Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Electric power Internet of Things terminal equipment side channel safety monitoring method based on adversarial reinforcement learning

A power Internet of Things and terminal equipment technology, applied in electrical components, data exchange networks, digital transmission systems, etc., can solve the problem of limited computing and storage resources, inability to take into account accuracy and monitoring speed, and the inability of terminals to deploy artificial intelligence algorithms, etc. problem, to achieve the effect of good analysis and rich information

Active Publication Date: 2020-04-07
JILIN ELECTRIC POWER RES INST +3
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the firmware of power grid smart terminals is formulated by the manufacturer when it leaves the factory. It often lacks a corresponding attack and intrusion monitoring system, and the computing and storage resources of power IoT terminal equipment are limited. Terminals often cannot deploy complex artificial intelligence algorithms. Even if they are deployed, they cannot be accurate. speed and speed of monitoring

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Electric power Internet of Things terminal equipment side channel safety monitoring method based on adversarial reinforcement learning
  • Electric power Internet of Things terminal equipment side channel safety monitoring method based on adversarial reinforcement learning
  • Electric power Internet of Things terminal equipment side channel safety monitoring method based on adversarial reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0026] The present invention preprocesses and statistically analyzes a variety of side channel information of terminal equipment, and based on the feature selection method in correlation and machine learning, determines the combination of features related to the change of the working state of the terminal equipment, and collects a variety of information under normal working conditions. The side channel information of , and the preprocessed side channel features are used as the input of the anomaly detection model. Input the historical side channel data under the normal working state of the terminal equipment as normal samples into the abnormal monitoring model, train a variety of abnormal monitoring models based on single classification under normal working conditions, and verify the data based on the side channel information through the new abnormal state data of the terminal equipment The effectiveness and performance of the terminal equipment anomaly monitoring model. Using...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an electric power Internet of Things terminal equipment side channel safety monitoring method based on adversarial reinforcement learning, and belongs to the field of intelligent power grid safety. The method comprises the following steps: performing preprocessing and statistical analysis on power consumption side channel information of terminal equipment, determining a feature combination related to the change of the working state of the terminal equipment, and taking preprocessed side channel features as the input of an anomaly monitoring model; using historical sidechannel data of the terminal equipment in a normal working state as a normal sample to be input into the anomaly monitoring model; and training a single-classification-based exception monitoring modelin various normal working states, and verifying the effectiveness and performance of the terminal equipment exception monitoring model based on the side channel information through new terminal equipment exception state data. In the actual monitoring process, an anomaly monitoring agent is adopted to automatically select a single anomaly monitoring model execution program, adaptive adjustment ofalgorithm complexity is achieved, accuracy and rapidity are both considered, and the safety performance of the electric power Internet of Things terminal equipment is improved.

Description

technical field [0001] The invention belongs to the field of smart grid security, and relates to a side channel security monitoring method for electric power Internet of Things terminal equipment based on confrontation reinforcement learning. Background technique [0002] The security of power IoT terminal equipment is a part of power system security protection. In each link of the smart grid, all kinds of smart power IoT terminals, such as power distribution terminals, smart meters, power mobile operation terminals and other equipment, are closely related to power supply guarantees. The key link is related to the country's political stability, economic development and social harmony. Therefore, the safety and controllability of various power Internet of Things terminals is an important basis for building the Energy Internet. With the continuous expansion of the scale of the power grid and the diversified development of the power grid links, some power Internet of Things t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04L29/08H04L29/06H04L12/26H04L12/24
CPCH04L41/0631H04L41/145H04L43/08H04L43/0817H04L43/16H04L63/1416H04L67/125
Inventor 马立新李成钢姜栋潇田春光吕项羽李德鑫王伟张海锋刘宸张家郡刘威王杰徐相森徐文渊冀晓宇赵涛
Owner JILIN ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products