This study improves earth–air heat exchanger (EAHE) outlet temperature forecasting using artificial neural networks (ANNs) to enhance building energy efficiency. Leveraging data from Bechar, Algeria, an arid climate, a FFBPNN with one hidden layer was trained, validated, and tested. Increasing the number of neurons in the hidden layer significantly improved model accuracy. The optimal architecture, with 40 hidden neurons, demonstrated high predictive accuracy, as shown by reduced MSE and increased R2 values across datasets. This research highlights the potential of ANN-based models to optimize EAHE system performance, contributing to energy-efficient building designs, particularly in arid regions.
Kifouche, A., Kaddour, A., Lalmi, D., Chenini, N., Mohammed Ayad Alkhafaji, M. A., Chambashi, G., Kaid, N., Younes Menni, Y. (2024) .Enhancing real-time earth–air heat exchanger outlet temperature forecasting in arid climates using artificial neural network: a case study from Bechar, Algeria, International Journal of Low-Carbon Technologies, Volume 19, 2024, Pages 2493–2501, https://doi.org/10.1093/ijlct/ctae206