Training method and device for multi-fault prediction network model of power information system

Abstract

The invention discloses a training method and device for a multi-fault prediction network model of a power information system, and the method comprises the steps: obtaining an alarm data set of a timesequence, carrying out the data enhancement of the alarm data set, and obtaining an enhanced training sample set; obtaining an input sample for model training and a target output sample correspondingto the input sample based on the training sample set; and performing iterative training on a preset neural network model based on the input sample, the target output sample and a preset network modelloss function to obtain a multi-fault prediction network model. According to the method, data feature equalization is realized by performing data enhancement processing on the original data set, andthe multi-fault prediction network model obtained by performing model training fitting based on the training sample set after data enhancement has higher prediction precision and a more stable prediction effect.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to a training method and device for a multi-fault prediction network model of a power information system. Background technique [0002] Facing the development trend of more and more complex electric power information system, the traditional electric power information system is faced with the huge challenge of decreasing stability. On the one hand, the increase of system types and the expansion of network scale make the management and maintenance of all systems more and more difficult; on the other hand, with the continuous evolution of transmission technology, the requirements for data transmission on channel environment, modulation format, etc. continue to increase , some nonlinear parameter variables are introduced, which makes the evaluation of the running state of a single node exponentially more difficult. However, when a node or link failure occurs, the system requir...

AI Technical Summary

Problems solved by technology

However, in the process of using deep learning for feature learning, there are large differences in the category distribution in the data set, which will cause the deep learning algorithm to tend to predict all samples as the majority class, which leads to accurate prediction of minority class samples. very low rate

Images