Power frequency modulation management method and system for power transformation scene

Abstract

The invention provides a power frequency modulation management method and system for a power transformation scene, and relates to the technical field of power grid frequency modulation, and the method comprises the steps: obtaining a scene mode switching sample of a transformer substation; performing a frequency modulation test on the scene mode switching sample by using a power transformation twinborn model to obtain a frequency modulation test data sample; performing frequency modulation error analysis on the frequency modulation test data sample to obtain a frequency modulation error index; classifying the scene mode switching samples according to a frequency modulation error index to obtain a first type of mode switching samples and a second type of mode switching samples; and performing partition frequency modulation management on the first type of mode switching samples and the second type of mode switching samples. The technical problems of low power grid frequency modulation precision and poor power grid operation stability caused by low matching degree of power grid frequency modulation parameters and substation working modes can be solved, and the adaptability of the power grid frequency modulation parameters in different substation working modes can be improved, so that the power grid frequency modulation accuracy is improved, and the power grid frequency modulation efficiency is improved. And the operation stability of the grid system is ensured.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power grid frequency regulation, and more specifically, to a power frequency regulation management method and system for power transformation scenarios. Background Art

[0002] Power frequency regulation in substations is an important power control technology, which is mainly used to maintain the frequency stability of the power system. This technology is crucial to the safe and reliable operation of the power grid and to meeting the power needs of users.

[0003] When performing power frequency modulation, existing substations usually only set frequency modulation control parameters according to the current power load, without taking into account the frequency modulation control deviation of the substation under different working modes, resulting in low adaptability of the frequency modulation control parameters to the substation working mode, causing poor frequency modulation quality of the power grid and affecting the safe and stable operation of the power grid.

[0004] The shortcomings of the existing power grid frequency regulation method are: due to the low matching degree between the power grid frequency regulation parameters and the substation working mode, the power grid frequency regulation accuracy is low, resulting in poor power grid operation stability. Summary of the invention

[0005] Therefore, in order to solve the above technical problems, the technical solutions adopted by the embodiments of the present disclosure are as follows:

[0006] The method for managing power frequency regulation for substation scenarios comprises the following steps: establishing a substation twin model of the substation by collecting historical operation data of the substation; obtaining scene mode switching samples of the substation, wherein the scene mode switching samples are samples of the substation switching from a current mode to another mode; performing frequency regulation tests on the scene mode switching samples using the substation twin model to obtain frequency regulation test data samples corresponding to the scene mode switching samples; obtaining frequency regulation error indicators by performing frequency regulation error analysis on the frequency regulation test data samples; classifying the scene mode switching samples according to the frequency regulation error indicators to obtain first-category mode switching samples and second-category mode switching samples, wherein the first-category mode switching samples are samples whose frequency regulation error indicators are less than a preset frequency regulation error indicator, and the second-category mode switching samples are samples whose frequency regulation error indicators are greater than or equal to the preset frequency regulation error indicator; performing partition frequency regulation management on the first-category mode switching samples and the second-category mode switching samples.

[0007] An electric power frequency regulation management system for a substation scenario, comprising: a substation twin model establishment module, the substation twin model establishment module is used to establish a substation twin model of the substation by collecting historical operation data of the substation; a scene mode switching sample acquisition module, the scene mode switching sample acquisition module is used to obtain scene mode switching samples of the substation, wherein the scene mode switching samples are samples of the substation switching from a current mode to another mode; a frequency modulation test data sample acquisition module, the frequency modulation test data sample acquisition module is used to perform a frequency modulation test on the scene mode switching samples using the substation twin model, and obtain frequency modulation test data samples corresponding to the scene mode switching samples; frequency modulation An error analysis module, the frequency modulation error analysis module is used to obtain a frequency modulation error index by performing frequency modulation error analysis on the frequency modulation test data samples; a mode switching sample classification module, the mode switching sample classification module is used to classify the scene mode switching samples according to the frequency modulation error index to obtain a first type of mode switching samples and a second type of mode switching samples, wherein the first type of mode switching samples are samples whose frequency modulation error index is less than a preset frequency modulation error index, and the second type of mode switching samples are samples whose frequency modulation error index is greater than or equal to the preset frequency modulation error index; a partitioned frequency modulation management module, the partitioned frequency modulation management module is used to perform partitioned frequency modulation management on the first type of mode switching samples and the second type of mode switching samples.

[0008] Due to the adoption of the above technical method, the present disclosure has achieved the following technical advances compared with the prior art:

[0009] The invention can solve the technical problem that the matching degree between the grid frequency regulation parameters and the substation working mode is low, resulting in low grid frequency regulation accuracy and poor grid operation stability in the traditional grid frequency regulation method. First, the historical operation data of the substation is collected, and the substation twin model of the substation is established according to the data collection result; the scene mode switching sample of the substation is obtained, wherein the scene mode switching sample is a sample of the substation switching from the current mode to another mode; then the substation twin model is used to perform a frequency modulation test on the scene mode switching sample to obtain the frequency modulation test data samples corresponding to the scene mode switching samples; the frequency modulation error analysis is performed on the frequency modulation test data sample to obtain the frequency modulation error index; the scene mode switching sample is classified according to the frequency modulation error index to obtain the first type of mode switching sample and the second type of mode switching sample, wherein the first type of mode switching sample is a sample whose frequency modulation error index is less than the preset frequency modulation error index, and the second type of mode switching sample is a sample whose frequency modulation error index is greater than or equal to the preset frequency modulation error index; finally, the first type of mode switching sample and the second type of mode switching sample are subjected to partition frequency modulation management. By carrying out zone frequency regulation management, the adaptability of grid frequency regulation parameters in different working modes of substations can be improved, thereby improving the accuracy of grid frequency regulation and ensuring the stability of grid system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for describing the embodiments are briefly introduced below.

[0011] Figure 1 A flow chart of a method for managing power frequency regulation in a power transformation scenario is provided for this application;

[0012] Figure 2 A schematic diagram of a process for performing zone frequency regulation management on a first type of mode switching sample and a second type of mode switching sample in a power frequency regulation management method for a power transformation scenario is provided for the present application;

[0013] Figure 3 A structural schematic diagram of an electric power frequency regulation management system for a substation scenario is provided for this application.

[0014] Explanation of the accompanying drawings: substation twin model establishment module 01, scene mode switching sample acquisition module 02, frequency modulation test data sample acquisition module 03, frequency modulation error analysis module 04, mode switching sample classification module 05, partition frequency modulation management module 06. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present disclosure will be described below in conjunction with the drawings in the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0016] Embodiment 1

[0017] Based on the above description, if Figure 1 As shown, the present disclosure provides a power frequency regulation management method for a power transformation scenario, comprising:

[0018] The method provided in the present application is used to intelligently manage the power frequency regulation of the substation, so that the adaptability of the power grid frequency regulation parameters in different working modes of the substation can be improved, thereby achieving the technical effect of improving the accuracy of the power grid frequency regulation and ensuring the safe and stable operation of the power grid system. The method is specifically implemented in a power frequency regulation management system for substation scenarios.

[0019] By collecting historical operation data of the substation, a substation twin model of the substation is established;

[0020] In the embodiment of the present application, first, the historical operation data of the substation is collected, and the historical operation data includes the historical voltage transformation data, historical power distribution data, historical power flow data, etc. of the substation. Then, based on the digital twin technology, simulation modeling is performed in a visual simulation platform according to the historical operation data to generate a substation twin model of the substation, wherein the digital twin is a technical means to simulate the operating state of an entity in the real world through a digital model; commonly used visual simulation modeling platforms include AutoCAD software, Siemens Simcenter software, etc., and technicians in this field can select an adaptive simulation platform for modeling according to actual conditions.

[0021] By building a substation twin model based on digital twin technology, the authenticity and accuracy of the substation simulated frequency modulation can be improved, thereby improving the accuracy of the frequency modulation test data due to the advantages of digital twin technology such as interoperability, scalability, real-time, and fidelity.

[0022] Acquire a scene mode switching sample of the substation, wherein the scene mode switching sample is a sample of the substation switching from a current mode to another mode;

[0023] In an embodiment of the present application, multiple substation working modes of the substation are obtained, wherein the substation working modes can be set according to actual conditions, including incoming power supply mode, external power supply mode, reactive power regulation mode, dispatching control mode, etc. Then, scene mode switching samples are obtained according to the multiple substation working modes, wherein the scene mode switching samples are samples of the substation switching from the current mode to another mode, for example: the substation switches from reactive power regulation mode to dispatching control mode. By obtaining the scene mode switching samples, support is provided for frequency modulation deviation analysis during mode switching.

[0024] Using the substation twin model to perform a frequency modulation test on the scene mode switching samples, and obtaining frequency modulation test data samples corresponding to the scene mode switching samples;

[0025] In an embodiment of the present application, under the scene mode switching sample, a frequency modulation test is performed through the substation twin model, and frequency modulation test data samples corresponding to different scene mode switching samples are obtained according to the frequency modulation test results.

[0026] In one embodiment, the method further comprises:

[0027] Among them, each scene mode switching sample corresponds to a group of frequency modulation test data samples, and each group of frequency modulation test data samples includes phase change data samples of multiple operating points on the adjustment characteristic curve corresponding to the scene mode switching, error data samples of the same operating point on the adjustment characteristic curve shifting up and down, and lag data samples of multiple operating point signals on the adjustment characteristic curve.

[0028] In the embodiment of the present application, each scene mode switching sample corresponds to a set of frequency modulation test data samples, and each set of frequency modulation test data samples includes phase change data samples of multiple operating points on the adjustment characteristic curve corresponding to the scene mode switching, error data samples of the same operating point on the adjustment characteristic curve shifting up and down, and hysteresis data samples of multiple operating point signals on the adjustment characteristic curve. The adjustment characteristic curve is a fluctuation curve describing the change of power load over time, and the time is usually used as the horizontal coordinate and the load value is used as the vertical coordinate in the adjustment characteristic curve.

[0029] Among them, the error data sample refers to the deviation value between the power load of the node and the power load of the same timing node in the standard regulation characteristic curve at the same fixed timing node, and the standard regulation characteristic curve is the standard power load operation trajectory during frequency regulation under ideal conditions; the lag data sample refers to the data at the same timing node where there is a lag in the power load between the regulation characteristic curve and the standard regulation characteristic curve, that is, the power load value appears first in the standard regulation characteristic curve and later in the regulation characteristic curve, and the timing node that appears in the standard regulation characteristic curve is earlier than the timing node that appears in the regulation characteristic curve.

[0030] By using the substation twin model to conduct frequency modulation tests, frequency modulation test data samples were obtained, which provided support for the next step of frequency modulation error analysis under different scenario mode switching samples.

[0031] Obtaining a frequency modulation error index by performing frequency modulation error analysis on the frequency modulation test data sample;

[0032] In an embodiment of the present application, a frequency modulation error analysis is performed on the frequency modulation test data samples. First, a first frequency modulation test data sample is randomly selected from the frequency modulation test data samples, wherein the first frequency modulation test data sample is an frequency modulation test data sample corresponding to any one of a plurality of scene mode switching samples; then, the number of error data in the error data sample in the first frequency modulation test data sample and the number of lag data in the lag data sample are extracted; a first weight is set for the error data sample, and a second weight is set for the lag data sample, wherein the sum of the first weight and the second weight is 1, and the values ​​of the first weight and the second weight can be set according to the degree of influence of the error data and the lag data on the overall frequency modulation error, wherein the greater the degree of influence of any indicator, the greater the corresponding weight, and the weight setting can be performed through the existing coefficient of variation method.

[0033] Then, the number of error data and the number of lagging data are weightedly calculated according to the first weight and the second weight, and the weighted calculation result is used as the first FM error index of the first scene mode switching sample corresponding to the first FM test data sample; the same method is used for calculation to obtain multiple FM error indexes corresponding to multiple scene mode switching samples in turn.

[0034] By obtaining multiple frequency modulation error indicators, a basis is provided for the next step of scene mode switching sample division, and the accuracy of scene mode switching sample division can be improved.

[0035] Classifying the scene mode switching samples according to the frequency modulation error index to obtain a first type of mode switching samples and a second type of mode switching samples, wherein the first type of mode switching samples are samples whose frequency modulation error index is less than a preset frequency modulation error index, and the second type of mode switching samples are samples whose frequency modulation error index is greater than or equal to the preset frequency modulation error index;

[0036] In the embodiment of the present application, first, a preset frequency modulation error index is obtained, and the preset frequency modulation error index can be set by a person skilled in the art according to actual conditions. Then, the multiple frequency modulation error indexes are judged according to the preset frequency modulation error index, and when the frequency modulation error index is less than the preset frequency modulation error index, the scene mode switching sample corresponding to the frequency modulation error index is set as the first type of mode switching sample; when the frequency modulation error index is greater than or equal to the preset frequency modulation error index, the scene mode switching sample corresponding to the frequency modulation error index is set as the second type of mode switching sample; the scene mode switching samples are classified in turn to obtain the first type of mode switching sample and the second type of mode switching sample.

[0037] Partition frequency modulation management is performed on the first-type mode switching samples and the second-type mode switching samples.

[0038] In an embodiment of the present application, when performing power frequency modulation, different frequency modulation control parameters are set for the first type of mode switching samples and the second type of mode switching samples to perform zone frequency modulation management. The above method can solve the technical problem that the traditional power grid frequency modulation method has a low matching degree between the power grid frequency modulation parameters and the substation working mode, resulting in low power grid frequency modulation accuracy and poor power grid operation stability. By performing zone frequency modulation management, the adaptability of the power grid frequency modulation parameters in different substation working modes can be improved, thereby improving the accuracy of the power grid frequency modulation and ensuring the stability of the power grid system operation.

[0039] like Figure 2 As shown, in one embodiment, the method further includes:

[0040] Partitioning and configuring the first type of mode switching samples and the second type of mode switching samples respectively to obtain a first frequency modulation module and a second frequency modulation module;

[0041] In one embodiment, the method further comprises:

[0042] Wherein, the first frequency modulation module and the second frequency modulation module are connected to the anti-interference module;

[0043] When either the first frequency modulation module or the second frequency modulation module triggers a frequency modulation signal, an interference index of the current signal is detected. If the interference index of the current signal meets a preset threshold, the anti-interference module is used to perform anti-interference processing on the frequency modulation signal.

[0044] In an embodiment of the present application, when performing partition frequency modulation management on the first type of mode switching samples and the second type of mode switching samples, first, the first type of mode switching samples and the second type of mode switching samples are respectively configured for partitions, and the area corresponding to the first type of mode switching samples is used as the first frequency modulation module, and the area corresponding to the second type of mode switching samples is used as the second frequency modulation module.

[0045] The first frequency modulation module and the second frequency modulation module are connected to an anti-interference module, and the anti-interference module is used to perform anti-interference processing on the frequency modulation signal to improve the transmission quality and reliability of the frequency modulation signal.

[0046] When either the first FM module or the second FM module triggers an FM signal, that is, receives an FM signal, interference detection is performed on the current FM signal. Commonly used signal interference detection methods include instrument detection method, software detection method, etc. An adaptive method can be selected according to actual conditions to perform signal interference detection to obtain an interference index of the current signal. The greater the degree of signal interference, the greater the interference index.

[0047] The interference index of the current signal is judged according to a preset threshold. The preset threshold can be set by a person skilled in the art according to the actual quality requirement of the FM signal, wherein the higher the required quality, the smaller the preset threshold; when the interference index is greater than the preset threshold, the anti-interference module is used to perform anti-interference processing on the FM signal.

[0048] In one embodiment, the method further comprises:

[0049] Positioning a signal transmission channel of the frequency modulation signal to obtain channel distribution information of the signal transmission channel;

[0050] In an embodiment of the present application, a method for performing anti-interference processing on the frequency modulation signal using the anti-interference module is as follows: first, the signal transmission channel of the frequency modulation signal is located, wherein the signal transmission channel refers to the transmission medium and related equipment through which the frequency modulation signal passes during the transmission process, and the channel distribution information of the signal transmission channel is obtained.

[0051] In one embodiment, the method further comprises:

[0052] Perform interference identification on each channel according to the channel distribution information to obtain an interference index of each channel;

[0053] Accumulating interference indicators of the respective channels to obtain an accumulated interference indicator;

[0054] A signal amplifier is provided, the anti-interference module is connected to the signal amplifier, and an amplification parameter of the signal amplifier is configured according to the accumulated interference index.

[0055] In an embodiment of the present application, after obtaining the channel distribution information of the signal transmission channel, first, interference is identified for each channel based on the channel distribution information to obtain the interference index of each channel, wherein the channel interference identification method includes spectrum analysis method, waveform observation method, bit error rate analysis method, etc., which can be selected according to actual conditions, wherein the greater the degree of interference to the channel during FM signal transmission, the greater the corresponding interference index.

[0056] The interference index of each channel is accumulated in turn to obtain the accumulated interference index, and then a signal amplifier is set, wherein the signal amplifier is an electronic device for amplifying signals, usually including an input stage, an intermediate stage and an output stage, wherein the input stage is a differential input circuit for suppressing common-mode interference signals; the intermediate stage is composed of an amplifier circuit for amplifying the signal; the output stage is an output voltage follower circuit for improving the load capacity of the load; and the anti-interference module is connected to the signal amplifier, and the amplification parameters of the signal amplifier are configured according to the accumulated interference index, wherein the amplification parameters are greater than or equal to the accumulated interference index.

[0057] By configuring the amplification parameters of the signal amplifier according to the accumulated interference index, the accuracy and rationality of the method parameter setting can be improved, and the resource waste of the signal amplifier can be reduced while meeting the basic signal anti-interference requirements.

[0058] Perform interference identification on each channel according to the channel distribution information to obtain an identified transmission channel, wherein an interference index of the identified transmission channel is greater than or equal to a preset interference index;

[0059] A signal amplifier is arranged at the transmission entrance of the identification transmission channel, for amplifying the signal input into the identification transmission channel.

[0060] In an embodiment of the present application, interference identification is performed on each channel in the channel distribution information to obtain an interference index for each channel. A preset interference index is obtained, and the preset interference index can be set by a person skilled in the art according to actual conditions. The interference index of each channel is judged according to the preset interference index, and a transmission channel whose interference index is greater than or equal to the preset index is set as an identification transmission channel to obtain an identification transmission channel.

[0061] Then, a signal amplifier is set at the transmission entrance of the identification transmission channel, wherein each identification transmission channel corresponds to a signal amplifier, and during the frequency modulation signal transmission process, the signal input into the identification transmission channel is amplified by the signal amplifier, wherein this anti-interference method is the second channel anti-interference method. Compared with the above-mentioned method of setting only one total signal amplifier, this method has better anti-interference effect, but at the same time, more signal amplifier resources are required. Those skilled in the art can freely choose between these two channel anti-interference methods according to actual needs. Among them, those with higher signal transmission quality requirements are recommended to choose the second channel anti-interference method for signal amplification.

[0062] Construct a steady-state reverse incentive network layer;

[0063] In one embodiment, the method further comprises:

[0064] Defining a frequency modulation learning factor of the steady-state reverse excitation network layer, wherein the frequency modulation learning factor includes a frequency modulation inequality rate, a frequency difference dead zone, and a frequency modulation limit;

[0065] Perform frequency modulation steady-state identification according to the frequency modulation inequality rate, the frequency difference dead zone and the frequency modulation limit to obtain a frequency modulation steady-state index;

[0066] The frequency modulation steady-state index is learned with a preset steady-state index as an incentive target, so that the steady-state reverse incentive network layer performs feedback incentive learning on the real-time frequency modulation parameters belonging to the second type of mode switching samples.

[0067] In an embodiment of the present application, a steady-state reverse excitation network layer is constructed, wherein the steady-state reverse excitation network layer is a neural network architecture that trains the neural network through a back-propagation algorithm and uses an excitation function to control the output of neurons. The function of this network layer is to achieve nonlinear mapping, so that the neural network can better learn and simulate complex input-output relationships.

[0068] First, the frequency modulation learning factor of the steady-state reverse excitation network layer is defined, wherein the frequency modulation learning factor includes frequency modulation inequality, frequency difference dead zone and frequency modulation limit, wherein the frequency modulation inequality represents the phase difference of the frequency modulation speed change from small to large during the frequency modulation process when different substation working modes are switched. Since the power load changes to a certain extent when different working modes are switched, the frequency modulation inequality when different substation working modes are switched is also different; the frequency difference dead zone represents the frequency difference range under the premise of meeting the frequency modulation requirements, which can reduce the frequency modulation redundancy during small-range adjustment, wherein the smaller the frequency difference dead zone, the smaller the redundancy during frequency modulation; the frequency modulation limit includes frequency change rate limit, maximum and minimum power limit, etc. The frequency change rate limit is set to ensure the stability of the system frequency. When the system frequency changes too fast, the generator set will limit its adjustment action. The maximum and minimum power limits are set to ensure that the generator set does not exceed its rated power range.

[0069] The frequency modulation stability is identified according to the frequency modulation inequality, the frequency difference dead zone and the frequency modulation limit, wherein the smaller the redundancy during frequency modulation, the higher the frequency modulation stability, and the frequency modulation stability index is obtained. A preset stability index is obtained, and the preset stability index can be set by a person skilled in the art according to actual needs, wherein the higher the required frequency modulation quality, the larger the preset stability index.

[0070] Then, the preset steady-state index is used as the excitation target of the frequency modulation steady-state index, and the frequency modulation steady-state index is learned, so that the steady-state reverse excitation network layer performs feedback excitation learning on the real-time frequency modulation parameters belonging to the second type of mode switching samples. The training method of the steady-state reverse excitation network layer is implemented by a back propagation algorithm, wherein, during the training process, the input and output signals of the neural network are transmitted layer by layer until the target output is reached, and then the error of each layer of neurons is calculated according to the difference between the target output and the actual output, and the weight of the neuron is updated using the gradient descent method, and the direction of the weight update is the direction that reduces the error, thereby gradually reducing the error and improving the accuracy of the neural network.

[0071] The steady-state reverse excitation network layer is encapsulated into the second frequency modulation module. If the current scene mode switching of the substation belongs to the second type of mode switching sample, the steady-state reverse excitation network layer is used to perform feedback excitation adjustment on the real-time frequency modulation parameters.

[0072] In an embodiment of the present application, the steady-state reverse excitation network layer is finally encapsulated into the second frequency modulation module. When the current scene mode switching of the substation belongs to the second type of mode switching sample, the steady-state reverse excitation network layer is used to perform feedback excitation adjustment on the real-time frequency modulation parameters, thereby realizing partition frequency modulation management.

[0073] By constructing a steady-state reverse excitation network layer, it is possible to set a steady-state excitation to perform feedback excitation adjustment on the real-time frequency modulation parameters when the frequency modulation deviation is large, thereby improving the adaptability of the frequency modulation parameters and scene mode switching and improving the accuracy of power grid frequency regulation.

[0074] Embodiment 2

[0075] Based on the same inventive concept as the power frequency regulation management method for power substation scenario in the above-mentioned embodiment 1, as Figure 3 As shown, the present application also provides a power frequency regulation management system for a substation scenario, including: a substation twin model establishment module 01, a scenario mode switching sample acquisition module 02, a frequency regulation test data sample acquisition module 03, a frequency regulation error analysis module 04, a mode switching sample classification module 05, and a partition frequency regulation management module 06, wherein:

[0076] A substation twin model establishment module 01, wherein the substation twin model establishment module 01 is used to establish a substation twin model of the substation by collecting historical operation data of the substation;

[0077] A scene mode switching sample acquisition module 02, wherein the scene mode switching sample acquisition module 02 is used to acquire scene mode switching samples of the substation, wherein the scene mode switching samples are samples of the substation switching from a current mode to another mode;

[0078] A frequency modulation test data sample obtaining module 03, wherein the frequency modulation test data sample obtaining module 03 is used to perform a frequency modulation test on the scene mode switching sample using the substation twin model to obtain frequency modulation test data samples corresponding to the scene mode switching samples;

[0079] A frequency modulation error analysis module 04, the frequency modulation error analysis module 04 is used to obtain a frequency modulation error index by performing frequency modulation error analysis on the frequency modulation test data sample;

[0080] A mode switching sample classification module 05, wherein the mode switching sample classification module 05 is used to classify the scene mode switching samples according to the frequency modulation error index, and obtain a first type of mode switching samples and a second type of mode switching samples, wherein the first type of mode switching samples are samples whose frequency modulation error index is less than a preset frequency modulation error index, and the second type of mode switching samples are samples whose frequency modulation error index is greater than or equal to the preset frequency modulation error index;

[0081] The partition frequency modulation management module 06 is used to perform partition frequency modulation management on the first type mode switching samples and the second type mode switching samples.

[0082] In one embodiment, the system further comprises:

[0083] A partition configuration module, the partition configuration module is used to partition the first type of mode switching samples and the second type of mode switching samples to obtain a first frequency modulation module and a second frequency modulation module;

[0084] A steady-state reverse excitation network layer construction module, wherein the steady-state reverse excitation network layer construction module is used to construct a steady-state reverse excitation network layer;

[0085] A feedback excitation regulation module is used to encapsulate the steady-state reverse excitation network layer into the second frequency modulation module. If the current scene mode switching of the substation belongs to the second type of mode switching sample, the steady-state reverse excitation network layer is used to perform feedback excitation regulation on the real-time frequency modulation parameters.

[0086] In one embodiment, the system further comprises:

[0087] A frequency modulation learning factor definition module, wherein the frequency modulation learning factor definition module is used to define the frequency modulation learning factor of the steady-state reverse excitation network layer, wherein the frequency modulation learning factor includes a frequency modulation inequality rate, a frequency difference dead zone, and a frequency modulation limit;

[0088] A frequency modulation stability identification module, the frequency modulation stability identification module is used to identify the frequency modulation stability according to the frequency modulation inequality, the frequency difference dead zone and the frequency modulation limit, and obtain a frequency modulation stability index;

[0089] A feedback incentive learning module is used to learn the frequency modulation steady-state index with a preset steady-state index as an incentive target, so that the steady-state reverse incentive network layer performs feedback incentive learning on the real-time frequency modulation parameters of the second type of mode switching samples.

[0090] In one embodiment, the system further comprises:

[0091] A frequency modulation test data sample module, wherein each scene mode switching sample corresponds to a group of frequency modulation test data samples, and each group of frequency modulation test data samples includes phase change data samples of multiple operating points on the adjustment characteristic curve corresponding to the scene mode switching, error data samples of the same operating point on the adjustment characteristic curve shifting up and down, and lag data samples of multiple operating point signals on the adjustment characteristic curve.

[0092] In one embodiment, the system further comprises:

[0093] An anti-interference module, wherein the first frequency modulation module and the second frequency modulation module are connected to the anti-interference module;

[0094] The anti-interference processing module is used to detect the interference index of the current signal when either the first frequency modulation module or the second frequency modulation module triggers a frequency modulation signal. If the interference index of the current signal meets a preset threshold, the anti-interference module is used to perform anti-interference processing on the frequency modulation signal.

[0095] In one embodiment, the system further comprises:

[0096] A channel distribution information acquisition module, the channel distribution information acquisition module is used to locate the signal transmission channel of the frequency modulation signal and acquire channel distribution information of the signal transmission channel;

[0097] An identification transmission channel acquisition module, the identification transmission channel acquisition module is used to perform interference identification on each channel according to the channel distribution information, and acquire an identification transmission channel, wherein the interference index of the identification transmission channel is greater than or equal to a preset interference index;

[0098] A signal amplifier setting module is used to set a signal amplifier at the transmission entrance of the identification transmission channel to amplify the signal input into the identification transmission channel.

[0099] In one embodiment, the system further comprises:

[0100] An interference identification module, the interference identification module is used to identify interference for each channel according to the channel distribution information, and obtain an interference index for each channel;

[0101] An accumulated interference index acquisition module, the accumulated interference index acquisition module is used to accumulate interference indicators of each channel to obtain an accumulated interference index;

[0102] An amplification parameter configuration module is used to set a signal amplifier, connect the anti-interference module with the signal amplifier, and configure the amplification parameters of the signal amplifier according to the accumulated interference index.

[0103] In summary, compared with the prior art, the embodiments of the present disclosure have the following technical effects:

[0104] (1) By carrying out zone frequency regulation management, the adaptability of grid frequency regulation parameters in different working modes of substations can be improved, thereby improving the accuracy of grid frequency regulation and ensuring the stability of grid system operation.

[0105] (2) By configuring the amplification parameters of the signal amplifier according to the accumulated interference index, the accuracy and rationality of the method parameter setting can be improved, and the resource waste of the signal amplifier can be reduced while meeting the basic signal anti-interference requirements.

[0106] (3) By constructing a steady-state reverse excitation network layer, it is possible to set a steady-state excitation to perform feedback excitation adjustment on the real-time frequency modulation parameters when the frequency modulation deviation is large, thereby improving the adaptability of the frequency modulation parameters and scene mode switching and improving the accuracy of power grid frequency modulation.

[0107] The above-described embodiments only express several implementation methods of the present disclosure, but they cannot be understood as limiting the scope of the invention patent. Therefore, without departing from the scope of the present disclosure concept as defined by the attached claims, a person of ordinary skill in the art may make various types of substitutions, modifications and changes, and these substitutions, modifications and changes all belong to the protection scope of the present disclosure.

Claims

1. A power frequency regulation management method for a power transformation scenario, characterized in that: The method comprises: By collecting historical operation data of the substation, a substation twin model of the substation is established; Acquire a scene mode switching sample of the substation, wherein the scene mode switching sample is a sample of the substation switching from a current mode to another mode; Using the substation twin model to perform a frequency modulation test on the scene mode switching samples, and obtaining frequency modulation test data samples corresponding to the scene mode switching samples; Obtaining a frequency modulation error index by performing frequency modulation error analysis on the frequency modulation test data sample; Classifying the scene mode switching samples according to the frequency modulation error index to obtain a first type of mode switching samples and a second type of mode switching samples, wherein the first type of mode switching samples are samples whose frequency modulation error index is less than a preset frequency modulation error index, and the second type of mode switching samples are samples whose frequency modulation error index is greater than or equal to the preset frequency modulation error index; Partition frequency modulation management is performed on the first-type mode switching samples and the second-type mode switching samples.

2. The method according to claim 1, characterized in that Performing partition frequency modulation management on the first type of mode switching samples and the second type of mode switching samples includes: Partitioning and configuring the first type of mode switching samples and the second type of mode switching samples respectively to obtain a first frequency modulation module and a second frequency modulation module; Construct a steady-state reverse incentive network layer; The steady-state reverse excitation network layer is encapsulated into the second frequency modulation module. If the current scene mode switching of the substation belongs to the second type of mode switching sample, the steady-state reverse excitation network layer is used to perform feedback excitation adjustment on the real-time frequency modulation parameters.

3. The method according to claim 2, characterized in that The method of constructing a steady-state reverse excitation network layer includes: Defining a frequency modulation learning factor of the steady-state reverse excitation network layer, wherein the frequency modulation learning factor includes a frequency modulation inequality rate, a frequency difference dead zone, and a frequency modulation limit; Perform frequency modulation steady-state identification according to the frequency modulation inequality rate, the frequency difference dead zone and the frequency modulation limit to obtain a frequency modulation steady-state index; The frequency modulation steady-state index is learned with a preset steady-state index as an incentive target, so that the steady-state reverse incentive network layer performs feedback incentive learning on the real-time frequency modulation parameters belonging to the second type of mode switching samples.

4. The method according to claim 1, characterized in that FM test data samples corresponding to the scene mode switching samples are obtained, wherein each scene mode switching sample corresponds to a group of FM test data samples, and each group of FM test data samples includes phase change data samples of multiple operating points on the adjustment characteristic curve corresponding to the scene mode switching, error data samples of the same operating point on the adjustment characteristic curve shifting up and down, and hysteresis data samples of the signals of multiple operating points on the adjustment characteristic curve.

5. The method according to claim 2, characterized in that Partitioning the first type of mode switching samples and the second type of mode switching samples respectively to obtain a first frequency modulation module and a second frequency modulation module, include: Wherein, the first frequency modulation module and the second frequency modulation module are connected to the anti-interference module; When either the first frequency modulation module or the second frequency modulation module triggers a frequency modulation signal, an interference index of the current signal is detected. If the interference index of the current signal meets a preset threshold, the anti-interference module is used to perform anti-interference processing on the frequency modulation signal.

6. The method according to claim 5, characterized in that Using the anti-interference module to perform anti-interference processing on the frequency modulation signal includes: Positioning a signal transmission channel of the frequency modulation signal to obtain channel distribution information of the signal transmission channel; Perform interference identification on each channel according to the channel distribution information to obtain an identified transmission channel, wherein an interference index of the identified transmission channel is greater than or equal to a preset interference index; A signal amplifier is arranged at the transmission entrance of the identification transmission channel, for amplifying the signal input into the identification transmission channel.

7. The method according to claim 6, characterized in that After acquiring the channel distribution information of the signal transmission channel, the method further includes: Perform interference identification on each channel according to the channel distribution information to obtain an interference index of each channel; Accumulating interference indicators of the respective channels to obtain an accumulated interference indicator; A signal amplifier is provided, the anti-interference module is connected to the signal amplifier, and an amplification parameter of the signal amplifier is configured according to the accumulated interference index.

8. The power frequency regulation management system for power transformation scenarios is characterized by: The system comprises: A substation twin model establishment module, wherein the substation twin model establishment module is used to establish a substation twin model of the substation by collecting historical operation data of the substation; A scene mode switching sample acquisition module, the scene mode switching sample acquisition module is used to acquire scene mode switching samples of the substation, wherein the scene mode switching samples are samples of the substation switching from a current mode to another mode; A frequency modulation test data sample obtaining module, wherein the frequency modulation test data sample obtaining module is used to perform a frequency modulation test on the scene mode switching sample using the substation twin model to obtain frequency modulation test data samples corresponding to the scene mode switching samples; A frequency modulation error analysis module, the frequency modulation error analysis module is used to obtain a frequency modulation error index by performing frequency modulation error analysis on the frequency modulation test data sample; A mode switching sample classification module, wherein the mode switching sample classification module is used to classify the scene mode switching samples according to the frequency modulation error index to obtain a first type of mode switching samples and a second type of mode switching samples, wherein the first type of mode switching samples are samples whose frequency modulation error index is less than a preset frequency modulation error index, and the second type of mode switching samples are samples whose frequency modulation error index is greater than or equal to the preset frequency modulation error index; A partition frequency modulation management module, wherein the partition frequency modulation management module is used to perform partition frequency modulation management on the first type mode switching samples and the second type mode switching samples.

Images