Uncertainty modeling of renewable Distributed Generations (DGs) has significant impact on optimal design of microgrids. Although the conventional Monte-Carlo (MC) simulation is the most accurate method for the uncertainty modeling it is a time consuming approach. In this paper, a new approach based on MC simulation is proposed for uncertainty modeling. The proposed method has a high precision in spite of lower calculation time in comparison of conventional MC simulation. Firstly the probability density function of each energy resources and load profile is executed. Then, optimal sizing of DGs is considered as an optimization problem under technical and economic constraints which is solved by genetic algorithm. The objective function includes investment and reliability costs. Simulation results show the effectiveness of the proposed methodology. The results show the proposed procedure has suitable accuracy in spite of low computation time.
