With the rapid economic development of China, the usage of mineral resources continues to grow and pollution of the environment is also increasing. As a result, it is an important measure for China to develop wind power generation so as to realize low-carbon transformation. However, due to the strong instability of wind power generation, it brings greater uncertainty to the operation of the power grid. Therefore, this paper takes into account the uncertainty in the wind power generation process and models them to carry out the power grid planning. Firstly, this paper establishes a mathematical model of wind turbine output by modeling the uncertainty. Secondly, it proposes an optimal power flow model considering the uncertainty of wind power with the objective to simultaneously minimize the total cost and the total network loss. At the same time, an improved particle swarm optimization algorithm is proposed to solve the problem by using a local model and introducing dynamic inertia weight coefficients. By comparing it with the traditional particle swarm optimization algorithm with some real-world data, the novel algorithm is verified to have better performance in terms of solving speed, convergence and robustness.