An intelligent control method and system based on a high-voltage substation and an electronic device

Abstract

The application discloses an intelligent control method and system based on a high-voltage transformer substation and electronic equipment, the method comprising the following steps: reading corresponding recording wave data from a database in response to a pre-warning message sent by a region to be monitored, so as to determine a recording wave feature vector set according to the recording wave data; selecting Q initial populations from M groups of original data at any time based on each feature in the recording wave feature vector set; initializing the number of iterations, calculating the fitness value of each individual in each initial population based on a target function; outputting the individual with the highest fitness value as the optimal individual of the current population through genetic selection, so as to determine one or more elements associated with the optimal individual; marking a fault or a risk according to the number of elements; and controlling the disconnection of a fault element or a line to troubleshoot the fault element or the fault line. The application can retain elements with higher risk probabilities, and eliminate calculation errors and complexity caused by recording wave data redundancy.

Description

Technical Field

[0001] This invention belongs to the field of power grid fault prediction, specifically relating to an intelligent control method, system, and electronic equipment based on high-voltage substations. Background Technology

[0002] Fault recorders can record the electrical quantities of various disturbance components before and after a power grid fault over a continuous period of time. From these time-continuous record data, various fault characteristic quantities can be extracted, and the extracted characteristic quantities can indicate the operating status of power grid components.

[0003] Existing waveform recorders generally suffer from data redundancy and incompleteness. Specifically, a single waveform recorder typically collects electrical quantity data from multiple components, and adjacent or spaced-apart components may also be recorded. This can lead to data redundancy, meaning the recorder may record data from other components unrelated to the one it needs to record, while other recorders simultaneously record data they don't need to record, resulting in data redundancy and necessitating data deduplication during subsequent data processing. However, existing methods are ineffective at removing redundant data for analysis, thus hindering fault analysis. Summary of the Invention

[0004] To address the aforementioned problems in the existing technology, this invention provides an intelligent control method, system, and electronic equipment based on high-voltage substations. The technical problem to be solved by this invention is achieved through the following technical solution:

[0005] A smart control method based on high-voltage substations includes:

[0006] In response to an early warning message sent from the area to be monitored, the corresponding waveform data is read from the database to determine the waveform feature vector set based on the waveform data. The area to be monitored includes N components, the waveform data includes M sets of raw data, and the waveform feature vector set includes: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features.

[0007] Based on each feature in the waveform feature vector set, Q features are selected from the M sets of original data at any time as the initial population, and each individual in the initial population is associated with one or more elements.

[0008] Initialize the number of iterations, and calculate the fitness value of each individual in each initial population based on the objective function;

[0009] Select any two parent individuals from the initial population and pair them up. Perform crossover or mutation operations on the paired parent individuals until each parent individual has been paired up to obtain offspring individuals.

[0010] In response to the fulfillment of the iteration termination condition, the individual with the highest fitness value is selected as the optimal individual of the current population and output, so as to determine one or more associated elements based on the optimal individual;

[0011] In response to each feature identifying one or more associated components, components that appear at least 5 times are marked as faulty components or lines; lines that appear 2-5 times are marked as risky components or lines; lines that appear once are not marked.

[0012] The faulty component or line is disconnected to troubleshoot the faulty component or line.

[0013] In one specific implementation, any two parent individuals are selected from the initial population and paired up to perform crossover or mutation operations on the paired parent individuals, including:

[0014] Generate the first random number and set the mutation threshold;

[0015] Compare the relationship between the first random number and the mutation threshold. If the first random number is greater than the mutation threshold, then perform a crossover operation on the two parent individuals in the current population; if the first random number is less than or equal to the mutation threshold, then perform a mutation operation on the two parent individuals in the current population.

[0016] In one specific implementation, performing a crossover operation on two parent individuals within the current population includes:

[0017] Find the related elements of two parent individuals. If the two parent individuals have the same element, keep the same element and do not perform the crossover operation. Then, randomly swap one element from the parent individuals other than the same element to complete the crossover operation.

[0018] In one specific implementation, performing a mutation operation on two parent individuals within the current population includes:

[0019] Find the elements that are related between two parent individuals. If the two parent individuals have the same element, retain the same element and do not perform a mutation operation.

[0020] Generate a sample of mutated elements, wherein the sample of mutated elements is the element that exists in the parent individual but is removed from the set of N elements.

[0021] The mutation operation is completed by randomly replacing one element from the parent individual (excluding the identical elements) with any one of the mutated element samples.

[0022] In one specific implementation, the objective function is:

[0023]

[0024]

[0025]

[0026] Where X represents the set of selected elements X = {x1, x2, ..., x...} N}, x i Let N represent the i-th selected element, N represent the total number of selected elements, H(·) represent the information entropy, and D represent the information entropy. KLS (·) represents the symmetric KL divergence.

[0027] This invention also provides an intelligent control system based on a high-voltage substation, comprising:

[0028] The data acquisition module is used to respond to the early warning message sent by the area to be monitored, read the corresponding waveform data from the database, and determine the waveform feature vector set based on the waveform data. The area to be monitored includes N components, the waveform data includes M sets of raw data, and the waveform feature vector set includes: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features.

[0029] The initial population selection module is used to select Q individuals from M sets of original data as an initial population at any time based on the recorded feature vector set, wherein each individual in the initial population is associated with one or more elements;

[0030] The initialization module is used to initialize the number of iterations and calculate the fitness value of each individual in the initial population based on the objective function.

[0031] The crossover and mutation module is used to select any two parent individuals from the initial population and pair them up to perform crossover or mutation operations on the paired parent individuals until each parent individual has been paired up to obtain offspring individuals.

[0032] The iterative output module is used to select the individual with the highest fitness value as the optimal individual of the current population and output it in response to the fulfillment of the iteration termination condition, so as to determine one or more associated elements based on the optimal individual;

[0033] The risk determination module is used to identify one or more associated components for each feature, mark components that appear at least 5 times as faulty components or lines; mark lines that appear 2-5 times as risky components or lines; and leave lines that appear once unmarked.

[0034] The control module is used to control the disconnection of the risky component or risky line in order to troubleshoot the faulty component or faulty line.

[0035] In one specific implementation, the crossover mutation module includes:

[0036] A random number generation unit is used to generate a first random number and set a mutation threshold.

[0037] The crossover and mutation unit is used to compare the relationship between the first random number and the mutation threshold. If the first random number is greater than the mutation threshold, a crossover operation is performed on the two parent individuals in the current population. If the first random number is less than or equal to the mutation threshold, a mutation operation is performed on the two parent individuals in the current population.

[0038] In one specific embodiment, the crossover mutation unit includes:

[0039] The crossover subunit is used to find the associated elements of two parent individuals. If the two parent individuals have the same element, the same element is retained without crossover operation, and one element from the parent individuals other than the same element is randomly swapped to complete the crossover operation.

[0040] In one specific embodiment, the crossover mutation unit includes:

[0041] The mutation subunit is used to find the elements associated with two parent individuals. If the two parent individuals have the same element, the same element is retained and no mutation operation is performed. A mutation element sample is generated, wherein the mutation element sample is the element that exists in the parent individual but not in the set of N elements. A random element in the parent individual except for the same element is replaced with any one of the mutation element samples, thereby completing the mutation operation.

[0042] This invention also provides an electronic device, characterized in that it comprises:

[0043] The system consists of a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus.

[0044] Memory, used to store computer programs;

[0045] The processor, when executing the program stored in the memory, implements the above-mentioned intelligent control method based on high-voltage substations.

[0046] The beneficial effects of this invention are:

[0047] The intelligent control method for high-voltage substations of the present invention retains common components through cross-mutation operations, which enables the retention of components with higher risk probabilities, thereby eliminating the calculation errors and complexity caused by the redundancy of waveform data. In addition, in order to ensure the accuracy of fault risk, the present invention predicts each feature quantity in the waveform feature vector set separately and performs an overall evaluation based on the prediction results to avoid misjudgment.

[0048] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0049] Figure 1 This is a schematic diagram of a smart control method based on a high-voltage substation provided in an embodiment of the present invention;

[0050] Figure 2 This is a block diagram of an intelligent control system module based on a high-voltage substation provided in an embodiment of the present invention;

[0051] Figure 3 This is a block diagram of an electronic device module provided in an embodiment of the present invention. Detailed Implementation

[0052] The present invention will be further described in detail below with reference to specific embodiments, but the implementation of the present invention is not limited thereto.

[0053] Example 1

[0054] Please see Figure 1 , Figure 1 This is a schematic flowchart of an intelligent control method based on a high-voltage substation provided by an embodiment of the present invention, including:

[0055] S11. In response to the early warning message sent by the area to be monitored, read the corresponding waveform data from the database to determine the waveform feature vector set based on the waveform data. The area to be monitored includes N components, the waveform data includes M sets of raw data, and the waveform feature vector set includes: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features.

[0056] Waveform data is recorded by a waveform recorder. Generally, the waveform recorder begins acquiring analog signal information for waveform recording immediately upon startup. During waveform recording, the recorder has five operational requirements: 1. Recording the analog signal state before a major power grid disturbance; 2. Recording the initial information after a major system disturbance; 3. Recording the mid-term state information after a power system fault; 4. Recording the dynamic process of the power system; 5. Recording the dynamic data of the power system over a long period. In these five processes, waveform data sampling frequencies for steps 1-3 are high, typically at the millisecond (ms-s) level, while sampling frequencies for steps 4-5 are low, typically at the second (s-min) level. Because the waveform recorder, as a recorder, begins working upon startup, the amount of data generated for a power grid operating for extended periods is substantial. Therefore, current methods struggle to effectively utilize waveform data. It is generally only used after a fault occurs to examine the power grid's operating status before and after the fault, serving as a post-fault analysis tool to investigate the cause of the fault. Consequently, fault prediction is impossible, and therefore, intelligent control before accidents can not be achieved to prevent large-scale fault transmission.

[0057] The waveform data is recorded in the time domain. In this embodiment, feature quantities are extracted from the first waveform data to convert analog quantities into digital features, thereby forming a waveform feature vector set. Specifically, the waveform feature vector set includes: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features. The above features are generally extracted using full-wave Fourier transform, wavelet transform, Kirchhoff's laws, and other methods, which will not be elaborated here.

[0058] In one example, a waveform recording feature vector set with 7 elements is obtained based on the waveform recording data collected by the waveform recorder. Each vector feature in the waveform recording feature vector set corresponds to 200-500 sets of data. A waveform recorder detects one or more components in a monitored area. When a large power grid fluctuation occurs in the monitored area, an early warning message is sent to the background control terminal. The background control terminal then reads the waveform recording data of the corresponding waveform recorder based on the early warning message.

[0059] S12. Based on each feature in the waveform feature vector set, select Q from the M sets of original data as an initial population at any time. Each individual in the initial population is associated with one or more elements, where Q < M.

[0060] While ensuring the efficiency of the algorithm execution, select as much data as possible from the initial population. Ideally, 50 sets can be randomly selected from 200-500 sets of data for genetics.

[0061] S13. Initialize the number of iterations and calculate the fitness value of each individual in each initial population based on the objective function.

[0062] That is, the initial iteration count is 1. In order to retain as much useful individual information as possible and remove redundant individual information during the genetic process, the objective function in this embodiment is set as follows:

[0063]

[0064]

[0065]

[0066] Where X represents the set of selected elements X = {x1, x2, ..., x...} N}, x i Let N represent the i-th selected element, N represent the total number of selected elements, H(·) represent the information entropy, and D represent the information entropy. KLS (·) represents the symmetric KL divergence.

[0067] Information entropy measures the amount of information contained in a selected element; the higher the information entropy, the greater the amount of information contained in the selected element. Symmetric KL divergence D KLS (x i ||x j ) represents different components x i and x j The greater the difference between them, the larger the symmetric KL divergence indicates, the stronger the difference in x. i and x j The greater the difference between them, the greater the information entropy and the more components an individual contains. Conversely, the fewer components an individual contains, the less information redundancy and the smaller the information entropy. In this embodiment, minimizing both objective functions simultaneously ensures that as much useful individual information as possible is retained while removing redundant individual information.

[0068] S14. Select any two parent individuals from the initial population and pair them up. Perform crossover or mutation operations on the paired parent individuals until each parent individual has been paired up to obtain offspring individuals.

[0069] Specifically, any two parent individuals are selected from the initial population and paired up to perform crossover or mutation operations on the paired parent individuals, including:

[0070] Generate the first random number and set the mutation threshold;

[0071] Compare the relationship between the first random number and the mutation threshold. If the first random number is greater than the mutation threshold, then perform a crossover operation on the two parent individuals in the current population; if the first random number is less than or equal to the mutation threshold, then perform a mutation operation on the two parent individuals in the current population.

[0072] In the first iteration, all individuals in the initial population are used as parent individuals. When mutation or crossover occurs, two parent individuals are randomly selected to pair up until each parent individual has undergone crossover or mutation. Specifically, the first step is to determine whether to perform a crossover or mutation operation on two randomly selected individuals using a mutation threshold. The random number generation range is 0-1. The mutation threshold can be set according to specific circumstances. If the power grid network is relatively complex with excessive redundant information, a higher mutation threshold can be set, increasing the probability of mutation compared to the crossover probability. This prevents redundant data from being passed on to offspring through genetic inheritance. For example, a mutation threshold of 0.55-0.65 means that when the random number is greater than 0.65, a crossover operation is performed; when the random number is less than 0.65, a mutation operation is performed, resulting in a 65% mutation probability. Conversely, a lower mutation threshold can be set, allowing crossover to dominate. For example, a mutation threshold of 0.35-0.45 means that when the random number is greater than 0.35, a crossover operation is performed; when the random number is less than 0.35, a mutation operation is performed, resulting in a 35% mutation probability. In general networks, without special settings, the mutation threshold can be set to 0.5, meaning a 50% probability of mutation and a 50% probability of crossover.

[0073] During implementation, a crossover operation is performed on two parent individuals within the current population, including:

[0074] Find the related elements of two parent individuals. If the two parent individuals have the same element, keep the same element and do not perform the crossover operation. Then, randomly swap one element from the parent individuals other than the same element to complete the crossover operation.

[0075] First, iterate through the element sets of the two parent individuals. If a certain element exists in both parent individuals, it is retained as a dominant gene and will not be replaced by crossover. Then, crossover is performed on the elements other than the dominant gene element to obtain the offspring individuals.

[0076] Perform mutation operations on two parent individuals within the current population, including:

[0077] Find the elements that are related between two parent individuals. If the two parent individuals have the same element, retain the same element and do not perform a mutation operation.

[0078] Generate a sample of mutated elements, wherein the sample of mutated elements is the element that exists in the parent individual but is removed from the set of N elements.

[0079] The mutation operation is completed by randomly replacing one element from the parent individual (excluding the identical elements) with any one of the mutated element samples.

[0080] Similar to the crossover process described above, the component sets of the two parent individuals are first traversed. If a certain component exists in both parent individuals, it is retained as a dominant gene and will not be replaced by mutation. Then, the components other than the dominant gene component are mutated to obtain the offspring individuals. This method further ensures that high-probability components are retained and avoids redundancy.

[0081] S15. In response to the fulfillment of the iteration termination condition, select the individual with the highest fitness value as the optimal individual of the current population and output it, so as to determine one or more associated elements based on the optimal individual.

[0082] The iteration termination condition is the maximum number of iterations. If the maximum number of iterations is not met, the genetic process is repeated. If the maximum number of iterations is met, the iteration stops and the current best individual is output.

[0083] S16. In response to each feature identifying one or more associated elements, elements that appear at least 5 times are marked as faulty elements or lines; lines that appear 2-5 times are marked as risky elements or lines; lines that appear once are not marked.

[0084] The waveform recording feature vector set in this embodiment includes seven features: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features. Therefore, each feature determines a corresponding optimal individual. If certain components appear in the optimal individuals determined by multiple features, it indicates that the component has a fault risk from different angles, and thus it is identified as a risk component. If it appears at least five times, it can be identified as a fault component. If it appears only once, it indicates error interference and is not marked as a risk.

[0085] S17. Control the faulty component or line to disconnect in order to investigate the faulty component or line. For risky components or lines, it is necessary to further determine whether they are faulty components or lines. Specifically, obtain the adjacent recorders of the recorder corresponding to the risky component or line from the power grid, and perform risk prediction again according to the process of this embodiment. Since the algorithm of this embodiment has been optimized for redundant interference factors, if the risky component or line still appears in the components determined by other recorders, it indicates that the risky component or line is a faulty risk.

[0086] The intelligent control method based on high-voltage substations in this embodiment retains common components through cross-mutation operations, which allows components with higher risk probabilities to be retained, thereby eliminating the calculation errors and complexity caused by redundant waveform data. In addition, in order to ensure the accuracy of fault risk, this invention predicts each feature quantity in the waveform feature vector set separately and performs an overall evaluation based on the prediction results to avoid misjudgment.

[0087] Example 2

[0088] Please see Figure 2 This embodiment also provides an intelligent control system based on a high-voltage substation, including:

[0089] Data acquisition module 21 is used to respond to the early warning message sent by the area to be monitored, read the corresponding waveform data from the database, and determine the waveform feature vector set based on the waveform data. The area to be monitored includes N components, the waveform data includes M sets of raw data, and the waveform feature vector set includes: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features.

[0090] The initial population selection module 22 is used to select Q individuals from M sets of original data as an initial population based on the recorded waveform feature vector set, wherein each individual in the initial population is associated with one or more elements;

[0091] Initialization module 23 is used to initialize the number of iterations and calculate the fitness value of each individual in each initial population based on the objective function.

[0092] The crossover and mutation module 24 is used to select any two parent individuals from the initial population for pairing, and to perform crossover or mutation operations on the paired parent individuals until each parent individual has been paired to obtain offspring individuals.

[0093] The iterative output module 25 is used to select the individual with the highest fitness value as the optimal individual of the current population and output it in response to the fulfillment of the iteration termination condition, so as to determine one or more associated elements based on the optimal individual;

[0094] Risk determination module 26 is used to, in response to each feature identifying one or more associated components, mark components that appear at least 5 times as faulty components or lines; mark lines that appear 2-5 times as risky components or lines; and leave lines that appear once unmarked.

[0095] The control module 27 is used to control the disconnection of the risk element or risk line in order to troubleshoot the faulty element or faulty line.

[0096] In one specific implementation, the crossover mutation module includes:

[0097] A random number generation unit is used to generate a first random number and set a mutation threshold.

[0098] The crossover and mutation unit is used to compare the relationship between the first random number and the mutation threshold. If the first random number is greater than the mutation threshold, a crossover operation is performed on the two parent individuals in the current population. If the first random number is less than or equal to the mutation threshold, a mutation operation is performed on the two parent individuals in the current population.

[0099] In one specific embodiment, the crossover mutation unit includes:

[0100] The crossover subunit is used to find the associated elements of two parent individuals. If the two parent individuals have the same element, the same element is retained without crossover operation, and one element from the parent individuals other than the same element is randomly swapped to complete the crossover operation.

[0101] In one specific embodiment, the crossover mutation unit includes:

[0102] The mutation subunit is used to find the elements associated with two parent individuals. If the two parent individuals have the same element, the same element is retained and no mutation operation is performed. A mutation element sample is generated, wherein the mutation element sample is the element that exists in the parent individual but not in the set of N elements. A random element in the parent individual except for the same element is replaced with any one of the mutation element samples, thereby completing the mutation operation.

[0103] Example 3

[0104] This invention also provides an electronic device, such as... Figure 3 As shown, it includes a processor 31, a communication interface 32, a memory 33, and a communication bus 34. The processor 31, the communication interface 32, and the memory 33 communicate with each other through the communication bus 34.

[0105] Memory 33 is used to store computer programs;

[0106] When processor 31 executes the program stored in memory 33, it performs the following steps:

[0107] In response to an early warning message sent from the area to be monitored, the corresponding waveform data is read from the database to determine the waveform feature vector set based on the waveform data. The area to be monitored includes N components, the waveform data includes M sets of raw data, and the waveform feature vector set includes: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features.

[0108] Based on each feature in the waveform feature vector set, Q features are selected from the M sets of original data at any time as the initial population, and each individual in the initial population is associated with one or more elements.

[0109] Initialize the number of iterations, and calculate the fitness value of each individual in each initial population based on the objective function;

[0110] Select any two parent individuals from the initial population and pair them up. Perform crossover or mutation operations on the paired parent individuals until each parent individual has been paired up to obtain offspring individuals.

[0111] In response to the fulfillment of the iteration termination condition, the individual with the highest fitness value is selected as the optimal individual of the current population and output, so as to determine one or more associated elements based on the optimal individual;

[0112] In response to each feature identifying one or more associated components, components that appear at least 5 times are marked as faulty components or lines; lines that appear 2-5 times are marked as risky components or lines; lines that appear once are not marked.

[0113] The faulty component or line is disconnected to troubleshoot the faulty component or line.

[0114] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0115] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0116] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0117] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0118] The method provided in this invention can be applied to electronic devices. Specifically, the electronic device can be a desktop computer, a portable computer, a smart mobile terminal, a server, etc. No limitation is made herein; any electronic device that can implement this invention falls within the protection scope of this invention.

[0119] For the embodiments of the device / electronic device / storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and relevant parts can be referred to in the description of the method embodiments.

[0120] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. In addition, those skilled in the art can combine and integrate the different embodiments or examples described in this specification.

[0121] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0122] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects, all of which are collectively referred to herein as "modules" or "systems." Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The computer program may be stored / distributed in a suitable medium, provided with or as part of other hardware, or may take other distribution forms, such as via the Internet or other wired or wireless telecommunications systems.

[0123] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0124] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0125] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0126] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A smart control method based on high-voltage substations, characterized in that, include: In response to an early warning message sent from the area to be monitored, the corresponding waveform data is read from the database to determine the waveform feature vector set based on the waveform data. The area to be monitored includes N components, the waveform data includes M sets of raw data, and the waveform feature vector set includes: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features. Based on each feature in the waveform feature vector set, Q features are selected from the M sets of original data at any time as the initial population, and each individual in the initial population is associated with one or more elements. Initialize the number of iterations, and calculate the fitness value of each individual in each initial population based on the objective function; Select any two parent individuals from the initial population and pair them up. Perform crossover or mutation operations on the paired parent individuals until each parent individual has been paired up to obtain offspring individuals. In response to the fulfillment of the iteration termination condition, the individual with the highest fitness value is selected as the optimal individual of the current population and output, so as to determine one or more associated elements based on the optimal individual; In response to each feature identifying one or more associated components, components that appear at least 5 times are marked as faulty components or lines; lines that appear 2-5 times are marked as risky components or lines; lines that appear once are not marked. The faulty component or circuit is disconnected to troubleshoot the faulty component or circuit. Select any two parent individuals from the initial population and pair them up. Perform crossover or mutation operations on the paired parent individuals, including: Generate the first random number and set the mutation threshold; Compare the relationship between the first random number and the mutation threshold. If the first random number is greater than the mutation threshold, then perform a crossover operation on the two parent individuals in the current population; if the first random number is less than or equal to the mutation threshold, then perform a mutation operation on the two parent individuals in the current population. Performing a crossover operation on two parent individuals within the current population includes: Find the related elements of two parent individuals. If the two parent individuals have the same element, keep the same element and do not perform the crossover operation. Then, randomly swap one element from the parent individuals other than the same element to complete the crossover operation. Perform mutation operations on two parent individuals within the current population, including: Find the elements that are related between two parent individuals. If the two parent individuals have the same element, retain the same element and do not perform a mutation operation. Generate a sample of mutated elements, wherein the sample of mutated elements is the element that exists in the parent individual but is removed from the set of N elements. The mutation operation is completed by randomly replacing one element from the parent individual (excluding the identical elements) with any one of the mutated element samples. The objective function is: ， ， ， Where X represents the set of selected elements. , Indicates the selected number There are 10 components, where N represents the total number of components selected. Represents information entropy. This represents the symmetric KL divergence.

2. An intelligent control system based on a high-voltage substation, characterized in that, include: The data acquisition module is used to respond to the early warning message sent by the area to be monitored, read the corresponding waveform data from the database, and determine the waveform feature vector set based on the waveform data. The area to be monitored includes N components, the waveform data includes M sets of raw data, and the waveform feature vector set includes: voltage and current vector features, abrupt change features, wavelet coefficient ratio features, current longitudinal difference features, current phase difference features, fault direction features, and line modulus offset features. The initial population selection module is used to select Q individuals from M sets of original data as an initial population at any time based on the recorded feature vector set, wherein each individual in the initial population is associated with one or more elements; The initialization module is used to initialize the number of iterations and calculate the fitness value of each individual in the initial population based on the objective function. The crossover and mutation module is used to select any two parent individuals from the initial population and pair them up to perform crossover or mutation operations on the paired parent individuals until each parent individual has been paired up to obtain offspring individuals. The iterative output module is used to select the individual with the highest fitness value as the optimal individual of the current population and output it in response to the fulfillment of the iteration termination condition, so as to determine one or more associated elements based on the optimal individual; The risk determination module is used to identify one or more associated components for each feature, mark components that appear at least 5 times as faulty components or lines; mark lines that appear 2-5 times as risky components or lines; and leave lines that appear once unmarked. The control module is used to control the disconnection of the risky component or risky line in order to troubleshoot the faulty component or faulty line. The crossover mutation module includes: A random number generation unit is used to generate a first random number and set a mutation threshold. The crossover and mutation unit is used to compare the relationship between the first random number and the mutation threshold. If the first random number is greater than the mutation threshold, a crossover operation is performed on the two parent individuals in the current population. If the first random number is less than or equal to the mutation threshold, a mutation operation is performed on the two parent individuals in the current population. The crossover mutation unit includes: The crossover subunit is used to find the related elements of two parent individuals. If the two parent individuals have the same element, the same element is retained without crossover operation, and one element from the parent individuals other than the same element is randomly swapped to complete the crossover operation. The crossover mutation unit includes: The mutation subunit is used to find the elements associated with two parent individuals. If the two parent individuals have the same element, the same element is retained and no mutation operation is performed. A mutation element sample is generated, wherein the mutation element sample is the element that exists in the parent individual but not in the set of N elements. A random element in the parent individual except for the same element is replaced with any one of the mutation element samples, thereby completing the mutation operation. The objective function is: ， ， ， Where X represents the set of selected elements. , Indicates the selected number There are 10 components, where N represents the total number of components selected. Represents information entropy. This represents the symmetric KL divergence.

3. An electronic device, characterized in that, include: The system consists of a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. Memory, used to store computer programs; The processor, when executing the program stored in the memory, implements the intelligent control method based on a high-voltage substation as described in claim 1.

Images