With the increasingly complex power grid structure, the operation scheduling becomes more difficult, and the risk of large blackout accidents is increasing. Therefore, it is particularly important to be able to timely and effectively observe the security situation of the large power grid. In the extraction stage of situational factors, the security situation evaluation system of large power grid is constructed from two aspects of internal and external factors. The external factors are obtained through statistical analysis of the large blackout accidents of the national power grid from 1981 to 2015. In the stage of situational understanding, the comprehensive weights of each index are obtained by analytic hierarchy process and the improved entropy weight method, the weighted average is obtained from the safety situation assessment value of the large power grid to achieve comprehensive evaluation of the security situation of large power grids. In the stage of situation prediction, a deep neural network model is built to complete the prediction of the security situation of the large grid. In order to further verify the validity of the prediction model, it is compared with BP neural network and RBF neural network to verify that the model of deep neural network can effectively predict the security situation of large power grid, and the prediction accuracy is higher than the traditional neural network model.