The common practice to calculate wind generation capacity values relies more on heuristic approximations than true system estimations. In this paper we proposed a more accurate method. In the first part of our analysis, a Monte Carlo simulation was created based on Markov chains to provide an independent estimate of the true behavior of wind farm capacity value as a function of system penetration. With this curve as a baseline, a technique for using beta distributions to model the input variables was adopted. A final step to increase accuracy involved the use of numerical convolution within the program to eliminate summation estimates. (C) 2010 Elsevier Ltd. All rights reserved.