The hybrid energy storage is used to stabilize the wind fluctuations for intermittent generation and random of distributed generation system in DC micro network. The power of wind farm is analyzed by Fast Fourier transform (FFT) while the minimum hybrid energy storage compensation capacity is obtained by using anti Fourier transform. According to the characteristics of different energy storage devices, adopting battery and supercapacitor hybrid energy storage, with mixed storage cost as the objective function and hybrid energy storage's state of charge and the maximum output power system performance as the constraint, the chance constrained programming is used to make the fluctuation of output power under a certain confidence level, which also meet the electrical quality and economy. The optimal solution of hybrid energy storage capacity is carried out by using genetic algorithm based on stochastic simulation. Finally, the simulation results show that the method is effective.