Method, device, electronic device and storage medium for predicting the transmission capacity limit of power system transmission section

Through the two-stage clustering and fine rule fitting methods, the problems of insufficient generalization ability and interpretability of the accuracy of the existing power system transmission section limit transmission capacity evaluation model in complex scenarios are solved, and high accuracy and Interpretable power system transmission section limit transmission capacity prediction improves the safety evaluation and scheduling capabilities of the power system.

CN113592151BActive Publication Date: 2024-11-22TSINGHUA UNIVERSITY +3
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110766835.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-07
Publication Date
2024-11-22
Estimated Expiration
2041-07-07

AI Technical Summary

Technical Problem

When facing massive complex and changing operating scenarios, the existing data-driven power system transmission section limit transmission capacity evaluation model is insufficient in generalization capacity and the accuracy and interpretability are inconsistent, making it difficult to meet the needs of power system safety assessment.

Method used

The two-stage clustering method is used to divide the operating state of the power system into neighborhoods, and the fine regular model is fitted in each neighborhood to improve the generalization ability and accuracy of the model, and use linear models to perform high accuracy fitting to enhance the Interpretability of the model.

Benefits of technology

It improves the accuracy and robustness of the prediction of the limit transmission capacity of the power system transmission section, provides reliable safety assessment and scheduling basis for the operation and scheduling of the power system, and improves the safety of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113592151B_ABST
    Figure CN113592151B_ABST
Patent Text Reader

Abstract

The present application belongs to the technical field of safe operation of electric power systems, and specifically relates to methods, devices, electronic devices and storage media for predicting the ultimate transmission capacity of transmission sections of electric power systems. Based on the big data of electric power systems, the present disclosure establishes fine neighborhood rules for transmission sections of electric power systems, and can output predicted values ​​of TTC for transmission sections of electric power systems. Most of the existing TTC evaluation models based on data-driven methods have two major problems: one is that the generalization ability of a single model is insufficient when faced with massive, complex and changeable operating scenarios; the other is that there is a contradiction between the accuracy of the model and its interpretability. The present disclosure effectively makes up for this shortcoming by introducing a method for generating fine neighborhood rules for transmission sections of electric power systems based on two-stage clustering. The disclosed method can be applied to the field of safety analysis of electric power systems, which helps to improve the safety of power system dispatching.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the technical field of safe operation of power systems, and specifically relates to a method, device, electronic device and storage medium for predicting the limit transmission capacity of a power transmission section of a power system. Background Art

[0002] The power system is one of the largest energy systems. In the traditional way, system monitoring, safety analysis and system control are the three most important steps for dispatchers to maintain the safety and stability of the power system. Through system monitoring, dispatchers can obtain the latest information of the power system in real time and directly determine whether the current power system is in normal operation. Then, through safety analysis, the current operation of the power system is estimated, and the weak links that may appear in the power system under potential operation scenarios are detected based on the current operation scenario, mainly considering the N-1 fault situation. Finally, when the power system is judged to be in an abnormal situation, or a weak link appears in the potential operation scenario, the dispatcher needs to perform corresponding dispatch control to avoid safety problems in the power system. Complex power systems have a large number of operating states, and dispatchers cannot monitor them globally. The staff of the power system dispatch center usually pays attention to a series of transmission sections in the process of compiling the operation mode, formulating the stability limit and monitoring the dispatch station. The section that is more likely to exceed the limit is calculated and monitored. In the power system safety assessment, the evaluation of the total transfer capacity (TTC) of the transmission section is one of the most core links.

[0003] Data-driven methods have shown faster calculation speed and higher fitting accuracy in the problem of TTC assessment of transmission sections, and have been increasingly used in the problem of TTC assessment in recent years. However, most of the existing TTC assessment models based on data-driven methods have two major problems: first, the generalization ability of a single model is insufficient when facing a large number of complex and changeable operating scenarios; second, there is a contradiction between the accuracy of the model and its interpretability. The more accurate the model, such as the deep model, the worse its interpretability is, and it is difficult for on-site operators to understand and accept it, while simple models such as linear models have the problem of insufficient accuracy. Summary of the invention

[0004] In view of this, the present disclosure proposes a method, device, electronic device and storage medium for predicting the ultimate transmission capacity of a power system transmission section. Based on the power system big data, the power system operation status is clustered in the neighborhood and a fine rule model within the neighborhood is fitted, so that the transmission section TTC can be predicted.

[0005] According to a first aspect of the present disclosure, a method for predicting the transmission section limit transmission capacity of a power system is proposed, comprising:

[0006] Determine a sample set of labels for characterizing the operation state of the power system and the limit transmission capacity of a given transmission section;

[0007] Perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set;

[0008] Fit the neighborhood sample set with fine rules to obtain the neighborhood fine rules of the power system transmission section;

[0009] The ultimate transmission capacity of a given transmission section of the power system is predicted by using the refined neighborhood rules of the power system transmission section.

[0010] Optionally, the determining of a sample set S for characterizing the operation state of the power system and the limit transmission capacity label of a given transmission section includes:

[0011] (1) Collecting power system operation status data from the power system monitoring device to form a feature data vector x for characterizing the power system operation status, x = [x l ,x b ], where x l represents the AC line active power flow characteristic vector in the power system, x b Represents the power flow state characteristic vector corresponding to other equipment in the power system, x is the characteristic vector;

[0012] (2) For x l and x b After standardization, a sample set S of labels for characterizing the operation status of the power system and the limit transmission capacity of a given transmission section is obtained.

[0013] Optionally, performing two-stage clustering on a large number of power system operation status samples to obtain a neighborhood sample set includes:

[0014] (1) Perform the first stage of topological clustering;

[0015] (2) Based on the power flow state characteristic vector x corresponding to other equipment in the power system b , using the k-means clustering method, the k1 power system operating states obtained in step (2-1) are clustered and secondary clustering is performed in turn.

[0016] (3) Matching the samples in the power system operation status sample set with the neighborhood operation status set one by one to obtain a neighborhood sample set Where u is the label of the first cluster and v is the label of the second cluster.

[0017] Optionally, a first stage topological clustering is performed, including:

[0018] (1) Define the interruption transfer distribution factor of any AC line l in the power system to another AC line k after it is interrupted;

[0019] (2) According to the definition of step (1), the breaking transfer distribution factor of each AC line in the power system except the line in the section is traversed to the line in the section, and the breaking transfer distribution factor of all AC lines to another AC line after they are broken in sequence is calculated. All the breaking transfer distribution factors are summed to obtain the breaking transfer distribution factor of the line to the section.

[0020] (1-3) According to the active power flow characteristic vector x of the power system AC line l and the line section disconnection transfer distribution factor Construct a topological representation vector set x for the first stage clustering topo :If the operating state of the i-th power system but If the operating state of the i-th power system but

[0021] (1-4) According to the topological representation vector set x topo ,The k-means clustering algorithm is used to cluster the power system operation status at the topological level.

[0022] Optionally, perform secondary clustering, including:

[0023] (1) Cluster the jth operating state based on the power flow state feature vector x b , draw the second cluster number-silhouette coefficient curve in sequence, j=1~k1;

[0024] (2) The number of clusters corresponding to the maximum silhouette coefficient of the silhouette coefficient curve corresponding to the number of second clusters under the jth primary cluster in step (1) is taken as the number of secondary clusters of the jth primary cluster, denoted as

[0025] (3) performing k-means clustering on the power system operating state in the jth primary clustering result of step (2), wherein the number of clusters is set to the number of secondary clusters obtained in step (2), and obtaining a secondary cluster label corresponding to each operating state;

[0026] (4) The set of power system operating states contained in each secondary cluster is called a neighborhood operating state set, denoted by C uv , where u is the label of the first cluster and v is the label of the second cluster.

[0027] Optionally, performing fine rule fitting on the neighborhood sample set to obtain the fine rules corresponding to the power system transmission section in each neighborhood includes:

[0028] (1) Feature selection is performed on the input features of each neighborhood sample set, including:

[0029] (1-1) For each of the neighborhood sample sets, respectively calculate the maximum information coefficient value between each dimension feature and the label;

[0030] (1-2) Arrange the maximum information coefficient values ​​corresponding to each dimension feature in descending order, take the features corresponding to the highest 5 information coefficient values ​​as the result of feature selection, and form a neighborhood sample set after feature selection. The sample corresponding to the i-th power system operation state in each neighborhood sample set is recorded as (P TTCi ; x″ (i) ), where x″ (i) is x′ (i) Feature vector after feature selection;

[0031] (2) Fitting fine rules to the neighborhood sample set after feature selection, the steps are as follows:

[0032] (2-1) The form of the fine rule model is set as the following linear model:

[0033]

[0034] Among them, c0 is the constant term of the linear model, c r For the feature x″ r The corresponding regularity coefficient;

[0035] (2-2) Using the least squares method, the constant term and each rule coefficient of the linear fine rule are fitted on the neighborhood sample set after each feature selection, and the fine rule corresponding to the power system transmission section in each neighborhood is obtained.

[0036] Optionally, the use of the power system transmission section neighborhood refined rule to predict the transmission section limit transmission capacity of a given power system transmission section is as follows:

[0037] (1) The current operating status of the power system is collected from the power system monitoring device and a feature vector is formed. The power system feature vector is preprocessed using a step data preprocessing method;

[0038] (2) Calculate the Euclidean distance between the feature vector of the current running state and the center of each neighborhood sample, where the neighborhood sample center is defined as the vector formed by taking the mean of the sample set for each dimension of the sample feature;

[0039] (3) The neighborhood closest to the feature vector of the current operating state is taken as the neighborhood corresponding to the current operating state, and the features required in the current neighborhood fine rule are extracted from the feature vector and input into the current neighborhood fine rule model to obtain the predicted value of the limit transmission capacity of a given transmission section of the power system.

[0040] According to a second aspect of the present disclosure, a device for predicting the transmission section limit transmission capacity of a power system is provided, comprising:

[0041] A sample generation module, used for determining a sample set for characterizing the operation state of the power system and the limit transmission capacity label of a given transmission section;

[0042] The operation status clustering module is used to perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set;

[0043] A fine rule fitting module is used to fit fine rules to the neighborhood sample set to obtain fine rules for the neighborhood of the power system transmission section;

[0044] The limit transmission capacity prediction module is used to predict the limit transmission capacity of a given transmission section of the power system by using the fine rules of the neighborhood of the power system transmission section.

[0045] According to a third aspect of the present disclosure, an electronic device for predicting the transmission capacity limit of a power system transmission section is provided, comprising a memory and a processor; wherein:

[0046] Memory: used to store instructions executable by the processor;

[0047] Processor: The processor is configured to perform:

[0048] Determine a sample set of labels for characterizing the operation state of the power system and the limit transmission capacity of a given transmission section;

[0049] Perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set;

[0050] Fit the neighborhood sample set with fine rules to obtain the neighborhood fine rules of the power system transmission section;

[0051] The ultimate transmission capacity of a given transmission section of the power system is predicted by using the refined neighborhood rules of the power system transmission section.

[0052] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program is used to cause the computer to execute:

[0053] Determine a sample set of labels for characterizing the operation state of the power system and the limit transmission capacity of a given transmission section;

[0054] Perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set;

[0055] Fit the neighborhood sample set with fine rules to obtain the neighborhood fine rules of the power system transmission section;

[0056] The ultimate transmission capacity of a given transmission section of the power system is predicted by using the refined neighborhood rules of the power system transmission section.

[0057] The method, device, electronic device and storage medium for predicting the transmission capacity limit of the power system transmission section proposed in the present disclosure adopt two-stage clustering, which can divide the complex and changeable massive power system operation status into neighborhoods. By using multiple neighborhood models, the generalization ability of the model library in the power system operation status space is improved; the neighborhood fine rules are adopted in the present disclosure, and the operation scenario TTC in the neighborhood can be fitted with high accuracy using a simple linear model, and the model has strong interpretability. The present disclosure can be applied to the field of power system security assessment, improve the accuracy and robustness of security assessment, provide scheduling basis for power system operation and dispatching personnel, and improve the safety of power system dispatching. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a framework diagram of the power system transmission section limit transmission capacity prediction device proposed in the present disclosure. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0060] The method for predicting the transmission capacity limit of a power system transmission section shown in this embodiment can be applied to power system safety assessment equipment, such as equipment for setting section limits at the power system operation mode, real-time monitoring equipment for dispatchers, etc.

[0061] In step 1, a sample set of labels for characterizing the operation state of the power system and the limit transmission capacity of a given transmission section is determined.

[0062] In one embodiment, a specific process of determining a sample set for characterizing the operation state of the power system and the limit transmission capacity label of a given transmission section includes:

[0063] (1) Collecting power system operation status data from the power system monitoring device to form a feature data vector x for characterizing the power system operation status, x = [x l ,x b ], where x l represents the AC line active power flow characteristic vector in the power system, x b Represents the power flow state characteristic vector corresponding to other equipment in the power system, x is the characteristic vector;

[0064] x is constructed as follows:

[0065] (1-1-1) Power system AC line active power flow characteristic vector x l The specific composition is:

[0066]

[0067] in, represents the active power flow of the sth AC line in the power system, and the subscript m is the total number of AC lines in the power system;

[0068] (1-1-2) The power flow state characteristic vector x corresponding to other equipment in the power system b The specific composition is:

[0069]

[0070] in, is the fth power system power flow state characteristic quantity in the power system operation state. The power system power flow state characteristic quantity is composed of the generator active power, generator reactive power, generator terminal voltage amplitude, load node active power, load node reactive power and bus phase angle. The subscript p is the total number of system power flow state characteristic quantities.

[0071] (2) To avoid dependence on measurement units, x l and x b Standardization is performed to obtain a sample set S for characterizing the operation status of the power system and the limit transmission capacity label of a given transmission section. The specific steps are as follows:

[0072] (1-2-1) Calculate the mean absolute error of all active power flow characteristics of the sth power system AC line

[0073]

[0074] Wherein, N is the number of samples of the power system operating status collected in step (1-1), is the active power flow characteristic quantity of the AC line of the sth power system under the i-th operating state sample of the power system collected in step (1-1), m s is the average value of the active power flow characteristic quantity of the AC line of the sth power system;

[0075] (1-2-2) Calculate the mean absolute error of all power flow state characteristic quantities corresponding to other equipment in the fth power system

[0076]

[0077] Wherein, N is the number of samples of the power system operating status collected in step (1-1), is the power flow state characteristic quantity corresponding to the fth power system other equipment under the i-th operation state sample of the power system collected in step (1-1), m f is the average value of the power flow state characteristic quantity corresponding to other equipment in the f-th power system;

[0078] (1-2-3) For step (1-2-1) Standardize it, and record it as

[0079]

[0080] (1-2-4) For step (1-2-2) Standardize it, and record it as

[0081]

[0082] (1-2-5) According to the sample mean absolute error calculation in step (1-2-1) and the standardization method in step (1-2-3), the standardized AC line active power flow characteristic vector of the i-th power system operation state is obtained:

[0083]

[0084] (1-2-6) According to the sample mean absolute error calculation in step (1-2-2) and the standardization method in step (1-2-4), the power flow state vector corresponding to other devices in the i-th power system operation state after standardization is obtained:

[0085]

[0086] (1-2-7) The power system AC line active power flow characteristic vector standardized in step (1-2-5) is combined with the power flow state vector corresponding to other power system equipment standardized in step (1-2-6) to form a standardized power system operation state characteristic vector i

[0087] (1-2-8) Using the simulation tool PSASP and the repeated power flow method, the limit transmission capacity P of the section corresponding to the i-th power system operation state is calculated. TTCi , the limit transmission capacity P TTCi as the label corresponding to the feature vector of the i-th power system operating state;

[0088] (1-2-9) According to step (1-2-7) and the limit transmission capacity P of step (1-3) TTCi , forming a sample corresponding to the operating state of the i-th power system (P TTCi ; x′ (i) );

[0089] (1-2-10) Traverse all samples collected in step (1-1), repeat the operations from step (1-2-3) to step (1-2-9), and obtain a sample set S consisting of all samples.

[0090] In step 2, a two-stage clustering is performed on massive power system operating status samples to obtain a neighborhood sample set.

[0091] In one embodiment, a two-stage clustering is performed on a large number of power system operation status samples to obtain a neighborhood sample set, including:

[0092] (1) Perform the first stage of topological clustering:

[0093] (1-1) Define the disconnection transfer distribution factor of another AC line k after any AC line l is disconnected in the power system (l, k are arbitrary variables):

[0094]

[0095] Among them, D k-l is the breaking transfer distribution factor of AC line l to line k in section, P l is the active power flow before the AC line l is disconnected, which can be obtained by measurement, ΔP k is the change in active power flow of line k in the section before and after line l is disconnected, which can be calculated by the simulation tool PSASP based on the disconnection power flow method;

[0096] (1-2) According to the definition in step (2-1-1), the breaking transfer distribution factor of each AC line in the power system except the line in the section is traversed to the line in the section, and the breaking transfer distribution factor of all AC lines to another AC line after being broken in sequence is calculated. All breaking transfer distribution factors are summed to obtain:

[0097]

[0098] in is the breaking transfer distribution factor of the AC line l to the section, and g is the AC line in the section;

[0099] (1-3) According to the power system AC line active power flow characteristic vector x in step (1-1-1) l and the line section disconnection transfer distribution factor obtained in step (2-1-2) Construct a topological representation vector set x for the first stage clustering topo :If the operating state of the i-th power system but If the operating state of the i-th power system but

[0100] (1-4) According to the topological representation vector set x of step (2-1-3) topo , the k-means clustering algorithm is used to cluster the power system operation status at the topological level, including the following steps:

[0101] (1-4-1) Set the horizontal axis to the number of clusters, with a value ranging from 2 to 15, and the vertical axis to the silhouette coefficient. With the number of clusters as the horizontal axis and the silhouette coefficient under the current number of clusters as the vertical axis, draw a cluster number-silhouette coefficient curve to obtain the first cluster number-silhouette coefficient curve;

[0102] (1-4-2) The number of clusters corresponding to the maximum silhouette coefficient in the cluster number-silhouette coefficient curve is taken as the number of clusters in the k-means algorithm, denoted as k1;

[0103] (1-4-3) The topological representation vector set x of the power system operation status topo Perform k-means clustering on all topological representation vectors in , obtain the topological clustering labels corresponding to each operating state, and form k1 power system operating state primary clustering;

[0104] (2) Based on the power flow state characteristic vector x corresponding to other equipment in the power system b , using the k-means clustering method, the k1 power system operation status clusters obtained in step (2-1) are clustered again in turn, including the following steps:

[0105] (2-1) Cluster the jth operating state according to the method of step (2-1-4-1), based on the power flow state characteristic vector x b , draw the second cluster number-silhouette coefficient curve in sequence, j=1~k1;

[0106] (2-2) The number of clusters corresponding to the maximum silhouette coefficient of the second cluster number of step (2-2-1)-silhouette coefficient curve corresponding to the j-th primary clustering in step (2-2-1) is taken as the number of secondary clusters of the j-th primary clustering, denoted as

[0107] (2-3) performing k-means clustering on the power system operating state in the j-th primary clustering result of step (2-2-2), setting the number of clusters to the number of secondary clusters obtained in (2-2-2), and obtaining a secondary cluster label corresponding to each operating state;

[0108] (2-4) The set of power system operating states contained in each secondary cluster is called a neighborhood operating state set, denoted by C uv , where u is the label of the first cluster and v is the label of the second cluster;

[0109] (3) Match the samples in the power system operation status sample set obtained in step (1) with the neighborhood operation status set obtained in (2-2) one by one to obtain the neighborhood sample set Where u is the label of the first cluster and v is the label of the second cluster.

[0110] In step 3, fine rules are fitted on the neighborhood sample set to obtain fine neighborhood rules for the power system transmission section.

[0111] In one embodiment, fine rule fitting is performed on the neighborhood sample set to obtain fine rules corresponding to the power system transmission section in each neighborhood, including:

[0112] (1) Feature selection is performed on the input features of each neighborhood sample set, including the following steps:

[0113] (1-1) For each of the neighborhood sample sets, a maximum information coefficient calculation method is used to calculate the maximum information coefficient value between each dimensional feature and the label;

[0114] (1-2) Arrange the maximum information coefficient values ​​corresponding to each dimension feature in descending order, take the features corresponding to the highest 5 information coefficient values ​​as the result of feature selection, and form a neighborhood sample set after feature selection. The sample corresponding to the i-th power system operation state in each neighborhood sample set is recorded as (P TTCi ; x″(i) ), where x″ (i) is x′ (i) Feature vector after feature selection;

[0115] (2) Fitting fine rules to the neighborhood sample set after feature selection, the steps are as follows:

[0116] (2-1) The form of the fine rule model is set as the following linear model:

[0117]

[0118] Among them, c0 is the constant term of the linear model, c r For the feature x″ r The corresponding regularity coefficient is obtained by fitting in step (2-2);

[0119] (2-2) Using the least squares method, the constant term and each rule coefficient of the linear fine rule are fitted on each neighborhood sample set after feature selection obtained in step (1), and the fine rule corresponding to the power system transmission section in each neighborhood is obtained.

[0120] In step 4, the power system transmission section neighborhood refinement rule is used to predict the ultimate transmission capacity of a given transmission section of the power system.

[0121] In one embodiment, using the fine rules of the neighborhood of power system transmission sections, the transmission section limit transmission capacity prediction of a given power system transmission section is performed, including:

[0122] (1) The current operating status of the power system is collected from the power system monitoring device, and the power flow state quantity of the AC line and the power flow state quantity of other equipment are respectively extracted to form a feature vector, and the power system feature vector is preprocessed using a data preprocessing method of data standardization;

[0123] (2) Calculate the Euclidean distance between the feature vector of the current running state and the center of each neighborhood sample, where the neighborhood sample center is defined as the vector formed by taking the mean of the sample set for each dimension of the sample feature;

[0124] (3) The neighborhood closest to the feature vector of the current operating state is taken as the neighborhood corresponding to the current operating state, and the features required in the current neighborhood fine rule are extracted from the feature vector, and input into the current neighborhood fine rule model to obtain the predicted value of the limit transmission capacity of the given transmission section of the power system.

[0125] In the embodiments of the present invention, a method for generating fine neighborhood rules for power system transmission sections based on two-stage clustering is adopted, which can divide the complex and changeable operating state of the power system into neighborhoods, so that the operating states within the neighborhoods are similar, and obtain the fine TTC calculation rules within the neighborhoods by fitting linear models, taking into account the interpretability and high accuracy of the model, and can provide on-site dispatchers with interpretable control auxiliary information.

[0126] Corresponding to the above-mentioned embodiment of the method for predicting the transmission section limit transmission capacity of the power system, the present disclosure also proposes an embodiment of a device for predicting the transmission section limit transmission capacity of the power system. The framework diagram of the embodiment is shown in FIG. Figure 1 As shown, including:

[0127] A sample generation module, used for determining a sample set for characterizing the operation state of the power system and the limit transmission capacity label of a given transmission section;

[0128] The operation status clustering module is used to perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set;

[0129] A fine rule fitting module is used to fit fine rules to the neighborhood sample set to obtain fine rules for the neighborhood of the power system transmission section;

[0130] The limit transmission capacity prediction module is used to predict the limit transmission capacity of a given transmission section of the power system by using the fine rules of the neighborhood of the power system transmission section.

[0131] The embodiment of the present disclosure also provides an electronic device for predicting the transmission section limit transmission capacity of a power system, including a memory and a processor; wherein:

[0132] Memory: used to store instructions executable by the processor;

[0133] Processor: The processor is configured to perform:

[0134] Determine a sample set of labels for characterizing the operation state of the power system and the limit transmission capacity of a given transmission section;

[0135] Perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set;

[0136] Fit the neighborhood sample set with fine rules to obtain the neighborhood fine rules of the power system transmission section;

[0137] The ultimate transmission capacity of a given transmission section of the power system is predicted by using the refined neighborhood rules of the power system transmission section.

[0138] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to cause the computer to execute:

[0139] Determine a sample set of labels for characterizing the operation state of the power system and the limit transmission capacity of a given transmission section;

[0140] Perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set;

[0141] Fit the neighborhood sample set with fine rules to obtain the neighborhood fine rules of the power system transmission section;

[0142] The ultimate transmission capacity of a given transmission section of the power system is predicted by using the refined neighborhood rules of the power system transmission section.

[0143] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0144] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0145] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: receives a request from a first user to configure boot information for the access party software; provides a configuration page for the first user according to the request; obtains the display conditions and display location information set by the first user for the boot information on the configuration page; saves the display conditions and display location information of the boot information in the boot configuration system; and when it is monitored that the operation of the access party software meets the display conditions, controls the access party software to display the boot information according to the display location information.

[0146] Alternatively, the computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device: receives a request from a first user to configure boot information for the access party software; provides a configuration page for the first user based on the request; obtains display conditions and display location information set by the first user for the boot information on the configuration page; saves the display conditions and display location information of the boot information in the boot configuration system; and when it is monitored that the operation of the access party software meets the display conditions, controls the access party software to display the boot information based on the display location information.

[0147] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0148] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0149] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0150] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0151] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or otherwise processing in a suitable manner if necessary, and then stored in a computer memory.

[0152] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0153] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0154] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0155] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for predicting the transmission capacity limit of a power system transmission section, characterized in that The method includes: Determine a sample set of labels for characterizing the operation state of the power system and the limit transmission capacity of a given transmission section; Perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set; Fit the neighborhood sample set with fine rules to obtain the neighborhood fine rules of the power system transmission section; Use the fine rules of the power system transmission section neighborhood to predict the ultimate transmission capacity of a given power system transmission section; The method of determining a sample set for characterizing the operation state of the power system and the limit transmission capacity label of a given transmission section includes: (1-1) Collect power system operation status data from the power system monitoring device to form a feature data vector used to characterize the power system operation status , ,in, represents the AC line active power flow characteristic vector in the power system, Represents the power flow state characteristic vector corresponding to other equipment in the power system, x is the feature vector; (1-2) Yes and Standardization is performed to obtain a sample set of labels for characterizing the operating status of the power system and the limit transmission capacity of a given transmission section. S ; The two-stage clustering of massive power system operation status samples to obtain a neighborhood sample set includes: (2-1) Perform the first stage of topological clustering; (2-2) Based on the power flow state characteristic vector corresponding to other equipment in the power system , using the k-means clustering method, the k 1 power system operation status clustering, and then secondary clustering; including the following steps: (2-2-1) For j Running state clustering, based on the power flow state feature vector , and draw the second cluster number-silhouette coefficient curve in turn, j =1~ k 1; (2-2-2) Replace step (2-2-1) with j The number of clusters corresponding to the second clustering number of the step (2-2-1) under the first clustering - the number of clusters corresponding to the maximum silhouette coefficient of the silhouette coefficient curve is taken as the first j The number of secondary clusters of the first cluster is denoted by ; (2-2-3) For step (2-2-2) j Perform k-means clustering on the power system operating states in the first clustering results, and set the number of clusters to the number of second clusters obtained in (2-2-2), and obtain the second cluster label corresponding to each operating state; (2-2-4) The set of power system operating states contained in each secondary cluster is called a neighborhood operating state set, denoted as ,in u is the label of a cluster, v is the label of the secondary clustering; The first stage of topological clustering includes: (2-1-1) Define any AC line in the power system l After disconnecting, connect another AC line k The breaking transfer distribution factor; (2-1-2) According to the definition of step (2-1-1), traverse the disconnection transfer distribution factor of each AC line in the power system except the line in the section to the line in the section, calculate the disconnection transfer distribution factor of another AC line after all AC lines are disconnected in sequence, sum up all the disconnection transfer distribution factors, and obtain the line to section disconnection transfer distribution factor ; (2-1-3) According to the active power flow characteristic vector of the AC line of the power system and the line section disconnection transfer distribution factor , construct a set of topological representation vectors for the first stage clustering : If i The operating status of the power system ,but , i The operating status of the power system ,but ; (2-1-4) According to the topological representation vector set , the k-means clustering algorithm is used to cluster the power system operation status at the topological level; (2-3) Matching the samples in the power system operation status sample set with the neighborhood operation status set one by one to obtain a neighborhood sample set ,in u is the label of a cluster, v is the label of the secondary clustering; The method of performing fine rule fitting on the neighborhood sample set to obtain the fine rules corresponding to the power system transmission section in each neighborhood includes: (3-1) Feature selection is performed on the input features of each neighborhood sample set, including: (3-1-1) For each of the neighborhood sample sets, the maximum information coefficient value between each dimension feature and the label is calculated respectively; (3-1-2) Arrange the maximum information coefficient values ​​corresponding to each dimension feature in descending order, take the features corresponding to the five highest information coefficient values ​​as the result of feature selection, and form the neighborhood sample set after feature selection. i The sample corresponding to the power system operation state is recorded as ,in, for Feature vector after feature selection; (3-2) Fitting fine rules to the neighborhood sample set after feature selection, the steps are as follows: (3-2-1) The form of the fine rule model is set as the following linear model: in, is the constant term of the linear model, For and Features The corresponding regularity coefficient; (3-2-2) Using the least squares method, on each of the neighborhood sample sets after feature selection, the constant term and each rule coefficient of the linear fine rule are fitted to obtain the fine rule corresponding to the power system transmission section in each neighborhood; The power system transmission section neighborhood fine rule is used to predict the limit transmission capacity of a given transmission section of the power system as follows: (4-1) Collecting the current operating status of the power system from the power system monitoring device and forming a feature vector, and preprocessing the power system feature vector using a data preprocessing method of data standardization; (4-2) Calculate the Euclidean distance between the feature vector of the current running state and the center of each neighborhood sample, where the neighborhood sample center is defined as the vector formed by taking the mean of the sample set for each dimension of the sample feature; (4-3) The neighborhood closest to the feature vector of the current operating state is taken as the neighborhood corresponding to the current operating state, the features required in the current neighborhood fine rule are extracted from the feature vector, and the features are input into the current neighborhood fine rule model to obtain the predicted value of the limit transmission capacity of the given transmission section of the power system.

2. A device for predicting the transmission section limit transmission capacity of a power system using the method as claimed in claim 1, characterized in that include: A sample generation module, used for determining a sample set for characterizing the operation state of the power system and the limit transmission capacity label of a given transmission section; The operation status clustering module is used to perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set; A fine rule fitting module is used to fit fine rules to the neighborhood sample set to obtain fine rules for the neighborhood of the power system transmission section; The limit transmission capacity prediction module is used to predict the limit transmission capacity of a given transmission section of the power system by using the fine rules of the neighborhood of the power system transmission section.

3. An electronic device for predicting the transmission capacity limit of a power system transmission section, characterized in that The method comprises a memory and a processor; and is used to execute the method for predicting the transmission section limit transmission capacity of the power system according to claim 1, wherein: Memory: used to store instructions executable by the processor; Processor: The processor is configured to perform: Determine a sample set of labels for characterizing the operation state of the power system and the limit transmission capacity of a given transmission section; Perform two-stage clustering on massive power system operation status samples to obtain a neighborhood sample set; Fit the neighborhood sample set with fine rules to obtain the neighborhood fine rules of the power system transmission section; The ultimate transmission capacity of a given transmission section of the power system is predicted using the refined neighborhood rules of the power system transmission section.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to enable the computer to execute the method for predicting the limit transmission capacity of the power system transmission section according to claim 1.

Citation Information

Patent Citations

  • Power system transmission section limit probability evaluation method and electronic equipment

    CN112632846A

  • Available power transmission capability probability calculation method considering wind power correlation

    CN112736914A