This paper proposes a methodology to develop a probabilistic model that determines the power output of a wind power park as a probability discrete distribution function, taking into account wind speed, wind direction, state of operation of wind turbines and grid components of wind parks. Probabilistic Monte Carlo simulation is used to develop the modeling. Then, this discrete model is used to develop a reliability assessment of the bulk power system applying the theorem of total probability. The proposed model is tested on the IEEE Reliability Test System of 24 nodes.