With the large-scale access of renewable energy sources, the stable operation of microgrids has been seriously affected, thus increasing the peaking burden of the system. To solve this problem, this paper proposes a two-stage robust peaking strategy for microgrids that takes into account the uncertainty of renewable energy sources. In the first stage, planning is based on forecast data with the objective of minimizing net load fluctuations. In the second stage, wind power uncertainty is considered to find the wind power output in the worst scenario and adjust the strategy in the first stage to ensure the stability of the microgrid. Secondly, for the problem of single interval two-stage robust conservatism, a multi-interval uncertainty set is employed and solved using the nested column and constraint generation (C&CG) algorithm. Finally, the rationality and effectiveness of the strategy in this paper are verified by an arithmetic example analysis.