LSTM Network for Carrier Module Detection Data Classification

At any time the popularity of the Internet, the city's smart grid has been developing rapidly. At the same time, the number of smart meters has increased year by year. The effective mining of the power module carrier module data has also been upgraded to a new level. However, due to the fact that the existing carrier module data analysis scheme is not mature enough, a complete set of data analysis schemes for carrier module is urgently needed in the market. Through the most advanced detection technology and data analysis method, we can realize the data mining of carrier module and improve the use value of data. In the past, traditional statistical learning methods are used, such as naive Bayes and support vector machines, but with the progress of the times, these technologies can not meet the needs of people. Different from the past, this paper proposes a deep learning network based algorithm for data mining of carrier module detection. The carrier module detection data is modeled by LSTM deep neural network to automatically identify the different noise environment, and then the carrier module is dynamically adjusted according to the recognition results. Experiments show that the model has very good results. In addition, the technology solution will not affect the existing business processes. As far as we know, this is the first time to apply the deep learning method to the analysis of the carrier module detection data, which has a great inspiration for the future power system data processing.