Black start method and system for integrated wind and storage equipment at station level based on data-driven model

Abstract

The present invention provides a site-level wind-storage integrated machine black start method and system based on a data-driven model, including: obtaining the operating data of the wind turbine side and the converter side of the onshore wind farm throughout the year; constructing a neural network model with the operating data as a training set; inputting the test set into the neural network model, comparing the output value with the actual value to obtain the actual and predicted deviations, and then optimizing the wind turbine data-driven model; taking the annual average of the power of a single wind turbine output by the wind turbine data-driven model, and sorting them from high to low to form a wind farm wind turbine power output capacity sequence, and thereby determining the installation position of the wind-storage integrated machine; designing a site-level black start timing based on the wind-storage integrated machine, and after all the wind-storage integrated machines are connected to the grid, calculating the total power that can be provided by the started wind-storage integrated machines and the power required by the single wind turbine that has not been started in the field. The wind-storage integrated machine black start method of the present invention is used to improve the support capacity of the wind farm for the onshore power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of wind farm black start, and in particular to a site-level wind farm integrated storage machine black start method and system based on a data-driven model. Background Art

[0002] At present, the proportion of new energy in my country is showing a trend of vigorous development. A large number of power electronic equipment are connected to the power grid, and the inertial support capacity of the power grid is gradually reduced. At the same time, the scale of my country's power system is very large and the power grid structure is extremely complex. Under this background, the power grid is more sensitive to extreme weather, accidents and other events, and is more prone to large-scale power outages and other power grid operation accidents.

[0003] At present, most of the mainstream black start schemes in my country's power grid choose thermal power plants or hydropower plants as black start power sources. The application of new energy technologies such as wind power and energy storage to black start schemes is still under research. As an emerging technology, wind-storage integrated machine has the advantages of flexible operation and strong controllability. How to reasonably and efficiently apply wind-storage integrated machine to the black start scheme of the power grid has become an urgent problem to be solved.

[0004] Based on this, the inventor of the present application designed a black start method and system for a station-level wind-storage integrated machine based on a data-driven model to overcome the above-mentioned technical problems. Summary of the invention

[0005] The technical problem to be solved by the present invention is to overcome the defect of weak supporting capacity of wind farms for power grids in the prior art, and to provide a black start method and system for a site-level wind-storage integrated machine based on a data-driven model.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] The present invention provides a black start method for a station-level wind-storage integrated machine based on a data-driven model, which is characterized by comprising:

[0008] Obtain the operating data of wind turbines and converters on onshore wind farms throughout the year;

[0009] Using the operating data as a training set and building a neural network model;

[0010] The test set is input into the neural network model, the output value is compared with the actual value and the deviation between the actual value and the predicted value is obtained, and then the wind turbine data-driven model is optimized;

[0011] The power of a single wind turbine output by the wind turbine data driving model is averaged annually and sorted from high to low to form a wind farm wind turbine power output capacity sequence, and the installation position of the wind-storage integrated machine is determined based on this;

[0012] Design a station-level black start timing based on the wind-storage integrated machine, and after all the wind-storage integrated machines are connected to the grid, calculate the total power that can be provided by the started wind-storage integrated machines and the power required by the single wind turbine that has not been started in the field;

[0013] The integrated wind and energy storage machine is used to support other wind turbines to complete the start-up without energy storage one by one. After all wind turbines in the wind farm meet the grid connection requirements and are connected to the grid, a stable bus voltage of the collector line in the wind farm is established to complete the black start task at the wind farm station level.

[0014] According to one embodiment of the present invention, the operation data on the wind turbine side includes wind speed and machine-end output power;

[0015] The operation data on the converter side includes three-phase voltage and three-phase current.

[0016] According to one embodiment of the present invention, the neural network model includes a four-layer neural network structure of an input layer, a perception layer, a hidden layer and an output layer;

[0017] The input layer is the input data of the wind turbine side and the converter side, the perception layer includes ten neurons, the hidden layer includes two layers with a total of 16 neurons, and the output layer is the power and impedance of a motor node. At the same time, according to the Thevenin equivalent principle, a wind turbine node is equivalent to a voltage source and an impedance in parallel.

[0018] According to an embodiment of the present invention, the power of a single wind turbine output by the wind turbine data driving model is averaged annually and sorted from high to low to form a wind farm wind turbine power output capacity sequence, and the installation position of the wind turbine storage integrated machine is determined based on this, including:

[0019] Taking into account the economic cost of the energy storage unit, the line loss cost and the node voltage deviation, the number of the wind-storage integrated machines connected to the bus is determined, and the specific installation positions of the wind-storage integrated machines are determined according to the sequence.

[0020] According to an embodiment of the present invention, the design is based on the site-level black start timing of the wind-storage integrated machine, including:

[0021] The integrated wind and energy storage machine is started first to provide excitation current for the wind turbine. After the voltage amplitude, phase and frequency of the driving wind turbine meet the grid-connected requirements, the integrated wind and energy storage machine is connected to the collector line bus to provide voltage and frequency reference for other wind turbines to be started.

[0022] According to an embodiment of the present invention, after all the wind turbines and energy storage integrated machines are connected to the grid, the total power that can be provided by the started wind turbines and energy storage integrated machines and the power required by the single wind turbines that have not been started in the field are calculated, including:

[0023] According to the following formula:

[0024]

[0025] Among them, n NEW is the number of wind turbines that are not started that can be driven by the electric energy generated by the wind turbines that have been started in the wind farm, wherein the started wind turbines include the started wind turbines and energy storage integrated machines; P W The power required to start a single fan;

[0026] According to the obtained wind turbine node voltage support capability sequence, the wind turbines that have been set as the wind-storage integrated machine are excluded, and the top n wind turbines with the strongest voltage support capability are determined. NEW The typhoon turbine started up and connected to the grid.

[0027] According to an embodiment of the present invention, the wind-storage integrated machine is used to support other wind turbines to complete the start-up without energy storage one by one. After all wind turbines in the wind farm meet the grid connection requirements and are connected to the grid, a stable bus voltage of the collector line in the wind farm is established to complete the black start task at the wind farm station level, including:

[0028] The control mode of the energy storage unit of the wind-storage integrated machine is switched from V / f control to P / Q control for subsequent other power grid restoration work.

[0029] The present invention also provides a station-level wind-storage integrated machine black start system based on a data-driven model, which is characterized by comprising:

[0030] The acquisition module obtains the operating data of the wind turbine and converter sides of the onshore wind farm throughout the year;

[0031] A construction module, used to use the operating data as a training set and construct a neural network model;

[0032] An optimization module, used for inputting the test set into the neural network model, comparing the output value with the actual value and obtaining the deviation between the actual value and the predicted value, and then optimizing the wind turbine data-driven model;

[0033] A determination module is used to take the annual average of the power of a single wind turbine output by the wind turbine data driving model, and sort them from high to low to form a wind farm wind turbine power output capacity sequence, and thereby determine the installation location of the wind-storage integrated machine;

[0034] The calculation module is used to design a site-level black start timing based on the wind-storage integrated machine, and after all the wind-storage integrated machines are connected to the grid, calculate the total power that can be provided by the started wind-storage integrated machines and the power required by a single wind turbine that has not been started in the site.

[0035] The present invention also provides an electronic device, which is characterized in that it includes: a processor and a memory, the memory stores programs or instructions that can be run on the processor, and the program or instructions are executed by the processor to implement the black start method of the station-level wind-storage integrated machine based on the data-driven model as described above.

[0036] The present invention also provides a readable storage medium, which is characterized in that a program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the black start method of the station-level wind-storage integrated machine based on the data-driven model as described above is implemented.

[0037] The positive and progressive effects of the present invention are:

[0038] The present invention provides a site-level wind-storage integrated machine black start method and system based on a data-driven model. In order to solve the problem that the structure and operating parameters of the wind turbine change slightly after a long period of operation, resulting in reduced accuracy of the wind turbine model, the wind turbine data-driven model obtained by training a neural network with the wind turbine historical data is closer to the actual model of the wind turbine at this time, which is conducive to real-time perception and prediction of the wind turbine status.

[0039] Moreover, based on the black start control timing of the station-level integrated wind and storage machines, the wind farm follows the black start strategy provided by the present invention, first using multiple integrated wind and storage machines to quickly start, establish stable voltage and frequency references, and then quickly drive other wind turbines in the station to start. Compared with the traditional solution of starting and connecting a single wind turbine to the grid in sequence, the black start time of the entire station-level wind farm is effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and other features, properties and advantages of the present invention will become more apparent through the following description in conjunction with the accompanying drawings and embodiments, in which:

[0041] Figure 1 It is a flow chart of a black start method of a station-level wind-storage integrated machine based on a data-driven model of the present invention;

[0042] Figure 2 This is a diagram of the station-level black start hierarchical model of the present invention;

[0043] Figure 3 The neural network and equivalent model diagram of the data-driven fan of the present invention;

[0044] Figure 4 This is a timing flow chart of the black start of the station-level wind and storage integrated machine of the present invention;

[0045] Figure 5 It is a schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0047] Embodiments of the present invention will now be described in detail with reference to the accompanying drawings. Reference will now be made in detail to preferred embodiments of the present invention, examples of which are shown in the accompanying drawings. Wherever possible, the same reference numerals will be used in all drawings to represent the same or similar parts. In addition, although the terms used in the present invention are selected from well-known and commonly used terms, some of the terms mentioned in the specification of the present invention may be selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant parts of the description of this article. In addition, it is required to understand the present invention not only by the actual terms used, but also by the meaning implied by each term.

[0048] Reference Figure 1 The present invention proposes a black start method for a station-level wind and storage integrated machine based on a data-driven model, comprising:

[0049] S110. Obtaining the operating data of the wind turbine side and the converter side of the onshore wind farm throughout the year.

[0050] Please refer to Figure 2 , Figure 2 This is a hierarchical model diagram of the station-level black start of the present invention. Among them, the wind turbine side selects wind speed and machine-end output power, and the converter side selects three-phase current and three-phase voltage.

[0051] S120, using the running data as a training set and building a neural network model.

[0052] Please refer to Figure 3 ,The neural network model adopts a four-layer neural network structure of input layer, ,perception layer, hidden layer and output layer. The input layer is the input data of the wind ,turbine side and the converter side. The perception layer is composed of ten neural units, the hidden layer is composed of two layers of 16 neural units. The output layer is designed as the power and impedance of a wind ,turbine node.

[0053] S130, input the test set into the neural network model, compare the output value with the actual value and obtain the deviation between the actual and the predicted value, and then optimize the wind turbine data-driven model.

[0054] Specifically, the neural network algorithm uses the Adam algorithm. The Adam algorithm is applied to large models and data sets, and its optimization training effect is the best. The Adam algorithm iterates once, inputs the data set, obtains the random target gradient within the time step, and updates the biased first-order moment estimate and the second-order original moment estimate:

[0055] g t ←▽ θ f t (θt-1 );

[0056] m t ←β1·m t-1 +(1-β1)·g t ;

[0057]

[0058] Calculate the bias-corrected first-order moment estimate and the second-order original moment estimate at this moment:

[0059]

[0060] Substitute it into the iteration formula to complete an update of the input data.

[0061]

[0062] The algorithm parameters are set to the default values ​​α = 0.001, β1 = 0.9, β2 = 0.999, Where α is the learning rate of the neural network, which is used to control the update rate of the weights; β1 and β2 are the exponential decay rates of the first-order moment estimate and the second-order moment estimate, respectively; m t is the data momentum; v t is the variance of the gradient transformation, respectively g t The output set of the neural network is the node power value and impedance value of a single wind turbine. By using the Thevenin equivalent principle, a wind turbine node is equivalent to the external characteristics of a voltage source in parallel with an impedance, which is convenient for the subsequent site selection analysis of the wind-storage integrated machine.

[0063] S140, taking the annual average of the power of a single wind turbine output by the wind turbine data driving model, and sorting them from high to low to form a wind farm wind turbine power output capacity sequence, and using this to determine the installation location of the wind-storage integrated machine.

[0064] Specifically, the economic cost of the energy storage unit, the line loss cost and the node voltage deviation are taken into consideration to determine the number of wind-storage integrated machines connected to the bus, and the specific installation locations of the wind-storage integrated machines are determined based on the sequence.

[0065] S150. Design the station-level black start timing based on the wind-storage integrated machine, and after all the wind-storage integrated machines are connected to the grid, calculate the total power that can be provided by the started wind-storage integrated machines and the power required by the single wind turbine that has not been started in the site.

[0066] Reference Figure 4 The specific black start sequence process at the station level is as follows:

[0067] n WEThe wind turbine energy storage system starts to provide excitation current for the wind turbine, driving the voltage amplitude, phase and frequency of the wind turbine to meet the grid connection requirements. The wind turbine energy storage system is connected to the collector line bus to provide voltage and frequency reference for other wind turbines to be started. At this time, the energy storage unit adopts the V / f control mode, where the power that a single wind turbine energy storage system can provide is P WE .

[0068] After all wind turbines and energy storage systems are connected to the grid, calculate the total power that can be provided by the started wind turbines and energy storage systems and the power required by the single wind turbines that have not been started in the field according to the following formula:

[0069]

[0070] n NEW The power required to start a single wind turbine is P W According to the obtained wind turbine node voltage support capability sequence, exclude the wind turbines that have been set as wind-storage integrated machines, and determine the top n wind turbines with the strongest voltage support capability. NEW The typhoon turbine was started and connected to the grid.

[0071] Judgement NEW After the wind turbine is fully started, if not, wait for the wind turbine to start. If it is fully started, determine whether all wind turbines in the entire wind farm have started. Repeat this process until all wind turbines have started and are connected to the grid.

[0072] S160, using the wind-storage integrated machine to support other wind turbines to complete the start-up without energy storage one by one, and after all wind turbines in the wind farm meet the grid-connected requirements and are connected to the grid, establish a stable bus voltage of the collector line in the wind farm to complete the station-level black start task of the wind farm.

[0073] The specific timing process of starting the present invention is as follows:

[0074] The first wind-storage integrated machine uses energy storage as a backup power supply to provide control power to achieve the yaw and pitch control of the unit, and drives the impeller and generator through wind power. After the generator speed reaches the set value, the converter starts automatically, establishes a stable AC voltage on the grid side, and cuts out the energy storage device. The main control system receives instructions from the converter and stabilizes the generator speed at a reasonable value through pitch control. Except for the wind-storage integrated machine, other wind turbines in the wind farm, combined with the previous startup sequence, obtain the stable power supply (i.e. voltage and frequency reference) provided by the wind-storage integrated machine through the collector line, and finally realize the startup and isolated grid operation of the entire wind farm.

[0075] That is, in the event of a total power outage at the wind farm, the wind-storage integrated machine can still rely on the short-term support of energy storage, and with the help of the voltage source control mode of the wind power converter and the assistance of the main control system, realize the autonomous black start process of a single wind turbine. Afterwards, through the collector line, the wind-storage integrated machine wind turbine can provide a stable power supply (i.e., voltage and frequency reference) for other wind turbines in the wind farm, supporting other wind turbines to complete the start-up without energy storage one by one, and finally realize the black start and isolated grid operation of the entire wind farm.

[0076] In summary, the present invention provides a black start method and system for a station-level wind-storage integrated machine based on a data-driven model. In order to solve the problem that the structure and operating parameters of the wind turbine change slightly after a long period of operation, resulting in reduced accuracy of the wind turbine model, the wind turbine data-driven model obtained by training a neural network with historical data of the wind turbine is closer to the actual model of the wind turbine at this time, which is conducive to real-time perception and prediction of the wind turbine status.

[0077] Moreover, based on the black start control timing of the station-level integrated wind and storage machines, the wind farm follows the black start strategy provided by the present invention, first using multiple integrated wind and storage machines to quickly start, establish stable voltage and frequency references, and then quickly drive other wind turbines in the station to start. Compared with the traditional solution of starting and connecting a single wind turbine to the grid in sequence, the black start time of the entire station-level wind farm is effectively reduced.

[0078] The present invention further proposes a station-level wind-storage integrated machine black start system based on a data-driven model. The station-level wind-storage integrated machine black start system based on a data-driven model adopts the above station-level wind-storage integrated machine black start method based on a data-driven model. The black start system includes:

[0079] An acquisition module is used to obtain the operating data of the wind turbine side and the converter side of the onshore wind farm throughout the year;

[0080] A building module is used to use the running data as a training set and build a neural network model;

[0081] The optimization module is used to input the test set into the neural network model, compare the output value with the actual value and obtain the deviation between the actual and predicted values, and then optimize the wind turbine data-driven model;

[0082] A determination module is used to sort the power averages output by the wind turbine data-driven model from high to low to form a wind turbine node voltage support capacity sequence, and thereby determine the installation location of the wind turbine storage integrated machine;

[0083] The calculation module is used to design the station-level black start timing based on the wind-storage integrated machine, and after all the wind-storage integrated machines are connected to the grid, calculate the total power that can be provided by the started wind-storage integrated machines and the power required by a single wind turbine that has not been started in the field.

[0084] Reference Figure 5 The present invention also provides an electronic device 900, including: a processor 901 and a memory 902, the memory 902 stores a program or instruction that can be run on the processor 901, and the program or instruction is executed by the processor 901 to implement the above-mentioned data-driven model-based station-level wind and storage integrated machine black start method. When the program or instruction is executed by the processor 901, each process of the implementation method of the above-mentioned data-driven model-based station-level wind and storage integrated machine black start method is implemented, and the same technical effect can be achieved. In order to avoid repetition, it will not be repeated here.

[0085] The present invention also provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the black start method of the station-level wind and storage integrated machine based on the data-driven model as described above is implemented. When the program or instruction is executed by the processor, each process of the implementation method of the black start method of the station-level wind and storage integrated machine based on the data-driven model is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0086] For those skilled in the art, the above invention disclosure is only used as an example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the exemplary implementation of the present application.

[0087] At the same time, the present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0088] Some aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". The processor may be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or combinations thereof. In addition, various aspects of the present application may be expressed as computer products located in one or more computer-readable media, which include computer-readable program codes. For example, computer-readable media may include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, tapes ...), optical disks (e.g., compact disks CDs, digital versatile disks DVDs ...), smart cards, and flash memory devices (e.g., cards, sticks, key drives ...).

[0089] A computer-readable medium may include a propagated data signal containing computer program code, such as in baseband or as part of a carrier wave. The propagated signal may have a variety of manifestations, including electromagnetic, optical, etc., or a suitable combination. A computer-readable medium may be any computer-readable medium other than a computer-readable storage medium, which may be connected to an instruction execution system, device or apparatus to communicate, propagate or transmit a program for use. The program code on the computer-readable medium may be propagated via any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar medium, or any combination of the above mediums.

[0090] Similarly, it should be noted that in order to simplify the description disclosed in this application, so as to help understand one or more embodiments of the invention, in the above description of the embodiments of the present application, sometimes multiple features are merged into one embodiment, drawings or descriptions thereof. However, this disclosure method does not mean that the features required by the object of the present application are more than the features mentioned in the claims. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above. In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "approximately", "approximately" or "substantially" in some examples. Unless otherwise specified, "approximately", "approximately" or "substantially" indicate that the number allows a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of the present application are approximate values, in specific embodiments, such numerical settings are as accurate as possible within the feasible range.

[0091] Although the present invention is disclosed as above in terms of preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art may make possible changes and modifications without departing from the spirit and scope of the present invention. Therefore, any modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the scope of protection defined by the claims of the present invention.

Claims

1. A black start method for a station-level wind and energy storage integrated machine based on a data-driven model, characterized in that: include: Obtain the operating data of wind turbines and converters on onshore wind farms throughout the year; Using the operating data as a training set and building a neural network model; The test set is input into the neural network model, the output value is compared with the actual value and the deviation between the actual value and the predicted value is obtained, and then the wind turbine data-driven model is optimized; The power of a single wind turbine output by the wind turbine data-driven model is averaged annually and sorted from high to low to form a wind farm wind turbine power output capacity sequence, and the installation position of the wind-storage integrated machine is determined based on this; wherein, the economic cost of the energy storage unit, the line loss cost, and the node voltage deviation are considered to determine the number of the wind-storage integrated machine connected to the bus, and the specific installation position of the wind-storage integrated machine is determined based on the sequence; Design a station-level black start timing based on the wind-storage integrated machine, and after all the wind-storage integrated machines are connected to the grid, calculate the total power that can be provided by the started wind-storage integrated machines and the power required by the single wind turbine that has not been started in the field; The integrated wind and energy storage machine is used to support other wind turbines to complete the start-up without energy storage one by one. After all wind turbines in the wind farm meet the grid connection requirements and are connected to the grid, a stable bus voltage of the collector line in the wind farm is established to complete the black start task at the wind farm station level.

2. The method for black start of a wind farm-level integrated storage unit based on a data-driven model according to claim 1, characterized in that: The operation data of the wind turbine side includes wind speed and machine-end output power; The operation data on the converter side includes three-phase voltage and three-phase current.

3. The black start method of a station-level wind and energy storage integrated machine based on a data-driven model according to claim 1, characterized in that: The neural network model includes a four-layer neural network structure of input layer, perception layer, hidden layer and output layer; The input layer is the input data of the wind turbine side and the converter side, the perception layer includes ten neurons, the hidden layer includes two layers with a total of 16 neurons, and the output layer is the power and impedance of a motor node. At the same time, according to the Thevenin equivalent principle, a wind turbine node is equivalent to a voltage source and an impedance in parallel.

4. The method for black start of a wind farm-level integrated storage unit based on a data-driven model according to claim 1, characterized in that: The design is based on the station-level black start timing of the wind-storage integrated machine, including: The integrated wind and energy storage machine is started first to provide excitation current for the wind turbine. After the voltage amplitude, phase and frequency of the driving wind turbine meet the grid-connected requirements, the integrated wind and energy storage machine is connected to the collector line bus to provide voltage and frequency reference for other wind turbines to be started.

5. The method for black start of a wind farm-level integrated storage unit based on a data-driven model according to claim 4 is characterized in that: After all the wind turbines and energy storage integrated machines are connected to the grid, the total power that can be provided by the started wind turbines and energy storage integrated machines and the power required by the single wind turbines that have not been started in the field are calculated, including: According to the following formula: Among them, n NEW is the number of wind turbines that are not started that can be driven by the electric energy generated by the wind turbines that have been started in the wind farm, wherein the started wind turbines include the started wind turbines and energy storage integrated machines; P W The power required to start a single fan; According to the obtained wind turbine node voltage support capability sequence, the wind turbines that have been set as the wind-storage integrated machine are excluded, and the top n wind turbines with the strongest voltage support capability are determined. NEW The typhoon turbine started up and connected to the grid.

6. The method for black start of a wind farm-level integrated storage unit based on a data-driven model according to claim 1, characterized in that: The wind-storage integrated machine is used to support other wind turbines to complete the start-up without energy storage one by one. After all wind turbines in the wind farm meet the grid connection requirements and are connected to the grid, a stable bus voltage of the collector line in the wind farm is established to complete the black start task at the wind farm station level, including: The control mode of the energy storage unit of the wind-storage integrated machine is switched from V / f control to P / Q control for subsequent other power grid restoration work.

7. A station-level wind and energy storage integrated machine black start system based on a data-driven model, characterized in that: The station-level wind-storage integrated machine black start system based on a data-driven model adopts the station-level wind-storage integrated machine black start method based on a data-driven model as claimed in any one of claims 1 to 6, and the black start system includes: An acquisition module is used to obtain the operating data of the wind turbine side and the converter side of the onshore wind farm throughout the year; A construction module, used to use the operating data as a training set and construct a neural network model; An optimization module, used for inputting the test set into the neural network model, comparing the output value with the actual value and obtaining the deviation between the actual value and the predicted value, and then optimizing the wind turbine data-driven model; A determination module is used to sort the power averages output by the wind turbine data driving model from high to low to form a wind turbine node voltage support capacity sequence, and thereby determine the installation position of the wind turbine storage integrated machine; The calculation module is used to design a site-level black start timing based on the wind-storage integrated machine, and after all the wind-storage integrated machines are connected to the grid, calculate the total power that can be provided by the started wind-storage integrated machines and the power required by a single wind turbine that has not been started in the site.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and the programs or instructions are executed by the processor to implement the black start method of a site-level wind-storage integrated machine based on a data-driven model as described in any one of claims 1-6.

9. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the black start method of the site-level wind-storage integrated machine based on the data-driven model as described in any one of claims 1-6 is implemented.

Images