Machine Learning Models for the Prediction of Energy Consumption Based on Cooling and Heating Loads in Internet-of-Things-Based Smart Buildings

Creative Commons License

Ghasemkhani B., Yılmaz R., Birant D., Kut R. A.

SYMMETRY-BASEL, vol.14, no.8, 2022 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 14 Issue: 8
  • Publication Date: 2022
  • Doi Number: 10.3390/sym14081553
  • Journal Name: SYMMETRY-BASEL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Communication Abstracts, INSPEC, Metadex, zbMATH, Directory of Open Access Journals, Civil Engineering Abstracts
  • Keywords: machine learning, Internet of things, energy consumption, smart buildings, tri-layered neural networks, cooling load, heating load, IOT, PERFORMANCE
  • Dokuz Eylül University Affiliated: Yes


In this article, the consumption of energy in Internet-of-things-based smart buildings is investigated. The main goal of this work is to predict cooling and heating loads as the parameters that impact the amount of energy consumption in smart buildings, some of which have the property of symmetry. For this purpose, it proposes novel machine learning models that were built by using the tri-layered neural network (TNN) and maximum relevance minimum redundancy (MRMR) algorithms. Each feature related to buildings was investigated in terms of skewness to determine whether their distributions are symmetric or asymmetric. The best features were determined as the essential parameters for energy consumption. The results of this study show that the properties of relative compactness and glazing area have the most impact on energy consumption in the buildings, while orientation and glazing area distribution are less correlated with the output variables. In addition, the best mean absolute error (MAE) was calculated as 0.28993 for heating load (kWh/m(2)) prediction and 0.53527 for cooling load (kWh/m(2)) prediction, respectively. The experimental results showed that our method outperformed the state-of-the-art methods on the same dataset.