Machine Learning Models for Energy Prediction in a Low Carbon Building

Globally, buildings are responsible for an estimated 40% of energy consumption and 33% of CO₂ emissions. In a bid to reduce CO₂ emissions and hence, global warming, it has become necessary to ensure theenergy efficient construction and operation of buildings. Understanding how a building utilises energy is acritical step to increase its efficiency. In this study, we leverage on an open-source data obtained from UCIdata repository. Exploratory data analysis and feature engineering were used to eliminate non-contributingfeatures while identifying key attributes of the data for model training. Linear Regression (LR) and SupportVector Regression (SVR) were employed as the machine learning techniques for the study. The modelswere trained using a repeated cross-validation technique. The models' performance was evaluated on anindependent data set segregated for testing. The LR model was trained with nine out of thirty-three features, while the Support Vector Regression (SVR) model used twenty-eight features for its training. The SVRmodel had a higher variance (0.48), accuracy (92.41%), and lower Mean Absolute Percentage Error (MAPE)of 7.59% compared to the LR model's variance of 0.26, accuracy of 91.87%, and MAPE of 8.13%. TheSVR model was more accurate in predicting energy consumption, as it showed better accuracy on the testset with lower MAPE and higher R-squared value. Both models outperformed a relatively complex andcomputationally expensive model in a previous study. It also identified areas with high energy consumptionwhich could be used to inform the building's energy management strategy.