Predicting the PCM-incorporated building's performance using optimized linear kernel and tree-based machine learning methods

Abstract

The devising of a precise machine learning-based energy consumption prediction model holds significant importance for taking effective decisions during the early stages of phase change material (PCM) incorporated building design to reduce energy consumption. Few researchers have developed prediction models for estimating the consumption of energy in PCM incorporated buildings. However, there is a need to develop the best-performing machine learning-based prediction model, which is less complex, involve a lower number of hyperparameters, and has a greater ability to generalize hidden patterns among the dependent and independent variables. To address the above shortcomings, the linear kernel and tree model-based prediction models were formulated for PCM-incorporated buildings located in eight cities of subtropical highland climate, considering the variations in their hyperparameters. The evaluation and validation of the formulated models for prediction were performed utilizing several statistical metrics. Test results substantiated that the ensemble-boosted tree-based prediction model (EBT20) exhibited superior efficacy in estimating the energy consumption for PCM-integrated building, having an average R2 > 0.93, NMBE <4 %, and CV-RMSE <8 %. The developed model showed less complexity and better generalization ability at the optimized values of ensemble boosted tree hyperparameters, which are as follows: minimum leaf size = 32, number of learners = 99, and learning rate = 0.1. From comprehensive evaluation conducted to evaluate the interpretability of the prediction model, it was found that the building orientation and PCMs melting temperature are the most influential parameters for achieving energy savings of up to 33 % in the selected climate zone.