Heating Load of Residential Buildings Using Multiple Linear Regression Artificial Neural Network

Global warming is one metric of climate change which defined as an increase in the average global temperature. Residential buildings contribute significantly to pollution that causes change. It essential have a comprehensive understanding functions highly energy efficient view projected projections, quality their heating systems, and impact on human health well-being. Thus, this study, effects six input variables are Overall Height, Glazing Area, Wall Relative Compactness, Roof Area Distribution output variable, namely Heating Load (HL) residential was investigated using Multiple Linear Regression Artificial Neural Network (MLR-ANN) approaches. Two-layer hyperbolic tangent-identity transfer with 6-3-1 configurations were employed it found best neural network model. A dataset 768 used for secondary data. The Mean Square Error (MSE), determination coefficients R2, well percentage normalized importance analysis assess statistical prediction capabilities MLR-ANN Based current findings, most contributing factor towards HL, followed by Distribution. can be suggested HVAC (heating, ventilation, air conditioning) systems should implemented reduce use. Natural ventilation encouraged through vernacular design, radiant cooling very effective way providing thermal comfort within structure.