 This paper investigates the problem of energy consumption prediction in public buildings. It uses data from a university campus to test two different models, nonlinear autoregressive, NR, and nonlinear autoregressive in neural networks, NRX. The results show that both models can be used to accurately predict future energy consumption, however, adding exogenous data can further improve the accuracy of the model. This article was authored by Luis Gonzaga Baca Ruiz, Manuel Pagallajar Cuellar, Miguel Del Dotto, Calval Flores, and others.