Stacked LSTM-based network element alarm prediction method and device
A prediction method and network element technology, applied in the direction of prediction, neural learning method, biological neural network model, etc., can solve the problems of reducing accuracy and model influence, and achieve the effect of improving prediction accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0033] Such as figure 1 As shown, a network element alarm prediction method based on stacked LSTM aims at network element alarm prediction, and proposes a time series prediction based on the stacked LSTM model. This method not only improves the prediction accuracy, but also improves the maintenance efficiency of network element operation and maintenance personnel. and reduce the rate of user complaints; the specific plan is as follows:
[0034] The time series is used for network element alarm prediction, and the time series prediction is combined with the stacked LSTM network element model, which specifically includes the following steps:
[0035] S1: Construct network element alarm timing data, extract real-time sampling values, and group by time, cell, and channel number to obtain real-time group data; network element alarm timing data is collected from the operator's network management, and can be realized according to time, cell, and channel number grouping.
[0036] S2...
Embodiment 2
[0058] A stacked LSTM-based network element alarm prediction device includes a memory: used to store executable instructions; a processor: used to execute the executable instructions stored in the memory to implement a stacked LSTM-based network element alarm prediction method.
[0059] The present invention introduces multi-layer LSTM network elements into sequence training and prediction, as a deep learning model, through the increase of network element layers and the optimization of parameters, the prediction efficiency and prediction accuracy can be improved as much as possible; and the prediction will be automatically The result is compared with the threshold to identify the warning area and improve the maintenance efficiency of the operation and maintenance personnel.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More