Adaptive thermal comfort approach to save energy in tropical climate educational building by artificial intelligence

This work shows a comparative study of energy savings in an air-conditioning educational building in Aw's tropical climate regarding annual cooling load and degree-days, with adequate comfort levels following the adaptive thermal comfort approach. The comfort temperature modeling was by fuzzy logic-based (FL-BM), artificial neural networks based (ANN-BM), adaptive neuro-fuzzy inference system based (ANFIS-BM) and CIBSE Guide A and a Local linear model, concerning the Mexican standard. In modeling, the mean predicted dissatisfied percentage was 18.1 +/- 3.4% and the mean predicted mean vote 0.2 +/- 0.08. The ANN-BM was (R2/R2); 24.5 (0.98/0.04) times more accurate than the Local model, 2.9 (0.98/0.34) than FL-BM and 1.7 (0.98/0.57) than ANFIS-BM. The yearly cooling load savings by ANN-BM were 43.7% and 15.6% by the Local model. The ANN-BM annual cooling degree-days showed savings of 33.2% and by Local model 3.2%. ANFIS-BM outputs reduced cooling loads by 15.1% and cooling degree-days by 9.3%. The energy savings appeared when the determined mean Tcomf increases by using more accurate modeling. In air-conditioning buildings in a tropical climate, considering the adaptive approach, the AI-BM allows that Tcomf increase, enabling significant cooling loads re-ductions and energy savings, providing thermal comfort to the occupants at the same time.