A method, device and system for controlling power of offshore wind turbines

Abstract

The present invention discloses a power control method, device and system for an offshore wind turbine. The power control method, device and system first simulate and obtain the unit frequency and wind turbine load reduction power of the offshore wind turbine according to the wind turbine electromagnetic power, the system frequency, a preset first additional control loop and a preset second additional control loop; then, according to the unit frequency and the wind turbine load reduction power, output the optimal control frequency through a preset rolling prediction method; finally, according to the optimal control frequency and the system frequency, the frequency of the offshore wind turbine is controlled within a preset frequency adjustment range, so as to timely sense the sudden change of external load and control the frequency of the offshore wind turbine, thereby improving the stability of the offshore wind turbine system.

Description

Technical Field

[0001] The present invention relates to the technical field of power control of offshore wind turbines, and in particular to a power control method, device, computer-readable storage medium and system for offshore wind turbines. Background Art

[0002] Wind power generation is one of the most mature and commercially promising power generation methods in the field of renewable energy utilization. Due to the rich wind resources at sea and the urgent need for offshore wind power development and application worldwide, the transmission and grid connection of large-scale offshore wind power has become a hot topic in wind power development and research. The purpose of offshore wind power remote cluster control is to integrate and centrally coordinate the wind farm clusters that are geographically adjacent, related in characteristics, and have a common access point, effectively smooth out the volatility and intermittency of output, and form a power source that is similar to conventional power plants in scale and external regulation characteristics, with the ability to flexibly respond to grid dispatch and control. Compared with onshore wind power, the difficulty of power prediction for offshore wind power has increased significantly, and the speed and difficulty of power control have increased.

[0003] In the prior art, the improved virtual synchronous generator (IVSG) technology is usually introduced into the converter control link, so that the converter can be equivalent to a synchronous generator, simulating the active frequency regulation and reactive voltage regulation characteristics of the generator. When a power shortage occurs in the weak power grid, secondary frequency regulation can be achieved to maintain the stable operation of the weak power grid. Compared with the existing multi-terminal direct current transmission system (MMC-MTDC) inter-converter power coordination control, this method takes into account the power over-limit constraint of the AC system to which the converter is connected, and takes into account the participation of wind farms in frequency regulation, which can effectively reduce the DC voltage deviation and the power fluctuation of the AC system.

[0004] However, the prior art still has the following defects: it is impossible to quickly and accurately control the power of offshore wind turbines.

[0005] Therefore, there is a need for a power control method, device, computer-readable storage medium and system for an offshore wind turbine generator system, so as to overcome the above-mentioned defects in the prior art. Summary of the invention

[0006] Embodiments of the present invention provide a power control method, device, computer-readable storage medium and system for an offshore wind turbine generator set, thereby improving the efficiency of power control of the offshore wind turbine generator set.

[0007] An embodiment of the present invention provides a power control method for an offshore wind turbine generator set, the power control method comprising:

[0008] Obtain electromagnetic power and system frequency of offshore wind turbines;

[0009] According to the electromagnetic power of the wind turbine, the system frequency, the preset first additional control loop and the preset second additional control loop, simulate and obtain the unit frequency of the offshore wind turbine unit and the wind turbine load reduction power;

[0010] According to the unit frequency and the wind turbine load reduction power, an optimal control frequency is outputted through a preset rolling prediction method;

[0011] The frequency of the offshore wind turbine is controlled within a preset frequency adjustment range according to the optimal control frequency and the system frequency.

[0012] As an improvement of the above scheme, according to the electromagnetic power of the wind turbine, the system frequency, the preset first additional control loop and the preset second additional control loop, the unit frequency of the offshore wind turbine and the wind turbine load reduction power are simulated and obtained, specifically including:

[0013] Obtaining a preset coupling quantitative relationship;

[0014] According to the coupling quantitative relationship, the electromagnetic power of the wind turbine and the system frequency are recoupled through a first additional control loop and a second additional control loop to obtain the unit frequency of the offshore wind turbine and the wind turbine load reduction power.

[0015] As an improvement of the above solution, according to the unit frequency and the wind turbine load reduction power, the optimal control frequency is output through a rolling prediction method, which specifically includes:

[0016] Input the unit frequency and the wind turbine load shedding power into a preset rolling prediction network model, and store the output value into a first optimal control parameter group; the output value includes a first predicted unit frequency and a first predicted wind turbine load shedding power;

[0017] According to the first optimal control parameter group and the rolling prediction network model, multi-step prediction, rolling optimization and feedback correction are performed to obtain an optimal control frequency.

[0018] As an improvement of the above scheme, according to the coupling quantitative relationship, the electromagnetic power of the wind turbine and the system frequency are recoupled through the first additional control loop and the second additional control loop to obtain the unit frequency of the offshore wind turbine and the wind turbine load reduction power, specifically including:

[0019] Determining whether the system frequency changes;

[0020] If the system frequency changes, then the corresponding system frequency difference and system frequency change rate are calculated;

[0021] releasing rotor kinetic energy of the fan to output active power according to the system frequency difference through a first additional control loop, and controlling electromagnetic power of the fan to output load reduction power according to the system frequency change rate through a second additional control loop;

[0022] Determining whether the electromagnetic power of the wind turbine and the system frequency are coupled according to the coupling quantitative relationship, the active power, the load reduction power and the system frequency;

[0023] If not, repeat the above steps;

[0024] If so, the unit frequency of the offshore wind turbine unit and the wind turbine load reduction power are output according to the active power, the load reduction power and the system frequency.

[0025] As an improvement of the above solution, according to the first optimal control parameter group and the rolling prediction network model, multi-step prediction, rolling optimization and feedback correction are performed to obtain the optimal control frequency, specifically including:

[0026] The first optimal control parameter group is used as a training data set to train the rolling prediction network model, and the rolling prediction network model is updated according to the training result.

[0027] As an improvement of the above scheme, the frequency adjustment range is ±0.2H Z .

[0028] Another embodiment of the present invention provides a power control device for an offshore wind turbine generator set, the power control device comprising a data acquisition unit, a simulation unit, a rolling prediction unit and a frequency control unit, wherein:

[0029] The data acquisition unit is used to obtain the electromagnetic power and system frequency of the wind turbine of the offshore wind turbine;

[0030] The simulation unit is used to simulate and obtain the unit frequency and the wind turbine load reduction power of the offshore wind turbine according to the wind turbine electromagnetic power, the system frequency, the preset first additional control loop and the preset second additional control loop;

[0031] The rolling prediction unit is used to output the optimal control frequency through a preset rolling prediction method according to the unit frequency and the wind turbine load reduction power;

[0032] The frequency control unit is used to perform frequency control on the offshore wind turbine set within a preset frequency adjustment range according to the optimal control frequency and the system frequency.

[0033] As an improvement of the above solution, the simulation unit is also used for:

[0034] Obtaining a preset coupling quantitative relationship;

[0035] According to the coupling quantitative relationship, the electromagnetic power of the wind turbine and the system frequency are recoupled through a first additional control loop and a second additional control loop to obtain the unit frequency of the offshore wind turbine and the wind turbine load reduction power.

[0036] As an improvement of the above solution, the rolling prediction unit is further used for:

[0037] Input the unit frequency and the wind turbine load shedding power into a preset rolling prediction network model, and store the output value into a first optimal control parameter group; the output value includes a first predicted unit frequency and a first predicted wind turbine load shedding power;

[0038] According to the first optimal control parameter group and the rolling prediction network model, multi-step prediction, rolling optimization and feedback correction are performed to obtain an optimal control frequency.

[0039] As an improvement of the above solution, the simulation unit is also used for:

[0040] Determining whether the system frequency changes;

[0041] If the system frequency changes, then the corresponding system frequency difference and system frequency change rate are calculated;

[0042] releasing rotor kinetic energy of the fan to output active power according to the system frequency difference through a first additional control loop, and controlling electromagnetic power of the fan to output load reduction power according to the system frequency change rate through a second additional control loop;

[0043] Determining whether the electromagnetic power of the wind turbine and the system frequency are coupled according to the coupling quantitative relationship, the active power, the load reduction power and the system frequency;

[0044] If not, repeat the above steps;

[0045] If so, the unit frequency of the offshore wind turbine unit and the wind turbine load reduction power are output according to the active power, the load reduction power and the system frequency.

[0046] As an improvement of the above solution, the rolling prediction unit is further used for:

[0047] The first optimal control parameter group is used as a training data set to train the rolling prediction network model, and the rolling prediction network model is updated according to the training result.

[0048] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power control method for the offshore wind turbine set as described above.

[0049] Another embodiment of the present invention provides a power control system for an offshore wind turbine group, the power control system comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the power control method for the offshore wind turbine group as described above.

[0050] Compared with the prior art, this technical solution has the following beneficial effects:

[0051] The present invention provides a power control method, device, computer-readable storage medium and system for an offshore wind turbine set. Additional control is established through a first additional control loop and a second additional control loop to recouple the system frequency of the offshore wind turbine set and the electromagnetic power of the wind turbine, so that sudden changes in external loads can be sensed in time to control the frequency of the offshore wind turbine set. The power control method, device, computer-readable storage medium and system improve the stability of the offshore wind turbine set system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart of a power control method for an offshore wind turbine generator set provided by an embodiment of the present invention;

[0053] Figure 2 It is a structural schematic diagram of a power control device for an offshore wind turbine generator set provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Specific embodiment 1

[0056] The embodiment of the present invention firstly describes a power control method for an offshore wind turbine. Figure 1 It is a flow chart of a power control method for an offshore wind turbine provided in one embodiment of the present invention.

[0057] like Figure 1 As shown, the power control method includes:

[0058] S1: Obtain the electromagnetic power and system frequency of the offshore wind turbine.

[0059] In this embodiment, the power control method of the offshore wind turbine is applicable to a doubly-fed wind generator (DFIG).

[0060] As one of the main types of wind power generation, the rotor side of the doubly-fed wind turbine is highly decoupled from the system frequency side, which results in the doubly-fed wind turbine being unable to directly respond to the frequency changes of the system. The rotor side of the doubly-fed wind turbine is connected to the grid side through an inverter device, so that the grid frequency and the generator rotor are in a decoupled state. When the system frequency changes due to a sudden change in external load, the doubly-fed wind turbine cannot sense the change in the grid frequency in time, causing the system frequency to drop and destroying the stability of the system.

[0061] S2: According to the electromagnetic power of the wind turbine, the system frequency, a preset first additional control loop and a preset second additional control loop, simulate and obtain the unit frequency and the load reduction power of the offshore wind turbine unit.

[0062] In order to improve the stability and safety of the system frequency, it is necessary to control the inertia to enable wind turbines to participate in the frequency regulation process of the system. The inertia of the power system can slow down the change of the system frequency and increase or decrease the output of the generator set to balance the system power. However, the generator speed of the wind turbine is decoupled from the system frequency of the offshore wind turbine, and it cannot actively provide inertia support, resulting in a continuous decrease in the system inertia level. The specific calculation principle is to recouple the frequency of the wind turbine with the electromagnetic power of the wind turbine through an additional power control link, in which the electromagnetic power has a quantitative relationship with the supplementary power and load reduction power of the wind turbine. The inertia time constant of the wind turbine is similar to that of a conventional synchronous unit, and the adjustable speed range is greater than that of a thermal power unit, which can theoretically provide a very considerable virtual inertia.

[0063] In one embodiment, according to the electromagnetic power of the wind turbine, the system frequency, a preset first additional control loop and a preset second additional control loop, the unit frequency of the offshore wind turbine and the wind turbine load reduction power are simulated and obtained, specifically including: obtaining a preset coupling quantitative relationship; according to the coupling quantitative relationship, re-coupling the electromagnetic power of the wind turbine and the system frequency through the first additional control loop and the second additional control loop to obtain the unit frequency of the offshore wind turbine and the wind turbine load reduction power.

[0064] In one embodiment, according to the coupling quantitative relationship, the electromagnetic power of the wind turbine and the system frequency are recoupled through a first additional control loop and a second additional control loop to obtain the unit frequency of the offshore wind turbine and the wind turbine load reduction power, specifically including: judging whether the system frequency has changed; if the system frequency has changed, calculating the corresponding system frequency difference and the system frequency change rate; releasing the rotor kinetic energy of the wind turbine according to the system frequency difference to output active power through the first additional control loop, and controlling the electromagnetic power of the wind turbine according to the system frequency change rate to output load reduction power through the second additional control loop; judging whether the electromagnetic power of the wind turbine and the system frequency are coupled according to the coupling quantitative relationship, the active power, the load reduction power and the system frequency; if not, repeating the above steps; if yes, outputting the unit frequency of the offshore wind turbine and the wind turbine load reduction power according to the active power, the load reduction power and the system frequency.

[0065] S3: Outputting the optimal control frequency through a preset rolling prediction method according to the unit frequency and the wind turbine load reduction power.

[0066] Model Predictive Control (MPC) is a control algorithm that uses control strategies such as multi-step prediction, rolling optimization and feedback correction to optimize the control of nonlinear, uncertain and time-varying signals. It has the characteristics of strong robustness, good control effect and low requirements on model accuracy.

[0067] Among them, the model predictive control (MPC) should consider the following control objectives when controlling according to the characteristics of wind power generation in the power system: 1. While ensuring the stable and safe operation of the power grid, when the external load is disturbed, it must be ensured that the wind turbine will not be cut off due to excessive kinetic energy input; in addition, the frequency change fluctuation should be kept within a small range to reduce the impact of harmonics on the power grid; 2. Make full use of the kinetic energy of the wind turbine within a certain range and coordinate the traditional synchronous generator to share the system frequency changes.

[0068] In one embodiment, the optimal control frequency is outputted through a rolling prediction method according to the unit frequency and the wind turbine load reduction power, which specifically includes: inputting the unit frequency and the wind turbine load reduction power into a preset rolling prediction network model, and storing the output value into a first optimal control parameter group; the output value includes a first predicted unit frequency and a first predicted wind turbine load reduction power; and according to the first optimal control parameter group and the rolling prediction network model, performing multi-step prediction, rolling optimization and feedback correction to obtain the optimal control frequency.

[0069] The rolling prediction uses the latest data received by the network not only as the basis for prediction, but also as training data together with the prediction results of the previous moment. The new data rules are learned again, and the network parameters of the model are fine-tuned, so that the network can track the data change rules in real time and make the next prediction more accurate. The rolling prediction method can not only achieve good results on the trained wind turbine, but also be quickly migrated and applied to other wind turbines. If it is necessary to quickly apply it to other wind turbines, the historical data of the target wind turbine can be learned, the network can be preliminarily trained, and then applied to the target wind turbine. If the target wind turbine has no historical data, the wind turbine data of the nearby wind farm or the wind turbine data under similar terrain and climatic conditions can be learned, and then the power change rules of the target wind turbine can be mastered through rolling prediction, and then corresponding predictions or controls can be made. When the network of the model makes actual predictions, the network parameters will be automatically updated from a certain moment to track the parameter change rules in time, which is conducive to improving the control quality. In addition, in order to prevent the occurrence of overfitting, the learning rate adopted in network model training is an exponential decay strategy, while in testing, that is, simulating actual applications, a fixed and very small learning rate is used to control the adjustable range of network parameters in each rolling prediction, so that the model network can fine-tune the network parameters in the rolling prediction test, track the latest data changes, and is less likely to overfit.

[0070] S4: According to the optimal control frequency and the system frequency, the frequency of the offshore wind turbine is controlled within a preset frequency adjustment range.

[0071] In one embodiment, based on the first optimal control parameter group and the rolling prediction network model, multi-step prediction, rolling optimization and feedback correction are performed to obtain the optimal control frequency, specifically including: using the first optimal control parameter group as a training data set, training the rolling prediction network model, and updating the rolling prediction network model according to the training results.

[0072] Since the system frequency will drop once the external load fluctuates, the control module needs to respond quickly to the frequency change of the system and use the wind power to quickly supplement the missing power of the system, thereby reducing the frequency drop. Therefore, the power-frequency prediction control system is formed by the aforementioned model predictive control (MPC), and the system frequency is adjusted by constraining the frequency within the range of ±0.2 Hz. That is, in one embodiment, the frequency adjustment range is ±0.2 Hz.

[0073] An embodiment of the present invention describes a power control method for an offshore wind turbine set, which establishes additional control through a first additional control loop and a second additional control loop, and recouples the system frequency of the offshore wind turbine set and the electromagnetic power of the wind turbine, so that sudden changes in external loads can be sensed in time and the frequency of the offshore wind turbine set can be controlled. The power control method improves the stability of the offshore wind turbine set system. Specific embodiment 2

[0075] In addition to the above method, an embodiment of the present invention further discloses a power control device for an offshore wind turbine. Figure 2 It is a structural schematic diagram of a power control device for an offshore wind turbine generator set provided by an embodiment of the present invention.

[0076] like Figure 2 As shown, the power control device includes a data acquisition unit 11, a simulation unit 12, a rolling prediction unit 13 and a frequency control unit 14.

[0077] The data acquisition unit 11 is used to obtain the electromagnetic power and system frequency of the wind turbine of the offshore wind turbine.

[0078] The simulation unit 12 is used to simulate and obtain the unit frequency and wind turbine load reduction power of the offshore wind turbine according to the wind turbine electromagnetic power, the system frequency, the preset first additional control loop and the preset second additional control loop.

[0079] In one embodiment, the simulation unit 12 is also used to: obtain a preset coupling quantitative relationship; according to the coupling quantitative relationship, recouple the wind turbine electromagnetic power and the system frequency through a first additional control loop and a second additional control loop to obtain the unit frequency of the offshore wind turbine and the wind turbine load reduction power.

[0080] In one embodiment, the simulation unit 12 is also used to: determine whether the system frequency has changed; if the system frequency has changed, calculate the corresponding system frequency difference and the system frequency change rate; through a first additional control loop, release the rotor kinetic energy of the wind turbine according to the system frequency difference to output active power, and through a second additional control loop, control the electromagnetic power of the wind turbine according to the system frequency change rate to output load reduction power; according to the coupling quantitative relationship, the active power, the load reduction power and the system frequency, determine whether the wind turbine electromagnetic power and the system frequency are coupled; if not, repeat the above steps; if so, output the unit frequency of the offshore wind turbine and the wind turbine load reduction power according to the active power, the load reduction power and the system frequency.

[0081] The rolling prediction unit 13 is used to output the optimal control frequency through a preset rolling prediction method according to the unit frequency and the wind turbine load reduction power.

[0082] In one embodiment, the rolling prediction unit 13 is also used to: input the unit frequency and the wind turbine load reduction power into a preset rolling prediction network model, and store the output value into a first optimal control parameter group; the output value includes a first predicted unit frequency and a first predicted wind turbine load reduction power; according to the first optimal control parameter group and the rolling prediction network model, perform multi-step prediction, rolling optimization and feedback correction to obtain the optimal control frequency.

[0083] In one embodiment, the rolling prediction unit 13 is further configured to: use the first optimal control parameter group as a training data set to train the rolling prediction network model, and update the rolling prediction network model according to the training result.

[0084] The frequency control unit 14 is used to control the frequency of the offshore wind turbine generator set within a preset frequency adjustment range according to the optimal control frequency and the system frequency.

[0085] Wherein, if the integrated unit of the power control device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power control method of the offshore wind turbine as described above.

[0086] Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0087] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the units indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0088] An embodiment of the present invention describes a power control device and a computer-readable storage medium for an offshore wind turbine set. Additional control is established through a first additional control loop and a second additional control loop, and the system frequency of the offshore wind turbine set and the electromagnetic power of the wind turbine are recoupled, so that sudden changes in external loads can be sensed in time and the frequency of the offshore wind turbine set can be controlled. The power control device and the computer-readable storage medium improve the stability of the offshore wind turbine set system. Specific embodiment three

[0090] In addition to the above method and apparatus, the embodiment of the present invention also describes a power control system for an offshore wind turbine.

[0091] The power control system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the power control method of the offshore wind turbine set as described above is implemented.

[0092] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect the various parts of the entire device.

[0093] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0094] An embodiment of the present invention describes a power control system for an offshore wind turbine set, which establishes additional control through a first additional control loop and a second additional control loop, and recouples the system frequency of the offshore wind turbine set and the electromagnetic power of the wind turbine, so that sudden changes in external loads can be sensed in time to control the frequency of the offshore wind turbine set. The power control system improves the stability of the offshore wind turbine set system.

[0095] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A power control method for an offshore wind turbine, characterized in that: The power control method comprises: Obtain electromagnetic power and system frequency of offshore wind turbines; According to the electromagnetic power of the wind turbine, the system frequency, the preset first additional control loop and the preset second additional control loop, simulate and obtain the unit frequency of the offshore wind turbine unit and the wind turbine load reduction power; According to the unit frequency and the wind turbine load reduction power, an optimal control frequency is outputted through a preset rolling prediction method; According to the optimal control frequency and the system frequency, frequency control is performed on the offshore wind turbine generator set within a preset frequency adjustment range; The simulating and obtaining the unit frequency and the wind turbine load reduction power of the offshore wind turbine unit according to the wind turbine electromagnetic power, the system frequency, the preset first additional control loop and the preset second additional control loop specifically includes: Obtaining a preset coupling quantitative relationship; According to the coupling quantitative relationship, the electromagnetic power of the wind turbine and the system frequency are recoupled through a first additional control loop and a second additional control loop to obtain a unit frequency of the offshore wind turbine and a load reduction power of the wind turbine; Outputting the optimal control frequency by a rolling prediction method according to the unit frequency and the wind turbine load reduction power specifically includes: Input the unit frequency and the wind turbine load shedding power into a preset rolling prediction network model, and store the output value into a first optimal control parameter group; the output value includes a first predicted unit frequency and a first predicted wind turbine load shedding power; According to the first optimal control parameter group and the rolling prediction network model, multi-step prediction, rolling optimization and feedback correction are performed to obtain an optimal control frequency.

2. The power control method of an offshore wind turbine according to claim 1, characterized in that: According to the coupling quantitative relationship, the electromagnetic power of the wind turbine and the system frequency are recoupled through the first additional control loop and the second additional control loop to obtain the unit frequency of the offshore wind turbine and the wind turbine load reduction power, specifically including: Determining whether the system frequency changes; If the system frequency changes, then the corresponding system frequency difference and system frequency change rate are calculated; releasing rotor kinetic energy of the fan to output active power according to the system frequency difference through a first additional control loop, and controlling electromagnetic power of the fan to output load reduction power according to the system frequency change rate through a second additional control loop; Determining whether the electromagnetic power of the wind turbine and the system frequency are coupled according to the coupling quantitative relationship, the active power, the load reduction power and the system frequency; If not, repeat the above steps; If so, the unit frequency of the offshore wind turbine unit and the wind turbine load reduction power are output according to the active power, the load reduction power and the system frequency.

3. The power control method of an offshore wind turbine according to claim 2, characterized in that: According to the first optimal control parameter group and the rolling prediction network model, multi-step prediction, rolling optimization and feedback correction are performed to obtain the optimal control frequency, specifically including: The first optimal control parameter group is used as a training data set to train the rolling prediction network model, and the rolling prediction network model is updated according to the training result.

4. The power control method for an offshore wind turbine according to any one of claims 1 to 3, characterized in that: The frequency adjustment range is ±0.2H Z .

5. A power control device for an offshore wind turbine, characterized in that: The power control device adopts the power control method of the offshore wind turbine set as claimed in any one of claims 1 to 4; The power control device includes a data acquisition unit, a simulation unit, a rolling prediction unit and a frequency control unit, wherein: The data acquisition unit is used to obtain the electromagnetic power and system frequency of the wind turbine of the offshore wind turbine; The simulation unit is used to simulate and obtain the unit frequency and the wind turbine load reduction power of the offshore wind turbine according to the wind turbine electromagnetic power, the system frequency, the preset first additional control loop and the preset second additional control loop; The rolling prediction unit is used to output the optimal control frequency through a preset rolling prediction method according to the unit frequency and the wind turbine load reduction power; The frequency control unit is used to perform frequency control on the offshore wind turbine set within a preset frequency adjustment range according to the optimal control frequency and the system frequency.

6. The power control device for an offshore wind turbine according to claim 5, characterized in that: The simulation unit is also used for: Obtaining a preset coupling quantitative relationship; According to the coupling quantitative relationship, the electromagnetic power of the wind turbine and the system frequency are recoupled through a first additional control loop and a second additional control loop to obtain the unit frequency of the offshore wind turbine and the wind turbine load reduction power.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power control method for an offshore wind turbine set according to any one of claims 1 to 4.

8. A power control system for an offshore wind turbine, characterized in that: The power control system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the power control method for the offshore wind turbine set according to any one of claims 1 to 4 is implemented.

Images