Unlock instant, AI-driven research and patent intelligence for your innovation.

Power grid cascading failure prediction method based on Q learning network attack

A technology of cascading faults and learning networks, applied in the field of power systems, can solve problems such as huge amount of calculation, scenarios where multiple network attacks are not considered, and difficulty in discovering general laws, so as to improve prediction efficiency, shorten calculation time, and improve accuracy Effect

Pending Publication Date: 2022-04-22
HEFEI UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, when most scholars study network attacks, they mainly focus on the cascading failures caused by a single network attack or the failure of the information network itself, without considering the scenario of multiple network attacks, and the traditional cascading failure analysis model is difficult to find general laws or calculations. too much

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
  • Power grid cascading failure prediction method based on Q learning network attack
  • Power grid cascading failure prediction method based on Q learning network attack
  • Power grid cascading failure prediction method based on Q learning network attack

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In this embodiment, a method for predicting cascading failures of power grids based on Q-learning network attacks is performed in the following steps:

[0047] Step 1. Taking the fault-free tripping of the circuit breaker as the target, construct an attack tree model based on fuzzy analytic hierarchy process, and obtain the success probability of each attack path of the circuit breaker fault-free tripping attack, where the i-th attack path M i The probability of success is denoted as P(M i );

[0048] The schemes to realize the goal G of the circuit breaker’s fault-free tripping include: attacking the control center, attacking the communication network between the control center and the substation, accessing the HMI of the substation, accessing the RTU and accessing the protection relay. figure 1Shown, F 1 -F 11 is a leaf node, F 1 , F 2 Indicates that through port scanning and accessing the switch and invading the control center server; F 3 Indicates the intercep...

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 a Q learning network attack-based power grid cascading failure prediction method, which comprises the steps of 1, constructing a network attack model, and determining the success probability of each attack path of a circuit breaker fault-free tripping attack, 2, constructing a Q learning-based cascading failure evolution model, and training by using a Q learning algorithm, a Q value table is generated to select an optimal network attack scheme, and attack paths with large risks can be screened out. On the basis of considering the network attack success probability, the Q learning algorithm is utilized to select the network attack path, so that large-range calculation of a similar traversal algorithm can be avoided, the calculation time is greatly shortened, the workload and the completeness are well balanced, and theoretical guidance is provided for power grid cascading failure prevention and control in a network attack scene.

Description

technical field [0001] The invention belongs to the field of power systems, in particular to a method for predicting grid cascading failures based on Q-learning network attacks. Background technique [0002] With the deep coupling of the power system and the information system, the information system will introduce new fault forms while improving the performance of the power grid, and change the propagation path of cascading faults. Therefore, the traditional cascading fault prediction method needs to be improved accordingly. At present, when most scholars study network attacks, they mainly focus on the cascading failures caused by a single network attack or the failure of the information network itself, without considering the scenario of multiple network attacks, and the traditional cascading failure analysis model is difficult to find general laws or calculations. The quantity is too large. Contents of the invention [0003] In order to solve the shortcomings of the ab...

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): G06F30/27G06Q10/06G06Q50/06G06F111/08
CPCG06F30/27G06Q10/0635G06Q50/06G06F2111/08
Inventor 张晶晶赵沛东齐先军杨熙
Owner HEFEI UNIV OF TECH