The high volatility of wind power and photo voltaic output makes it difficult for micro-grid to maintain a balance between supply and demand. Based on the consideration of the correlation between electricity price and load response, a day ahead optimal scheduling model is established, which aims at the lowest operation cost, the highest proportion of wind and solar energy consumption and the best customer satisfaction of micro -grid. The model takes the load, the wind speed and the solar radiation of micro-grid as the uncertain parameters, and uses the response compensation as the signal to guide the users to participate in the demand response based on the time-of-use price. The multi-objective gravitation search algorithm based on Pareto dominating method is used to solve the optimization problem, which proves the feasibility and accuracy of the algorithm to solve such problems. The results show that this strategy can effectively improve the impact of high permeability distributed generation connection on the system, and has a good effect of peak cutting and valley filling.