Digital Power Grid Communication Data Diversion Method Based on Deep Learning
With the rapid development of smart grid,real-time processing of massive multi-source heterogeneous communication data has become an urgent problem.Based on this,a digital power grid communication data distribution method based on deep learning is proposed,and the spatial and temporal characteristics of data are automatically extracted by using a mixed model of Convolutional Neural Network(CNN)and Long Short-Term Memory(LSTM),so as to realize efficient and accurate classification and optimal transmission.Through in-depth analysis of the characteristics of power grid communication data flow,a complete data diversion scheme including data preprocessing,model training and diversion decision is designed.Experimental results show that this method is superior to traditional methods in classification accuracy,real-time performance and generalization ability.
deep learningdigital power gridcommunication data shuntConvolutional Neural Network(CNN)Long Short-Term Memory(LSTM)