CN113506186B - Method and device for screening disturbed track of power system, electronic equipment and storage medium - Google Patents
Method and device for screening disturbed track of power system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113506186B CN113506186B CN202110693996.9A CN202110693996A CN113506186B CN 113506186 B CN113506186 B CN 113506186B CN 202110693996 A CN202110693996 A CN 202110693996A CN 113506186 B CN113506186 B CN 113506186B
- Authority
- CN
- China
- Prior art keywords
- disturbed
- input
- transient stability
- track
- tracks
- 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
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012216 screening Methods 0.000 title claims abstract description 34
- 230000001052 transient effect Effects 0.000 claims abstract description 198
- 238000013210 evaluation model Methods 0.000 claims abstract description 75
- 238000012549 training Methods 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 25
- 238000010606 normalization Methods 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000013097 stability assessment Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 abstract description 7
- 230000007547 defect Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000001687 destabilization Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for screening disturbed tracks of a power system, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a disturbed trajectory set input to a transient stability evaluation model of the power system; determining a sample point which is closest to the disturbed trajectory set in the model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set; determining the importance index of each input track in the disturbed track set according to the parameter curve and the transient stability characteristics of the system output by the transient stability evaluation model; and respectively sorting the input tracks of the same category in the disturbed track set according to the descending order of the importance indexes, and determining the input tracks of the specified number which are ranked at the top in each category input track as the key disturbed tracks of the corresponding category. The method can quickly position the key disturbed track input to the transient stability evaluation model, and overcomes the defect of a black box in the deep learning method in the prior art.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a method and a device for screening disturbed tracks of an electric power system, electronic equipment and a storage medium.
Background
In the operation analysis of the power system, the rapid and accurate transient stability analysis is the basis of the real-time decision-making emergency control system of the power system.
In the prior art, a deep learning method is used for modeling the correlation between the operation characteristics of the power system and the transient stability, and a transient stability evaluation model based on a disturbed track is constructed according to the correlation. The model performs layer-by-layer transformation and abstraction on the original feature space given system features, extracts the transient and stable relevant feature expression of the system, and further generates model output.
However, the deep learning method in the prior art is similar to the characteristic of a black box, so that an operator cannot know the relationship between the disturbed trajectory and the transient stability evaluation model output, and cannot quickly locate the key disturbed trajectory in the system.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a device for screening disturbed tracks of a power system, electronic equipment and a storage medium.
The invention provides a method for screening disturbed tracks of an electric power system, which comprises the following steps:
acquiring a disturbed trajectory set input into a transient stability evaluation model of the power system; the transient stability evaluation model is used for establishing correlation between the operation characteristics of the power system and the transient stability characteristics of the system; the disturbed trajectory set refers to a two-dimensional matrix of more than two input trajectories which are input into the transient stability evaluation model when transient instability occurs in the system after an expected fault;
determining a sample point which is closest to the disturbed trajectory set in a pre-acquired model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set;
determining importance indexes of all input tracks in the disturbed track set according to the parameter curve and system transient stability characteristics output by the transient stability evaluation model; the importance index is used for representing the contribution size of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model changes from a sample point to the disturbed track set;
and respectively sequencing the input tracks of the same category in the disturbed track set from large to small according to the importance indexes, and determining the input tracks of the specified number which are ranked at the top in each category input track as the key disturbed tracks of the corresponding category.
According to the method for screening the disturbed track of the power system provided by the invention, the determining the importance index of each input track in the disturbed track set according to the parameter curve and the transient stability characteristics of the system output by the transient stability evaluation model comprises the following steps:
determining an integral gradient result matrix of the system transient stability characteristic relative to the disturbed trajectory set based on the parameter curve and the system transient stability characteristic output by the transient stability evaluation model;
and determining the importance index of each input track in the disturbed track set according to the integral gradient result matrix.
According to the method for screening the disturbed track of the power system, the importance index of each input track in the disturbed track set is determined according to the integral gradient result matrix, and the method comprises the following steps:
and summing the rows of the integral gradient result matrix to obtain the importance index of each input track in the disturbed track set.
According to the method for screening the disturbed track of the power system, provided by the invention, two endpoints of the parameter curve are the sample point and the disturbed track set.
According to the method for screening the disturbed track of the power system provided by the invention, the acquiring of the disturbed track set input into the transient stability evaluation model of the power system comprises the following steps: acquiring more than two disturbed trajectory sets input into the transient stability evaluation model;
the step of sorting the input tracks of the same category in the disturbed track set from large to small according to the importance indexes, and determining the input tracks of the specified number with the top ranking in each category input track as the key disturbed tracks of the corresponding category comprises the following steps:
respectively carrying out normalization calculation on the importance indexes of the input tracks in the disturbed track sets to obtain the normalization results of the importance indexes of the input tracks in the disturbed track sets;
respectively carrying out average calculation on the normalization results of the importance indexes of the input tracks in the same row in each disturbed track set to obtain the average result of the normalization results of the importance indexes of the input tracks in each row in each disturbed track set;
and respectively sorting the input tracks of the same category in the input tracks of each row of each disturbed track set according to the descending order of the average result of the normalization results of the importance indexes of the input tracks of each row in each disturbed track set, and determining the input tracks of the specified number which are ranked at the top in each category input track as the key disturbed tracks of the corresponding category.
According to the method for screening the disturbed track of the power system, provided by the invention, the transient stability characteristics of the system comprise any one or a combination of the following indexes: transient stability, the maximum power angle difference of the transient process of the system maintaining transient stability after the expected fault, and the transient instability time of the system generating transient instability after the expected fault.
According to the method for screening the disturbed track of the power system provided by the invention, the input track comprises any one of the following categories or combinations: a line tide curve, a node voltage curve and a power angle curve of the generator.
The invention also provides a device for screening disturbed tracks of an electric power system, which comprises:
the acquisition unit is used for acquiring a disturbed trajectory set input into the transient stability evaluation model of the power system; the transient stability evaluation model is used for establishing correlation between the operation characteristics of the power system and the transient stability characteristics of the system; the disturbed trajectory set refers to a two-dimensional matrix of more than two input trajectories which are input into the transient stability evaluation model when transient instability occurs in the system after an expected fault;
the first determining unit is used for determining a sample point which is closest to the disturbed trajectory set in a pre-acquired model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set;
the second determining unit is used for determining the importance index of each input track in the disturbed track set according to the parameter curve and the system transient stability characteristics output by the transient stability evaluation model; the importance index is used for representing the contribution size of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model changes from a sample point to the disturbed track set;
and the sorting unit is used for sorting the input tracks of the same category in the disturbed track set according to the descending order of the importance indexes, and determining the input tracks of the specified number which are ranked at the top in each category of input tracks as the key disturbed tracks of the corresponding category.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of any one of the above-mentioned electric power system disturbed track screening methods.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for screening disturbed trajectory of an electrical power system as described in any one of the above.
The method, the device, the electronic equipment and the storage medium for screening the disturbed track of the power system provided by the invention have the advantages that the parameter curve connecting the reference point and the disturbed track set passes through the prediction classification surface of transient stability and transient instability by taking the sample point which is closest to the disturbed track set and is transient stability in the model training set as the reference point, and the importance index of each input track calculated according to the parameter curve and the transient stability characteristic of the system can be understood as the transient contribution of each input track to the change of the transient stability when a transient stability sample nearest to the current point moves to the current point in the transient instability space, obviously, the disturbed track with higher importance index has strong correlation with the transient stability characteristic of the system, thereby realizing the rapid positioning of the key disturbed track input to the transient stability evaluation model of the power system, the method can assist the generation of the transient stability emergency control decision of the power system, and overcomes the defect of 'black box' in the deep learning method in the prior art.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for screening disturbed tracks of an electric power system according to the present invention;
FIG. 2 is a schematic flow chart illustrating a process for determining an importance indicator of an input trajectory according to the present invention;
FIG. 3 is a schematic flow chart of determining a critical disturbed trajectory according to the present invention;
FIG. 4 is a schematic structural diagram of a disturbed track screening device of an electric power system provided by the invention;
fig. 5 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The method for screening disturbed track of power system according to the present invention is described below with reference to fig. 1 to 3.
Fig. 1 is a schematic flow chart of a method for screening disturbed tracks of an electrical power system, as shown in fig. 1, the method includes:
Specifically, the system transient stability characteristics may include any one or a combination of the following: transient stability, namely predicting the maximum power angle difference of a transient process of maintaining the transient stability of the system after a fault and predicting the transient instability time of the system generating the transient instability after the fault; wherein,
transient stability: if transient instability occurs after a fault is expected, outputting a transient instability classification result; otherwise, outputting a transient stability classification result. The analysis results are categorical variables. For the case of transient instability of the system after the expected fault, the expected fault may also be referred to as an expected instability fault.
Maximum power angle difference in transient process: if the system maintains transient stability after the expected fault, the maximum value of the power angle difference between any two generators of the system is in the transient process. The analysis result is a regression variable related to the transient stability margin of the system: if the maximum power angle difference in the transient process is smaller, the system is farther away from the transient stability boundary.
Transient destabilization time: and if the system is subjected to transient instability after the expected fault, the time period from the occurrence of the expected fault to the occurrence of the transient instability of the system is long. The analysis result is a regression variable related to the transient stability margin of the system: if the value is smaller, the system is farther from the transient stability boundary.
Specifically, the input trajectory includes any one or a combination of the following categories: line tide curve, node voltage curve, generator power angle curve. The input track is in a two-dimensional matrix form, and the rows and the columns of the two-dimensional matrix respectively represent the track number and the track sampling point number.
And step 120, determining a sample point which is closest to the disturbed trajectory set in the pre-acquired model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set.
Specifically, the two endpoints of the parametric curve are the sample point and the disturbed trajectory set. In step 120, the sample point which is closest to the disturbed trajectory set in the model training set and is transient stable is used as a reference point, so that a parameter curve connecting the reference point and the disturbed trajectory set passes through a prediction classification surface of transient stability and transient instability, and then an importance index of each input trajectory can be calculated in step 130 according to the parameter curve and the transient stability characteristics of the system.
In particular, the importance indicator may reflect a degree of sensitivity of the transient stability assessment model to the input trajectory.
And 140, respectively sorting the input tracks of the same category in the disturbed track set according to the descending order of the importance indexes, and determining the input tracks with the designated number which are ranked at the top in each category input track as the key disturbed tracks of the corresponding category.
The method for screening the disturbed track of the power system, provided by the invention, has the advantages that the sample point which is closest to the disturbed track set in the model training set and is transient stable is taken as the reference point, so that the parameter curve connecting the reference point and the disturbed track set passes through the prediction classification surface of the transient stability and the transient instability, and the importance index of each input track obtained by calculation according to the parameter curve and the transient stability characteristic of the system can be understood as the contribution of each input track to the change of the transient stability when a transient stability sample nearest to the current point moves to the current point in the transient instability space, obviously, the disturbed track with higher importance index has strong correlation with the transient stability characteristic of the system, thereby realizing the fast positioning of the key disturbed track input to the transient stability evaluation model of the power system, assisting the generation of the transient stability emergency control decision of the power system, the defect of 'black box' in the deep learning method in the prior art is overcome.
Based on the foregoing embodiment, fig. 2 is a schematic flowchart of a process for determining an importance indicator of an input track according to the present invention, and as shown in fig. 2, step 130 may include:
and 131, determining an integral gradient result matrix of the transient stability characteristic of the system relative to the disturbed trajectory set based on the transient stability characteristic of the system output by the parameter curve and the transient stability evaluation model.
Specifically, the integral gradient result matrix can be calculated using equation (1):
wherein, F (x) is the system transient stability characteristic output by the transient stability evaluation model, x is the disturbed track set, x 0 Is a sample point; gamma (alpha), alpha ∈ [0,1 ]]Representing a connection sample point x 0 And a parameter curve of the disturbed trajectory set x, γ (0) ═ x 0 Where γ (1) ═ x, in formula (1), the parametric curve γ (α) takes the connecting sample point x 0 And the straight line of the disturbed trajectory set x.
And 132, determining the importance index of each input track in the disturbed track set according to the integral gradient result matrix.
Specifically, summing up each row of the integral gradient result matrix to obtain the importance index of each input track in the disturbed track set.
According to the method for screening the disturbed track of the power system, the integral gradient result matrix of the transient stability characteristic of the system on the disturbed track set is calculated, and the importance of integral gradient attention in the relative meaning is adopted, so that the importance index can reflect the contribution of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model is changed from a sample point to the disturbed track set, and the key disturbed track input to the transient stability evaluation model of the power system is quickly positioned.
Based on the above embodiment, acquiring a disturbed trajectory set input to a transient stability evaluation model of a power system includes: more than two disturbed trajectory sets input to the transient stability assessment model are acquired. Considering a plurality of unstable predicted faults, namely scanning predicted fault sets for a given tidal current mode, a plurality of disturbed track sets x are obtained 1 ,x 2 ,…，
And comprehensively considering all the instability predicted faults in the predicted fault set, and determining a key disturbed trajectory set of the power flow mode. Fig. 3 is a schematic flowchart of determining a critical disturbed track according to the present invention, and as shown in fig. 3, step 140 may include:
and step 141, respectively performing normalization calculation on the importance indexes of the input tracks in each disturbed track set to obtain a normalization result of the importance indexes of the input tracks in each disturbed track set.
Specifically, scanning an expected fault set for a given power flow mode results in a plurality of disturbed trajectory sets x 1 ，x 2 ，…，
The number of disturbed trace sets is N s Examples are given; for the jth perturbed track set x j The disturbed trajectory set x may be determined based on the method provided in the above embodiment j Importance index s of each input track j For x j Importance index of the ith input track
Can be obtained by the following formula (2)Calculating the sensitivity of the line normalization section to obtain a normalization result
And 142, respectively carrying out average calculation on the normalization results of the importance indexes of the input tracks in the same row in each disturbed track set to obtain the average result of the normalization results of the importance indexes of the input tracks in each row in each disturbed track set.
Specifically, the following formula (3) is adopted to calculate the average result s of the normalized results of the importance indexes of the input tracks of all rows in all disturbed track sets pf : the importance index of the input track under a plurality of instability prediction fault scenes can be obtained:
and 143, sorting the input tracks of the same category in the input tracks of each row of each disturbed track set respectively according to the descending order of the average result of the normalization results of the importance indexes of the input tracks of each row in each disturbed track set, and determining the input tracks of the specified number which are ranked at the top in each category of input tracks as the key disturbed tracks of the corresponding category.
According to the method for screening the disturbed track of the power system, provided by the invention, all instability predicted faults in a predicted fault set need to be comprehensively considered, normalization is carried out firstly, then an averaging method is adopted, the disturbed track importance indexes under a plurality of instability predicted faults are integrated, and a key disturbed track set considering the plurality of instability predicted faults is obtained, so that the key disturbed track input to a transient stability evaluation model of the power system is quickly positioned, the generation of a transient stability emergency control decision of the power system can be assisted, and the defect of 'black box' in a deep learning method in the prior art is overcome.
The following describes the disturbed track screening device of the power system provided by the present invention, and the disturbed track screening device of the power system described below and the disturbed track screening method of the power system described above can be referred to correspondingly.
Based on any of the above embodiments, fig. 4 is a schematic structural diagram of a disturbed track screening apparatus of an electric power system provided by the present invention, as shown in fig. 4, the apparatus includes:
an obtaining unit 401, configured to obtain a disturbed trajectory set input to a transient stability evaluation model of the power system; the transient stability evaluation model is used for establishing correlation between the operation characteristics of the power system and the transient stability characteristics of the system; the disturbed trajectory set refers to a two-dimensional matrix of more than two input trajectories which are input into the transient stability evaluation model when transient instability occurs in the system after an expected fault;
a first determining unit 402, configured to determine a sample point in a pre-obtained model training set that is closest to the disturbed trajectory set and is transient stable, and determine a parameter curve used to connect the sample point and the disturbed trajectory set;
a second determining unit 403, configured to determine an importance indicator of each input trajectory in the disturbed trajectory set according to the parameter curve and a system transient stability characteristic output by the transient stability evaluation model; the importance index is used for representing the contribution size of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model changes from a sample point to the disturbed track set;
the sorting unit 404 is configured to sort the input tracks of the same category in the disturbed track set according to the descending order of the importance indexes, and determine an input track of a specified number ranked earlier in each category input track as a key disturbed track of a corresponding category.
The disturbed trajectory screening device of the power system provided by the invention has the advantages that the sample point which is closest to the disturbed trajectory set in the model training set and is transient stability is taken as the reference point, so that the parameter curve connecting the reference point and the disturbed trajectory set passes through the prediction classification surface of the transient stability and the transient instability, and the importance index of each input trajectory obtained by calculation according to the parameter curve and the transient stability characteristic of the system can be understood as the contribution of each input trajectory to the change of the transient stability when a transient stability sample nearest to the current point moves to the current point in the transient instability space, obviously, the disturbed trajectory with higher importance index has strong correlation with the transient stability characteristic of the system, thereby realizing the rapid positioning of the key disturbed trajectory input to the transient stability evaluation model of the power system, and assisting the generation of the transient stability emergency control decision of the power system, the defect of 'black box' in the deep learning method in the prior art is overcome.
Fig. 5 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 5: a processor (processor)510, a communication Interface (Communications Interface)520, a memory (memory)530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a power system disturbed trajectory screening method comprising: acquiring a disturbed trajectory set input into a transient stability evaluation model of the power system; the transient stability evaluation model is used for establishing correlation between the operation characteristics of the power system and the transient stability characteristics of the system; the disturbed trajectory set refers to a two-dimensional matrix of more than two input trajectories which are input into the transient stability evaluation model when transient instability occurs in the system after an expected fault; determining a sample point which is closest to the disturbed trajectory set in a pre-acquired model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set; determining importance indexes of all input tracks in the disturbed track set according to the parameter curve and system transient stability characteristics output by the transient stability evaluation model; the importance index is used for representing the contribution size of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model changes from a sample point to the disturbed track set; and respectively sequencing the input tracks of the same category in the disturbed track set from large to small according to the importance indexes, and determining the input tracks of the specified number which are ranked at the top in each category input track as the key disturbed tracks of the corresponding category.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer, the computer can execute the method for filtering disturbed track of an electric power system provided by the above methods, the method includes: acquiring a disturbed trajectory set input into a transient stability evaluation model of the power system; the transient stability evaluation model is used for establishing correlation between the operation characteristics of the power system and the transient stability characteristics of the system; the disturbed trajectory set refers to a two-dimensional matrix of more than two input trajectories which are input into the transient stability evaluation model when transient instability occurs in the system after an expected fault; determining a sample point which is closest to the disturbed trajectory set in a pre-acquired model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set; determining importance indexes of all input tracks in the disturbed track set according to the parameter curve and system transient stability characteristics output by the transient stability evaluation model; the importance index is used for representing the contribution size of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model changes from a sample point to the disturbed track set; and respectively sequencing the input tracks of the same category in the disturbed track set from large to small according to the importance indexes, and determining the input tracks of the specified number which are ranked at the top in each category input track as the key disturbed tracks of the corresponding category.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the method for filtering disturbed trajectory of a power system provided in the above aspects, the method including: acquiring a disturbed trajectory set input to a transient stability evaluation model of the power system; the transient stability evaluation model is used for establishing correlation between the operation characteristics of the power system and the transient stability characteristics of the system; the disturbed trajectory set refers to a two-dimensional matrix of more than two input trajectories which are input into the transient stability evaluation model when transient instability occurs in the system after an expected fault; determining a sample point which is closest to the disturbed trajectory set in a pre-acquired model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set; determining importance indexes of all input tracks in the disturbed track set according to the parameter curve and system transient stability characteristics output by the transient stability evaluation model; the importance index is used for representing the contribution size of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model changes from a sample point to the disturbed track set; and respectively sequencing the input tracks of the same category in the disturbed track set from large to small according to the importance indexes, and determining the input tracks of the specified number which are ranked at the top in each category input track as the key disturbed tracks of the corresponding category.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for screening disturbed tracks of an electric power system is characterized by comprising the following steps:
acquiring a disturbed trajectory set input into a transient stability evaluation model of the power system; the transient stability evaluation model is used for establishing correlation between the operation characteristics of the power system and the transient stability characteristics of the system; the disturbed trajectory set refers to a two-dimensional matrix of more than two input trajectories which are input into the transient stability evaluation model when transient instability occurs in the system after an expected fault;
determining a sample point which is closest to the disturbed trajectory set in a pre-acquired model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set;
determining importance indexes of all input tracks in the disturbed track set according to the parameter curves and system transient stability characteristics output by the transient stability evaluation model; the importance index is used for representing the contribution size of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model changes from a sample point to the disturbed track set;
and respectively sequencing the input tracks of the same category in the disturbed track set from large to small according to the importance indexes, and determining the input tracks of the specified number which are ranked at the top in each category input track as the key disturbed tracks of the corresponding category.
2. The method for screening disturbed trajectories of claim 1, wherein the determining the importance index of each input trajectory in the disturbed trajectory set according to the parameter curve and the transient stability characteristics of the system output by the transient stability evaluation model comprises:
determining an integral gradient result matrix of the system transient stability characteristic with respect to the disturbed trajectory set based on the parameter curve and the system transient stability characteristic output by the transient stability evaluation model;
and determining the importance index of each input track in the disturbed track set according to the integral gradient result matrix.
3. The method for screening disturbed trajectories of a power system according to claim 2, wherein the determining the importance index of each input trajectory in the disturbed trajectory set according to the integral gradient result matrix comprises:
and summing the rows of the integral gradient result matrix to obtain the importance index of each input track in the disturbed track set.
4. The method according to claim 1, wherein two endpoints of the parameter curve are the sample point and the disturbed trajectory set.
5. The method according to claim 1, wherein the obtaining of the disturbed trajectory set input to the power system transient stability assessment model comprises: acquiring more than two disturbed trajectory sets input into the transient stability assessment model;
the step of sorting the input tracks of the same category in the disturbed track set from large to small according to the importance indexes, and determining the input tracks of the specified number with the top ranking in each category input track as the key disturbed tracks of the corresponding category comprises the following steps:
respectively carrying out normalization calculation on the importance indexes of the input tracks in the disturbed track sets to obtain the normalization results of the importance indexes of the input tracks in the disturbed track sets;
respectively carrying out average calculation on the normalization results of the importance indexes of the input tracks in the same row in each disturbed track set to obtain the average result of the normalization results of the importance indexes of the input tracks in each row in each disturbed track set;
and respectively sequencing the input tracks of the same category in the input tracks of each row of each disturbed track set according to the descending order of the average result of the normalization results of the importance indexes of the input tracks of each row in each disturbed track set, and determining the input tracks of the designated number with the top rank in each category of input tracks as the key disturbed tracks of the corresponding category.
6. The method according to claim 1, wherein the system transient stability characteristics include any one or a combination of the following: transient stability, the maximum power angle difference of the transient process of the system maintaining transient stability after the expected fault, and the transient instability time of the system generating transient instability after the expected fault.
7. The electric power system disturbed trajectory screening method of claim 1, wherein the input trajectory comprises any one of or a combination of the following categories: a line tide curve, a node voltage curve and a power angle curve of the generator.
8. An electric power system disturbed track screening device, characterized by comprising:
the acquisition unit is used for acquiring a disturbed trajectory set input into the transient stability evaluation model of the power system; the transient stability evaluation model is used for establishing correlation between the operation characteristics of the power system and the transient stability characteristics of the system; the disturbed trajectory set refers to a two-dimensional matrix of more than two input trajectories which are input into the transient stability evaluation model when transient instability occurs in the system after an expected fault;
the first determining unit is used for determining a sample point which is closest to the disturbed trajectory set in a pre-acquired model training set and is transient stable, and determining a parameter curve for connecting the sample point and the disturbed trajectory set;
the second determining unit is used for determining the importance index of each input track in the disturbed track set according to the parameter curve and the system transient stability characteristics output by the transient stability evaluation model; the importance index is used for representing the contribution size of each input track in the disturbed track set to the output change of the transient stability evaluation model when the input of the transient stability evaluation model is changed from a sample point to the disturbed track set;
and the sorting unit is used for sorting the input tracks of the same category in the disturbed track set according to the descending order of the importance indexes, and determining the input tracks of the specified number which are ranked at the top in each category of input tracks as the key disturbed tracks of the corresponding category.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for filtering disturbed trajectory in an electrical power system according to any of claims 1 to 7 when executing the program.
10. A non-transitory computer readable storage medium, having a computer program stored thereon, wherein the computer program, when being executed by a processor, implements the steps of the method for filtering disturbed trajectory in an electrical power system according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110693996.9A CN113506186B (en) | 2021-06-22 | 2021-06-22 | Method and device for screening disturbed track of power system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110693996.9A CN113506186B (en) | 2021-06-22 | 2021-06-22 | Method and device for screening disturbed track of power system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113506186A CN113506186A (en) | 2021-10-15 |
| CN113506186B true CN113506186B (en) | 2022-09-27 |
Family
ID=78010687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110693996.9A Active CN113506186B (en) | 2021-06-22 | 2021-06-22 | Method and device for screening disturbed track of power system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113506186B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117215205B (en) * | 2023-11-09 | 2024-02-06 | 国网经济技术研究院有限公司 | DC system control parameter analysis method based on decision tree and ISS theory |
| CN117910367B (en) * | 2024-03-20 | 2024-05-28 | 浙江大学 | Power system disturbed trajectory prediction method based on physical information neural network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108964046A (en) * | 2018-08-03 | 2018-12-07 | 东北电力大学 | A kind of power system transient stability appraisal procedure based on disturbed track in short-term |
| CN111784106A (en) * | 2020-05-26 | 2020-10-16 | 国电南瑞南京控制系统有限公司 | Active splitting section offline screening method and device based on disturbed track |
-
2021
- 2021-06-22 CN CN202110693996.9A patent/CN113506186B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108964046A (en) * | 2018-08-03 | 2018-12-07 | 东北电力大学 | A kind of power system transient stability appraisal procedure based on disturbed track in short-term |
| CN111784106A (en) * | 2020-05-26 | 2020-10-16 | 国电南瑞南京控制系统有限公司 | Active splitting section offline screening method and device based on disturbed track |
Non-Patent Citations (2)
| Title |
|---|
| 基于短时受扰轨迹的电力系统暂态稳定评估方法;安军等;《电网技术》;20190505(第05期);全文 * |
| 基于自忆性灰色Verhulst模型的暂态稳定受扰轨迹实时预测;黄丹等;《高电压技术》;20180416(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113506186A (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111124840B (en) | Method and device for predicting alarm in business operation and maintenance and electronic equipment | |
| CN107391852B (en) | Transient stability real-time evaluation method and device based on deep belief network | |
| CN106251059B (en) | Cable state evaluation method based on probabilistic neural network algorithm | |
| CN109117380B (en) | Software quality evaluation method, device, equipment and readable storage medium | |
| CN113506186B (en) | Method and device for screening disturbed track of power system, electronic equipment and storage medium | |
| US20200184308A1 (en) | Methods, systems, and computer readable mediums for determining a system state of a power system using a convolutional neural network | |
| CN110766137A (en) | Power electronic circuit fault diagnosis method based on longicorn whisker optimized deep confidence network algorithm | |
| CN110232434A (en) | A kind of neural network framework appraisal procedure based on attributed graph optimization | |
| CN112508442B (en) | Transient stability assessment method and system based on automatic and interpretable machine learning | |
| CN111523778A (en) | Power grid operation safety assessment method based on particle swarm algorithm and gradient lifting tree | |
| CN108647707B (en) | Probabilistic neural network creation method, failure diagnosis method and apparatus, and storage medium | |
| CN112561303B (en) | Power system dynamic analysis method based on integrated learning and power grid topology change | |
| CN111680875B (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| CN112287556A (en) | Method and device for determining insulation state of cable | |
| CN107451596A (en) | A kind of classified nodes method and device | |
| CN108595884A (en) | Power system transient stability appraisal procedure and device | |
| CN115238980A (en) | Micro-grid transient power angle trajectory prediction method based on attention mechanism and space-time diagram convolutional neural network | |
| CN115902642A (en) | Battery state of charge estimation method and device, electronic equipment and storage medium | |
| CN112232381A (en) | Model parameter post-processing method and device for leading load parameter noise identification | |
| CN110378358A (en) | A kind of power distribution network isomeric data integration method and system | |
| CN113740671A (en) | Fault arc identification method based on VMD and ELM | |
| LU505740B1 (en) | Data monitoring method and system | |
| CN116204771A (en) | Power system transient stability key feature selection method, device and product | |
| CN116911161A (en) | Data-enhanced deep learning transient voltage stability evaluation method | |
| CN115713032A (en) | Power grid prevention control method, device, equipment and medium |
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 |