Power distribution network relay protection artificial intelligence setting method based on reinforcement learning algorithm

A technology of relay protection and reinforcement learning, applied in the field of distribution network, can solve the problems of unremovable fault, unable to meet the requirements of rapidity, selectivity and sensitivity of relay protection, long removal time, etc., and achieve the setting result. Accurate and reliable, the effect of solving the deterioration of the tuning result and improving the tuning efficiency

Active Publication Date: 2021-10-22
STATE GRID TIANJIN ELECTRIC POWER +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the manual calculation method is usually used in the setting of distribution network relay protection. This manual calculation method not only has a large amount of calculation, but also when the grid structure is complex and the number of circuit breakers is large, the setting value is difficult to calculate accurately and timely. out, the problem of setting value mismatch often occurs, and the setting results often fail to meet the requirements for the quickness, selectivity, and sensitivity of relay protection, which leads to leapfrog tripping of the distribution network, faults that cannot be removed, and the removal time is too long And other issues

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 distribution network relay protection artificial intelligence setting method based on reinforcement learning algorithm
  • Power distribution network relay protection artificial intelligence setting method based on reinforcement learning algorithm
  • Power distribution network relay protection artificial intelligence setting method based on reinforcement learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0053] An artificial intelligence setting method for distribution network relay protection based on reinforcement learning algorithm, comprising the following steps:

[0054] Step 1. According to the basic properties of distribution network relay protection, a reward function is established.

[0055] The present invention sets rewards and punishments according to the basic nature of the distribution network relay protection, and the size of the reward value should reflect the rationality of the current fixed value setting. The basic properties of distribution network relay protection include:

[0056] (1) Selectivity: Environmental data should have a topological relationship. The upstream of the fault point and the circuit breaker closest to the fault point are defined as the "should act" circuit breaker. The reward obtained when the circuit b...

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 relates to a power distribution network relay protection artificial intelligence setting method based on a reinforcement learning algorithm. The method is technically characterized by comprising the following steps of: establishing a reward function according to basic properties of relay protection of a power distribution network; calculating a reward value of each circuit breaker in the power distribution network according to the reward function, filling the reward values into a Q-Table table, and establishing a Q-Table table of an algorithm in reinforcement learning; carrying out iteration on the Q values in the Q-Table table; and after all the Q values in the Q-Table table are iterated, obtaining a final constant value of the power distribution network circuit breaker. According to the invention, the automatic setting function of the relay protection constant value of the power distribution network is realized, the setting efficiency of the constant value of the power distribution network is improved, the workload of employees is reduced, the problem of degradation of the setting result caused by constant value mismatch in the traditional setting calculation is effectively solved, the adaptation degree of the setting fixed value to the quickness, selectivity and sensitivity is improved, and then the problems of override tripping, failure in fault removal, overlong removal time and the like of the power distribution network caused by fixed value degradation are solved.

Description

technical field [0001] The invention belongs to the technical field of distribution networks, and relates to a relay protection method in a distribution network, in particular to an artificial intelligence setting method for relay protection of a distribution network based on a reinforcement learning algorithm. Background technique [0002] The power system is closely related to industrial production and people's life, so how to ensure the safe and stable operation of the power grid is particularly important. When faults such as short circuit and disconnection occur in the power grid, relevant measures must be taken to restore the system to a stable operating state at the lowest possible cost. The relay protection device acting on a single component of the power system is the most important of these measures. When a short-circuit fault occurs in the power grid, the protective devices installed on each component of the system with a cooperative relationship can identify the ...

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): H02H3/00H02H1/00H02H7/26
CPCH02H3/006H02H1/0092H02H7/26
Inventor 蔺维维张永伍杨畅王洋胡静娴赵若阳齐昕段佳莉王新铭王志远胡宗栩拱志新王海波王冲杜明
Owner STATE GRID TIANJIN ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products