Large-scale new energy pressures on the grids bring challenges to power system's security and stability. In order to optimize the user's electricity consumption behavior and ease pressure

which is caused by new energy on the grid

this paper proposes a time-of-use price model that takes wind power uncertainty into account. First

the interval prediction method is used to predict wind power. Then typical wind power scenes are selected by random sampling and bisecting the K-means algorithm. On this basis

integer programming is used to divide the peak-valley period of the multi-scenes load. Finally

under the condition of many factors such as user response based on consumer psychology

user electricity charge and power consumption

this paper takes the peak-valley difference of equivalent net load and the user dissatisfaction degree as the goal

and using the NSGA-II multi-objective optimization algorithm

evaluates the Pareto solution set to obtain the optimal solution. In order to test the validity of the model proposed in this paper

we apply it to an industrial user and wind farms in Yan'an city

China. The results show that the model can effectively ensure the user's electrical comfort while achieving the role of peak shaving and valley filling.