In order to obtain more ideal effect of power system reliability evaluation,the basic framework of power system stability evaluation and decision-making is analyzed.The structure of deep confidence network is improved and the parameters are optimized by particle swarm optimization algorithm.Thus,the reliability evaluation model of intelligent power system is constructed.Experiments show that the performance indexes of the research model are higher than those of the other two models,and the accuracy,security,relia-bility,and geometric average values of reliability and security are 90.6％,91.38％,90.0％,90.26％,respectively.The reliability of the research model is better,with an average of 96.89％in the four new scenarios.In conclusion,the power system evaluation model based on transfer learning improves the reliability of the model in new scenarios,enables the model to adapt to the changes of the power grid,and helps to realize continuous and accurate online evaluation of the power system with large topological changes.
维普
万方数据