CN108183460B - Power distribution network self-adaptive protection setting method based on association rule learning - Google Patents
Power distribution network self-adaptive protection setting method based on association rule learning Download PDFInfo
- Publication number
- CN108183460B CN108183460B CN201711484275.7A CN201711484275A CN108183460B CN 108183460 B CN108183460 B CN 108183460B CN 201711484275 A CN201711484275 A CN 201711484275A CN 108183460 B CN108183460 B CN 108183460B
- Authority
- CN
- China
- Prior art keywords
- protection
- change
- data
- state
- distribution network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000004224 protection Effects 0.000 title claims abstract description 143
- 238000000034 method Methods 0.000 title claims abstract description 18
- 230000008859 change Effects 0.000 claims abstract description 60
- 230000003044 adaptive effect Effects 0.000 claims description 11
- 102100024841 Protein BRICK1 Human genes 0.000 claims description 6
- 101710084314 Protein BRICK1 Proteins 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 150000001875 compounds Chemical class 0.000 claims description 3
- 230000009471 action Effects 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000008092 positive effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
- H02H3/006—Calibration or setting of parameters
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H1/00—Details of emergency protective circuit arrangements
- H02H1/0092—Details of emergency protective circuit arrangements concerning the data processing means, e.g. expert systems, neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a power distribution network self-adaptive protection setting method based on association rule learning, which is technically characterized by comprising the following steps of: the method comprises the following steps: step 1, dividing data in a power distribution network into three types of state data S, operation data O and protection data P, formatting data structures of the various types of data, and integrating and storing all information to form an operation state database; step 2, when the operation mode and the topological structure of the power distribution network change, the variable quantity of the protection constant value caused by the change can be calculated in an off-line manner, so that the association rule between the specific operation mode and the topological structure change of the power distribution network and the protection constant value is obtained; and 3, when the change of the operation mode or the topological structure of the power distribution network is detected, carrying out self-adaptive setting on the protection according to the current real-time operation state. The invention greatly reduces the calculation amount and communication time required by the online real-time setting of the self-adaptive protection fixed value, and improves the quick action of the self-adaptive protection.
Description
Technical Field
The invention belongs to the technical field of power distribution network protection control, relates to a power distribution network self-adaptive protection setting method, and particularly relates to a power distribution network self-adaptive protection setting method based on association rule learning.
Background
The current development situation of the relay protection technology of the power distribution network goes through four development stages of an electromagnetic type, a transistor type, an integrated circuit type, a computer type and the like. The concept of adaptive relay protection of a power distribution network is provided in the last 80 th century. In 1984, the CIGRE working group listed the application conditions for adaptive protection. In 1989, eiska, usa proposed: the self-adaptive relay protection is characterized in that the system parameters can be automatically changed according to the change of the power network conditions. Adaptive relay protection is defined as "protection capable of changing the protection principle, characteristic or constant value in real time according to the change of the operation mode and fault state of the power system".
The concept of adaptive protection is introduced in China in the later 80 th of the last century, and research work on adaptive relay protection is started successively by various colleges and scientific research institutions in China, and great progress is made. Adaptive protection is increasingly being applied to reclosers, feeder protection and traveling wave protection. With the development of the power grid dispatching automation system and the rapid popularization of the substation automation technology and the unattended operation mode in China, the self-adaptive principle is applied to microcomputer protection to different degrees, a great deal of experience is accumulated for the research and popularization of the self-adaptive protection, and the intellectualization of the microcomputer protection in China is further improved.
Generally, works with high efficiency are respectively carried out on a power distribution network relay protection self-adaptive technology and a big data analysis technology at home and abroad, and positive effects are played on promotion of a power distribution network data information analysis processing technology and improvement of power distribution network power supply safety and reliability, but existing achievements still need to be further inherited and developed.
Aiming at the problem, the self-adaptive protection setting method with faster setting speed needs to be researched on the basis of the existing self-adaptive protection setting method.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides the association rule learning-based power distribution network adaptive protection setting method which is reasonable in design, short in protection setting time and high in adaptive protection action speed.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
a power distribution network self-adaptive protection setting method based on association rule learning comprises the following steps:
step 2, when the operation mode and the topological structure of the power distribution network change, the variable quantity of the protection constant value caused by the change can be calculated in an off-line manner, so that the association rule between the specific operation mode and the topological structure change of the power distribution network and the protection constant value is obtained;
and 3, when the change of the operation mode or the topological structure of the power distribution network is detected, carrying out self-adaptive setting on the protection according to the current real-time operation state.
Further, the specific steps of step 2 include:
(1) acquiring the change of operation data O representing the change of the operation state in two adjacent groups of data;
the operational data O in the packet k before the operational status change is:
wherein BRKn (n ═ 1,2,3, …) represents a breaker number, and an on-off closure represents 1, otherwise represents 0;
the operation data O in the packet k +1 before the operation state change is changed to
The change in the operating state caused by the scheduling control operation is described as
O1→O2 BRK1:1→0
(2) Calculating the protection constant value change quantity of two adjacent groups of data;
taking the instantaneous current quick-break protection constant value as an example, the protection constant value P1 corresponding to the operation state O1 is
In the formula (I), the compound is shown in the specification,the setting value of protection 1 in the O1 state is shown, subscript numbers show protection numbers, superscripts show state numbers, and the like; rn (n ═ 1,2,3, …) is a protection number
The protection constant P2 corresponding to the operation state O2 is
The amount of change of the protection constant is
(3) Screening the protection with the protection fixed value change larger than a threshold value, determining the influenced protection range after the scheduling control operation occurs, and recording the protection fixed values of the front state and the rear state;
(4) integrating the running state change, the scheduling control operation description and the influenced protection fixed value, recording the influenced protection and the fixed value before and after the change of the influenced protection, and eliminating the influenced protection, wherein the association rule is finally formed as follows:
(5) and integrating and storing the association rules to form an association rule database.
Further, the specific steps of step 3 include:
(1) retrieving state data corresponding to the current operating state and topology in a state database, and acquiring a corresponding operating state number;
(2) searching corresponding association rules in the association rules between the specific operation mode of the power distribution network and the change of the topological structure and the protection fixed value in the step 2 according to the operation state number, wherein the association rules comprise the associated protection and the corresponding fixed value under the current operation state or the topological condition;
(3) and issuing a protection fixed value to the protection device through the dispatching center to finish the self-adaptive setting of the protection.
The invention has the advantages and positive effects that:
1. the invention provides a setting method of power distribution network self-adaptive protection, which avoids a large amount of repeated inefficient communication and protection constant value calculation through the learning of the association rule between the protection constant value and the power distribution network operation mode and topology change, thereby greatly shortening the time of protection setting and better meeting the quick action of self-adaptive protection.
2. According to the method, the calculation amount and the communication time required by the online real-time setting of the self-adaptive protection fixed value are greatly reduced through the learning of the association rule between the running state of the power distribution network and the change of the topological structure in the offline historical data and the protection fixed value, and the quick action of the self-adaptive protection is improved.
Drawings
FIG. 1 is a schematic diagram of an n-node power distribution network topology of the present invention;
FIG. 2 is a flow chart of association rule formation of the present invention;
FIG. 3 is a flow chart of the power distribution network real-time operation state identification and protection adaptive setting of the present invention;
fig. 4 is a schematic diagram of the power distribution network of the present invention.
Detailed Description
The embodiments of the invention will be described in further detail below with reference to the accompanying drawings:
the invention firstly provides a method for establishing a power distribution network state database, then learns the association rule between the running state and the topological structure change in the historical data and the protection fixed value to form an association rule set, and finally carries out online real-time self-adaptive setting on the protection by utilizing the association rule.
A power distribution network self-adaptive protection setting method based on association rule learning comprises the following steps:
in this embodiment, taking the power distribution network shown in fig. 1 as an example, data in the power distribution network is classified to form an operation state database; parameters of a power distribution network line and a transformer are relatively long-term, the change frequency is far less than the switch operation frequency, and the data are recorded as state data State (S); the change of the switch state is relatively frequent, and the switch data and the transformer (tap) transformation ratio data can be used as operation data operation (O) for distinguishing and identifying different operation states; and taking each protection fixed value obtained by calculating each group of data as protection data protection (P). The data structure after such division is as follows:
after the above-mentioned data structure formatting is carried out to every packet data, all the information is integrated and stored, so that it is called operation state data base.
And 2, when the operation mode and the topological structure of the power distribution network change, the variation of the protection constant value caused by the change can be calculated in an off-line manner, so that the association rule between the specific operation mode and the topological structure change of the power distribution network and the protection constant value is obtained.
As shown in fig. 2, the specific steps of step 2 include:
(1) acquiring the change of operation data O representing the change of the operation state in two adjacent groups of data;
in the present embodiment, the operation data O in the packet k before the operation state change is (BRKn is a switch number, and the on/off state is represented by 1, whereas it is represented by 0)
The change in the operating state caused by the scheduling control operation is described as
O1→O2 BRK1:1→0
(2) Calculating the protection constant value change quantity of two adjacent groups of data;
taking the instantaneous current quick-break protection constant value as an example, the protection constant value P1 corresponding to the operation state O1 is
In the formula (I), the compound is shown in the specification,subscript numerical table showing setting values of protection 1 corresponding to O1 stateIndicating a protection number, and superscripting to indicate a state number, and so on; rn (n ═ 1,2,3, …) is a protection number
The protection constant P2 corresponding to the operation state O2 is
The amount of change of the protection constant is
(3) Screening the protection with the protection fixed value change larger than a threshold value, determining the influenced protection range after the scheduling control operation occurs, and recording the protection fixed values of the front state and the rear state;
(4) integrating the running state change, the scheduling control operation description and the influenced protection fixed value, recording the influenced protection and the fixed value before and after the change of the influenced protection, and eliminating the influenced protection, wherein the association rule is finally formed as follows:
(5) and integrating and storing the association rules to form an association rule database.
It should be noted that, since the formation of the association rule uses offline data, i.e. a large amount of historical databases, the formation process of the association rule does not affect the real-time performance of the adaptive protection tuning.
the specific steps of step 3 include, as shown in fig. 3:
(1) retrieving state data corresponding to the current operating state and topology in a state database, and acquiring a corresponding operating state number;
(2) and (3) retrieving corresponding association rules (including associated protection and corresponding fixed values thereof under the current operation state or topology condition) from the association rules between the specific operation mode and the topology structure change of the power distribution network and the protection fixed values in the step 2 according to the operation state number.
(3) And issuing a protection fixed value to the protection device through the dispatching center to finish the self-adaptive setting of the protection.
The present invention is illustrated in detail by taking a typical radial distribution network model shown in fig. 4 as an example:
in the distribution network shown in fig. 4, the switches corresponding to the protections 1,2,3, and 4 are BRK1, BRK2, BRK3, and BRK4, respectively.
1) And classifying the data in the power distribution network to form an operation state database, as shown in table 1.
TABLE 1 run State database
2) Acquiring changes in data O characterizing changes in operating conditions in two sets of data, e.g., changes in operating conditions caused by changes in the state of BRK4 are described as
O1→O2 BRK1:1→0
The operating state transitions resulting from the state changes of BRK3 and BRK4 are described as:
O1→O3 BRK3:1→0&BRK4:1→0
the remaining state transitions may also be similarly described.
3) And calculating the protection constant value change quantity of the corresponding two groups of data. The protection constant value is changed to O2 state from O1 state
The protection constant value is changed to O3 state from O1 state
4) Screening protection fixed value change quantity larger than threshold value delta Iact.thAnd (4) determining the influenced protection range after the scheduling control operation occurs and recording the protection fixed values of the front state and the rear state. For example, when the following formula is satisfied
The transition from operating state O1 to O2 resulting from the change in state of BRK1 is considered to be influential for protection 1, and protection 1 in O2 state is fixed to the value of
5) Integrating the running state, the scheduling control operation and the affected protection fixed value, and finally forming an association rule as follows:
6) and integrating and storing the association rules to form an association rule database.
7) When the operation state is changed from O1 to O3, the state data corresponding to the current operation state and topology is retrieved in the state database, and the corresponding state change number is acquired as 2.
8) Retrieving corresponding association rules in association rule retrieval according to the running state number
9) Issuing protection definite value by dispatching centerAnd finishing the self-adaptive setting of the protection on the protection device.
It should be emphasized that the described embodiments of the present invention are illustrative rather than restrictive, and thus the present invention includes embodiments that are not limited to the embodiments described in the detailed description, and that other embodiments derived from the technical solutions of the present invention by those skilled in the art are also within the scope of the present invention.
Claims (2)
1. A power distribution network self-adaptive protection setting method based on association rule learning is characterized by comprising the following steps: the method comprises the following steps:
step 1, dividing data in a power distribution network into three types of state data S, operation data O and protection data P, formatting data structures of the various types of data, and integrating and storing all information to form an operation state database;
step 2, when the operation mode and the topological structure of the power distribution network change, the variable quantity of the protection constant value caused by the change can be calculated in an off-line manner, so that the association rule between the specific operation mode and the topological structure change of the power distribution network and the protection constant value is obtained;
step 3, when the change of the operation mode or the topological structure of the power distribution network is detected, self-adaptive setting is carried out on the protection according to the current real-time operation state;
the specific steps of the step 2 comprise:
(1) acquiring the change of operation data O representing the change of the operation state in two adjacent groups of data;
the operational data O in the packet k before the operational status change is:
wherein BRKn (n ═ 1,2,3, …) represents a breaker number, and an on-off closure represents 1, otherwise represents 0;
the operation data O in the packet k +1 before the operation state change is changed to
The change in the operating state caused by the scheduling control operation is described as
O1→O2 BRK1:1→0
(2) Calculating the protection constant value change quantity of two adjacent groups of data;
when the protection constant value is the instantaneous current quick-break protection constant value, the protection constant value P1 corresponding to the operation state O1 is
In the formula (I), the compound is shown in the specification,the setting value of protection 1 in the O1 state is shown, subscript numbers show protection numbers, superscripts show state numbers, and the like; rn (n ═ 1,2,3, …) is a protection number
The protection constant P2 corresponding to the operation state O2 is
The amount of change of the protection constant is
(3) Screening the protection with the protection fixed value change larger than a threshold value, determining the influenced protection range after the scheduling control operation occurs, and recording the protection fixed values of the front state and the rear state;
(4) integrating the running state change, the scheduling control operation description and the influenced protection fixed value, recording the influenced protection and the fixed value before and after the change of the influenced protection, and eliminating the influenced protection, wherein the association rule is finally formed as follows:
(5) and integrating and storing the association rules to form an association rule database.
2. The power distribution network adaptive protection setting method based on association rule learning of claim 1, wherein: the specific steps of the step 3 comprise:
(1) retrieving state data corresponding to the current operating state and topology in a state database, and acquiring a corresponding operating state number;
(2) searching corresponding association rules in the association rules between the specific operation mode of the power distribution network and the change of the topological structure and the protection fixed value in the step 2 according to the operation state number, wherein the association rules comprise the associated protection and the corresponding fixed value under the current operation state or the topological condition;
(3) and issuing a protection fixed value to the protection device through the dispatching center to finish the self-adaptive setting of the protection.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711484275.7A CN108183460B (en) | 2017-12-29 | 2017-12-29 | Power distribution network self-adaptive protection setting method based on association rule learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711484275.7A CN108183460B (en) | 2017-12-29 | 2017-12-29 | Power distribution network self-adaptive protection setting method based on association rule learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108183460A CN108183460A (en) | 2018-06-19 |
CN108183460B true CN108183460B (en) | 2020-03-24 |
Family
ID=62549249
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711484275.7A Active CN108183460B (en) | 2017-12-29 | 2017-12-29 | Power distribution network self-adaptive protection setting method based on association rule learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108183460B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109103991B (en) * | 2018-10-23 | 2021-10-22 | 国网陕西省电力公司铜川供电公司 | Big data analysis method for intelligent power distribution network |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101562332B (en) * | 2009-05-27 | 2012-05-16 | 天津大学 | Self-adaptive current fast tripping protection method for distribution network comprising inverse distributed power |
CN102403792A (en) * | 2011-09-08 | 2012-04-04 | 天津理工大学 | Multi-Agent power grid self-adapting intelligent coordination protection control method and control system |
CN103426128B (en) * | 2013-08-29 | 2016-06-08 | 江苏省电力公司扬州供电公司 | Self adaptation relay protection constant value changing method based on power distribution network dispatching patcher |
-
2017
- 2017-12-29 CN CN201711484275.7A patent/CN108183460B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN108183460A (en) | 2018-06-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110490376B (en) | Intelligent soft switch planning method for improving reliability and economy of power distribution network | |
CN107657019B (en) | Network topology structure obtaining method and system of power grid system | |
CN102930344A (en) | Method for forecasting ultra-short term bus load based on load trend changes | |
CN104505820B (en) | Based on the power distribution network intelligent reconstruction method that multi-information correlation is utilized | |
CN110674282B (en) | Expert knowledge rule base-based one-key sequential control operation order intelligent simulation method | |
CN110994626B (en) | 500-220kV regional power grid automatic voltage control method based on voltage trend prediction | |
CN103414169A (en) | Relay protection and error prevention system based on power grid dispatching automation system and working method | |
CN108183460B (en) | Power distribution network self-adaptive protection setting method based on association rule learning | |
CN104407577A (en) | Intelligent check anti-maloperation method based on real-time trend | |
CN106056466B (en) | Bulk power grid critical circuits recognition methods based on FP-growth algorithm | |
CN112615368A (en) | Distributed sensing-based platform area topology generation method and sensing terminal device | |
CN111191333B (en) | Automatic power distribution network topology identification method based on node electrical distance | |
CN108490282B (en) | Method and system for presetting alarm test data of intelligent substation | |
CN106229974B (en) | A method of the electric power networks rapid topology analysis based on chart database | |
CN111784106B (en) | Active splitting section offline screening method and device based on disturbed track | |
CN111553040B (en) | Power grid topology analysis high-performance computing method and device based on GPU acceleration | |
Liu et al. | Fault location method for distribution network with distributed generation based on deep learning | |
CN109787285B (en) | Method and system for deciding new energy machine group grid-connected scheme | |
CN106295226A (en) | Consider the standby decision method of Power System Reliability and economy as a whole | |
CN108229863B (en) | Power supply reliability calculation method for power distribution network | |
Lan et al. | A Short-term Load Forecasting Method of Distribution Network Based on Improved AlexNet-GRU Deep Learning Network | |
CN105182903B (en) | Same machining feature defines method | |
CN111401481A (en) | Power grid operation mode automatic identification method based on multi-source information fusion technology | |
CN110971466A (en) | Intelligent power grid information-physical multi-agent system | |
CN108964016A (en) | The consumer electronics operating condition recognition methods of meter and discrete total electricity consumption data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |