Prediction of building energy performance using mathematical gene-expression programming for a selected region of dry-summer climate

Developing energy-efficient buildings considering building design parameters can help reduce buildings' energy consumption. The energy efficiency of residential buildings is considered a top priority for the energy policies of a country. Thus, this study utilizes gene-expression programming (GEP) to estimate the energy performance of residential buildings. The energy consumption evaluations were carried out using the Etotect energy simulation software. Eight building parameters with 768 data points were considered to generate the database for the heating load (H-L) and cooling load (C-L), including relative compactness, surface area, wall area, roof area, overall building height, glazing orientation, glazing area, and distribution of glazing area. Different GEP predictive models with varying parameters for building H-L and C-L were developed, and the best-performing prediction model was selected. In addition, several statistical indices were utilized to measure the accuracy of the proposed GEP models. The results revealed that GEP14 gives the most robust prediction model for H-L having R-2-value greater than 0.9 for both the training and validation set. Likewise, R-2-value >0.9 is achieved for best- C-L (GEP11). Furthermore, the mean absolute error (MAE) values for both the predictive H-L' and C-L' by prediction models were relatively less for both the training and testing databases. The sensitivity and parametric analysis reveal that the overall height (H-o), roof area (A(f)), and glazing area (A(g)) were the most influential parameters for both predictive models. Thus, GEP results demonstrate the robust performance in predicting the building energy.