To improve the automated analysis capability of data information of distribution automation terminal,a distribution automation terminal based on ARM+field programmable gate array(FPGA)dual core computing is designed.To improve the computational capability of the module,a stacked autoencoder-neural network(SAE-NN)deep learning algorithm model is constructed in the module.The neural network(NN)model is fused based on the conventional stacked autoencoder(SAE)deep learning model,and the limitation of the traditional NN on the number of layered nodes is improved in the application process.The test results show that the designed terminal can eventually achieve more than 95％accuracy as the system runs,while the existing SAE model only achieves about 85％accuracy.By comparing with the literature[1]and literature[2]method,the designed terminal has a higher scheduling capability.The design significantly improves the accuracy of distribution network data and information,and greatly enhances the accuracy and efficiency of grid applications for data and information processing.
维普
万方数据