With the up-scaling of wind farms, wake effect has become a major factor which restricts wind power generation. Accurate simulation of the wind turbine wake velocity decay is of great significance to improve the current situation. Against the limitation of the neutral atmospheric hypothesis in wake simulation, the impact of atmospheric stability is taken into consideration in this paper. Establish the geometric models of single wind turbine, use different Monin-Obuhkov length values to represent diverse atmospheric stability classifications, carry on flow numerical simulation with RANS method. And then obtain wind speed distributions under stable, neural and unstable atmospheric stabilities. Extract the wind speed on hub height behind rotor, and do research on the wake velocity recovery conditions under various atmosphere status. Results show that wake velocity curves under different M-O length take on a variety of distribution characters. The average wind speed in wake area from high to low in order is unstable, neutral and stable atmosphere status. The more stable the atmosphere status, the slower the wake recovery rate. But for any selected atmosphere status, the wake speed in 30 times diameter length behind rotor can all recover to 90% of the inflow wind.