Frequency control method and device for new energy station

Abstract

The application provides a frequency control method and device for a new energy station. The application trains a neural network by using grid-connected point data, external data and control data of the new energy station, obtains a primary frequency modulation model and a secondary frequency modulation model of the new energy station, and predicts a control strategy of the new energy station based on the primary frequency modulation model and the secondary frequency modulation model, so that the frequency control of the new energy station is realized. The application mines digital features of new energy data based on a neural network training method, establishes a prediction model of a new energy control strategy, simplifies a modeling method of the new energy station, reduces the complexity of the control strategy prediction model, reduces the calculation time, improves the determination efficiency of the control strategy, and realizes the rapid frequency control of the new energy station.

Description

Frequency control methods and devices for new energy power stations Technical Field

[0001] This invention relates to the field of new energy power generation technology, and in particular to a frequency control method and device for new energy power plants. Background Technology

[0002] With the continuous advancement of large-scale wind power development, high-penetration renewable energy grid connection is a future trend in power grid development. The gradual replacement of traditional synchronous generators by high-penetration renewable energy sources with the grid weakens the system's equivalent inertia, profoundly affecting the grid's frequency dynamic characteristics and posing a threat to the system's safe and stable operation. Therefore, the grid frequency stability issue related to renewable energy integration has become a key factor affecting the development of high-penetration renewable energy, and further in-depth research is needed on frequency response technologies adapted to high-penetration renewable energy grid connection.

[0003] In the study of power system simplified models for power grid frequency problems, the most efficient simplified model for simulation is the Frequency Response (SFR) model. The classic SFR model is only applicable to power systems with pure thermal power units, but it has been extended to accommodate power systems containing hydropower and renewable energy generation. However, the current SFR model is a simplification of the complete power system, used to analyze the frequency response of the entire system. Renewable energy does not have an independent module in the existing SFR model; therefore, a renewable energy frequency response model needs to be established, suitable for research on renewable energy participation in power grid frequency support. Renewable energy power plants typically consist of dozens, hundreds, or even thousands of renewable energy units, employing detailed simulation models (electromagnetic transient models) that include dynamics of power electronic switches and electromagnetic transients of generators. While this model can comprehensively reflect the dynamic characteristics of actual renewable energy units, it has limitations when used to study system frequency dynamics, including long simulation calculation times, difficulty in identifying the main factors affecting virtual inertia control, significant delays in control strategies developed based on simulation results, and difficulty in directly designing and optimizing system control strategies using simulation results. Furthermore, it cannot perform real-time control of wind turbine generators. Summary of the Invention

[0004] This invention provides a frequency control method and apparatus for new energy power stations, which can improve the efficiency of determining control strategies and realize real-time control of new energy power stations.

[0005] In a first aspect, the present invention provides a frequency control method for a renewable energy power station. The method includes: acquiring PMU data at the grid connection point of the renewable energy power station, an external feature set of the renewable energy power station, and control data of the controllable switches of each renewable energy unit; the PMU data includes voltage data, current data, phase angle data, and frequency data; the external feature set includes meteorological characteristics and load characteristics; training a new neural network model based on the PMU data, the external feature set, and the control data to obtain a primary frequency regulation model and a secondary frequency regulation model; predicting a target control strategy based on real-time PMU data, real-time external features, the primary frequency regulation model, and the secondary frequency regulation model; and controlling the controllable switches of each renewable energy unit based on the target control strategy to achieve frequency control of the renewable energy power station.

[0006] In one possible implementation, a target control strategy is predicted based on real-time PMU data, real-time external features, a primary frequency regulation model, and a secondary frequency regulation model. This includes: predicting a first control strategy for the controllable switching of each new energy unit based on the primary frequency regulation model and real-time PMU data; predicting a second control strategy for the controllable switching of each new energy unit based on the secondary frequency regulation model and real-time external features; and adjusting the first control strategy based on the second control strategy to obtain the target control strategy.

[0007] In one possible implementation, a new neural network model is trained based on PMU data, an external feature set, and control data to obtain a primary frequency modulation model and a secondary frequency modulation model, including: generating a first training sample based on PMU data and control data; training a primary frequency modulation model based on the first training sample; generating a second training sample based on the external feature set and control data; and training a secondary frequency modulation model based on the second training sample.

[0008] In one possible implementation, generating a first training sample based on PMU data and control data includes: performing time difference analysis on the PMU data to determine the active power time series and frequency time series; performing principal component analysis on the active power time series and frequency time series to obtain the active power and frequency of multiple scenarios; and determining the first training sample based on the active power and frequency of the multiple scenarios and the control data corresponding to the multiple scenarios.

[0009] In one possible implementation, a second training sample is generated based on an external feature set and control data, including: performing time difference analysis on the external feature set to determine meteorological feature time series and load feature time series; performing principal component analysis on the meteorological feature time series and load feature time series to obtain meteorological features and load features for multiple scenarios; and determining the second training sample based on the meteorological features and load features of multiple scenarios, as well as control data corresponding to multiple scenarios.

[0010] In one possible implementation, the target control strategy includes the active power and frequency output by the renewable energy power station; based on the target control strategy, the controllable switches of each renewable energy unit are controlled to achieve frequency control of the renewable energy power station, including: determining the renewable energy units in operation and their active power based on the active power and the rated power of each renewable energy unit; determining the switching state of the controllable switches of the renewable energy units in operation based on the active power of the units in operation and the frequency output by the renewable energy power station; and controlling the controllable switches of each renewable energy unit based on the switching state of the controllable switches of the units in operation.

[0011] Secondly, embodiments of the present invention provide a frequency control device for a new energy power station. The device includes a communication module and a processing module. The communication module is used to acquire PMU data at the grid connection point of the new energy power station, an external feature set of the new energy power station, and control data of the controllable switches of each new energy unit. The PMU data includes voltage data, current data, phase angle data, and frequency data. The external feature set includes meteorological characteristics and load characteristics. The processing module is used to train a new neural network model based on the PMU data, the external feature set, and the control data to obtain a primary frequency regulation model and a secondary frequency regulation model. Based on real-time PMU data, real-time external features, the primary frequency regulation model, and the secondary frequency regulation model, a target control strategy is predicted. Based on the target control strategy, the controllable switches of each new energy unit are controlled to achieve frequency control of the new energy power station.

[0012] In one possible implementation, the processing module is specifically used to predict a first control strategy for the controllable switching of each new energy unit based on a primary frequency regulation model and real-time PMU data; predict a second control strategy for the controllable switching of each new energy unit based on a secondary frequency regulation model and real-time external characteristics; and adjust the first control strategy based on the second control strategy to obtain the target control strategy.

[0013] In one possible implementation, the processing module is specifically used to generate a first training sample based on PMU data and control data; train a primary frequency modulation model based on the first training sample; generate a second training sample based on the external feature set and control data; and train a secondary frequency modulation model based on the second training sample.

[0014] In one possible implementation, the processing module is specifically used to perform time difference analysis on the PMU data to determine the active power time series and frequency time series; perform principal component analysis on the active power time series and frequency time series to obtain the active power and frequency of multiple scenarios; and determine the first training sample based on the active power and frequency of multiple scenarios and the control data corresponding to the multiple scenarios.

[0015] In one possible implementation, the processing module is specifically used to perform time difference analysis on the external feature set to determine the meteorological feature time series and the load feature time series; perform principal component analysis on the meteorological feature time series and the load feature time series to obtain the meteorological features and load features of multiple scenarios; and determine the second training sample based on the meteorological features and load features of multiple scenarios and the control data corresponding to the multiple scenarios.

[0016] In one possible implementation, the target control strategy includes the active power and frequency output by the renewable energy power station; a processing module, specifically used to determine the renewable energy units in operation and their active power based on the active power and the rated power of each renewable energy unit; to determine the switching state of the controllable switches of the renewable energy units in operation based on the active power of the units in operation and the frequency output by the renewable energy power station; and to control the controllable switches of each renewable energy unit based on the switching state of the controllable switches of the units in operation.

[0017] Thirdly, embodiments of the present invention provide a power system control device, including a memory and a processor. The memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to perform the steps of the method as described in the first aspect and any possible implementation thereof.

[0018] Fourthly, embodiments of the present invention provide a power system including a frequency control device as described in the first aspect and any possible implementation thereof, which performs the steps of the method as described in the first aspect and any possible implementation thereof to realize frequency control of the power system.

[0019] Fifthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the method as described in the first aspect and any possible implementation thereof.

[0020] This invention provides a frequency control method and apparatus for renewable energy power plants. By training a primary frequency regulation model and a secondary frequency regulation model using PMU data, external feature sets, and control data, a target control strategy is predicted based on these models. Then, based on the target control strategy, the controllable switches of each renewable energy unit are controlled to achieve frequency control of the renewable energy power plant. In this process, there is no need to simulate the circuit model of the renewable energy power plant; only real-time data needs to be input into the model to obtain the control strategy. This achieves digital frequency control of the renewable energy power plant, improves the efficiency of control strategy determination, and realizes real-time control of the renewable energy power plant. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 is a flowchart illustrating a frequency control method for a new energy power station provided in an embodiment of the present invention;

[0023] Figure 2 is a structural schematic diagram of a frequency control device for a new energy power station provided in an embodiment of the present invention;

[0024] Figure 3 is a schematic diagram of the structure of a power system control device provided in an embodiment of the present invention. Detailed Implementation

[0025] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0026] In the description of this invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" and "more than one" refer to two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0027] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0028] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or device.

[0029] To make the objectives, technical solutions, and advantages of the present invention clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0030] As shown in Figure 1, this embodiment of the invention provides a frequency control method for a new energy power station. The executing entity is the frequency control device of the new energy power station. The frequency control method includes steps S101-S105.

[0031] S101. Obtain PMU data of the grid connection point of the new energy power station, the external feature set of the new energy power station, and the control data of the controllable switches of each new energy unit.

[0032] Among them, new energy power stations include wind power stations and photovoltaic power stations.

[0033] In this embodiment, the PMU data includes voltage data, current data, phase angle data, and frequency data.

[0034] It should be noted that the PMU data is obtained by a phasor measurement unit (PMU) that uses a synchronous clock (such as the timing signal of GPS) as the data sampling reference clock source.

[0035] For example, PMU data may include positive sequence voltage magnitude, positive sequence voltage angle, A-phase voltage magnitude, A-phase voltage angle, B-phase voltage magnitude, B-phase voltage angle, C-phase voltage magnitude, C-phase voltage angle, positive sequence current magnitude, positive sequence current phase angle, A-phase current value, A-phase current phase angle, B-phase current value, B-phase current phase angle, C-phase current value, C-phase current phase angle, active power, reactive power, frequency, and frequency change rate.

[0036] In this embodiment of the application, the external feature set includes meteorological features and load features.

[0037] In some embodiments, the external feature set may also include hydrological features and external environmental features.

[0038] In some embodiments, the control data of the controllable switches of each new energy unit includes the switch's on / off state, on-time sequence, off-time sequence, etc.

[0039] In some embodiments, the control data for the controllable switches of each new energy unit may also include the active power and frequency of each new energy unit.

[0040] S102. Based on PMU data, external feature set and control data, train the new neural network model to obtain the primary frequency modulation model and the secondary frequency modulation model.

[0041] As one possible implementation, step S102 can be specifically implemented as steps S1021-S1024.

[0042] S1021. Generate a first training sample based on the PMU data and the control data.

[0043] For example, the frequency control device can perform time difference analysis on the PMU data to determine the active power time series and frequency time series; perform principal component analysis on the active power time series and frequency time series to obtain the active power and frequency of multiple scenarios; and determine the first training sample based on the active power and frequency of the multiple scenarios and the control data corresponding to the multiple scenarios.

[0044] In some embodiments, the first training sample takes PMU data as input and control data as output.

[0045] S1022. Based on the first training sample, the first frequency modulation model is trained.

[0046] S1023. Generate a second training sample based on the external feature set and the control data.

[0047] For example, the frequency control device can perform time difference analysis on the external feature set to determine the meteorological feature time series and the load feature time series; perform principal component analysis on the meteorological feature time series and the load feature time series to obtain meteorological features and load features for multiple scenarios; and determine the second training sample based on the meteorological features and load features of the multiple scenarios and the control data corresponding to the multiple scenarios.

[0048] In some embodiments, the second training sample takes meteorological and load characteristics as input and control data as output.

[0049] S1024. Based on the second training sample, the second frequency modulation model is trained.

[0050] S103. Based on real-time PMU data, real-time external features, primary frequency modulation model and secondary frequency modulation model, the target control strategy is predicted.

[0051] As one possible implementation, step S103 can be specifically implemented as steps S1031-S1033.

[0052] S1031. Based on the primary frequency regulation model and the real-time PMU data, the first control strategy for the controllable switch of each new energy unit is predicted.

[0053] S1032. Based on the secondary frequency modulation model and the real-time external characteristics, predict the second control strategy for the controllable switch of each new energy unit.

[0054] S1033. Adjust the first control strategy based on the second control strategy to obtain the target control strategy.

[0055] In this embodiment of the application, the target control strategy includes the active power and frequency output by the new energy power station.

[0056] As one possible implementation, the frequency control device can calculate the difference between the first control strategy and the second control strategy. If the difference is within a preset range, the second control strategy is directly determined as the target control strategy; if the difference is not within the preset range, the intermediate value between the first control strategy and the second control strategy is determined as the target control strategy.

[0057] S104. Based on the target control strategy, control the controllable switches of each new energy unit to realize the frequency control of the new energy power station.

[0058] As one possible implementation, step S104 can be specifically implemented as steps S1041-S1043.

[0059] S1041. Based on the active power and the rated power of each new energy unit, determine the new energy units put into operation among the new energy units, and the active power of the new energy units put into operation.

[0060] S1042. Based on the active power of the new energy generating unit put into operation and the frequency output by the new energy power station, determine the switching state of the controllable switch of the new energy generating unit put into operation.

[0061] S1043. Based on the switching status of the controllable switches of the new energy generating units that have been put into operation, control the controllable switches of each new energy generating unit.

[0062] This invention provides a frequency control method, apparatus, and control equipment for renewable energy power plants. By using PMU data, external feature sets, and control data, a primary frequency regulation model and a secondary frequency regulation model are trained. Based on these models, a target control strategy is predicted. Then, based on the target control strategy, the controllable switches of each renewable energy unit are controlled to achieve frequency control of the renewable energy power plant. In this process, there is no need to simulate the circuit model of the renewable energy power plant; only real-time data needs to be input into the model to obtain the control strategy. This achieves digital frequency control of the renewable energy power plant, improves the efficiency of control strategy determination, and realizes real-time control of the renewable energy power plant.

[0063] It should be noted that this invention separates the PMU data of new energy power plant grid connection points from the full sample set, and obtains the active power and frequency time series of power plant level or distributed new energy through data preprocessing, thereby deeply mining the digital characteristics in the sample set and better realizing the frequency response principle.

[0064] It should be noted that this invention uses methods such as component analysis to decompose the first frequency modulation response process sequence, and uses the time difference method to identify the frequency modulation parameters, thereby obtaining various components and principal components in the sample, thus enabling better model training and data mining.

[0065] It should be noted that this invention analyzes the frequency response principle of active power control strategies for various types of new energy sources, establishes its external characteristic model based on the composition of the power electronic interface at the power station level, and verifies the effectiveness of the theoretical model in characterizing the external characteristics of the power station.

[0066] It should be noted that this invention is based on the full sample dataset of the system to obtain a wide-area feature set such as meteorological resources, load, hydrological resources, and external environmental attribute data. It uses neural networks and other methods to learn the correlation between the station ontological control strategy, the wide-area feature set and the frequency response characteristics of new energy sources.

[0067] It should be noted that this invention uses decision numbers and other methods to classify and aggregate new energy power stations with various features as input, thereby achieving data aggregation for different types of new energy power stations and enabling the prediction of control strategies for different types of new energy power stations.

[0068] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0069] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0070] Figure 2 shows a schematic diagram of a frequency control device for a new energy power station according to an embodiment of the present invention. The frequency control device 200 includes a communication module 201 and a processing module 202.

[0071] The communication module 201 is used to acquire PMU data of the grid connection point of the new energy power station, the external feature set of the new energy power station, and the control data of the controllable switches of each new energy unit; the PMU data includes voltage data, current data, phase angle data and frequency data; the external feature set includes meteorological features and load features.

[0072] The processing module 202 is used to train a new neural network model based on PMU data, external feature set and control data to obtain a primary frequency regulation model and a secondary frequency regulation model; based on real-time PMU data, real-time external features, primary frequency regulation model and secondary frequency regulation model, predict the target control strategy; based on the target control strategy, control the controllable switches of each new energy unit to realize the frequency control of the new energy power station.

[0073] In one possible implementation, the processing module 202 is specifically used to predict a first control strategy for the controllable switch of each new energy unit based on a primary frequency regulation model and real-time PMU data; predict a second control strategy for the controllable switch of each new energy unit based on a secondary frequency regulation model and real-time external characteristics; and adjust the first control strategy based on the second control strategy to obtain a target control strategy.

[0074] In one possible implementation, the processing module 202 is specifically used to generate a first training sample based on PMU data and control data; train a primary frequency modulation model based on the first training sample; generate a second training sample based on the external feature set and control data; and train a secondary frequency modulation model based on the second training sample.

[0075] In one possible implementation, the processing module 202 is specifically used to perform time difference analysis on the PMU data to determine the active power time series and frequency time series; perform principal component analysis on the active power time series and frequency time series to obtain the active power and frequency of multiple scenarios; and determine the first training sample based on the active power and frequency of multiple scenarios and the control data corresponding to the multiple scenarios.

[0076] In one possible implementation, the processing module 202 is specifically used to perform time difference analysis on the external feature set to determine the meteorological feature time series and the load feature time series; perform principal component analysis on the meteorological feature time series and the load feature time series to obtain the meteorological features and load features of multiple scenarios; and determine the second training sample based on the meteorological features and load features of multiple scenarios and the control data corresponding to the multiple scenarios.

[0077] In one possible implementation, the target control strategy includes the active power and frequency output by the renewable energy power station; the processing module 202 is specifically used to determine the renewable energy units in operation and their active power based on the active power and the rated power of each renewable energy unit; to determine the switching state of the controllable switches of the renewable energy units in operation based on the active power of the renewable energy units in operation and the frequency output by the renewable energy power station; and to control the controllable switches of each renewable energy unit based on the switching state of the controllable switches of the renewable energy units in operation.

[0078] Figure 3 is a schematic diagram of the structure of a power system control device according to an embodiment of the present invention. As shown in Figure 3, the control device 300 of this embodiment includes: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. When the processor 301 executes the computer program 303, it implements the steps in the above-described method embodiments, such as steps 101 to 104 shown in Figure 1. Alternatively, when the processor 301 executes the computer program 303, it implements the functions of each module / unit in the above-described device embodiments, such as the functions of the communication module 201 and the processing module 202 shown in Figure 2.

[0079] For example, the computer program 303 can be divided into one or more modules / units, which are stored in the memory 302 and executed by the processor 301 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 303 in the control device 300. For example, the computer program 303 can be divided into a communication module 201 and a processing module 202 as shown in FIG. 2.

[0080] The processor 301 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0081] The memory 302 can be an internal storage unit of the control device 300, such as a hard disk or memory of the control device 300. The memory 302 can also be an external storage device of the control device 300, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the control device 300. Furthermore, the memory 302 can include both internal storage units and external storage devices of the control device 300. The memory 302 is used to store the computer program and other programs and data required by the terminal. The memory 302 can also be used to temporarily store data that has been output or will be output.

[0082] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0083] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0084] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0085] In the embodiments provided by this invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0086] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0087] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0088] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0089] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A frequency control method for a new energy power station, characterized in that, include: Acquire PMU data of the grid connection point of the new energy power station, the external feature set of the new energy power station, and the control data of the controllable switches of each new energy unit; the PMU data includes voltage data, current data, phase angle data, and frequency data; the external feature set includes meteorological features and load features; Based on the PMU data, the external feature set, and the control data, a new neural network model is trained to obtain a primary frequency regulation model and a secondary frequency regulation model, including: generating a first training sample based on the PMU data and the control data; training the primary frequency regulation model based on the first training sample; generating a second training sample based on the external feature set and the control data; training the secondary frequency regulation model based on the second training sample; predicting a target control strategy based on real-time PMU data, real-time external features, the primary frequency regulation model, and the secondary frequency regulation model; and controlling the controllable switching of each new energy unit based on the target control strategy to achieve frequency control of the new energy power station. Generating the first training sample based on the PMU data and the control data includes: performing time difference analysis on the PMU data to determine the active power time series and frequency time series; performing principal component analysis on the active power time series and frequency time series to obtain the active power and frequency for multiple scenarios; and determining the first training sample based on the active power and frequency for the multiple scenarios and the control data corresponding to the multiple scenarios.

2. The frequency control method for new energy power stations according to claim 1, characterized in that, The step of predicting the target control strategy based on real-time PMU data, real-time external features, the primary frequency regulation model, and the secondary frequency regulation model includes: predicting a first control strategy for the controllable switching of each new energy unit based on the primary frequency regulation model and the real-time PMU data; predicting a second control strategy for the controllable switching of each new energy unit based on the secondary frequency regulation model and the real-time external features; and adjusting the first control strategy based on the second control strategy to obtain the target control strategy.

3. The frequency control method for new energy power stations according to claim 1, characterized in that, The step of generating a second training sample based on the external feature set and the control data includes: performing time difference analysis on the external feature set to determine meteorological feature time series and load feature time series; performing principal component analysis on the meteorological feature time series and load feature time series to obtain meteorological features and load features for multiple scenarios; and determining the second training sample based on the meteorological features and load features of the multiple scenarios and the control data corresponding to the multiple scenarios.

4. The frequency control method for new energy power stations according to claim 1, characterized in that, The target control strategy includes the active power and frequency output by the renewable energy power station; the step of controlling the controllable switches of each renewable energy unit based on the target control strategy to achieve frequency control of the renewable energy power station includes: determining the renewable energy units in operation and their active power based on the active power and the rated power of each renewable energy unit; determining the switching state of the controllable switches of the renewable energy units in operation based on the active power and the frequency output by the renewable energy power station; and controlling the controllable switches of each renewable energy unit based on the switching state of the controllable switches of the renewable energy units in operation.

5. A frequency control device for a new energy power station, characterized in that, include: The communication module is used to acquire PMU data of the grid connection point of the new energy power station, the external feature set of the new energy power station, and the control data of the controllable switches of each new energy unit; the PMU data includes voltage data, current data, phase angle data, and frequency data; the external feature set includes meteorological features and load features; The processing module is used to train a new neural network model based on the PMU data, the external feature set, and the control data to obtain a primary frequency regulation model and a secondary frequency regulation model; predict a target control strategy based on real-time PMU data, real-time external features, the primary frequency regulation model, and the secondary frequency regulation model; and control the controllable switches of each new energy unit based on the target control strategy to realize the frequency control of the new energy power station.

6. The frequency control device for a new energy power station according to claim 5, characterized in that, The processing module is specifically used to predict a first control strategy for the controllable switching of each new energy unit based on the primary frequency regulation model and the real-time PMU data; and to predict a second control strategy for the controllable switching of each new energy unit based on the secondary frequency regulation model and the real-time external characteristics. The first control strategy is adjusted based on the second control strategy to obtain the target control strategy.

7. A control device for a power system, characterized in that, The control device includes a memory and a processor. The memory stores a computer program, and the processor is used to call and run the computer program stored in the memory to perform the method as described in any one of claims 1 to 4.

8. An electric power system, characterized in that, The power system includes a frequency control device for a new energy power station as described in claim 5 or 6, to perform the method as described in any one of claims 1 to 4 to achieve frequency control of the power system.

Images