Short-term office building elevator energy consumption forecast using SARIMA.

Renewable energy source integration in buildings can contribute to achieving sustainable energy use and reducing fossil fuel dependence. However, the intermittent and random nature of these energies, mainly photovoltaic and wind energy, make necessary the development of tools and strategies as forecasting to get a correct balance between demand and generation. In this paper, an energy consumption module based on the SARIMA statistical model is presented. This module is used to forecast the energy consumption of a green-elevator, which integrates photovoltaic and batteries, in different short-term time horizons. Genetic algorithms were used to speed up the optimal SARIMA model parametrization, and the chosen model was applied in a new and independent data set to test its effectiveness. Finally, the results were compared with the ANN technique and the GAM models. The SARIMA approach performed slightly better, and the best results were obtained with the time horizon of 1 h. [ABSTRACT FROM AUTHOR]