Exploratory Analysis of Machine Learning Techniques to predict Energy Efficiency in Buildings

The utilization of energy in the most efficient manner is an urgent demand of the modern era, as energy is being used in each and every field. Globally buildings consume the largest percentage of energy, and HVAC system consumes most of the energy in a building. HVAC maintains desired temperature within a building by meeting Heating load and Cooling load requirements. These requirements should be less to lessen energy consumption and achieve energy efficiency. Some of the characteristics of buildings greatly affect the Heating load and Cooling load requirements. This research analyses eight important characteristics of a building-Relative Compactness, Surface Area, Wall Area, Roof Area, Overall Height, orientation, Glazing Area, Glazing Area Distribution and uses them for predicting Heating load and Cooling load. Experiments have been performed using three Machine Learning algorithms-Multiple Linear Regression, K Nearest Neighbours, Support Vector Regresion and three Ensemble algorithms-Random Forests, Gradient Boosting Machines, Extreme Gradient Boosting. Models have been evaluated using performance metrics: RMSE, MSE, MAE, R Squared and Accuracy. Results show that Ensemble techniques outperform Machine Learning techniques with an appreciable margin.