A method, system, device and medium for automatically marking a dominant instability mechanism group

Abstract

The application discloses a kind of leading instability machine group automatic marking method, system, device and medium, belong to electric power technical field.The method includes: obtaining input sample, judge whether input sample is transient instability sample, if yes, leading instability machine group is marked;For transient instability sample, obtain the power angle curve set of all generators {δ i (t)}, according to power angle curve set {δ i (t)} Similarity matrix ρ is obtained;Based on similarity matrix ρ, after AP clustering, get the homology machine group clustering result set G AP ={G1,G2,…,G K};According to homology machine group clustering result set G AP Marking result is obtained.The application is dynamically obtained after each generator fault, and clustering mode is automatically carried out generator homology grouping, and the most leading machine group is regarded as leading instability machine group, and leading instability machine group of mass sample can be marked spontaneously and in batches, to provide fine-grained generator level stability index for data-driven stability evaluation model.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power, and in particular to a leading unstable machine group automatic marking method, system, device and medium. BACKGROUND

[0002] With the transition from traditional synchronous generator dominated power system to new energy high proportion new power system, time domain simulation with large calculation burden and long time consumption has been difficult to adapt to real-time transient stability evaluation. The booming development of massive data storage of power system and computer hardware such as GPU has given birth to data-driven stability evaluation model, which can establish the correlation between system response data and concerned stability indicators offline, so as to give a quick stability discrimination online. Most data-driven stability evaluation models focus on the prediction of system-level stability indicators, which is difficult to provide sufficient guidance information for dispatch personnel to implement preventive control. In the process of power angle swing, the leading machine group composed of one to several generators with the fastest relative motion speed has a decisive influence on stability discrimination. When the power angle difference between the leading machine group and the slowest machine group exceeds the engineering threshold, it is considered that the system has transient instability. Therefore, the discrimination of leading unstable machine group is of great significance for preventive control considering economic cost and safety. SUMMARY

[0003] To at least partially solve one of the technical problems existing in the prior art, the purpose of the present application is to provide a leading unstable machine group automatic marking method, system, device and medium.

[0004] The technical solution adopted by the present application is:

[0005] A leading unstable machine group automatic marking method, comprising the following steps:

[0006] Obtaining an input sample, judging whether the input sample is a transient instability sample, and if so, marking the leading unstable machine group;

[0007] For the transient instability sample, obtaining a power angle curve set {δ i (t)} of all generators, and obtaining a similarity matrix ρ according to the power angle curve set {δ i (t)}; wherein δ i (t) represents the power angle curve of the i-th generator;

[0008] Based on the similarity matrix ρ, after AP clustering, a homology machine group clustering result set G AP ={G1,G2,…,G K} is obtained, wherein K is the number of clusters automatically given by AP clustering;

[0009] According to the homology machine group clustering result set G AP , a marking result readable by a data-driven stability evaluation model is obtained.

[0010] Further, the similarity matrix ρ is obtained according to the power angle curve set {δ i (t)} and includes:

[0011] The power angle curve of the generator is sampled one by one, and the most leading unit is searched out:

[0012] Define n as the sampling point number, and Δt as the sampling interval, and the total number of samples is The power angle curve δ i (t) is sampled and expressed as a set δ i :

[0013] δ i ={δ i,1 ,…,δ i,n ,…,δ i,N} (1)

[0014] At the n-th sampling point, all generator power angle values form a set Then the absolute value peak |Δδ n | max of any two generator power angles is expressed as:

[0015] |Δδ n | max =max i,j |δ i,n -δ j,n |,i,j∈G (2)

[0016] In the formula, G is the generator set;

[0017] Let n=0, the engineering threshold Δδ th , and the search step of the most leading unit is as follows:

[0018] 1) Calculate the formula (2) to obtain the generator power angle absolute value peak |Δδ n | max ;

[0019] 2) Compare |Δδ n | max with Δδ th , if |Δδ n | max is greater than Δδ th , output true; if |Δδ n | max is less than Δδ th , output false;

[0020] 3) If the output is true, record the current n value as n r , and output |Δδ n | maxThe corresponding generator pair {i r ,j r};if the output is false, let n=n+1, and obtain the next input sample;

[0021] 4) comparison and if The most advanced group number is i r ;otherwise, the most advanced group number is j r .

[0022] Further, the similarity matrix ρ is defined as follows:

[0023] Given the number of similarity sampling steps N th , the similarity of any two generators is defined as:

[0024]

[0025] The normalized power angle value δ' is represented as: i,n

[0026]

[0027] Let the diagonal elements of the similarity matrix ρ (i,i) be the median of all similarity values.

[0028] Further, the clustering result set G AP of the coherent machine group is obtained according to the marking result, including:

[0029] According to the clustering result set G AP of the coherent machine group, all coherent machine groups G k , 0<k<K, are traversed to determine whether G k contains the most advanced group number.

[0030] The coherent machine group containing the most advanced group number is taken as the leading unstable machine group G d ; finally, the leading unstable machine group G d is converted into a binary label c to describe the final marking result, and the elements of the binary label c are represented as follows:

[0031]

[0032] Another technical solution adopted by the present application is:

[0033] A leading unstable machine group automatic marking system, comprising:

[0034] A transient instability judgment module is used to obtain an input sample, judge whether the input sample is a transient instability sample, and if so, mark the leading unstable machine group. ​

[0035] The similarity matrix generating module is configured to obtain a power angle curve set {δ i (t)} of all generators for the transient instability sample, and obtain a similarity matrix ρ according to the power angle curve set {δ i (t)}; wherein δ i (t) represents a power angle curve of the i-th generator.

[0036] The coherent generator cluster module is configured to obtain a coherent generator cluster result set G AP ={G1, G2, …, G K} based on the similarity matrix ρ after AP clustering.

[0037] The dominant unstable generator cluster vectorization module is configured to obtain a marking result according to the coherent generator cluster result set G AP .

[0038] Further, the similarity matrix ρ is obtained according to the power angle curve set {δ i (t)}, and the similarity matrix ρ includes the following steps.

[0039] The power angle curves of the generators are sampled one by one, and the most leading generator set is searched out.

[0040] n is defined as the sampling point number, and Δt is defined as the sampling interval, so that the total number of samples is n·Δt. The power angle curve δ i (t) is sampled and represented as a set δ i .

[0041] δ i ={δ i,1 ,…,δ i,n ,…,δ i,N} (3)

[0042] At the n-th sampling point, the power angle values of all generators form a set Then, the absolute value peak |Δδ n | max of the power angle of any two generators is represented as:

[0043] |Δδ n | max =max i,j |δ i,n -δ j,n |,i,j∈G (4)

[0044] In the formula, G represents the generator set.

[0045] Let n=0, and the engineering threshold Δδ th . The search step of the most leading generator set is as follows:

[0046] 1) Calculate the absolute value of the peak of the generator angle |Δδ n | max ;

[0047] 2) Compare |Δδ n | max and Δδ th , if |Δδ n | max is greater than Δδ th , output is true; if |Δδ n | max is less than Δδ th , output is false;

[0048] 3) If the output is true, record the current n value as n r , output |Δδ n | max corresponding to the generator pair {i r , j r}; if the output is false, let n = n + 1, and get the next input sample;

[0049] 4) Compare and if the most leading unit number is i r ; otherwise, the most leading unit number is j r .

[0050] Further, the similarity matrix ρ is defined as follows:

[0051] Given the number of similarity sampling steps N th , the similarity between any two generators is defined as:

[0052]

[0053] The normalized power angle value δ′ i,n is represented as:

[0054]

[0055] Let the diagonal elements of the similarity matrix ρ (i,i) be uniform, which is the median of all similarity values.

[0056] Further, the labeled result is obtained according to the set of coherent machine group clustering results G AP , including:

[0057] According to the set of coherent machine group clustering results G AP , traverse all coherent machine groups G k , 0 < k < K, judge G kwhether to contain the most leading machine group sequence number;

[0058] the coherent machine group containing the most leading machine group sequence number as the leading unstable machine group G d ; finally, the leading unstable machine group G d is converted into a binary label c to describe the final labeling result, and the elements of the binary label c are represented as follows:

[0059]

[0060] Another technical solution adopted by the present application is:

[0061] An automatic leading unstable machine group labeling device, comprising:

[0062] at least one processor;

[0063] at least one memory for storing at least one program;

[0064] When the at least one program is executed by the at least one processor, the at least one processor implements the method as described above.

[0065] Another technical solution adopted by the present application is:

[0066] A computer-readable storage medium, wherein a processor-executable program is stored, and the processor-executable program is used to execute the method as described above when executed by a processor.

[0067] The present application has the beneficial effects that: after obtaining the fault of each generator, the present application automatically performs generator coherent grouping in a clustering manner, takes the most leading machine group as the leading unstable machine group, can spontaneously and in batches label the leading unstable machine group of a large amount of samples, and provides a fine-grained generator-level stability index for a data-driven stability evaluation model. BRIEF DESCRIPTION OF DRAWINGS

[0068] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following introduces the drawings of the related technical solutions in the embodiments of the present application or the prior art. It should be understood that the drawings in the following introduction are only for the convenience of clearly describing part of the embodiments in the technical solutions of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0069] Figure 1 is a step flow chart of an automatic leading unstable machine group labeling method in an embodiment of the present application;

[0070] Figure 2 is a post-fault time-domain simulation curve schematic diagram in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The embodiments of the present application are described below in detail with reference to the accompanying drawings, wherein the same or similar components or components having the same or similar functions are denoted by the same or similar reference numerals throughout. The embodiments described below by reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application. For the step numbers in the following embodiments, they are only set for the convenience of the description of the specification, and the order between the steps is not limited in any way, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0072] In the description of the present application, it should be understood that the orientation description, such as the orientation or position relationship indicated by the upper, lower, front, rear, left, right, etc. is based on the orientation or position relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, and is not intended to indicate or imply that the device or component referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0073] In the description of the present application, the meaning of several is one or more, and the meaning of multiple is two or more. Greater than, less than, more than, etc. are understood as not including the number, and above, below, etc. are understood as including the number. If it is described as first, second, it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or the order of indicated technical features.

[0074] In addition, in the description of the present application, unless otherwise specified, "a plurality of" means two or more. The association relationship of the associated objects is described, which means that there can be three relationships, for example, A and / or B, which can represent three cases: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the front and rear associated objects.

[0075] In the description of the present application, unless otherwise explicitly limited, the words such as setting, installing, connecting, etc. should be broadly understood, and those skilled in the art can reasonably determine the specific meaning of the above words in the present application in combination with the specific content of the technical solution.

[0076] The present application designs a dominant unstable machine group automatic marking method for data-driven power system transient stability evaluation. Based on the dynamic of each generator after fault obtained by time domain simulation, the clustering method is used to automatically group the generators in the same tone, and the most leading machine group is taken as the dominant unstable machine group. The method can automatically and batch mark the dominant unstable machine group of a large number of samples, and provide fine-grained generator-level stability indicators for data-driven stability evaluation models.

[0077] AsFigure 1 The embodiment shown provides a leading instability machine group automatic marking method, including the following steps:

[0078] S1, obtaining an input sample, judging whether the input sample is a transient instability sample, if yes, marking the leading instability machine group.

[0079] Given an input sample, the input sample first passes through a transient instability judgment module. It should be noted that the transient instability judgment module can be completed by using a typical engineering threshold, which will not be described here. If the transient instability criterion is not met, it is a stable sample and does not need to be marked for the leading instability machine group; otherwise, it is determined as a transient instability sample.

[0080] S2, for the transient instability sample, obtaining a power angle curve set {δ i (t)} of all generators, and obtaining a similarity matrix ρ according to the power angle curve set {δ i (t)}; wherein δ i (t) represents the power angle curve of the i-th generator.

[0081] Definition is a generator set, T is the maximum simulation time length, and δ i (t), i∈G, 0<t<T is the time-domain simulation power angle curve of the i-th generator. For the transient instability sample, the power angle curve set {δ i (t)} of all generators is taken as the input of the similarity matrix generation module, and the similarity matrix ρ is obtained.

[0082] The generation of the similarity matrix ρ specifically includes the following steps:

[0083] (1) obtaining the most leading unit

[0084] First, the generator power angle curve is used one by one to find the most leading unit. Specifically, define n as the sampling point number, Δt as the sampling interval, and the total number of samples as Thus, the sampled δ i (t) is expressed as the set δ i :

[0085] δ i ={δ i,1 ,…,δ i,n ,…,δ i,N} (1)

[0086] At the n-th sampling point, all generator power angle values form a set Then the absolute value peak |Δδ n | max of the power angle of any two generators is expressed as:

[0087] |Δδn | max = max i,j | δ i,n - δ j,n |, i,j e G (2)

[0088] Let n = 0, the engineering threshold Δδ th The most leading unit search steps are as follows:

[0089] 1) Calculate the absolute value of the generator angle |Δδ n | max ;

[0090] 2) Compare |Δδ n | max and Δδ th , if |Δδ n | max is greater than Δδ th , the output is true; if |Δδ n | max is less than Δδ th , the output is false;

[0091] 3) If the output is true, record the current n value as n r , output |Δδ n | max corresponding to the generator pair {i r ,j r}; if the output is false, let n = n + 1, and get the next input sample;

[0092] 4) Compare and If the most leading unit sequence number is i r ; otherwise, the most leading unit sequence number is j r .

[0093] (2) Similarity matrix ρ definition

[0094] Given the number of similarity sampling steps N th , the similarity of any two generators is defined as:

[0095]

[0096] The normalized angle value δ′ i,n is expressed as:

[0097]

[0098] Let the diagonal elements ρ (i,i) of the similarity matrix be uniform, which is the median of all similarity values.

[0099] S3, based on the similarity matrix p, the AP clustering is performed to obtain a coherent machine group clustering result set G AP ={G1, G2, …, G K K}, where K is the number of clusters automatically given by the AP clustering.

[0100] In this embodiment, the existing AP (affinity propagation) clustering algorithm is used to process the similarity matrix p to obtain a coherent machine group clustering result set G AP ={G1, G2, …, G K K}.

[0101] S4, according to the coherent machine group clustering result set G AP , the data-driven stable evaluation model readable marking result is obtained.

[0102] According to the coherent machine group clustering result set G AP , all coherent machine groups G k 0 < k < K are traversed to determine whether G k contains the most leading machine group sequence number.

[0103] The coherent machine group containing the most leading machine group sequence number is taken as the leading unstable machine group G d ; finally, the leading unstable machine group G d is converted into a binary label c to describe the final marking result, and the elements of the binary label c are represented as follows:

[0104]

[0105] The above method is explained and described in detail in combination with the drawings and specific embodiments.

[0106] Take the IEEE 10-machine 39-node system as a test system, which contains N G = 10 generators, and the generator sequence number set G = {1, 2, L, 10}. In the demonstration case, the simulation duration T = 4, the fault occurs at 0.2s, and the fault is cleared at 0.3s. The time-domain simulation curve after the fault is shown in Figure 2 Obviously, the No. 9 generator has a significant difference in the speed and swing amplitude of the power angle change from the remaining machine groups, which constitutes the leading unstable machine group in engineering.

[0107] For the automatic marking process of the leading unstable machine group, the basic parameters are set as Dd th = 180°, N th = 10, and At = 0.01s. First, it is known from the transient instability judgment module that this case is a transient instability sample, and enters the similarity matrix generation link. For Figure 2the fault time domain simulation curve is sampled, and |Δδ n | max Some data is shown in Table 1.

[0108] Table 1 Time domain simulation curve sampling and |Δδ n | max Calculation

[0109]

[0110] As shown in Table 1, when n = 69, |Δδ n | max >Δδ th , the output is true, so n r = 69. The serial number set of the corresponding unit pair is {9, 10}, since δ 9,nr >δ 10,nr , the serial number of the most leading unit is 9.

[0111] According to formula (3), the similarity between each pair of units is calculated, and the median is-0.735. The similarity matrix is shown in Table 2.

[0112] Table 2 Similarity matrix

[0113]

[0114]

[0115] Based on the above similarity matrix, AP clustering is performed, and the coherent group set is G AP = {{1, 10}, {2, 3, 4, 5, 8}, {6, 7}, {9}}. Since {9} contains the most leading unit, the dominant unstable group is G d = {9}. It can be seen that the automatic identification result is consistent with the result identified according to engineering experience in 4.1, and the rationality is verified. According to formula (5), the dominant unstable group marking result can be converted into a binary vector c = [0, 0, 0, 0, 0, 0, 0, 0, 1, 0].

[0116] The above dominant unstable group automatic marking process is implemented by using 1000 cases, and the average single time consumption is not more than 1s. In summary, the method described in the embodiment not only meets the calculation efficiency problem of automatically marking a large number of samples in engineering, but also accurately marks the dominant unstable group without giving the number of coherent groups.

[0117] In summary, compared with the prior art, the present application has at least the following advantages and beneficial effects:

[0118] 1) It can automatically label the dominant unstable clusters, which significantly improves the computational efficiency of large-scale sample labeling in engineering.

[0119] 2) Applying the AP clustering algorithm to the identification of coherent machine groups can achieve the identification accuracy requirements of dominant unstable machine groups in engineering without pre-setting the number of coherent machine groups.

[0120] This embodiment also provides an automatic marking system for a dominant unstable cluster, including:

[0121] The transient instability discrimination module is used to acquire input samples, determine whether the input samples are transient instability samples, and if so, mark the dominant instability cluster.

[0122] The similarity matrix generation module is used to obtain the set of power angle curves {δ} of all generators for transient instability samples. i (t)}, according to the set of work angle curves {δ i (t)} obtains the similarity matrix ρ; where δ i (t) represents the power angle curve of the i-th generator;

[0123] The coherent machine swarm clustering module is used to obtain the coherent machine swarm clustering result set G based on the similarity matrix ρ and AP clustering. AP ={G1,G2,…,G K}, where K is the number of clusters automatically given by AP clustering;

[0124] The dominant unstable swarm vectorization module is used to perform clustering based on the homogeneous swarm clustering result set G. AP Get the tagging results.

[0125] As an optional implementation, the step of basing the work angle curves on the set {δ} i (t)} Obtain the similarity matrix ρ, including:

[0126] The power angle curves of the generators are sampled one by one, and the leading unit is searched out:

[0127] Let n be the sampling point number and Δt be the sampling interval, then the total number of samples is: Work angle curve δ i (t) is represented as the set δ after sampling. i :

[0128] δ i ={δ i,1 ,…,δ i,n ,…,δ i,N} (6)

[0129] At the nth sampling point, all generator power angle values ​​form a set. Then the peak value of the absolute value of the power angle of any two generators |Δδn | max is expressed as:

[0130] |Δδ n | max = max i,j |δ i,n -δ j,n |,i,j∈G (7)

[0131] where G is the generator set;

[0132] Let n = 0, the engineering threshold Δδ th The search steps of the most leading unit are as follows:

[0133] 1) Calculate the absolute value peak |Δδ n | max of the generator angle according to formula (7);

[0134] 2) Compare |Δδ n | max with Δδ th . If |Δδ n | max is greater than Δδ th , output is true; if |Δδ n | max is less than Δδ th , output is false;

[0135] 3) If the output is true, record the current n value as n r , output |Δδ n | max corresponding to the generator pair {i r ,j r}; if the output is false, let n = n + 1, and obtain the next input sample;

[0136] 4) Compare and If , the most leading unit number is i r ; otherwise, the most leading unit number is j r .

[0137] Further as an optional embodiment, the similarity matrix ρ is defined as follows:

[0138] Given the similarity sampling step length N th , the similarity of any two generators is defined as:

[0139]

[0140] The normalized power angle value δ′ i,n is expressed as:

[0141]

[0142] the diagonal elements of the similarity matrix are set to the median of all similarity values. (i,i) the median of all similarity values.

[0143] Further, as an optional implementation, the step of obtaining the clustering result set G of the coherent machine group comprises: AP obtaining the marking result, comprising:

[0144] obtaining the clustering result set G of the coherent machine group comprises: AP traversing all coherent machine groups G k , 0 < k < K, and determining whether G k contains the most leading machine group sequence number;

[0145] taking the coherent machine group containing the most leading machine group sequence number as the leading unstable machine group G d ; and finally, converting the leading unstable machine group G d into a binary label c to describe the final marking result, wherein an element of the binary label c is represented as follows:

[0146]

[0147] The leading unstable machine group automatic marking system of the embodiment can execute the leading unstable machine group automatic marking method provided by the method embodiment, can execute any combination of the method embodiment, has the corresponding functions and beneficial effects of the method.

[0148] The embodiment further provides a leading unstable machine group automatic marking device, comprising:

[0149] at least one processor;

[0150] at least one memory for storing at least one program;

[0151] When the at least one program is executed by the at least one processor, the at least one processor implements the method as shown in the method embodiment. Figure 1

[0152] The leading unstable machine group automatic marking device of the embodiment can execute the leading unstable machine group automatic marking method provided by the method embodiment, can execute any combination of the method embodiment, has the corresponding functions and beneficial effects of the method.

[0153] ​The embodiment of the present application further discloses a computer program product or computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device can read the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the method shown in the method. Figure 1

[0154] The embodiment further provides a storage medium storing instructions or programs for performing the method for automatically marking a dominant instability mechanism group.

[0155] In some alternative embodiments, the functions / operations mentioned in the block diagram can not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two blocks shown in succession can actually be executed substantially simultaneously or the blocks can sometimes be executed in reverse order. In addition, the embodiments presented and described in the flowcharts of the present application are provided by way of example, and the purpose is to provide a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are independently executed.

[0156] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and / or features can be integrated in a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It can also be understood that a detailed discussion of the actual implementation of each module is unnecessary for an understanding of the present application. Rather, consideration of the properties, functions and internal relationships of the various functional modules in the devices disclosed herein, within the context of the ordinary skill of the engineer, will be sufficient to understand the actual implementation of the module. Therefore, those skilled in the art can implement the present application as set forth in the claims without undue experimentation using ordinary skill in the art. It can also be understood that the disclosed specific concepts are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the appended claims and their equivalents.

[0157] ​If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0158] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, which can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch the instructions from the instruction execution system, apparatus or device and execute the instructions, or in conjunction with these instructions execution systems, apparatus or devices. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by or in connection with an instruction execution system, apparatus or device, or in conjunction with these instruction execution systems, apparatus or devices.

[0159] More specific examples (non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, because the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by editing, interpreting or otherwise processing, if necessary, in other suitable ways, to be electronically obtained and then stored in the computer memory.

[0160] It should be understood that various parts of the present application can be implemented in hardware, software, firmware or a combination thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or their combinations can be used: a discrete logic circuit having logic gates for implementing logic functions on data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), or the like.

[0161] In the above description of the present specification, the description of the terms "one embodiment / one example", "another embodiment / another example", or "certain embodiments / certain examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0162] Although the embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made thereto without departing from the principles and spirit of the present application, the scope of which is defined by the claims and their equivalents.

[0163] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the above-described embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present application, and these equivalent modifications or substitutions are included in the scope defined by the claims of the present application.

Claims

1. A method for automatically labeling a dominant instability machine group, characterized by, The method comprises the following steps: acquiring an input sample, judging whether the input sample is a transient instability sample, if yes, marking a leading instability machine group; For transient instability samples, obtain the set of power angle curves for all generators. According to the set of work angle curves Obtain the similarity matrix ;in, Indicates the first i The power angle curve of the generator; Based on similarity matrix After clustering by AP, get the set of coherent machine cluster results Wherein The number of clusters automatically given by AP clustering; According to the coherent machine group clustering result set Obtaining a marking result; The power angle curve set Obtaining the similarity matrix , comprising: sampling the power angle curve of the generator one by one and searching out the most leading machine group; Definitions n is the sample point number, is the sampling interval, then the total number of samples is is the power angle curve is represented as a set after sampling （1） At the first n sampling point, all generator power angle values form a set Then the absolute value peak of any two generator power angles is represented as: （2） In the formulae, is a set of generators; Let , the engineering threshold The search step of the most leading group is as follows: 1) The peak value of the absolute value of the machine power angle is obtained by the calculation formula (2) ; 2) compare with , if is greater than , the output is true; if is less than , the output is false; 3) if the output is true, record the current n value as , output the corresponding generator pair ; if the output is false, let , and get the next input sample; 4) compare and if the most advanced group number is ; otherwise, the most advanced group number is ; The set of coherent machine cluster results Obtaining a marking result, comprising: According to the set of coherent machine cluster results , traverse all coherent machine clusters , determine whether the most leading machine group sequence number is contained; The coherent machine group containing the most leading machine group number is taken as the leading unstable machine group ; finally, the leading unstable machine group is converted into a binary label to describe the final marking result, the binary label element is represented as follows: 。 2. The method of claim 1, wherein, the similarity matrix is defined as follows: The number of sampling steps for the similarity is given as The similarity of any two generators is defined as Normalized power angle value is expressed as: Let the diagonal elements of the similarity matrix be uniformly the median of all similarity values.

3. A system for automatically labeling a dominant instability machine fleet, the system comprising: The method comprises the following steps: a transient instability judging module, configured to acquire an input sample, judge whether the input sample is a transient instability sample, if yes, mark a leading instability machine group; The similarity matrix generation module is used to obtain a set of power angle curves for all generators for transient instability samples. According to the set of work angle curves Obtain the similarity matrix ;in, Indicates the first i The power angle curve of the generator; A coherent machine cluster module is used to cluster the coherent machines based on the similarity matrix After clustering by AP, a coherent machine cluster result set is obtained Wherein The number of clusters automatically given by AP clustering; The dominant instability mechanism vectorization module is configured to vectorize the set of homology mechanism clusters based on the set of homology mechanism cluster results Obtaining a labeling result; The power angle curve set Obtaining the similarity matrix , comprising: sampling the power angle curve of the generator one by one and searching out the most leading machine group; Definitions n is the sample point number, is the sampling interval, then the total number of samples is is the power angle curve is represented as a set after sampling （3） At the first n sampling point, all generator power angle values form a set Then the absolute value peak of any two generator power angles is represented as: （4） In the formulae, is a set of generators; Let , the engineering threshold The search step for the most advanced team is as follows: 1) The peak value of the absolute value of the machine power angle is obtained by the calculation formula (4) ; 2) compare with , if is greater than , the output is true; if is less than , the output is false; 3) If the output is true, record the current n value as , output the corresponding generator pair ; if the output is false, let and get the next input sample; 4) compare and if the most advanced group number is ; otherwise, the most advanced group number is ; The set of coherent machine cluster results Obtaining a tagging result, comprising: According to the set of coherent machine cluster results , traverse all coherent machine clusters , determine whether the most leading machine group serial number is contained; The coherent machine group containing the most leading machine group number is taken as the leading unstable machine group ; finally, the leading unstable machine group is converted into a binary label to describe the final marking result, the binary label element is represented as follows: 。 4. The system of claim 3, wherein, The similarity matrix is defined as follows: The number of sampling steps for the similarity is given as The similarity of any two generators is defined as Normalized power angle value is expressed as: Let the diagonal elements of the similarity matrix be uniformly the median of all similarity values.

5. A master instability machine fleet automatic labeling device characterized by, The method comprises the following steps: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method of claim 1 or 2.

6. A computer readable storage medium having stored therein a program which is executable by a processor, characterized in that, The program executable by the processor, when executed by the processor, is used to execute the method of claim 1 or 2.

Images