Green building's heat loss reduction analysis through two novel hybrid approaches

Abstract

One of the key reasons for the performance discrepancy between a building's intended usage and the actual operation is Heat Loss, which describes a building's envelope efficiency during in-use circumstances. In this setting, the ANN models’ use for energy analysis of green buildings has become more established. This research aims to anticipate the heat loss of green buildings utilizing two artificial neural network-based methodologies (ANN). In particular, TLBO and BBO are used and contrasted. Additionally, RMSE, MAE, and R2 are used to calculate an absolute error for predicting heat loss to gauge the accuracy of the findings. The suggested TLBO-MLP standard is a reliable method with a positive outcome (RMSE = 0.01012 and 0.05216, and R2 = 0.99536 and 0.9651). Also, according to the training error ranges of [−0.0006078, 0.01133] and [−0.00040708, 0.010181] and testing error ranges of [0.0004724, 0.068666] and [0.0021984, 0.057688] for BBO-MLP and TLBO-MLP, respectively, shows that the TLBO-MLP reaches the lower range of error and can predict the heat loss with higher accuracy and it could properly forecast the heat loss of building technologies. Even so, the BBO-MLP standard provides this research with satisfactory performance (R2 = 0.9943 and 0.95175, and RMSE = 0.01122 and 0.06112). To increase the precision of calculating the heat loss of buildings, specifically integrating them with optimization algorithms, further study is required.