Estimation of Building Energy Efficiency Performance Using Radial Basis Function Neural Network

Abstract

Since a pass few decades up to recent, building energy efficiency performance is the top priority due to the sustainability of energy and quality of life. According to recent study related to computer experiment, there are various types of the model has been proposed by the researcher to improve the performance of building energy efficiency. However, there is no empirical evidence to prove the best method in prediction and estimation of energy efficiency that ensure adequate energy to meet todays and future needs. The objective of this paper is to propose Radial Basis Function Neural Network (RBFNN) for estimating the heating load and cooling load of a residential building. This study set out to evaluate different estimation methods of residential building energy efficiency using RBFNN. The data of residential building are obtained from UCI Machine Learning Repository. The dataset of simulation using Ecotect consists of 768 samples with 8 input features and 2 output variables were used to train and test the algorithm of RBFNN. The input variables involved in this experiment are relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution of a building, while the output variables are heating and cooling loads of the building. The analytical result of the proposed method shows that RBFNN produces better result and performance compared with the previous researches.

Binary Bitwise Artificial Bee Colony as Feature Selection Optimization Approach within Taguchi’s T-Method

“…Table 4 and Figure 2 illustrate the example of the performance analysis for the heating load case study. Researchers often use this dataset to interact with several other techniques that rely on regression analysis [38,39]. Similar procedures were applied to the remaining seven datasets applied within this study.…”