A network security situation assessment method for power Internet of things based on multi-channel sae-adaboost

Abstract

The invention relates to the field of information system network security situation evaluation, and provides a multi-channel SAE-AdaBoost-based power Internet of Things network security situation evaluation method, aiming to solve the problems of poor accuracy and large generalization error of the existing evaluation methods. The main scheme includes step 1: The network security situation indicator is divided into multiple channels T 1 , T 2 , Λ, T n ; Step 2: For each channel, SAE maps each unlabeled training sample k-dimensional vector x′ into an m-dimensional encoded vector x through the hidden layer h , to obtain a low-dimensional representation x of high-dimensional data h ; Step 3: The AdaBoost algorithm continuously changes the weight of the samples from the training data, learns a series of weak learners in series, and linearly combines these weak learners into a strong learner, using this strong learner to its corresponding Channels are evaluated; Step 4: AHP comprehensively considers the relative importance of channels, integrates the evaluation results of multiple channels, and obtains the overall network security situation.

Description

technical field [0001] The invention relates to the field of information system network security situation evaluation, in particular to a method for comprehensively evaluating the power Internet of Things network security situation based on a multi-channel architecture combined with a sparse autoencoder and an AdaBoost integrated learning algorithm. Background technique [0002] In recent years, with the continuous development of the power Internet of things, the types of access devices have increased, and the structure of the power Internet of things has become increasingly complex, which has increased the complexity and uncertainty of the information network in the power industry, and the information security protection of the power Internet of Things is facing Great challenge. Therefore, the regulatory requirements for the overall network security situation of the system will continue to increase, and traditional network security situation assessment methods will not be a...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the existing method does not take into account the corresponding relationship between indicators and security issues, ignoring the different network security issues represented by different types of indicators, resulting in the mixed characteristics of different types of indicators, which interferes with the overall characteristics , which leads to the problems of poor accuracy and large generalization error of the existing evaluation methods

Images