Micro-grid optimization scheduling is an effective technical means to absorb intermittent distributed energy. In order to achieve the dual goals of economic and environmental optimization of micro- grid, a micro- grid optimization model including photovoltaic cells,fans, micro-gas turbines, diesel generators and batteries is established. The model is solved by an improved whale algorithm. In view of the problems of slow convergence and easy to fall into the local optimal solution of the traditional whale algorithm, Tent map is used to initialize the population, adding the sine and cosine operators to improve the bubble net attack phase of the whale algorithm, and Levy flight is introduced to enhance the global search ability. The improved whale algorithm is applied to the microgrid. Compared with traditional particle swarm optimization and basic whale algorithm, the results show that the improved whale algorithm with mixed sine and cosine operators has faster iteration speed and better economy, and has a good solution effect for the optimization scheduling problem of microgrid.