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

A detection method for power network events and intrusions

A technology of power network and detection method, which is applied in the field of power network, can solve the problem that synchrophasor data cannot detect network events or attacks, and achieve the effect of reducing manual marking operations and improving accuracy

Active Publication Date: 2020-03-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above-mentioned deficiencies in the prior art, a detection method for power network events and intrusions provided by the present invention solves the problems that most of the current network events or attacks cannot be detected by using only synchrophasor data, and how to target new events and attacks in a more automated and intelligent way to construct accurate network events and intrusion detection model detection problems

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
  • A detection method for power network events and intrusions
  • A detection method for power network events and intrusions
  • A detection method for power network events and intrusions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] Such as Figure 1-Figure 2 As shown, the present invention provides a detection method based on power network events and intrusions, and its implementation method includes the following steps:

[0051] (S1) Use the wide area monitoring system WAMS to monitor the power network in real time and extract valid data;

[0052] (S2) Preprocess the extracted effective data, and use a feature selection algorithm to extract some features, specifically, part of the marked data T 1 ={ψ 1 ,ψ 2 ...ψ n} and some unlabeled data T 2 ={Φ 1 ,Φ 2 ...Φ m} merged into a data set T, where n is the total number of partially labeled data, and m is the total number of partially unlabeled data;

[0053] (S3) Utilize the K-means algorithm to cluster according to the extracted partial features to obtain a first-level cluster. The specific steps are as follows:

[0054] (a1) Cluster the data set T into different K clusters {C 1 ,C 2 ...C K}, where C is a cluster and K is the total number...

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 provides a detection method for power network events and intrusions. The power network is monitored in real time through WAMS to complete the capture of valid data; the captured data is preprocessed, and a feature selection algorithm is used to extract some features; ‑means algorithm is used for clustering; for each cluster obtained by K‑means algorithm, GC‑Forest is used to classify power network events and intrusions; entropy calculation is used to determine whether unknown events or intrusions have occurred for the classified results. Unknown events or intrusions, the detection of power network events and intrusions is terminated. The invention solves the problem that all power network events or attacks cannot be detected only by using synchrophasor data, and how to construct accurate power network events and intrusion detection methods for new events and attacks with a more automated and intelligent method question. The method of the invention is flexible and has universality and applicability.

Description

technical field [0001] The invention belongs to the technical field of electric power network, and in particular relates to a detection method of electric power network event and intrusion. Background technique [0002] Electricity transmission systems are networked, cyber-physical systems that transport large quantities of electricity from generators to distribution systems that deliver power system loads to homes and businesses. The traditional power distribution system transmits the electrical energy generated in the generator by increasing the voltage level, and then passes it to the home and business users by gradually reducing the voltage level. The traditional power transmission system has low efficiency, inability to integrate multiple generation sources, cost Expensive and incapable of precise control and other issues. In order to solve these problems, the smart grid came into being. Based on communication and information technology, the smart grid fully controls 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
Patent Type & Authority Patents(China)
IPC IPC(8): H04L29/06G06K9/62
Inventor 廖丹章苇杭金海陆李慧
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com