基于深度学习的数字电网通信数据分流方法

Digital Power Grid Communication Data Diversion Method Based on Deep Learning

随着智能电网的快速发展,海量多源异构通信数据的实时处理成为急需解决的问题。基于此,提出一种基于深度学习的数字电网通信数据分流方法,采用卷积神经网络(Convolutional Neural Network,CNN)和长短期记忆(Long Short-Term Memory,LSTM)混合模型自动提取数据的时空特征,实现高效准确的分类和优化传输。通过深入分析电网通信数据流特点,设计包括数据预处理、模型训练、分流决策的完整数据分流方案。实验结果表明,该方法在分类准确率、实时性能以及泛化能力上均优于传统方法。

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.