Pumped storage unit frequency control method and device, computer equipment, storage medium and computer program product

Abstract

The invention relates to a pumped storage unit frequency control method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps that according to a current frequency value, a current power value, a preset frequency value and a preset power value of a to-be-analyzed pumped storage unit, a frequency difference value, a power difference value and combined data corresponding to the to-be-analyzed pumped storage unit are obtained; according to a target unit type of the to-be-analyzed pumped storage unit, querying a corresponding relation between the unit type and a frequency control instruction prediction model to obtain a target frequency control instruction prediction model corresponding to the to-be-analyzed pumped storage unit; inputting the frequency difference value, the power difference value and the combined data into a target frequency control instruction prediction model to obtain a target frequency control instruction corresponding to the pumped storage unit to be analyzed; and performing corresponding frequency control processing on the pumped storage unit to be analyzed according to the target frequency control instruction. By adopting the method, the frequency control accuracy of the pumped storage unit can be improved.

Description

Technical Field

[0001] The present application relates to the field of power grid technology, and in particular to a frequency control method, device, computer equipment, computer-readable storage medium and computer program product for a pumped-storage unit. Background Art

[0002] At present, in order to improve the power quality of the power system, it is crucial to accurately control the frequency of the pumped storage units in the power system.

[0003] In traditional technology, manual adjustment is generally used in the process of frequency control of pumped storage units; however, this manual adjustment method has subjective factors and is prone to errors, resulting in low frequency control accuracy of pumped storage units. Summary of the invention

[0004] Based on this, it is necessary to provide a pumped-storage unit frequency control method, device, computer equipment, computer-readable storage medium and computer program product that can improve the frequency control accuracy of the pumped-storage unit in response to the above technical problems.

[0005] In a first aspect, the present application provides a frequency control method for a pumped storage unit, comprising:

[0006] In response to a frequency control request for the pumped-storage unit to be analyzed, obtaining a current frequency value, a current power value, a preset frequency value, and a preset power value of the pumped-storage unit to be analyzed;

[0007] Performing a difference processing on the current frequency value and the preset frequency value to obtain a frequency difference value corresponding to the pumped-storage unit to be analyzed, performing a difference processing on the current power value and the preset power value to obtain a power difference value corresponding to the pumped-storage unit to be analyzed, and performing a combination processing on the current frequency value and the current power value to obtain combination data corresponding to the pumped-storage unit to be analyzed;

[0008] According to the target unit type of the pumped-storage unit to be analyzed, query the corresponding relationship between the unit type and the frequency control instruction prediction model to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed;

[0009] Inputting the frequency difference, the power difference and the combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed;

[0010] According to the target frequency control instruction, corresponding frequency control processing is performed on the pumped-storage unit to be analyzed.

[0011] In one embodiment, the correspondence between the unit type and the frequency control instruction prediction model is constructed in the following manner:

[0012] Obtain multiple trained frequency control instruction prediction models corresponding to each sample pumped storage unit; each trained frequency control instruction prediction model corresponds to a prediction accuracy and a prediction efficiency;

[0013] Selecting a frequency control instruction prediction model with a prediction efficiency greater than a preset efficiency from a plurality of trained frequency control instruction prediction models corresponding to each sample pumped-storage unit as a candidate frequency control instruction prediction model corresponding to each sample pumped-storage unit;

[0014] Selecting the candidate frequency control instruction prediction model with the highest prediction accuracy from the candidate frequency control instruction prediction models corresponding to each sample pumped-storage unit as the target frequency control instruction prediction model corresponding to each sample pumped-storage unit;

[0015] The unit type of each sample pumped-storage unit is obtained, and according to the unit type of each sample pumped-storage unit and the target frequency control instruction prediction model corresponding to each sample pumped-storage unit, a corresponding relationship between the unit type and the frequency control instruction prediction model is constructed.

[0016] In one embodiment, the step of obtaining a plurality of trained frequency control instruction prediction models corresponding to each sample pumped-storage unit includes:

[0017] Obtaining a current sample frequency value, a current sample power value, a preset sample frequency value, and a preset sample power value for each sample pumped-storage unit;

[0018] Performing a difference processing on the current sample frequency value and the preset sample frequency value to obtain a sample frequency difference value corresponding to each sample pumped-storage unit, performing a difference processing on the current sample power value and the preset sample power value to obtain a sample power difference value corresponding to each sample pumped-storage unit, and performing a combination processing on the current sample frequency value and the current sample power value to obtain sample combination data corresponding to each sample pumped-storage unit;

[0019] Inputting the sample frequency difference, the sample power difference and the sample combination data into a plurality of frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit to obtain a predicted frequency control instruction corresponding to each sample pumped-storage unit;

[0020] The actual frequency control instruction corresponding to each sample pumped-storage unit is obtained, and according to the difference between the predicted frequency control instruction and the actual frequency control instruction, multiple frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit are iteratively trained to obtain multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit.

[0021] In one embodiment, the frequency difference, the power difference and the combined data are input into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped storage unit to be analyzed, including:

[0022] Inputting the frequency difference, the power difference and the combined data into a feature extraction model for feature extraction processing respectively, to obtain a first feature vector corresponding to the frequency difference, a second feature vector corresponding to the power difference and a third feature vector corresponding to the combined data;

[0023] fusing the first eigenvector, the second eigenvector and the third eigenvector to obtain a fused eigenvector corresponding to the pumped-storage unit to be analyzed;

[0024] The fused feature vector is input into the target frequency control instruction prediction model to obtain the target frequency control instruction.

[0025] In one embodiment, the obtaining of the current frequency value, the current power value, the preset frequency value and the preset power value of the pumped-storage unit to be analyzed includes:

[0026] Acquiring current information of the pumped-storage unit to be analyzed;

[0027] Preprocessing the current current information to obtain preprocessed current current information;

[0028] The current frequency value and the current power value are determined according to the preprocessed current current information.

[0029] In one embodiment, after performing corresponding frequency control processing on the pumped storage unit to be analyzed according to the target frequency control instruction, the method further includes:

[0030] Obtaining an updated frequency value of the pumped-storage unit to be analyzed;

[0031] Performing a difference process on the updated frequency value and the preset frequency value to obtain an updated frequency difference value corresponding to the pumped-storage unit to be analyzed;

[0032] In the case where the updated frequency difference is greater than the preset difference, generating early warning information corresponding to the pumped-storage unit to be analyzed;

[0033] A target dispatch center terminal corresponding to the pumped-storage unit to be analyzed is determined, and the warning information is sent to the target dispatch center terminal.

[0034] In a second aspect, the present application also provides a pumped storage unit frequency control device, comprising:

[0035] a data acquisition module, configured to obtain, in response to a frequency control request for the pumped-storage unit to be analyzed, a current frequency value, a current power value, a preset frequency value, and a preset power value of the pumped-storage unit to be analyzed;

[0036] a data combination module, configured to perform a difference process on the current frequency value and the preset frequency value to obtain a frequency difference value corresponding to the pumped-storage unit to be analyzed, perform a difference process on the current power value and the preset power value to obtain a power difference value corresponding to the pumped-storage unit to be analyzed, and perform a combination process on the current frequency value and the current power value to obtain combination data corresponding to the pumped-storage unit to be analyzed;

[0037] A model determination module, for querying the correspondence between the unit type and the frequency control instruction prediction model according to the target unit type of the pumped-storage unit to be analyzed, and obtaining the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed;

[0038] An instruction generation module, used for inputting the frequency difference, the power difference and the combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed;

[0039] The frequency control module is used to perform corresponding frequency control processing on the pumped-storage unit to be analyzed according to the target frequency control instruction.

[0040] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0041] In response to a frequency control request for the pumped-storage unit to be analyzed, obtaining a current frequency value, a current power value, a preset frequency value, and a preset power value of the pumped-storage unit to be analyzed;

[0042] Performing a difference processing on the current frequency value and the preset frequency value to obtain a frequency difference value corresponding to the pumped-storage unit to be analyzed, performing a difference processing on the current power value and the preset power value to obtain a power difference value corresponding to the pumped-storage unit to be analyzed, and performing a combination processing on the current frequency value and the current power value to obtain combination data corresponding to the pumped-storage unit to be analyzed;

[0043] According to the target unit type of the pumped-storage unit to be analyzed, query the corresponding relationship between the unit type and the frequency control instruction prediction model to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed;

[0044] Inputting the frequency difference, the power difference and the combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed;

[0045] According to the target frequency control instruction, corresponding frequency control processing is performed on the pumped-storage unit to be analyzed.

[0046] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0047] In response to a frequency control request for the pumped-storage unit to be analyzed, obtaining a current frequency value, a current power value, a preset frequency value, and a preset power value of the pumped-storage unit to be analyzed;

[0048] Performing a difference processing on the current frequency value and the preset frequency value to obtain a frequency difference value corresponding to the pumped-storage unit to be analyzed, performing a difference processing on the current power value and the preset power value to obtain a power difference value corresponding to the pumped-storage unit to be analyzed, and performing a combination processing on the current frequency value and the current power value to obtain combination data corresponding to the pumped-storage unit to be analyzed;

[0049] According to the target unit type of the pumped-storage unit to be analyzed, query the corresponding relationship between the unit type and the frequency control instruction prediction model to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed;

[0050] Inputting the frequency difference, the power difference and the combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed;

[0051] According to the target frequency control instruction, corresponding frequency control processing is performed on the pumped-storage unit to be analyzed.

[0052] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0053] In response to a frequency control request for the pumped-storage unit to be analyzed, obtaining a current frequency value, a current power value, a preset frequency value, and a preset power value of the pumped-storage unit to be analyzed;

[0054] Performing a difference processing on the current frequency value and the preset frequency value to obtain a frequency difference value corresponding to the pumped-storage unit to be analyzed, performing a difference processing on the current power value and the preset power value to obtain a power difference value corresponding to the pumped-storage unit to be analyzed, and performing a combination processing on the current frequency value and the current power value to obtain combination data corresponding to the pumped-storage unit to be analyzed;

[0055] According to the target unit type of the pumped-storage unit to be analyzed, query the corresponding relationship between the unit type and the frequency control instruction prediction model to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed;

[0056] Inputting the frequency difference, the power difference and the combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed;

[0057] According to the target frequency control instruction, corresponding frequency control processing is performed on the pumped-storage unit to be analyzed.

[0058] The above-mentioned pumped storage unit frequency control method, device, computer equipment, storage medium and computer program product first respond to the frequency control request for the pumped storage unit to be analyzed, obtain the current frequency value, current power value, preset frequency value and preset power value of the pumped storage unit to be analyzed, then perform difference processing on the current frequency value and the preset frequency value to obtain the frequency difference value corresponding to the pumped storage unit to be analyzed, perform difference processing on the current power value and the preset power value to obtain the power difference value corresponding to the pumped storage unit to be analyzed, and combine the current frequency value and the current power value. Processing is performed to obtain the combined data corresponding to the pumped-storage unit to be analyzed; then, according to the target unit type of the pumped-storage unit to be analyzed, the corresponding relationship between the unit type and the frequency control instruction prediction model is queried to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed; then, the frequency difference, power difference and combined data are input into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed; finally, according to the target frequency control instruction, the pumped-storage unit to be analyzed is subjected to corresponding frequency control processing. In this way, in the process of frequency control of the pumped-storage unit, by obtaining the current frequency value, current power value, preset frequency value and preset power value of the pumped-storage unit to be analyzed, and performing a series of processing such as difference calculation, combination processing, model prediction, etc., the target frequency control instruction corresponding to the pumped-storage unit to be analyzed can be accurately obtained, and then the corresponding frequency control processing can be performed on the pumped-storage unit to be analyzed more accurately, which is beneficial to improving the frequency control accuracy of the pumped-storage unit; moreover, the whole process does not require human intervention, avoiding the subjective factors in the manual adjustment method, which is prone to errors and leads to the defect of low frequency control accuracy of the pumped-storage unit, thereby improving the frequency control accuracy of the pumped-storage unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 A schematic flow chart of a frequency control method for a pumped storage unit in one embodiment;

[0061] Figure 2 A schematic flow chart of a frequency control method for a pumped storage unit in another embodiment;

[0062] Figure 3A schematic flow chart of a frequency control method for a pumped storage unit in yet another embodiment;

[0063] Figure 4 A schematic diagram of a process of frequency signal acquisition in one embodiment;

[0064] Figure 5 A schematic diagram of a flow chart of receiving a control instruction in one embodiment;

[0065] Figure 6 A schematic diagram of a flow chart of program calculation in one embodiment;

[0066] Figure 7 A schematic diagram of a flow chart of command distribution in one embodiment;

[0067] Figure 8 A schematic diagram of the operation flow of the main modules in one embodiment;

[0068] Fig. 9 is a structural block diagram of a frequency control device for a pumped storage unit in one embodiment;

[0069] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0071] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0072] At present, pumped-storage units have a long operating life and it is difficult for them to meet compatibility requirements, which leads to a series of problems such as large frequency automatic control adjustment errors. In order to improve the power quality of the power system, it is crucial to accurately control the frequency of the pumped-storage units in the power system. However, in the process of frequency control of pumped-storage units, manual adjustment is generally adopted; however, this manual adjustment method has subjective factors and is prone to errors, resulting in low frequency control accuracy of the pumped-storage units. Therefore, the present application provides a frequency control method for pumped-storage units, which can solve the problem of low frequency control accuracy of pumped-storage units and achieve the effect of improving the frequency control accuracy of pumped-storage units.

[0073] In an exemplary embodiment, Figure 1 As shown, a method for frequency control of a pumped storage unit is provided. This embodiment uses the method applied to a server as an example for illustration; it can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be but is not limited to various personal computers, laptops, smart phones and tablet computers; the server can be implemented with an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0074] Step S101 , in response to a frequency control request for a pumped-storage unit to be analyzed, obtaining a current frequency value, a current power value, a preset frequency value and a preset power value of the pumped-storage unit to be analyzed.

[0075] The pumped storage unit to be analyzed refers to the pumped storage unit that needs frequency control.

[0076] The frequency control request refers to the request information for frequency control of the pumped storage unit to be analyzed.

[0077] The current frequency value refers to the frequency value of the pumped storage unit to be analyzed at the current time.

[0078] The current power value refers to the power value of the pumped storage unit to be analyzed at the current time.

[0079] The preset frequency value refers to the frequency setting value. It should be noted that the preset frequency value depends on the situation.

[0080] The preset power value refers to a power setting value. It should be noted that the preset power value depends on the situation.

[0081] Exemplarily, the server receives a frequency control request for a pumped-storage unit to be analyzed, and verifies the frequency control request to obtain a verification result corresponding to the frequency control request; when the verification result indicates that the frequency control request is passed, the server obtains the current frequency value, current power value, preset frequency value and preset power value of the pumped-storage unit to be analyzed.

[0082] Step S102, performing difference processing on the current frequency value and the preset frequency value to obtain the frequency difference value corresponding to the pumped-storage unit to be analyzed, performing difference processing on the current power value and the preset power value to obtain the power difference value corresponding to the pumped-storage unit to be analyzed, and performing combination processing on the current frequency value and the current power value to obtain the combination data corresponding to the pumped-storage unit to be analyzed.

[0083] The frequency difference is used to represent the difference between the current frequency value and the preset frequency value.

[0084] The power difference is used to indicate the difference between the current power value and the preset power value.

[0085] The combined data is used to represent data obtained by combining the current frequency value and the current power value.

[0086] Exemplarily, the server performs difference processing on the current frequency value and the preset frequency value to obtain the difference between the current frequency value and the preset frequency value as the frequency difference corresponding to the pumped-storage unit to be analyzed; then, the server performs difference processing on the current power value and the preset power value to obtain the difference between the current power value and the preset power value as the power difference corresponding to the pumped-storage unit to be analyzed; then, the server combines the current frequency value and the current power value in a preset combination method to obtain combined data corresponding to the pumped-storage unit to be analyzed.

[0087] Step S103, according to the target unit type of the pumped-storage unit to be analyzed, query the corresponding relationship between the unit type and the frequency control instruction prediction model to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed.

[0088] The target unit type refers to the unit type to which the pumped storage unit to be analyzed belongs.

[0089] The corresponding relationship between the unit type and the frequency control instruction prediction model is used to represent the association information between the unit type and the frequency control instruction prediction model. For example, unit type A corresponds to frequency control instruction prediction model a, unit type B corresponds to frequency control instruction prediction model b, and unit type C corresponds to frequency control instruction prediction model c.

[0090] Among them, the target frequency control instruction prediction model refers to the frequency control instruction prediction model corresponding to the pumped storage unit to be analyzed.

[0091] Among them, the frequency control instruction prediction model refers to a network model that can use the frequency difference, power difference and combination data corresponding to the pumped-storage unit to be analyzed to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed, such as a deep neural network model, a convolutional neural network model, etc.

[0092] Exemplarily, the server queries the correspondence between the unit type and the frequency control instruction prediction model according to the target unit type of the pumped-storage unit to be analyzed, and obtains the frequency control instruction prediction model corresponding to the target unit type of the pumped-storage unit to be analyzed as the target frequency control instruction prediction model.

[0093] Step S104, inputting the frequency difference, power difference and combined data into a target frequency control instruction prediction model to obtain a target frequency control instruction corresponding to the pumped storage unit to be analyzed.

[0094] Among them, the target frequency control instruction refers to the frequency control instruction corresponding to the pumped storage unit to be analyzed.

[0095] Exemplarily, the server preprocesses the frequency difference, power difference and combined data to obtain preprocessed frequency difference, preprocessed power difference and preprocessed combined data; then, the server inputs the preprocessed frequency difference, preprocessed power difference and preprocessed combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed.

[0096] Step S105: performing corresponding frequency control processing on the pumped storage unit to be analyzed according to the target frequency control instruction.

[0097] Exemplarily, the server performs integrity verification on the target frequency control instruction to obtain a verification result corresponding to the target frequency control instruction; when the verification result indicates that the target frequency control instruction is passed, the server performs corresponding frequency control processing on the pumped-storage unit to be analyzed according to the target frequency control instruction.

[0098] In the above-mentioned frequency control method for pumped-storage units, first, in response to a frequency control request for the pumped-storage unit to be analyzed, the current frequency value, current power value, preset frequency value and preset power value of the pumped-storage unit to be analyzed are obtained, and then the current frequency value and the preset frequency value are subjected to difference processing to obtain the frequency difference value corresponding to the pumped-storage unit to be analyzed, the current power value and the preset power value are subjected to difference processing to obtain the power difference value corresponding to the pumped-storage unit to be analyzed, and the current frequency value and the current power value are subjected to combination processing to obtain the combination data corresponding to the pumped-storage unit to be analyzed. Then, according to the target unit type of the pumped-storage unit to be analyzed, the correspondence between the unit type and the frequency control instruction prediction model is queried to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed. Then, the frequency difference value, the power difference and the combination data are input into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed. Finally, according to the target frequency control instruction, the corresponding frequency control processing is performed on the pumped-storage unit to be analyzed. In this way, in the process of frequency control of the pumped-storage unit, by obtaining the current frequency value, current power value, preset frequency value and preset power value of the pumped-storage unit to be analyzed, and performing a series of processing such as difference calculation, combination processing, model prediction, etc., the target frequency control instruction corresponding to the pumped-storage unit to be analyzed can be accurately obtained, and then the corresponding frequency control processing can be performed on the pumped-storage unit to be analyzed more accurately, which is beneficial to improving the frequency control accuracy of the pumped-storage unit; moreover, the whole process does not require human intervention, avoiding the subjective factors in the manual adjustment method, which is prone to errors and leads to the defect of low frequency control accuracy of the pumped-storage unit, thereby improving the frequency control accuracy of the pumped-storage unit.

[0099] In an exemplary embodiment, in the above-mentioned step S103, the frequency control method of the pumped-storage unit provided in the present application also includes the step of constructing a correspondence between the unit type and the frequency control instruction prediction model, which specifically includes the following contents: obtaining multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit; each trained frequency control instruction prediction model corresponds to a prediction accuracy and a prediction efficiency; respectively, from the multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit, a frequency control instruction prediction model with a prediction efficiency greater than a preset efficiency is screened out as a candidate frequency control instruction prediction model corresponding to each sample pumped-storage unit; respectively, from the candidate frequency control instruction prediction models corresponding to each sample pumped-storage unit, a candidate frequency control instruction prediction model with the largest prediction accuracy is screened out as a target frequency control instruction prediction model corresponding to each sample pumped-storage unit; obtaining the unit type of each sample pumped-storage unit, and constructing a correspondence between the unit type and the frequency control instruction prediction model according to the unit type of each sample pumped-storage unit and the target frequency control instruction prediction model corresponding to each sample pumped-storage unit.

[0100] The sample pumped-storage unit refers to the pumped-storage unit for training the frequency control command prediction model.

[0101] The prediction accuracy is used to indicate the ability of the frequency control instruction prediction model to make correct predictions.

[0102] The prediction efficiency is used to indicate the time required for the frequency control instruction prediction model to make predictions.

[0103] The preset efficiency refers to a preset efficiency threshold value used to judge the prediction efficiency. It should be noted that the preset efficiency depends on the situation.

[0104] The candidate frequency control instruction prediction model refers to a frequency control instruction prediction model whose prediction efficiency is greater than a preset efficiency.

[0105] Exemplarily, the server obtains multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit; then, the server uses the preset efficiency to judge the prediction efficiency of the frequency control instruction prediction model, and respectively selects the frequency control instruction prediction models with a prediction efficiency greater than the preset efficiency from the multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit, and uses these frequency control instruction prediction models as the candidate frequency control instruction prediction models corresponding to each sample pumped-storage unit; then, the server selects the candidate frequency control instruction prediction model with the highest prediction accuracy from the candidate frequency control instruction prediction models corresponding to each sample pumped-storage unit, and uses the candidate frequency control instruction prediction model as the target frequency control instruction prediction model corresponding to each sample pumped-storage unit; then, the server obtains the unit type of each sample pumped-storage unit from the database; then, the server constructs a correspondence between the unit type and the frequency control instruction prediction model according to the unit type of each sample pumped-storage unit and the target frequency control instruction prediction model corresponding to each sample pumped-storage unit.

[0106] In this embodiment, by pre-constructing the corresponding relationship between the unit type and the frequency control instruction prediction model, it is convenient in practical applications to obtain the target unit type of the pumped-storage unit to be analyzed, and the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed can be quickly and directly determined, which is beneficial to improving the determination efficiency of the target frequency control instruction prediction model.

[0107] In an exemplary embodiment, a plurality of trained frequency control instruction prediction models corresponding to each sample pumped-storage unit are obtained, specifically including the following contents: obtaining the current sample frequency value, the current sample power value, the preset sample frequency value and the preset sample power value of each sample pumped-storage unit; performing difference processing on the current sample frequency value and the preset sample frequency value to obtain the sample frequency difference value corresponding to each sample pumped-storage unit, performing difference processing on the current sample power value and the preset sample power value to obtain the sample power difference value corresponding to each sample pumped-storage unit, and performing combination processing on the current sample frequency value and the current sample power value to obtain the sample power difference value corresponding to each sample pumped-storage unit. The present invention relates to a method for obtaining a plurality of frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit; inputting the sample frequency difference, the sample power difference and the sample combination data into the plurality of frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit, and obtaining the predicted frequency control instruction corresponding to each sample pumped-storage unit; obtaining the actual frequency control instruction corresponding to each sample pumped-storage unit, and iteratively training the plurality of frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit according to the difference between the predicted frequency control instruction and the actual frequency control instruction, and obtaining the plurality of trained frequency control instruction prediction models corresponding to each sample pumped-storage unit.

[0108] The current sample frequency value refers to the current frequency value of the sample pumped-storage unit.

[0109] The current sample power value refers to the current power value of the sample pumped-storage unit.

[0110] The preset sample frequency value refers to the preset frequency value of the sample pumped-storage unit.

[0111] The preset sample power value refers to the preset power value of the sample pumped-storage unit.

[0112] The sample frequency difference is used to represent the difference between the current sample frequency value and the preset sample frequency value.

[0113] The sample power difference is used to represent the difference between the current sample power value and the preset sample power value.

[0114] The sample combination data is used to represent data obtained by combining the current sample frequency value and the current sample power value.

[0115] The predicted frequency control instruction refers to the predicted value corresponding to the frequency control instruction of the sample pumped storage unit.

[0116] The actual frequency control instruction refers to the actual value corresponding to the frequency control instruction of the sample pumped storage unit.

[0117] Exemplarily, the server obtains the current sample frequency value, the current sample power value, the preset sample frequency value and the preset sample power value of each sample pumped-storage unit from the database; then, the server performs difference processing on the current sample frequency value and the preset sample frequency value to obtain the sample frequency difference value corresponding to each sample pumped-storage unit, performs difference processing on the current sample power value and the preset sample power value to obtain the sample power difference value corresponding to each sample pumped-storage unit, and performs combination processing on the current sample frequency value and the current sample power value to obtain the sample combination data corresponding to each sample pumped-storage unit; then, the server inputs the sample frequency difference value, the sample power difference value and the sample combination data into a plurality of frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit to obtain the predicted frequency control instruction corresponding to each sample pumped-storage unit. Command; then, the server obtains the actual frequency control instruction corresponding to each sample pumped-storage unit from the database, and obtains the loss value according to the difference between the predicted frequency control instruction and the actual frequency control instruction; then, the server adjusts the model parameters of the multiple frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit according to the loss value; then, the server re-trains the multiple frequency control instruction prediction models after the model parameters are adjusted corresponding to each sample pumped-storage unit, until the loss value obtained by the multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit is less than the loss value threshold, then the training is stopped, and the multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit are used as the multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit.

[0118] In this embodiment, by pre-training the frequency control instruction prediction model, it is convenient in practical applications to predict the target frequency control instruction corresponding to the pumped-storage unit to be analyzed after obtaining the frequency difference, power difference and combination data of the pumped-storage unit to be analyzed; moreover, the frequency control instruction prediction model receives new data in each round of iteration, and performs internal improvements and optimizations on the model, so as to be able to perform predictions more effectively, which is beneficial to improving the prediction accuracy of the frequency control instruction prediction model.

[0119] In an exemplary embodiment, the above step S104, inputs the frequency difference, power difference and combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed, specifically including the following contents: respectively inputs the frequency difference, power difference and combined data into the feature extraction model for feature extraction processing to obtain a first eigenvector corresponding to the frequency difference, a second eigenvector corresponding to the power difference and a third eigenvector corresponding to the combined data; fuses the first eigenvector, the second eigenvector and the third eigenvector to obtain a fused feature vector corresponding to the pumped-storage unit to be analyzed; inputs the fused feature vector into the target frequency control instruction prediction model to obtain the target frequency control instruction.

[0120] Among them, the feature extraction model refers to a network model that can obtain the feature vector corresponding to the data, such as the transformer model.

[0121] The first eigenvector refers to the eigenvector corresponding to the frequency difference.

[0122] The second eigenvector refers to the eigenvector corresponding to the power difference.

[0123] The third eigenvector refers to the eigenvector corresponding to the combined data.

[0124] The fused feature vector refers to a feature vector obtained by fusing the first feature vector, the second feature vector and the third feature vector.

[0125] Exemplarily, the server inputs the frequency difference, power difference and combined data into the feature extraction model for feature extraction processing, respectively, to obtain a first feature vector corresponding to the frequency difference, a second feature vector corresponding to the power difference and a third feature vector corresponding to the combined data; then, the server obtains a first weight corresponding to the frequency difference, a second weight corresponding to the power difference and a third weight corresponding to the combined data; then, the server fuses the first feature vector, the second feature vector and the third feature vector according to the first weight, the second weight and the third weight, to obtain a fused feature vector corresponding to the pumped-storage unit to be analyzed; then, the server inputs the fused feature vector into the target frequency control instruction prediction model, to obtain multiple predicted frequency control instructions corresponding to the pumped-storage unit to be analyzed, and a predicted probability of each predicted frequency control instruction; then, the server screens out the predicted frequency control instruction with the largest predicted probability from each predicted frequency control instruction, and uses the predicted frequency control instruction as the target frequency control instruction corresponding to the pumped-storage unit to be analyzed.

[0126] In this embodiment, three feature vectors extracted from the frequency difference, power difference and combined data are fused to obtain a fused feature vector, thereby realizing an organic combination of multi-dimensional features and providing more complete input information for the target frequency control instruction prediction model, so that the model can generate control instructions that are more in line with the actual situation, thereby improving the accuracy of determining the target frequency control instructions.

[0127] In an exemplary embodiment, the above step S101, obtaining the current frequency value, current power value, preset frequency value and preset power value of the pumped-storage unit to be analyzed, specifically includes the following contents: obtaining the current current information of the pumped-storage unit to be analyzed; preprocessing the current current information to obtain the preprocessed current current information; determining the current frequency value and the current power value based on the preprocessed current current information.

[0128] The current current information is used to represent the current signal corresponding to the pumped storage unit to be analyzed within the current time.

[0129] The pre-processed current current information refers to the current current information after pre-processing.

[0130] Exemplarily, the server obtains the current current information of the pumped-storage unit to be analyzed through a current sensor; then, the server denoises the current current information to obtain the denoised current current information as the preprocessed current current information; then, the server determines the current frequency value of the pumped-storage unit to be analyzed based on the preprocessed current current information; then, the server obtains the current voltage information of the pumped-storage unit to be analyzed through a voltage sensor, and denoises the current voltage information to obtain the denoised current voltage information as the preprocessed current voltage information; then, the server determines the current power value of the pumped-storage unit to be analyzed based on the preprocessed current current information and the preprocessed current voltage information.

[0131] In this embodiment, by preprocessing the current current information, interference information such as noise and abnormal values ​​in the current current information can be removed, so that the data can be closer to the actual current operating state of the pumped-storage unit, thereby ensuring the accuracy of the current frequency value and the current power value subsequently determined based on these data.

[0132] In an exemplary embodiment, the above-mentioned step S105, after performing corresponding frequency control processing on the pumped-storage unit to be analyzed according to the target frequency control instruction, specifically includes the following contents: obtaining the updated frequency value of the pumped-storage unit to be analyzed; performing difference processing on the updated frequency value and the preset frequency value to obtain the updated frequency difference corresponding to the pumped-storage unit to be analyzed; when the updated frequency difference is greater than the preset difference, generating early warning information corresponding to the pumped-storage unit to be analyzed; determining the target dispatching center terminal corresponding to the pumped-storage unit to be analyzed, and sending the early warning information to the target dispatching center terminal.

[0133] The updated frequency value refers to the frequency value corresponding to the pumped-storage unit to be analyzed after frequency control processing.

[0134] The updated frequency difference is used to represent the difference between the updated frequency value and the preset frequency value.

[0135] The preset difference refers to a preset difference threshold. It should be noted that the preset difference depends on the situation.

[0136] Among them, the early warning information is used to indicate the alarm information corresponding to the abnormal state of the pumped storage unit to be analyzed.

[0137] Among them, the target dispatching center terminal refers to the dispatching center terminal corresponding to the pumped storage unit to be analyzed.

[0138] Exemplarily, after the server performs frequency control processing on the pumped-storage unit to be analyzed, the server obtains the updated frequency value of the pumped-storage unit to be analyzed in real time; then, the server performs difference processing on the updated frequency value and the preset frequency value, and obtains the difference between the updated frequency value and the preset frequency value as the updated frequency difference corresponding to the pumped-storage unit to be analyzed; then, the server uses the preset difference to judge the updated frequency difference; when the updated frequency difference is greater than the preset difference, the server generates early warning information corresponding to the pumped-storage unit to be analyzed; then, the server determines the target dispatching center terminal corresponding to the pumped-storage unit to be analyzed, and sends the early warning information to the target dispatching center terminal.

[0139] In this embodiment, when it is detected that the updated frequency difference is greater than the preset difference, the warning information corresponding to the pumped-storage unit to be analyzed is immediately generated, so that the personnel receiving the information can quickly focus on the problem, facilitate the subsequent rapid adoption of corresponding response measures, improve the efficiency of problem solving, ensure that the pumped-storage unit resumes normal operation as soon as possible, and is conducive to improving the stability of the pumped-storage unit.

[0140] In an exemplary embodiment, Figure 2As shown, another frequency control method for a pumped storage unit is provided, which is described by taking the method applied to a server as an example, and includes the following steps:

[0141] Step S201, in response to a frequency control request for the pumped-storage unit to be analyzed, obtain current current information of the pumped-storage unit to be analyzed; preprocess the current current information to obtain preprocessed current current information; and determine the current frequency value and the current power value based on the preprocessed current current information.

[0142] Step S202, obtaining a preset frequency value and a preset power value of the pumped-storage unit to be analyzed.

[0143] Step S203, performing difference processing on the current frequency value and the preset frequency value to obtain the frequency difference value corresponding to the pumped-storage unit to be analyzed, performing difference processing on the current power value and the preset power value to obtain the power difference value corresponding to the pumped-storage unit to be analyzed, and performing combination processing on the current frequency value and the current power value to obtain the combination data corresponding to the pumped-storage unit to be analyzed.

[0144] Step S204, according to the target unit type of the pumped-storage unit to be analyzed, query the corresponding relationship between the unit type and the frequency control instruction prediction model to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed.

[0145] Step S205, respectively input the frequency difference, power difference and combined data into a feature extraction model for feature extraction processing to obtain a first feature vector corresponding to the frequency difference, a second feature vector corresponding to the power difference and a third feature vector corresponding to the combined data.

[0146] Step S206, fusing the first eigenvector, the second eigenvector and the third eigenvector to obtain a fused eigenvector corresponding to the pumped-storage unit to be analyzed.

[0147] Step S207, inputting the fused feature vector into a target frequency control instruction prediction model to obtain a target frequency control instruction.

[0148] Step S208: performing corresponding frequency control processing on the pumped storage unit to be analyzed according to the target frequency control instruction.

[0149] In the above-mentioned frequency control method for pumped-storage units, in the process of frequency control of the pumped-storage units, by obtaining the current frequency value, current power value, preset frequency value and preset power value of the pumped-storage units to be analyzed, and performing a series of processing such as difference calculation, combination processing, model prediction, etc., the target frequency control instruction corresponding to the pumped-storage units to be analyzed can be accurately obtained, and then the corresponding frequency control processing can be performed on the pumped-storage units to be analyzed more accurately, which is beneficial to improving the frequency control accuracy of the pumped-storage units; moreover, the whole process does not require human intervention, avoiding the subjective factors in the manual adjustment method, which is prone to errors and leads to the defect of low frequency control accuracy of the pumped-storage units, thereby improving the frequency control accuracy of the pumped-storage units.

[0150] In an exemplary embodiment, in order to more clearly illustrate the pumped storage unit frequency control method provided in the embodiment of the present application, the pumped storage unit frequency control method is specifically described below with a specific embodiment. In one embodiment, Figure 3 As shown, the present application also provides a method for controlling the frequency of a pumped-storage unit. In the process of frequency control of the pumped-storage unit, the method first responds to a frequency control request for the pumped-storage unit to be analyzed, obtains the current frequency value, current power value, preset frequency value and preset power value of the pumped-storage unit to be analyzed, then performs a difference processing on the current frequency value and the preset frequency value to obtain the frequency difference value corresponding to the pumped-storage unit to be analyzed, performs a difference processing on the current power value and the preset power value to obtain the power difference value corresponding to the pumped-storage unit to be analyzed, and performs a difference processing on the current frequency value and the current power value Perform combination processing to obtain the combination data corresponding to the pumped-storage unit to be analyzed. Then, according to the target unit type of the pumped-storage unit to be analyzed, query the correspondence between the unit type and the frequency control instruction prediction model to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed. Then, input the frequency difference, power difference and combination data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed. Finally, according to the target frequency control instruction, perform corresponding frequency control processing on the pumped-storage unit to be analyzed. Specifically include the following contents:

[0151] 1. Frequency signal acquisition process, such as Figure 4 As shown:

[0152] (1) Network frequency signal acquisition:

[0153] The grid frequency signal is taken from the PT (Potential Transformer) frequency measurement signal on the low-voltage side of the main transformer, converted into a 4-20mA current signal by a transmitter, and sent to the RTU (Remote Terminal Unit) controlling each unit. The signal sent by the RTU is converted by the preamplifier protocol and sent to the judgment program set in the host computer for logical operation.

[0154] (2) Frequency setting signal acquisition:

[0155] The frequency is set to 50Hz, and this value is directly written into the judgment program of the host computer.

[0156] 2. Control instruction receiving process, such as Figure 5 As shown:

[0157] (1) Dispatching remote command reception:

[0158] The dispatching remote adjustment control command is sent to the communication routing equipment on the power plant side through the dispatching side gateway, and then sent to the power plant gateway. After effective calculation, the value is sent to the host computer system.

[0159] (2) On-site control command reception:

[0160] The on-site control adjustment instructions are set by the operator on duty in the upper computer operator station. After a preliminary judgment of validity, the value is sent to the judgment program in the upper computer system without passing through the gateway.

[0161] 3. Program calculation process, such as Figure 6 As shown:

[0162] (1) Power target value calculation process:

[0163] The frequency difference between the actual bus frequency and the frequency setting is calculated by the PI (Proportional-Integral Controller) regulator, combined with the active setting value and various measurement feedback values ​​after being filtered by the gradient filter, and calculated by the AGC (Automatic Generation Control) to generate the power target setting value. After being reviewed by the effectiveness judgment and safety calculation module, it is distributed evenly to each actuator for frequency regulation and control.

[0164] (2) Frequency difference calculation process:

[0165] During the calculation process of this program, the collected network frequency is filtered and transmitted, and then compared with the frequency setting value (50Hz) to generate Deviation signal calculation = Δf + sΔp. This value is calculated by the PI adjustment module and sent to the AGC calculation module as an input of the AGC calculation process.

[0166] (3) AGC calculation module:

[0167] As the main part of the calculation process, AGC calculation is responsible for comparing the collected field signals with the set values, and then calculating the power setting target value. The AGC calculation module is the core part of the software design and the most important part of the entire frequency control program. This part completes many important functions such as frequency control optimization calculation, reasonable allocation, and optimal control; of course, the effective execution of the AGC calculation process requires effective coordination with other processes to complete its designed functions.

[0168] (4) Effective and secure computing:

[0169] The calculated power setting target value can only be sent to the executable agency for use by the executing agency after effective and safe calculation.

[0170] 4. Command distribution process, such as Figure 7 As shown:

[0171] (1) The local controller RTU has two control modes: "Remote" mode and "Local" mode. When the "Remote" mode is selected, the set value calculated by the safety calculation process can be used by the RTU and the speed governor to control the guide vanes and achieve the purpose of adjusting the active power. When the "Local" mode is selected, the active power can only be controlled by manual operation on site.

[0172] (2) The set value and unit start and stop commands calculated by the host computer monitoring system first pass through the host computer front-end machine and then are sent to the local controller RTU. The RTU controls the start and stop of the unit. The RTU sends the active power set value to the speed governor. The speed governor adjusts the guide vanes according to the current active power feedback to complete the closed-loop control and ensure that the final feedback value is consistent with the set value.

[0173] It should be noted that the overall software structure involved in this embodiment is divided into a control instruction receiving module, a program calculation module, a validity calculation module, a safety calculation module, a control command issuing module and a frequency signal acquisition module. The relationship between each module is as follows: Figure 8 shown.

[0174] In the above embodiment, in the process of frequency control of the pumped storage unit, by obtaining the current frequency value, current power value, preset frequency value and preset power value of the pumped storage unit to be analyzed, and performing a series of processing such as difference calculation, combination processing, model prediction, etc., the target frequency control instruction corresponding to the pumped storage unit to be analyzed can be accurately obtained, and then the corresponding frequency control processing can be performed on the pumped storage unit to be analyzed more accurately, which is conducive to improving the frequency control accuracy of the pumped storage unit; moreover, the whole process does not require manual intervention, avoiding the subjective factors in the manual adjustment method, which is prone to errors and leads to the defect of low frequency control accuracy of the pumped storage unit, thereby improving the frequency control accuracy of the pumped storage unit. At the same time, this embodiment enables the upper function of the energy storage unit to complete the automatic adjustment and control of the unit frequency according to the equipment operation demand or the change of the scheduling set value, and ensures that the set value or adjustment value meets various safety restriction requirements, and passes the review of the safety calculation module, and then sends the value to the executable mechanism through a remote command, and finally realizes the adjustment and control of the frequency. Through frequency control and regulation, the energy storage unit can operate safely and efficiently, ensuring the stability of the grid frequency, thereby ensuring that the unit completes the important tasks of peak load regulation and frequency regulation and accident standby.

[0175] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0176] Based on the same inventive concept, the embodiment of the present application also provides a pumped storage unit frequency control device for implementing the pumped storage unit frequency control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the pumped storage unit frequency control device provided below can refer to the limitations of the pumped storage unit frequency control method above, and will not be repeated here.

[0177] In an exemplary embodiment, Fig. 9As shown, a pumped storage unit frequency control device is provided, comprising: a data acquisition module 901, a data combination module 902, a model determination module 903, an instruction generation module 904 and a frequency control module 905, wherein:

[0178] The data acquisition module 901 is used to obtain the current frequency value, current power value, preset frequency value and preset power value of the pumped-storage unit to be analyzed in response to a frequency control request for the pumped-storage unit to be analyzed.

[0179] The data combination module 902 is used to perform difference processing on the current frequency value and the preset frequency value to obtain the frequency difference value corresponding to the pumped-storage unit to be analyzed, perform difference processing on the current power value and the preset power value to obtain the power difference value corresponding to the pumped-storage unit to be analyzed, and perform combination processing on the current frequency value and the current power value to obtain the combination data corresponding to the pumped-storage unit to be analyzed.

[0180] The model determination module 903 is used to query the correspondence between the unit type and the frequency control instruction prediction model according to the target unit type of the pumped-storage unit to be analyzed, and obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed.

[0181] The instruction generation module 904 is used to input the frequency difference, power difference and combination data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped storage unit to be analyzed.

[0182] The frequency control module 905 is used to perform corresponding frequency control processing on the pumped storage unit to be analyzed according to the target frequency control instruction.

[0183] In an exemplary embodiment, the pumped-storage unit frequency control device also includes a relationship construction module, which is used to obtain multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit; each trained frequency control instruction prediction model corresponds to a prediction accuracy and a prediction efficiency; from the multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit, a frequency control instruction prediction model with a prediction efficiency greater than a preset efficiency is screened out as a candidate frequency control instruction prediction model corresponding to each sample pumped-storage unit; from the candidate frequency control instruction prediction models corresponding to each sample pumped-storage unit, a candidate frequency control instruction prediction model with the largest prediction accuracy is screened out as a target frequency control instruction prediction model corresponding to each sample pumped-storage unit; the unit type of each sample pumped-storage unit is obtained, and according to the unit type of each sample pumped-storage unit and the target frequency control instruction prediction model corresponding to each sample pumped-storage unit, a corresponding relationship between the unit type and the frequency control instruction prediction model is constructed.

[0184] In an exemplary embodiment, the relationship building module is also used to obtain the current sample frequency value, the current sample power value, the preset sample frequency value and the preset sample power value of each sample pumped-storage unit; perform difference processing on the current sample frequency value and the preset sample frequency value to obtain the sample frequency difference value corresponding to each sample pumped-storage unit, perform difference processing on the current sample power value and the preset sample power value to obtain the sample power difference value corresponding to each sample pumped-storage unit, and perform combination processing on the current sample frequency value and the current sample power value to obtain the sample combination value corresponding to each sample pumped-storage unit data; input the sample frequency difference, sample power difference and sample combination data into a plurality of frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit to obtain the predicted frequency control instruction corresponding to each sample pumped-storage unit; obtain the actual frequency control instruction corresponding to each sample pumped-storage unit, and iteratively train the plurality of frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit according to the difference between the predicted frequency control instruction and the actual frequency control instruction to obtain a plurality of trained frequency control instruction prediction models corresponding to each sample pumped-storage unit.

[0185] In an exemplary embodiment, the instruction generation module 904 is also used to input the frequency difference, power difference and combined data into the feature extraction model for feature extraction processing, so as to obtain a first eigenvector corresponding to the frequency difference, a second eigenvector corresponding to the power difference and a third eigenvector corresponding to the combined data; to fuse the first eigenvector, the second eigenvector and the third eigenvector to obtain a fused feature vector corresponding to the pumped-storage unit to be analyzed; and to input the fused feature vector into the target frequency control instruction prediction model to obtain a target frequency control instruction.

[0186] In an exemplary embodiment, the data acquisition module 901 is also used to obtain the current current information of the pumped-storage unit to be analyzed; preprocess the current current information to obtain the preprocessed current current information; and determine the current frequency value and the current power value based on the preprocessed current current information.

[0187] In an exemplary embodiment, the pumped-storage unit frequency control device also includes an information sending module, which is used to obtain an updated frequency value of the pumped-storage unit to be analyzed; perform difference processing on the updated frequency value and the preset frequency value to obtain an updated frequency difference corresponding to the pumped-storage unit to be analyzed; when the updated frequency difference is greater than the preset difference, generate early warning information corresponding to the pumped-storage unit to be analyzed; determine the target dispatching center terminal corresponding to the pumped-storage unit to be analyzed, and send the early warning information to the target dispatching center terminal.

[0188] Each module in the above-mentioned pumped storage unit frequency control device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0189] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as current frequency values ​​and current power values. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a frequency control method of a pumped storage unit is implemented.

[0190] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0191] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0192] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0193] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0194] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0195] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0196] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A frequency control method for a pumped storage unit, characterized in that: The method comprises: In response to a frequency control request for the pumped-storage unit to be analyzed, obtaining a current frequency value, a current power value, a preset frequency value, and a preset power value of the pumped-storage unit to be analyzed; Performing a difference processing on the current frequency value and the preset frequency value to obtain a frequency difference value corresponding to the pumped-storage unit to be analyzed, performing a difference processing on the current power value and the preset power value to obtain a power difference value corresponding to the pumped-storage unit to be analyzed, and performing a combination processing on the current frequency value and the current power value to obtain combination data corresponding to the pumped-storage unit to be analyzed; According to the target unit type of the pumped-storage unit to be analyzed, query the corresponding relationship between the unit type and the frequency control instruction prediction model to obtain the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed; Inputting the frequency difference, the power difference and the combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed; According to the target frequency control instruction, corresponding frequency control processing is performed on the pumped-storage unit to be analyzed.

2. The method according to claim 1, characterized in that: The corresponding relationship between the unit type and the frequency control instruction prediction model is constructed in the following way: Obtain multiple trained frequency control instruction prediction models corresponding to each sample pumped storage unit; each trained frequency control instruction prediction model corresponds to a prediction accuracy and a prediction efficiency; Selecting a frequency control instruction prediction model with a prediction efficiency greater than a preset efficiency from a plurality of trained frequency control instruction prediction models corresponding to each sample pumped-storage unit as a candidate frequency control instruction prediction model corresponding to each sample pumped-storage unit; Selecting the candidate frequency control instruction prediction model with the highest prediction accuracy from the candidate frequency control instruction prediction models corresponding to each sample pumped-storage unit as the target frequency control instruction prediction model corresponding to each sample pumped-storage unit; The unit type of each sample pumped-storage unit is obtained, and according to the unit type of each sample pumped-storage unit and the target frequency control instruction prediction model corresponding to each sample pumped-storage unit, a corresponding relationship between the unit type and the frequency control instruction prediction model is constructed.

3. The method according to claim 2, characterized in that The step of obtaining a plurality of trained frequency control instruction prediction models corresponding to each sample pumped-storage unit comprises: Obtaining a current sample frequency value, a current sample power value, a preset sample frequency value, and a preset sample power value for each sample pumped-storage unit; Performing a difference processing on the current sample frequency value and the preset sample frequency value to obtain a sample frequency difference value corresponding to each sample pumped-storage unit, performing a difference processing on the current sample power value and the preset sample power value to obtain a sample power difference value corresponding to each sample pumped-storage unit, and performing a combination processing on the current sample frequency value and the current sample power value to obtain sample combination data corresponding to each sample pumped-storage unit; Inputting the sample frequency difference, the sample power difference and the sample combination data into a plurality of frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit to obtain a predicted frequency control instruction corresponding to each sample pumped-storage unit; The actual frequency control instruction corresponding to each sample pumped-storage unit is obtained, and according to the difference between the predicted frequency control instruction and the actual frequency control instruction, multiple frequency control instruction prediction models to be trained corresponding to each sample pumped-storage unit are iteratively trained to obtain multiple trained frequency control instruction prediction models corresponding to each sample pumped-storage unit.

4. The method according to claim 1, characterized in that: The step of inputting the frequency difference, the power difference and the combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed includes: Inputting the frequency difference, the power difference and the combined data into a feature extraction model for feature extraction processing respectively, to obtain a first feature vector corresponding to the frequency difference, a second feature vector corresponding to the power difference and a third feature vector corresponding to the combined data; fusing the first eigenvector, the second eigenvector and the third eigenvector to obtain a fused eigenvector corresponding to the pumped-storage unit to be analyzed; The fused feature vector is input into the target frequency control instruction prediction model to obtain the target frequency control instruction.

5. The method according to claim 1, characterized in that: The obtaining of the current frequency value, the current power value, the preset frequency value and the preset power value of the pumped-storage unit to be analyzed includes: Acquiring current information of the pumped-storage unit to be analyzed; Preprocessing the current current information to obtain preprocessed current current information; The current frequency value and the current power value are determined according to the preprocessed current current information.

6. The method according to any one of claims 1 to 5, characterized in that: After performing corresponding frequency control processing on the pumped storage unit to be analyzed according to the target frequency control instruction, the method further includes: Obtaining an updated frequency value of the pumped-storage unit to be analyzed; Performing a difference process on the updated frequency value and the preset frequency value to obtain an updated frequency difference value corresponding to the pumped-storage unit to be analyzed; In the case where the updated frequency difference is greater than the preset difference, generating early warning information corresponding to the pumped-storage unit to be analyzed; A target dispatch center terminal corresponding to the pumped-storage unit to be analyzed is determined, and the warning information is sent to the target dispatch center terminal.

7. A frequency control device for a pumped storage unit, characterized in that: The device comprises: a data acquisition module, configured to obtain, in response to a frequency control request for the pumped-storage unit to be analyzed, a current frequency value, a current power value, a preset frequency value, and a preset power value of the pumped-storage unit to be analyzed; a data combination module, configured to perform a difference process on the current frequency value and the preset frequency value to obtain a frequency difference value corresponding to the pumped-storage unit to be analyzed, perform a difference process on the current power value and the preset power value to obtain a power difference value corresponding to the pumped-storage unit to be analyzed, and perform a combination process on the current frequency value and the current power value to obtain combination data corresponding to the pumped-storage unit to be analyzed; A model determination module, for querying the correspondence between the unit type and the frequency control instruction prediction model according to the target unit type of the pumped-storage unit to be analyzed, and obtaining the target frequency control instruction prediction model corresponding to the pumped-storage unit to be analyzed; An instruction generation module, used for inputting the frequency difference, the power difference and the combined data into the target frequency control instruction prediction model to obtain the target frequency control instruction corresponding to the pumped-storage unit to be analyzed; The frequency control module is used to perform corresponding frequency control processing on the pumped-storage unit to be analyzed according to the target frequency control instruction.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images