Deep Learning in Modeling Energy Cost of Buildings in the Public Sector

Zekić–Sušac, Marijana; Knežević, Marinela; Scitovski, Rudolf

doi:10.1007/978-3-030-20055-8_10

Cited by 4 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advancement of machine learning, many methods from those fields are used for dimensionality reduction, such as convolutional neural networks [8], support vector machines [41], decision trees [42] and others. Information criteria such as joint mutual information maximisation [4], statistical methods such as random forest and its Gini importance [39], [48], correlations, χ 2 test [48], and many other methods for dimensionality reduction are also used. One of the most commonly used statistical variable extraction methods is the principal component analysis (PCA) which transforms the starting space into a lower-dimensional one by converting it into a new set of variables -principal components.…”

Section: Previous Researchmentioning

confidence: 99%

“…Methods such as support vector machine [16], decision trees [16], [46], Stochastic Impacts by Regression on Population, Affluence, and Technology (STIRPAT) [37], ridge regression [37], partition trees [49], CART [51], random forest [49], [51], and linear regression [24], [49], [50] were used. Neural network was also commonly used, as in [16], [38], [1], [48], [43], [9], [49], and [50]. The methods were performed on the whole sample or on a sample divided into clusters, as in [38] and [22].…”

Section: Previous Researchmentioning

confidence: 99%

See 1 more Smart Citation

The independent component analysis with the linear regression – predicting the energy costs of the public sector buildings in Croatia

Mokriš

2022

Croat. oper. res. rev. (Online)

View full text Add to dashboard Cite

In the European Union, the public sector buildings are considered significant energy consumers and are, thus, the subject of several directives that aim to ensure the renovation of existing and the construction of new buildings as nearly zero-energy buildings. Therefore, as part of the decision making, it is necessary to properly plan the renovation or construction. This research provides models for predicting the energy costs of the public sector buildings, which are dependent upon its characteristics (i. e., constructional, occupational, energy, etc.). For this purpose, a real data set of Croatian public buildings was used, which included 150 variables and 1724 observations. Since the data set consisted of a large number of variables, the motivation for the dimensionality reduction was addressed first. Then, the independent component analysis, the principal component analysis, and the factor analysis were performed as the dimensionality reduction methods for variable extraction. The results of these analyses were used as inputs for modelling the energy costs of the public sector buildings. The obtained models were compared to the model built on original variables. The obtained models show the application potential in decision making for building renovation and construction in the public sector of Croatia, whereas the best performance of prediction in terms of RMSE and SMAPE was achieved by the model that integrated the independent component analysis with the linear regression.

show abstract

Section: Previous Researchmentioning

confidence: 99%

Section: Previous Researchmentioning

confidence: 99%

The independent component analysis with the linear regression – predicting the energy costs of the public sector buildings in Croatia

Mokriš

2022

Croat. oper. res. rev. (Online)

View full text Add to dashboard Cite

show abstract

“…Several works were aimed at the study of the way that different attributes influence the energy cost [12] and the housing prices in general [12,14,15].…”

Section: Introductionmentioning

confidence: 99%

Primary energy consumption for insulating

Terekh

Tretyakova

2020

E3S Web Conf.

View full text Add to dashboard Cite

In this article a mathematical model for thermal protection level analysis is developed. It is based on the consumption rate of primary energy. It allows to calculate the relevant thickness of the selected insulation material under any climatic and economic conditions with any constant layers of building envelope taken from structural considerations. The key factors influencing the model are also evaluated. The main factors to influence the energy model are the region degree-days and the energy consumption rate for the production, transportation and installation of the insulation material. The following results were reached: this approach requires the data, which sometimes has no public access, provides us with an objective assessment criteria when comparing the level of building thermal protection in different countries.

show abstract