This paper proposes a new method for the planning of stand-alone microgrids. By means of clustering techniques, possible operating scenarios are obtained considering the daily patterns of wind and load profiles. Then,an approximate analytical model for reliability evaluationof battery energy storage system is developed in terms ofthe diverse scenarios, along with multistate models for wind energy system and diesel generating system. An optimal planning model is further illustrated based on the scenariosand the reliability models, with the objective of minimizing the present values of the costs occurring within the project lifetime, and with the constraints of system operation and reliability. Finally, a typical stand-alone microgrid is studied to verify the efficiency of the proposed method.