Abstract: Wind energy is renewable energy which can not pollute the environment, and it has huge growth potential to be one of the main development directions of China’s new energy sources. Because of the intermittent and non controllable characteristics of wind speed, large capacity wind power grid’s merging into the power system brings more risk factors. Considering the uncertainty of the load and wind speed, the Value at Risk (VaR) and Conditional Value at Risk (CVaR) theory are integrated into the short term economic dispatch model. This model with wind park is expected to reduce the uncertainty of the system risk while minimizing the operating cost.The genetic algorithm, immune algorithm and adaptive algorithm theory are combined to improve the effectiveness of computation. The simulation of system including ten generators and a wind park has verified the feasibility of the model and algorithms.