A methodology to model two types of random perturbation that affect the operation of electric power systems (EPS) are presented. The first uncertainty is wind power generation and is represented by a one-dimensional and by a multidimensional continuous stochastic process. The second one is power demand, and is modeled by using an hybrid structure based on harmonic regression and the Ornstein-Uhlenbeck (O-U) process. The stochastic models are applied to a real Chilean case, using real data for parametric estimation and validation models. (C) 2016 Elsevier Ltd. All rights reserved.