An Improved LSTM-based Fault Prediction Method for Power Communication Network Equipment

Abstract

The invention relates to an electric power telecommunication network device fault prediction method based on improved LSTM. The invention provides a data preprocessing and time sequence input construction method for the first time. Compared with the simple recurrent neural network, the LSTM is more likely to learn long-term dependence and can solve the prediction problems related to sequences. Because of the strong association between device alerts, the independence of variables can be ensured through PCA. The target replication strategy is also used for improving the LSTM, which can bring local error information in every step. Compared with a simple target output only in the last step, the strategy can improve the accuracy of the model and reduce the risk of over fitting. In combination with dropout, the invention proposes a prediction model of LSTM, which can achieve better prediction precision by deep learning. At the same time, the LSTM is usd for modeling electric power telecommunication network alarm data for the first time and identifying the timing sequence mode therein.

Description

technical field [0001] The invention belongs to the research category of power communication network equipment fault prediction, and relates to the application of big data in power communication network, deep learning, recurrent neural network, LSTM, fault prediction, power communication network equipment data analysis and other research fields. The invention proposes an improved LSTM-based power communication network equipment fault prediction model based on massive equipment alarm logs and dynamic ring data of a machine room. Background technique [0002] The application of big data in the power communication network: the data of the power communication network mainly comes from various links such as equipment alarm, equipment operation and maintenance, and business data. The data has the characteristics of large data volume, various data types, and high data value. Based on massive data, the prediction of equipment failure is of great significance for improving the reliab...

AI Technical Summary

Problems solved by technology

Jiang ZHONG et al. used the alarm data of a communication network device to predict faults using traditional machine learning algorithms such as random forests and Bayesian networks, but the prediction accuracy was poor

Images