Prediction of Cooling Load of Tropical Buildings with Machine Learning

Creative Commons License

BEKDAŞ G., Aydin Y., IŞIKDAĞ Ü., Sadeghifam A. N., Kim S., Geem Z. W.

SUSTAINABILITY, cilt.15, sa.11, 2023 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 15 Sayı: 11
  • Basım Tarihi: 2023
  • Doi Numarası: 10.3390/su15119061
  • Dergi Adı: SUSTAINABILITY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Social Sciences Citation Index (SSCI), Scopus, Aerospace Database, CAB Abstracts, Communication Abstracts, Food Science & Technology Abstracts, Geobase, INSPEC, Metadex, Veterinary Science Database, Directory of Open Access Journals, Civil Engineering Abstracts
  • İstanbul Üniversitesi Adresli: Hayır

Özet

Cooling load refers to the amount of energy to be removed from a space (or consumed) to bring that space to an acceptable temperature or to maintain the temperature of a space at an acceptable range. The study aimed to develop a series of models and determine the most accurate ones in the prediction of the cooling load of low-rise tropical buildings based on their basic architectural and structural characteristics. In this context, a series of machine learning (regression) algorithms were tested during the research to determine the most accurate/efficient prediction model. In this regard, a data set consisting of ten features indicating the basic characteristics of the building (floor area, aspect ratio, ceiling height, window material, external wall material, roof material, window wall ratio north faced, window wall ratio south faced, horizontal shading, orientation) were used to predict the cooling load of a low-rise tropical building. The dataset was generated utilizing a set of generative and algorithmic design tools. Following the dataset generation, a series of regression models were tested to find the most accurate model to predict the cooling load. The results of the tests with different algorithms revealed that the relationship between the predictor variables and cooling load could be efficiently modeled through Histogram Gradient Boosting and Stacking models.