Optimized BP Neural Network Based on GA Genetic Algorithm for Generator Speed Prediction

This study aims to optimize the dispatching operation and control of power system to reduce the increased operation cost caused by the uncertainty and volatility of wind power. To achieve this goal, a data model is proposed based on GA genetic algorithm optimized BP neural network. It can predict generator speed and perform network-wide power balancing, thus ensuring the safe and stable operation of the system. The study proceeds in three stages. First, data cleaning and pre-processing are performed on the data obtained from Kaggle. Second, a BP neural network model with 11 input indicators, such as the temperature of generator winding 1 and 2, rotor speed, and hub temperature, is constructed. The output of the model is the generator speed. The weights and thresholds of the BP neural network are optimized by genetic algorithm. Finally, we verify the effectiveness of our approach. By comparing the prediction results based on the BP model only, we demonstrate that the root mean square error of the proposed method is reduced by 31.28%. This confirms that the proposed model is an effective and feasible method for predicting generator speed. In summary, the proposed data model based on GA genetic algorithm optimized BP neural network can provide improved control over wind power variability and reduce operational costs. The results of this study pave the way for further research and application of advanced modeling and optimization techniques in power systems.