Application of genetic algorithm-neural network for the correction of bad data in power system

There are small amounts of bad data in power system real time data. If we do not correct them, they will have impact on security and stability of the power system. This text put forward a bad data correction algorithm based on genetic neural network algorithm. In order to overcome the BP neural network´s own defects, we use the genetic algorithm to define the optimum structure and the best initialized weights of the BP neural network. In this article, we use the real-time power data of Kunming power grid to simulation. The simulation results are accurate, and prove that this method can meet the need of improving the accuracy of the correction of bad data and enhancing the performance of the network.