Encryption internet of things terminal abnormal traffic detection method based on time-frequency holographic kinetic energy embedding features

By using time-frequency holographic kinetic energy embedding features and convolutional decision models, the real-time and accuracy issues of abnormal traffic detection for IoT terminals are solved, enabling efficient abnormal traffic detection for encrypted IoT terminals and improving the security and operation and maintenance efficiency of the power system.

CN122226355APending Publication Date: 2026-06-16INFORMATION & COMM CO OF STATE GRID JILIN ELECTRIC POWER CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
INFORMATION & COMM CO OF STATE GRID JILIN ELECTRIC POWER CO LTD
Filing Date
2026-03-12
Publication Date
2026-06-16

AI Technical Summary

Technical Problem

Existing technologies for detecting abnormal traffic in IoT terminals in power systems suffer from poor real-time performance and accuracy. They are unable to effectively identify abnormal behavior such as unknown attacks and undecrypted traffic, and static rules lead to high false alarm and false negative rates.

Method used

A method based on time-frequency holographic kinetic energy embedding features is adopted to extract the frequency domain signal of network traffic through Fourier transform, construct a 9-dimensional feature vector, and use a convolutional decision model to predict the model label and evaluate the confidence level, so as to realize the detection of abnormal traffic of encrypted IoT terminals.

Benefits of technology

It improves the accuracy and real-time performance of abnormal traffic detection, can identify known and unknown attacks, reduces false alarm and false negative rates, and improves the operation and maintenance efficiency and stability of power systems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122226355A_ABST
    Figure CN122226355A_ABST
Patent Text Reader

Abstract

The application relates to the field of power system management and analysis, and relates to an encryption Internet of Things terminal abnormal traffic detection method based on time-frequency holographic kinetic energy embedding features. Traditional detection methods have poor real-time performance and poor accuracy. The historical network traffic of m different types of Internet of Things terminals in n continuous periods is acquired, the average kinetic energy, kinetic energy peak value and spectrum entropy in three frequency bands are aggregated to form a 9n-dimensional feature vector, the corresponding Internet of Things terminal type label is marked according to each 9n-dimensional feature vector, each type label is taken as the output data of one sample, the 9n-dimensional feature vector of each type of Internet of Things terminal is taken as the input data, a convolution decision model is trained, the model after training is obtained, the network traffic of the Internet of Things terminal to be measured in n continuous periods is collected and input into the model after training, the type label and the confidence are output, the label and the confidence are sequentially judged, and whether the network traffic of the Internet of Things terminal to be measured is normal is detected. The application is used for detecting abnormal traffic of Internet of Things terminals.
Need to check novelty before this filing date? Find Prior Art