyn, R.J. Lowe, Energy efficiency uptake and energy savings in English houses: A cohort study, Energy Build. 118 (2016) 259–276. https://doi.org/10.1016/j.enbuild.2016.02.024.
• L. Zhang, Data-driven building energy modeling with feature selection and active learning for data predictive control, Energy Build. 252 (2021) 111436. https://doi.org/10.1016/j.enbuild.2021.111436.
• A. Tsanas, A. Xifara, Accurate quantitative estimation of energy performance of residential buildings using statistical machine learning tools, Energy Build. 49 (2012) 560–567. https://doi.org/10.1016/j.enbuild.2012.03.003.
• M.S. Roudsari, M. Pak, Ladybug: a parametric environmental plugin for grasshopper to help designers create an environmentally-conscious design, in: 13th Int. IBPSA Conf., Lyon, France, 2013: pp. 3128–3135.
• F. Pedregosa, V. Michel, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, J. Vanderplas, D. Cournapeau, F. Pedregosa, G. Varoquaux, A. Gramfort, B. Thirion, O. Grisel, V. Dubourg, A. Passos, M. Brucher, M. Perrot, É. Duchesnay, Scikit-learn: Machine Learning in Python, J. Mach. Learn. Res. 12 (2011) 2825–2830.
• J.L.M. Hensen, R. Lamberts, Building performance simulation for design and operation, in: J.L.M. Hensen, R. Lamberts (Eds.), Build. Perform. Simul. Des. Oper., Spon Press, 2012: pp. 1–14. https://doi.org/10.4324/9780203891612.
• M. Hamdy, S. Carlucci, P.J. Hoes, J.L.M. Hensen, The impact of climate change on the overheating risk in dwellings—A Dutch case study, Build. Environ. 122 (2017) 307–323. https://doi.org/10.1016/j.buildenv.2017.06.031.
• ASHRAE, Standard 55-2010, Thermal environmental conditions for human occupancy, 2010. https://doi.org/ISSN 1041-2336.
• K. Amasyali, N.M. El-Gohary, A review of data-driven building energy consumption prediction studies, Renew. Sustain. Energy Rev. 81 (2018) 1192–1205. https://doi.org/10.1016/j.rser.2017.04.095.
• L. Breiman, J.H. Friedman, R.A. Olshen, C.J. Stone, Classification and Regression Trees, CRC, 1984.
• S.B. Kotsiantis, Decision trees: A recent overview, Artif. Intell. Rev. 39 (2013) 261–283. https://doi.org/10.1007/s10462-011-9272-4.
• L. Breiman, Random Forests, Mach. Learn. 45 (2001) 5–32.
• R. Kohavi, A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection, 1995.
• ASHRAE, Standard 90.1-2013, Energy standard for buildings except low rise residential buildings, 2013.
• F. Ascione, N. Bianco, C. De Stasio, G.M. Mauro, G.P. Vanoli, Multi-stage and multi-objective optimization for energy retrofitting a developed hospital reference building: A new approach to assess cost-optimality, Appl. Energy. 174 (2016) 37–68. https://doi.org/10.1016/j.apenergy.2016.04.078.
• F. Salata, V. Ciancio, J. Dell’Olmo, I. Golasi, O. Palusci, M. Coppi, Effects of local conditions on the multi-variable and multi-objective energy optimization of residential buildings using genetic algorithms, Appl. Energy. 260 (2020) 114289. https://doi.org/10.1016/j.apenergy.2019.114289.
• F. Rosso, V. Ciancio, J. Dell’Olmo, F. Salata, Multi-objective optimization of building retrofit in the Mediterranean climate by means of genetic algorithm application, Energy Build. 216 (2020) 109945. https://doi.org/10.1016/j.enbuild.2020.109945.
• P. Pilechiha, M. Mahdavinejad, F. Pour Rahimian, P. Carnemolla, S. Seyedzadeh, Multi-objective optimisation framework for designing office windows: quality of view, daylight and energy efficiency, Appl. Energy. 261 (2020) 114356. https://doi.org/10.1016/j.apenergy.2019.114356.
• E. Thrampoulidis, G. Mavromatidis, A. Lucchi, K. Orehounig, A machine learning-based surrogate model to approximate optimal building retrofit solutions, Appl. Energy. 281 (2021) 116024. https://doi.org/10.1016/j.apenergy.2020.116024.
• D.B. Spalding, Handbook of heat transfer: Edited by W. M. Rohsenow and J. P. Hartnett. Mc-Graw-Hill, New York (1973). 1518 pp., 908 illustrations, Int. J. Heat Mass Transf. 18 (1975) 1221. https://doi.org/10.1016/0017-9310(75)90148-9.
• Integrated Environmental Solutions Limited, Apache-Tables User Guide IES Virtual Environment 6.4, 2012. http://www.iesve.com/downloads/help/ve2012/Thermal/ApacheTables.pdf.