Resource allocation method, apparatus, computer equipment, and storage medium for offshore wind power plants

Abstract

This application relates to the technical field of resource allocation and discloses a resource allocation method, device, computer device, and storage medium for offshore wind farms. The application combines a forecast wind energy data set with a predetermined adjustment period to determine different adjustment rates, and uses the determined adjustment rates to adjust the layout of each wind turbine in a wind power-based forecast twin model, which is advantageous for ensuring the stability of the wind turbine fleet during movement and realizing a tailored adjustment mechanism for the wind turbines according to different wind resource conditions. Optionally, based on the established wind power-based forecast twin model, a target layout of the wind turbine fleet and a target orientation of each wind turbine in the offshore wind farm to be allocated can be obtained, and the positions and orientations of the wind turbines can be adjusted simultaneously, further maximizing the utilization of offshore wind resources and improving wind power efficiency.

Description

[Technical Field]

[0001] This application relates to the technology of resource allocation, and more specifically to resource allocation methods, apparatus, computer apparatus, and storage media for offshore wind power plants. [Background technology]

[0002] Offshore wind resources refer to energy resources used to generate electricity by utilizing wind energy in the ocean. Because offshore winds are large and stable, offshore wind energy is considered a renewable energy source with great potential. Offshore wind farms are usually constructed on some kind of structure on the sea surface, such as a fixed platform or a floating device, to house the wind turbines. Resource allocation of offshore wind resources refers to rationally planning and arranging the construction and layout of offshore wind farms, taking into account the distribution and changes of offshore wind energy resources, and optimizing the layout according to the characteristics of the sea area and the distribution of wind energy. The purpose is to maximize the use of offshore wind energy resources and improve power generation efficiency.

[0003] Conventional technology adjusts wind turbine groups at a fixed rate, which can damage the turbines themselves when wind energy is relatively unstable. Furthermore, conventional technology often involves adjusting the orientation of a wind turbine after it has been positioned, which objectively reduces the efficiency of wind energy utilization. [Overview of the Initiative] [Problems that the invention aims to solve]

[0004] In view of this, the present invention provides a resource allocation method, apparatus, computer apparatus, and storage medium for an offshore wind power plant to solve the problems in the prior art in that adjusting a group of wind turbines at a fixed rate can damage the wind turbines themselves when wind energy is relatively unstable, and that adjusting the orientation of the wind turbines after they have been adjusted to their corresponding positions reduces the efficiency of wind energy utilization. [Means for solving the problem]

[0005] In a first aspect, the present invention provides a resource allocation method for an offshore wind farm, comprising the steps of: acquiring an initial measured wind energy dataset, an initial measured wind turbine dataset, and an initial forecast wind energy dataset for an offshore wind farm to be allocated; constructing a wind power generation-based prediction twin model based on the initial measured wind energy dataset, the initial measured wind turbine dataset, and the initial forecast wind energy dataset, wherein the wind power generation-based prediction twin model is used to acquire the total simulated power generated by various wind turbine layouts within the offshore wind farm to be allocated under the conditions of the forecast wind energy dataset; determining an adjustment rate based on the forecast wind energy dataset and a preset adjustment period; and adjusting the layout of each wind turbine in the wind power generation-based prediction twin model within the preset adjustment period based on the forecast wind energy dataset and the adjustment rate, until the total simulated power generated by the offshore wind farm to be allocated is maximized, thereby obtaining a target layout of the wind turbine group within the offshore wind farm to be allocated and a target orientation of each wind turbine.

[0006] The resource allocation method for offshore wind power plants according to this application is advantageous in ensuring the stability of the wind turbine group during movement by combining a predicted wind energy dataset with a pre-set adjustment period to determine different adjustment rates, and using the determined adjustment rates to adjust the layout of each wind turbine in a predictive twin model based on wind power generation. It can realize an adjustment mechanism that suits the purpose for wind turbines according to different wind resource conditions. Selectively, based on an established predictive twin model based on wind power generation, the target layout of the wind turbine group within the offshore wind power plant to be allocated and the target orientation of each wind turbine can be obtained. This allows for simultaneous adjustment of the position and orientation of the wind turbines, further maximizing the utilization of offshore wind resources and improving the efficiency of wind power generation.

[0007] In one selectable embodiment, the step of constructing a wind power-based predictive twin model based on an initial measured wind energy dataset, an initial measured wind turbine dataset, and an initial forecasted wind energy dataset is: The method includes the steps of: constructing a digital twin model based on wind power generation using digital twin technology based on an initial measured wind energy dataset and an initial measured wind turbine dataset; processing an initial forecast wind energy dataset with a pre-configured offshore wind energy prediction model to obtain a predicted wind energy dataset for offshore wind power plants to be allocated; and constructing a prediction twin model based on wind power generation based on the predicted wind energy dataset and the digital twin model based on wind power generation.

[0008] This invention constructs a digital twin model based on wind power generation by combining measured wind turbine data, and selectively combines this digital twin model with predicted wind energy data to construct a corresponding predictive twin model based on wind power generation. This provides support for determining the target layout of wind turbine groups within offshore wind farms targeted for subsequent allocation and the target orientation of each wind turbine.

[0009] In one selectable embodiment, the step of constructing a digital twin model based on wind power generation using digital twin technology, based on an initial measured wind energy dataset and an initial measured wind turbine dataset, is: The process includes the steps of: obtaining a characteristic dataset of wind turbines within an offshore wind farm to be allocated; processing the initial measured wind energy dataset and the initial measured wind turbine dataset to obtain a target measured wind energy dataset and a target measured wind turbine dataset; constructing a physical system model based on wind power generation based on the target measured wind turbine dataset and the characteristic dataset; and constructing a digital twin model based on wind power generation based on the target measured wind energy dataset and the physical system model based on wind power generation.

[0010] This invention improves the accuracy of a model by constructing a digital twin model based on wind power generation by combining it with a characteristic dataset of wind turbine groups within an offshore wind power plant subject to allocation. Furthermore, it provides support for improving the accuracy of determining the target layout of wind turbine groups within an offshore wind power plant subject to allocation and the target orientation of each wind turbine.

[0011] In one selectable embodiment, the method processes an initial forecast wind energy dataset using a pre-configured offshore wind energy forecasting model to obtain a forecast wind energy dataset for the offshore wind farms to be allocated, before the first step of which is: The method further includes the steps of: obtaining a first historical measured wind energy dataset and a historical forecast wind energy dataset for an offshore wind farm to be allocated; determining a second historical measured wind energy dataset corresponding to a historical forecast wind energy dataset in the first historical measured wind energy dataset; and constructing a pre-configured offshore wind energy prediction model based on the historical forecast wind energy dataset and the second historical measured wind energy dataset.

[0012] In one selectable embodiment, the step of determining the adjustment rate based on a predicted wind energy dataset and a preset adjustment period is: The method includes the steps of determining a predicted wind energy coefficient based on a predicted wind energy dataset and a preset adjustment period, and comparing the predicted wind energy coefficient with a preset threshold and determining an adjustment rate based on the comparison result.

[0013] In one selectable embodiment, the steps include adjusting the layout of each wind turbine in a wind-power-based predictive twin model based on a predicted wind energy dataset and adjustment rate within a preset adjustment cycle to obtain a target layout of the wind turbine group within the allocated offshore wind farm and a target orientation of each wind turbine until the total simulated power generated by the allocated offshore wind farm is maximized, Steps include: adjusting the position of each wind turbine and the distance between different wind turbines in a wind power-based prediction twin model within a predetermined adjustment period based on a predicted wind energy dataset and adjustment rate to obtain multiple layouts and multiple first simulation total power generation values ​​for the group of wind turbines in the offshore wind farm to be allocated; determining a target layout for the group of wind turbines in the offshore wind farm to be allocated in the multiple layouts based on the multiple first simulation total power generation values, wherein the total simulation power generation generated in the target layout by the group of wind turbines in the offshore wind farm to be allocated is the largest among the multiple first simulation total power generation values; and the target ray The process includes the steps of: determining the target steering rate of each wind turbine in the offshore wind farm to be allocated based on the output; adjusting the orientation of each wind turbine in a wind power-based predictive twin model based on the target layout and the target steering rate of each wind turbine to obtain a plurality of second simulated total power generation amounts and a plurality of first orientations for each wind turbine; and determining the target orientation of each wind turbine in the offshore wind farm to be allocated for a plurality of first orientations based on the plurality of second simulated total power generation amounts, wherein the simulated total power generation amount generated for the target orientation of each wind turbine in the offshore wind farm to be allocated is the largest among the plurality of second simulated total power generation amounts.

[0014] This invention allows for the simultaneous adjustment of the wind turbines within an offshore wind farm to their optimal orientation during the process of adjusting the wind turbine group within the allocated offshore wind farm to the optimal layout based on the target steering rate, thereby improving the efficiency of wind power generation.

[0015] In one selectable embodiment, the step of determining the target steering rate for each wind turbine in the offshore wind farm to be allocated based on the target layout is: The method includes the steps of: obtaining the measured position and measured orientation of each wind turbine in the offshore wind farm to be allocated; adjusting the orientation of each wind turbine in a predictive twin model based on wind power generation based on the target layout to obtain multiple third simulation total power generation amounts and multiple second orientations for each wind turbine; determining the third orientation of each wind turbine in the offshore wind farm to be allocated in multiple second orientations based on the multiple third simulation total power generation amounts, wherein the simulation total power generation amount generated in the third orientation of each wind turbine in the offshore wind farm to be allocated is the largest among the multiple third simulation total power generation amounts; determining the steering angle of each wind turbine based on the measured orientation and third orientation of each wind turbine; determining the adjustment time of each wind turbine based on the target layout and measured position; and determining the target steering rate of each wind turbine based on the adjustment time and steering angle of each wind turbine.

[0016] In the second aspect, the present application is: An acquisition module for obtaining the initial measured wind energy dataset, initial measured wind turbine dataset, and initial forecast wind energy dataset for offshore wind farms to be allocated, A construction module for constructing a predictive twin model for wind power generation based on an initial measured wind energy dataset, an initial measured wind turbine dataset, and an initial forecast wind energy dataset. The predictive twin model for wind power generation includes a construction module for obtaining the total simulated power generation generated by various wind turbine layouts in an offshore wind farm to be allocated under the conditions of the forecast wind energy dataset, a determination module for determining an adjustment rate based on the forecast wind energy dataset and a preset adjustment period, and an adjustment module for adjusting the layout of each wind turbine in the predictive twin model for wind power generation based on the forecast wind energy dataset and the adjustment rate within the preset adjustment period until the total simulated power generation generated by the offshore wind farm to be allocated reaches the maximum, so as to obtain the target layout of the wind turbine group and the target orientation of each wind turbine in the offshore wind farm to be allocated. An offshore wind farm resource allocation device is provided.

[0017] In a third aspect, the present application provides a computer device including a memory and a processor, the memory and the processor being communicably connected, computer instructions being stored in the memory, and the processor executing the computer instructions to execute the resource allocation method for an offshore wind farm according to any one of the first aspect or its corresponding embodiments.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the resource allocation method for an offshore wind farm according to any one of the first aspect or its corresponding embodiments.

[0019] To more clearly explain the specific embodiments of the present application or the technical solutions of the prior art, the following briefly describes the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings described below are some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative labor.

Brief Description of the Drawings

[0020] [Figure 1] It is a schematic flowchart of a resource allocation method for an offshore wind power plant according to an embodiment of the present application. [Figure 2] It is a schematic flowchart of another resource allocation method for an offshore wind power plant according to an embodiment of the present application. [Figure 3] It is a schematic flowchart of yet another resource allocation method for an offshore wind power plant according to an embodiment of the present application. [Figure 4] It is a structural block diagram of a resource allocation device for an offshore wind power plant according to an embodiment of the present application. [Figure 5] It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present application.

Embodiments for Carrying Out the Invention

[0021] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, hereinafter, the drawings of the embodiments of the present application and the technical solutions of the embodiments of the present application will be referred to for a clear and complete description. Obviously, the described embodiments are some, rather than all, of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts belong to the protection scope of the present application.

[0022] The embodiments of the present application provide a resource allocation method for an offshore wind power plant, which is advantageous for ensuring the stability during the movement of a wind turbine group by adjusting the layout of each wind turbine in a prediction twin model based on wind power generation at different adjustment rates, and can realize an adjustment mechanism suitable for the purpose for the wind turbines according to different wind resource situations. Optionally, based on the established prediction twin model based on wind power generation, the target layout of the wind turbine group and the target orientation of each wind turbine in the offshore wind power plant to be allocated can be obtained, the position and orientation of the wind turbines can be adjusted simultaneously, and furthermore, the maximization of the utilization of offshore wind resources can be realized, and the efficiency of wind power generation can be improved.

[0023] The embodiments of the present invention provide an embodiment of a resource allocation method for an offshore wind power plant, wherein the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the flowchart shows a logical order, the steps shown or described may be executed in an order different from that shown herein.

[0024] This embodiment provides a resource allocation method for an offshore wind power plant, and Figure 1 is a flowchart of the resource allocation method for an offshore wind power plant according to the embodiment of the present invention, and as shown in Figure 1, the process includes steps S101 to S104.

[0025] Step S101: Obtain the initial measured wind energy dataset, initial measured wind turbine dataset, and initial forecast wind energy dataset for the offshore wind farm to be allocated.

[0026] Specifically, the initial measured wind energy dataset represents the wind energy data of offshore wind farms currently being allocated, and may include data such as wind speed, wind direction, wind speed frequency distribution, wind energy density, wind energy potential, and wind resource distribution.

[0027] Wind speed and wind direction represent the speed and direction of the wind, wind speed frequency distribution represents the frequency of wind speed occurrences within different wind speed ranges, wind energy density represents the average wind energy per unit area or volume, wind energy potential represents an estimate of wind energy in a particular region or location, and wind resource distribution represents the spatial distribution of wind energy in a particular region or within a wind power plant.

[0028] Selectively, the initial measured wind turbine dataset may represent currently measured wind turbine data for allocated offshore wind farms and may include data such as rated power, rated wind speed, cut-in and cut-off wind speeds, power curves, and wind direction performance.

[0029] Rated power represents the power that a wind turbine can continuously and stably output under standard operating conditions; rated wind speed represents the lowest wind speed threshold at which the wind turbine begins generating power; cut-in and cut-off wind speeds represent the lowest wind speed threshold at which the wind turbine begins rotating and the highest wind speed threshold at which the wind turbine stops generating power; power curves represent the power of the wind turbine at different wind speeds; and wind direction performance represents the power generation performance and efficiency of the wind turbine under different wind direction conditions.

[0030] Selectively, initial forecast wind energy datasets represent forecast wind energy data over the ocean for different periods and can be obtained from weather forecast data from meteorological stations.

[0031] Step S102: A predictive twin model based on wind power generation is constructed based on the initial measured wind energy dataset, the initial measured wind turbine dataset, and the initial forecasted wind energy dataset.

[0032] A wind power-based predictive twin model can be used to obtain simulated total power generation generated by various wind turbine layouts within an offshore wind farm under the conditions of a predicted wind energy dataset.

[0033] Specifically, the acquired initial measured wind energy dataset, initial measured wind turbine dataset, and initial forecasted wind energy dataset can be used to construct a corresponding wind power generation-based predictive twin model.

[0034] Step S103: Determine the adjustment rate based on the predicted wind energy dataset and the preset adjustment cycle.

[0035] Specifically, the wind turbine group is adjusted at a fixed rate, but this adjustment method could potentially damage the wind turbines themselves if wind energy is relatively unstable.

[0036] Therefore, in this embodiment, the corresponding adjustment rate is determined by the predicted wind energy dataset and a preset adjustment period, and further support can be provided for adjusting subsequent wind turbine groups at different adjustment rates.

[0037] In step S104, within a predetermined adjustment cycle, the layout of each wind turbine in the wind power generation-based prediction twin model is adjusted based on the predicted wind energy dataset and adjustment rate, and the target layout of the wind turbine group within the allocated offshore wind farm and the target orientation of each wind turbine are obtained until the total simulated power generation generated by the allocated offshore wind farm is maximized.

[0038] Specifically, by adjusting the layout of each wind turbine by combining a predicted wind energy dataset and adjustment rate within a predetermined adjustment cycle, the stability of the wind turbine group during movement can be ensured, and an adjustment mechanism tailored to the purpose can be implemented for the wind turbines according to different wind resource conditions. Selectively, because the adjustment process is performed using a predictive twin model based on the constructed wind power generation, the position and orientation of the wind turbines can be adjusted simultaneously, further maximizing the utilization of offshore wind resources and improving the efficiency of wind power generation.

[0039] The resource allocation method for offshore wind power plants according to this embodiment is advantageous in ensuring the stability of the wind turbine group during movement by determining different adjustment rates by combining a predicted wind energy dataset with a pre-set adjustment period, and then using the determined adjustment rates to adjust the layout of each wind turbine in a predictive twin model based on wind power generation. This allows for the realization of an adjustment mechanism tailored to the purpose for wind turbines according to different wind resource conditions. Selectively, based on an established predictive twin model based on wind power generation, the target layout of the wind turbine group within the offshore wind power plant to be allocated and the target orientation of each wind turbine can be obtained. This allows for simultaneous adjustment of the position and orientation of the wind turbines, further maximizing the utilization of offshore wind resources and improving the efficiency of wind power generation.

[0040] This embodiment provides a resource allocation method for an offshore wind power plant, and Figure 2 is a flowchart of the resource allocation method for an offshore wind power plant according to the embodiment of this application, and as shown in Figure 2, the process includes steps S201 to S204.

[0041] In step S201, the initial measured wind energy dataset, initial measured wind turbine dataset, and initial forecast wind energy dataset for the offshore wind farm to be allocated are obtained. For details, please refer to step S101 of the embodiment shown in Figure 1, and a detailed explanation is omitted here.

[0042] Step S202: A predictive twin model based on wind power generation is constructed based on the initial measured wind energy dataset, the initial measured wind turbine dataset, and the initial forecasted wind energy dataset.

[0043] Specifically, step S202 above includes steps S2021 to S2026.

[0044] Step S2021: Based on the initial measured wind energy dataset and initial measured wind turbine dataset, a digital twin model based on wind power generation will be constructed using digital twin technology.

[0045] Digital twin technology is a technology that reflects the full lifecycle process of a corresponding physical device by making full use of data such as physical models, sensor updates, and operation history, integrating simulation processes across multiple fields, multiple physical quantities, multiple scales, and multiple probabilities, and completing mapping in a virtual space.

[0046] Specifically, by combining initial measured wind energy datasets and initial measured wind turbine data using digital twin technology, it is possible to construct a wind power-based digital twin model that reflects the simulated layout and full lifecycle process of the wind turbine group of the offshore wind farm to be allocated.

[0047] Step S2022: Obtain the first measured wind energy dataset and the historical forecast wind energy dataset for the offshore wind farms to be allocated.

[0048] Specifically, the first historical measured wind energy dataset represents wind energy data for the allocated offshore wind farms within a historical period, while the historical forecast wind energy dataset represents forecast wind energy data for the allocated offshore wind farms over different historical periods, and can be obtained from historical weather forecast data from weather stations.

[0049] Step S2023: In the first historical measured wind energy dataset, determine the second historical measured wind energy dataset that corresponds to the historical forecast wind energy dataset.

[0050] Specifically, based on the historical forecast wind energy dataset, the corresponding actual wind energy data, i.e., the historical second measured wind energy dataset, is determined in the first measured wind energy dataset of the historical data.

[0051] Step S2024: A pre-configured offshore wind energy prediction model is constructed based on the historical forecast wind energy dataset and the historical second measured wind energy dataset.

[0052] Specifically, by using a historical forecast wind energy dataset as the model's input and a historical second measured wind energy dataset as the model's output, and training the model based on the correspondence between the historical forecast wind energy dataset and the historical second measured wind energy dataset, a pre-configured offshore wind energy forecasting model for predicting wind energy data can be constructed.

[0053] In step S2025, the initial forecast wind energy dataset is processed by a pre-configured offshore wind energy prediction model to obtain a predicted wind energy dataset for the offshore wind farms to be allocated.

[0054] Specifically, by inputting an initial forecast wind energy dataset into a pre-trained offshore wind energy prediction model, it is possible to predict wind energy data corresponding to the initial forecast wind energy dataset, i.e., a predicted wind energy dataset.

[0055] Step S2026: Construct a wind power generation-based predictive twin model based on a predicted wind energy dataset and a digital twin model based on wind power generation.

[0056] Specifically, a predicted wind energy dataset can be input into a constructed digital twin model to obtain a predictive twin model based on wind power generation.

[0057] In some selective embodiments, step S2021 above is: Step a1 involves obtaining a characteristic dataset of wind turbines within the offshore wind farm to be allocated, Step a2 involves processing the initial measured wind energy dataset and the initial measured wind turbine dataset, respectively, to obtain the target measured wind energy dataset and the target measured wind turbine dataset. Step a3 involves constructing a physical system model based on wind power generation, using a target measured wind turbine dataset and a characteristics dataset. This includes step a4, which involves constructing a digital twin model based on wind power generation, based on a target measured wind energy dataset and a physical system model based on wind power generation.

[0058] Specifically, outlier removal, missing value removal, and normalization are performed on the initial measured wind energy dataset and the initial measured wind turbine dataset to obtain the corresponding usable target measured wind energy dataset and target measured wind turbine dataset.

[0059] Outlier handling is used to remove abnormal data, and methods such as the central absolute deviation outlier handling method can be used. Missing value handling is used to fill in missing data, and methods such as statistical embedding can be used. Normalization is used to standardize the data format, and methods such as the Z-score standardization method can be used.

[0060] By selectively using the processed target measured wind turbine dataset and combining it with the acquired wind turbine group characteristic dataset, a corresponding wind power-based physical system model can be constructed, including the structure of the wind turbines and the turbine group itself.

[0061] Selectively, the processed target measured wind energy dataset is correlated with the constructed wind power-based physical system model, the models of the target measured wind energy dataset and the wind power-based physical system model are aligned or calibrated, and a corresponding wind power-based digital twin model is constructed.

[0062] The digital twin model based on wind power generation simulates the input conditions for wind energy, simulates the power output of wind turbines and other performance indicators, verifies them by comparing them with actual operating data of wind power generation systems, and adjusts and optimizes the model based on the verification results. Subsequently, collected wind turbine data and wind energy data are connected to the digital twin model, and the model's input parameters are updated in real time.

[0063] In step S203, the adjustment rate is determined based on the predicted wind energy dataset and the preset adjustment period. For details, please refer to step S103 of the embodiment shown in Figure 1, and a detailed explanation is omitted here.

[0064] In step S204, within a predetermined adjustment cycle, the layout of each wind turbine in the wind power generation-based prediction twin model is adjusted based on the predicted wind energy dataset and adjustment rate, and the target layout of the wind turbine group within the allocated offshore wind farm and the target orientation of each wind turbine are obtained until the total simulated power generation generated by the allocated offshore wind farm is maximized. For details, please refer to step S104 of the embodiment shown in Figure 1, and a detailed explanation is omitted here.

[0065] The resource allocation method for offshore wind power plants according to this embodiment can improve the accuracy of the model by constructing a digital twin model based on wind power generation by combining it with a characteristic dataset of wind turbine groups within the offshore wind power plant to be allocated. By selectively combining this digital twin model based on wind power generation with predicted wind energy data, a corresponding predictive twin model based on wind power generation can be constructed. This predictive twin model based on wind power generation can be used to obtain the target layout of the wind turbine groups within the offshore wind power plant to be allocated and the target orientation of each wind turbine. This allows for simultaneous adjustment of the position and orientation of the wind turbines, further maximizing the utilization of offshore wind resources and improving the efficiency of wind power generation.

[0066] This embodiment provides a resource allocation method for an offshore wind power plant, and Figure 3 is a flowchart of the resource allocation method for an offshore wind power plant according to the embodiment of the present invention, and as shown in Figure 3, the process includes steps S301 to S303.

[0067] In step S301, the initial measured wind energy dataset, initial measured wind turbine dataset, and initial forecast wind energy dataset for the offshore wind farm to be allocated are obtained. For details, please refer to step S101 of the embodiment shown in Figure 1, and a detailed explanation is omitted here.

[0068] In step S302, a predictive twin model based on wind power generation is constructed based on the initial measured wind energy dataset, the initial measured wind turbine dataset, and the initial forecasted wind energy dataset. For details, please refer to step S202 of the example shown in Figure 2, and a detailed explanation is omitted here.

[0069] Step S303: Determine the adjustment rate based on the predicted wind energy dataset and the preset adjustment cycle.

[0070] Specifically, step S303 includes steps S3031 and S3032.

[0071] Step S3031: Determine the predicted wind energy coefficient based on the predicted wind energy dataset and the preset adjustment period.

[0072] First, obtain the number of wind direction changes in a pre-set adjustment period for the predicted wind energy dataset and F x Mark it as such.

[0073] The number of wind direction changes represents the number of wind direction changes that occur within a single pre-set adjustment cycle.

[0074] Next, based on the predicted wind energy data, the corresponding predicted wind speed is obtained and F s Mark it as such.

[0075] Subsequently, the predicted wind speed F was obtained. s and the number of wind direction changes F x Set the wind energy weights for each, and predict the wind speed F s The weight of wind energy is Q sSet it to, and the number of wind direction changes is F x Set the wind energy weight of x to Q.

[0076] Finally, calculate the predicted wind energy coefficient R according to the following formula (1). R = F x Q x + F s Q s (1)

[0077] Step S3032: Compare the predicted wind energy coefficient with a preset threshold value, and determine an adjustment rate based on the comparison result.

[0078] Specifically, compare the predicted wind energy coefficient R with a preset threshold value R0. When R ≤ R0, mark the predicted wind energy coefficient R as stable wind energy. When R > R0, mark the predicted wind energy coefficient R as unstable wind energy.

[0079] Optionally, when the predicted wind energy coefficient R is marked as stable wind energy, determine the adjustment rate as a high adjustment rate. When the predicted wind energy coefficient R is marked as unstable wind energy, determine the adjustment rate as a low adjustment rate.

[0080] Step S304: In a preset adjustment period, based on the predicted wind energy dataset and the adjustment rate, adjust the layout of each wind turbine in the predicted twin model based on wind power generation, and obtain the target layout of the wind turbine group and the target orientation of each wind turbine in the offshore wind power plant to be allocated until the total simulated power generation generated by the offshore wind power plant to be allocated is maximized.

[0081] Specifically, the above step S304 includes steps S3041 to S3045.

[0082] In step S3041, within a predetermined adjustment cycle, the position of each wind turbine and the distance between different wind turbines in the wind power generation-based prediction twin model are adjusted based on the predicted wind energy dataset and adjustment rate to obtain multiple layouts of wind turbine groups within the offshore wind farm to be allocated and multiple first simulation total power generation amounts.

[0083] Specifically, in a predictive twin model based on wind power generation, the simulated power generation of each wind turbine within the offshore wind farm to be allocated can be obtained by adjusting the position of each wind turbine and the distance between different wind turbines based on the predicted wind energy dataset and adjustment rate. Furthermore, the total simulated power generation of the group of wind turbines within the offshore wind farm to be allocated can be obtained based on the simulated power generation of each wind turbine.

[0084] By selectively performing multiple adjustments within a predetermined adjustment cycle, it is possible to obtain multiple layouts of wind turbine groups within the offshore wind farm targeted for allocation after adjustment, as well as multiple first-simulation total power generation amounts.

[0085] In step S3042, based on multiple first simulation total power generation values, the target layout of the wind turbine group within the offshore wind farm to be allocated is determined for multiple layouts.

[0086] Specifically, based on the multiple first simulation total power generation values ​​obtained, a corresponding line graph can be constructed, and then, based on the constructed line graph, the maximum simulation total power generation value can be obtained.

[0087] Selectively, the position of each wind turbine is recorded when the total simulated power generation is maximized, and the recorded positions of each wind turbine are marked as the optimal layout for the wind turbine group, i.e., the total simulated power generation generated by the wind turbine group within the allocated offshore wind farm in the target layout is the maximum among multiple first-generation total simulated power generation.

[0088] Step S3043: Determine the target steering rate for each wind turbine within the offshore wind farm to be allocated, based on the target layout.

[0089] Specifically, based on the optimal layout of the resulting wind turbine group, the target steering rate for each wind turbine within the offshore wind farm to be allocated can be further determined.

[0090] In step S3044, based on the target layout and the target steering rate of each wind turbine, the orientation of each wind turbine is adjusted in the predictive twin model based on wind power generation to obtain multiple second simulated total power generation and multiple first orientations of each wind turbine.

[0091] Specifically, by adjusting the orientation of each wind turbine in a predictive twin model based on wind power generation using the determined target steering rate for each wind turbine, based on the optimal layout of the obtained wind turbine group, the simulated power generation of each wind turbine in different orientations can be obtained. Furthermore, based on the simulated power generation of each wind turbine, the simulated total power generation of the wind turbine group within the offshore wind farm to be allocated can be obtained.

[0092] By selectively performing multiple adjustments within a predetermined adjustment cycle, it is possible to obtain multiple second-simulated total power generation amounts for the wind turbine group within the offshore wind farm targeted for allocation after adjustment, as well as multiple first orientations for each wind turbine.

[0093] In step S3045, the target orientation of each wind turbine within the offshore wind farm to be allocated in multiple first orientations is determined based on the total power generation of multiple second simulations.

[0094] Specifically, based on the multiple second simulation total power generation values ​​obtained, the maximum second simulation total power generation value can be obtained, the operating point of this maximum second simulation total power generation value is marked as the maximum power point, the orientation of the wind turbine at the maximum power point is obtained and marked as the optimal orientation, i.e., the target orientation.

[0095] In some selective embodiments, step S3043 above is: Step b1 involves obtaining the measured position and measured orientation of each wind turbine within the offshore wind farm to be allocated, Step b2 involves adjusting the orientation of each wind turbine in a predictive twin model based on the target layout to obtain multiple third simulation total power generation amounts and multiple second orientations for each wind turbine, Step b3 determines the third orientation of each wind turbine within the offshore wind farm to be allocated in multiple second orientations based on the total power generation of multiple third simulations, Step b4 involves determining the steering angle of each wind turbine based on the measured orientation and third orientation of each wind turbine, Step b5 involves determining the adjustment time for each wind turbine based on the target layout and measured position, The process includes step b6, which determines a target steering rate for each wind turbine based on the adjustment time and steering angle of each wind turbine.

[0096] First, based on the optimal layout of the wind turbine group obtained, the orientation of each wind turbine can be randomly adjusted in the wind power generation-based predictive twin model to obtain the simulated power generation of each wind turbine in different orientations. Furthermore, based on the simulated power generation of each wind turbine, the total simulated power generation of the wind turbine group within the offshore wind farm to be allocated can be obtained.

[0097] By selectively performing adjustments multiple times within a predetermined adjustment cycle, it is possible to obtain multiple third-generation simulated total power generation values ​​for the wind turbine group within the offshore wind power plant targeted for allocation after adjustment, as well as multiple second orientations for each wind turbine.

[0098] Next, based on the multiple obtained total power generation values ​​of the third simulation, the maximum total power generation value of the third simulation can be obtained, and the operating point of this maximum total power generation value of the third simulation can be marked as the maximum power point. The orientation of the wind turbine at the maximum power point can then be obtained and marked as the optimal orientation when randomly adjusted.

[0099] Selectively, based on the measured orientation of each wind turbine and the optimal orientation when randomly adjusted, the minimum angle of rotation required to adjust each wind turbine to the optimal orientation, i.e., the steering angle, can be obtained, Z j Mark it as such.

[0100] Subsequently, based on the measured position of each wind turbine and the position of each wind turbine in the target layout, the adjustment distance required to adjust each wind turbine to the target layout can be obtained.

[0101] Selectively, based on the adjustment distance and the corresponding adjustment rate, the corresponding adjustment time can be obtained and marked as Ts.

[0102] Finally, based on the adjustment time and steering angle of each wind turbine, the target steering rate Z for each wind turbine is as shown in equation (2) below. s You can obtain this. JPEG0007833559000001.jpg14145

[0103] The resource allocation method for offshore wind power plants according to this embodiment is advantageous in ensuring the stability of the wind turbine group during movement by determining different adjustment rates by combining a predicted wind energy dataset with a preset adjustment period, and then using the determined adjustment rates to adjust the layout of each wind turbine in a predictive twin model based on wind power generation. This allows for the realization of an adjustment mechanism tailored to the purpose for wind turbines according to different wind resource conditions. Selectively, in the process of adjusting the wind turbine group within the offshore wind power plant to be allocated to the optimal layout using a target steering rate, each wind turbine within the offshore wind power plant can be simultaneously adjusted to the optimal orientation, thereby simultaneously adjusting the position and orientation of the wind turbines and improving the efficiency of wind power generation.

[0104] This embodiment further provides a resource allocation device for an offshore wind farm, which is used to implement the above embodiment and optional embodiments, and will not be described again what has already been described. As used below, the term “module” may refer to a combination of software and / or hardware capable of implementing a predetermined function. The devices described in the following embodiments are preferably implemented in software, but can and are conceivable to be implemented in hardware, or a combination of software and hardware.

[0105] This embodiment provides a resource allocation device for an offshore wind power plant, and as shown in Figure 4, the device is An acquisition module 401 for obtaining the initial measured wind energy dataset, initial measured wind turbine dataset, and initial forecast wind energy dataset for offshore wind farms to be allocated, A construction module 402 for constructing a wind power generation-based predictive twin model based on an initial measured wind energy dataset, an initial measured wind turbine dataset, and an initial forecasted wind energy dataset, wherein the wind power generation-based predictive twin model is used to obtain the simulated total power generated by various wind turbine layouts within an offshore wind farm to be allocated under the conditions of the forecasted wind energy dataset, and A determination module 403 for determining the adjustment rate based on a predicted wind energy dataset and a pre-set adjustment period, The system includes an adjustment module 404 for adjusting the layout of each wind turbine in a wind power generation-based prediction twin model based on a predicted wind energy dataset and adjustment rate within a predetermined adjustment cycle, and obtaining the target layout of the wind turbine group within the allocated offshore wind farm and the target orientation of each wind turbine until the total simulated power generation generated by the allocated offshore wind farm is maximized.

[0106] In some selective embodiments, the construction module 402 is Based on the initial measured wind energy dataset and the initial measured wind turbine dataset, a first construction submodule is used to construct a digital twin model based on wind power generation using digital twin technology, A processing submodule for processing the initial forecast wind energy dataset using a pre-configured offshore wind energy prediction model to obtain a predicted wind energy dataset for the offshore wind farms to be allocated, It includes a second construction submodule for building a wind power-based predictive twin model based on a predicted wind energy dataset and a digital twin model based on wind power generation.

[0107] In some selective embodiments, the first construction submodule is: A first acquisition unit for obtaining a characteristic dataset of wind turbines within an offshore wind power plant that is subject to allocation, A processing unit for obtaining a target measured wind energy dataset and a target measured wind turbine dataset by processing the initial measured wind energy dataset and the initial measured wind turbine dataset, respectively. Based on the target measured wind turbine dataset and characteristic dataset, a first construction unit is used to construct a physical system model based on wind power generation, It includes a second construction unit for building a digital twin model based on wind power generation, based on a target measured wind energy dataset and a physical system model based on wind power generation.

[0108] In some selective embodiments, the construction module 402 is An acquisition submodule for obtaining the first measured wind energy dataset and the historical forecast wind energy dataset of the offshore wind power plants subject to allocation, In the first historical measured wind energy dataset, a first determination submodule is used to determine the second historical measured wind energy dataset corresponding to the historical forecast wind energy dataset, It further includes a third construction submodule for constructing a pre-configured offshore wind energy prediction model based on a historical forecast wind energy dataset and a historical second measured wind energy dataset.

[0109] In some selective embodiments, the decision module 403 is A second determination submodule for determining the predicted wind energy coefficient based on a predicted wind energy dataset and a preset adjustment period, It includes a comparison and determination submodule for comparing a predicted wind energy coefficient with a preset threshold and determining an adjustment rate based on the comparison results.

[0110] In some selective embodiments, the adjustment module 404 is A first adjustment submodule adjusts the position of each wind turbine and the distance between different wind turbines in a wind power generation-based prediction twin model based on a predetermined adjustment cycle, based on a predicted wind energy dataset and adjustment rate, in order to obtain multiple layouts of wind turbine groups within the offshore wind farm to be allocated and multiple first simulation total power generation amounts. A third decision submodule for determining the target layout of a group of wind turbines within an offshore wind farm to be allocated in multiple layouts based on multiple first simulation total power generation amounts, wherein the third decision submodule is the one in which the total simulation power generation generated by the group of wind turbines within the offshore wind farm to be allocated in the target layout is the largest among the multiple first simulation total power generation amounts, A fourth decision submodule for determining the target steering rate of each wind turbine within the offshore wind farm to be allocated, based on the target layout, A second adjustment submodule adjusts the orientation of each wind turbine in a wind power-based predictive twin model based on the target layout and target steering rate of each wind turbine, in order to obtain multiple second simulated total power generation amounts and multiple first orientations of each wind turbine. A fifth decision submodule for determining the target orientation of each wind turbine in an offshore wind farm to be allocated in multiple first orientations, based on multiple second simulation total power generation amounts, the fifth decision submodule having the largest simulation total power generation amount among the multiple second simulation total power generation amounts, where the simulation total power generation amount generated in the target orientation of each wind turbine in the offshore wind farm to be allocated is the largest.

[0111] In some selective embodiments, the fourth decision submodule is: A second acquisition unit for obtaining the measured position and orientation of each wind turbine within the offshore wind power plant subject to allocation, Based on the target layout, an adjustment unit adjusts the orientation of each wind turbine in a predictive twin model based on wind power generation to obtain multiple third-generation total power generation and multiple second orientations for each wind turbine, A first decision unit for determining the third orientation of each wind turbine in an offshore wind farm to be allocated in multiple second orientations, based on multiple third simulation total power generation amounts, wherein the first decision unit is the one in which the simulation total power generation generated in the third orientation of each wind turbine in the offshore wind farm to be allocated is the largest among the multiple third simulation total power generation amounts, A second determination unit for determining the steering angle of each wind turbine based on the measured orientation and third orientation of each wind turbine, A third decision unit for determining the adjustment time for each wind turbine based on the target layout and measured position, It includes a fourth determination unit for determining the target steering rate of each wind turbine based on the adjustment time and steering angle of each wind turbine.

[0112] Further descriptions of the functions of each of the above modules and units are the same as those of the corresponding embodiments described above, and therefore, detailed explanations are omitted here.

[0113] In this embodiment, the resource allocation device for the offshore wind power plant is implemented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0114] The embodiment of the present invention further provides a computer device having a resource allocation device for an offshore wind power plant as shown in Figure 4 above.

[0115] Referring to Figure 5, which is a schematic diagram of the structure of a computer device according to a selective embodiment of the present invention, as shown in Figure 5, the computer device includes one or more processors 10, memory 20, and interfaces for connecting each component, including high-speed and low-speed interfaces. Each component is connected to communicate with one another using different buses and installed on a common motherboard, or may be installed in other ways as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory for displaying GUI graphic information on external input / output devices (such as display devices coupled to the interfaces). In some selective embodiments, multiple processors and / or multiple buses can be used together with multiple memories as needed. Similarly, multiple computer devices can be connected so that each device provides a portion of the required operations (for example, functioning as a server array, a set of blade servers, or a multiprocessor system). Figure 5 shows a processor 10 as an example.

[0116] The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include hardware chips. The hardware chips may be application-specific integrated circuits, programmable logic devices, or a combination thereof. The programmable logic devices may be composite programmable logic devices, field-programmable gate arrays, general-purpose array logic, or any combination thereof.

[0117] Memory 20 stores instructions that can be executed by at least one processor 10 to implement the method shown in the above embodiment.

[0118] The memory 20 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs necessary for at least one function, and the data storage area may store data established based on the use of the computer device. In addition, the memory 20 may include high-speed random access memory and may further include non-temporary memory such as at least one magnetic disk storage device, a flash memory device, or other non-temporary solid-state storage device. In some selective embodiments, the memory 20 may optionally include memory located remotely from the processor 10, and these remote memories can be connected to the computer device via a network. The network includes, but is not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0119] Memory 20 may include volatile memory such as random access memory, memory may include non-volatile memory such as flash memory, hard disk, or solid-state drive, and memory 20 may further include combinations of the above types of memory.

[0120] The computer device further includes a communication interface 30 for communicating with other devices or communication networks.

[0121] Embodiments of the present application further provide a computer-readable storage medium, and the methods according to the embodiments of the present application can be implemented in hardware, firmware, or to be stored in a storage medium, or as computer code originally stored in a remote storage medium or a non-temporary device-readable storage medium and stored in a local storage medium, which is downloaded over a network, thereby enabling the methods described herein to be processed by a general-purpose computer, a dedicated processor, or software stored in a storage medium using programmable hardware or dedicated hardware. The storage medium may be a magnetic disk, an optical disk, read-only memory, random access memory, flash memory, a hard disk, or a solid-state drive, and optionally the storage medium may further include combinations of the above types of memory. To understand that a computer, processor, microprocessor controller, or programmable hardware includes a storage unit capable of storing or receiving software or computer code, and when the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the embodiments are implemented.

[0122] While embodiments of the present application have been described with reference to the drawings, those skilled in the art can make various modifications and alterations without departing from the spirit and scope of the present application, and all such modifications and alterations are limited to the scope of the attached claims.

Claims

1. A method for allocating resources for offshore wind power plants, The processor obtains the initial measured wind energy dataset, the initial measured wind turbine dataset, and the initial forecast wind energy dataset for the offshore wind farm to be allocated. The steps include: the processor constructing a wind power generation-based predictive twin model based on the initial measured wind energy dataset, the initial measured wind turbine dataset, and the initial forecasted wind energy dataset, wherein the wind power generation-based predictive twin model is used to obtain the simulated total power generation generated by various wind turbine layouts within the offshore wind farm to be allocated, under the conditions of the forecasted wind energy dataset; The processor performs the steps of determining an adjustment rate based on the predicted wind energy dataset and a preset adjustment period, A method for allocating resources to an offshore wind farm, characterized in that the processor adjusts the layout of each wind turbine in the predictive twin model based on the wind power generation based on the predicted wind energy dataset and the adjustment rate during the preset adjustment period, and obtains a target layout of the group of wind turbines in the offshore wind farm to be allocated and a target orientation of each wind turbine until the total simulated power generation generated by the offshore wind farm to be allocated is maximized.

2. The step of the processor constructing a predictive twin model based on wind power generation based on the initial measured wind energy dataset, the initial measured wind turbine dataset, and the initial forecasted wind energy dataset is: The processor constructs a digital twin model based on wind power generation using digital twin technology based on the initial measured wind energy dataset and the initial measured wind turbine dataset. The processor processes the initial forecast wind energy dataset using a pre-configured offshore wind energy prediction model to obtain a predicted wind energy dataset for the offshore wind farms to be allocated. The method according to claim 1, characterized in that the processor includes the step of constructing a wind power generation-based prediction twin model based on the prediction wind energy dataset and the wind power generation-based digital twin model.

3. The step of the processor constructing a digital twin model based on wind power generation using digital twin technology based on the initial measured wind energy dataset and the initial measured wind turbine dataset is: The processor obtains a characteristic dataset of the wind turbine group within the offshore wind power plant to be allocated, The processor processes the initial measured wind energy dataset and the initial measured wind turbine dataset, respectively, to obtain a target measured wind energy dataset and a target measured wind turbine dataset. The processor constructs a physical system model based on wind power generation based on the target measured wind turbine dataset and the characteristics dataset. The method according to claim 2, characterized in that the processor includes the step of constructing a digital twin model based on wind power generation based on the target measured wind energy dataset and the physical system model based on wind power generation.

4. Before the step in which the processor processes the initial forecast wind energy dataset using a pre-configured offshore wind energy forecasting model to obtain a forecast wind energy dataset for the offshore wind farm to be allocated, The processor takes the steps of acquiring a first measured wind energy dataset and a forecast wind energy dataset of the history of the offshore wind power plant to be allocated, The processor performs the steps of determining a second historical measured wind energy dataset corresponding to the forecast wind energy dataset in the first historical measured wind energy dataset, The method according to claim 2, further comprising the step of the processor constructing the pre-configured offshore wind energy prediction model based on the historical forecast wind energy dataset and the historical second measured wind energy dataset.

5. The step of the processor determining the adjustment rate based on the predicted wind energy dataset and a preset adjustment period is: The processor performs the steps of determining a predicted wind energy coefficient based on the predicted wind energy dataset and the preset adjustment period, The method according to claim 1, characterized in that the processor includes the step of comparing the predicted wind energy coefficient with a preset threshold and determining the adjustment rate based on the comparison result.

6. The step of the processor adjusting the layout of each wind turbine in the prediction twin model based on the wind power generation based on the prediction wind energy dataset and the adjustment rate in the preset adjustment period, and obtaining the target layout of the group of wind turbines in the offshore wind power plant to be allocated and the target orientation of each wind turbine until the total simulated power generated by the offshore wind power plant to be allocated is maximized, The processor adjusts the position of each wind turbine and the distance between different wind turbines in the predictive twin model based on the wind power generation based on the predicted wind energy dataset and the adjustment rate in the preset adjustment period, and obtains multiple layouts of wind turbine groups within the offshore wind farm to be allocated and multiple first simulated total power generation amounts. The processor determines the target layout of the group of wind turbines in the offshore wind farm to be allocated in the plurality of layouts based on the plurality of first simulated total power generation amounts, the step being that the simulated total power generation amount generated in the target layout by the group of wind turbines in the offshore wind farm to be allocated is the largest among the plurality of first simulated total power generation amounts, The processor determines a target steering rate for each wind turbine in the offshore wind farm to be allocated based on the target layout, The processor adjusts the orientation of each wind turbine in the predictive twin model based on the wind power generation, based on the target layout and the target steering rate of each wind turbine, and obtains a plurality of second simulated total power generation amounts and a plurality of first orientations of each wind turbine. The method according to claim 1, characterized in that the processor determines, based on the plurality of second total simulated power generation amounts, the target orientation of each wind turbine in the offshore wind farm to be allocated in the plurality of first orientations, wherein the total simulated power generation amount generated in the target orientation of each wind turbine in the offshore wind farm to be allocated is the largest among the plurality of second total simulated power generation amounts.

7. The step of the processor determining a target steering rate for each wind turbine in the offshore wind farm to be allocated based on the target layout is: The processor takes the step of acquiring the measured position and measured orientation of each wind turbine within the offshore wind power plant to be allocated, The processor adjusts the orientation of each wind turbine in the predictive twin model based on the wind power generation based on the target layout, and obtains a plurality of third simulated total power generation amounts and a plurality of second orientations for each wind turbine. The processor determines the third orientation of each wind turbine in the offshore wind farm to be allocated in the plurality of second orientations based on the plurality of third simulated total power generation amounts, wherein the simulated total power generation amount generated in the third orientation of each wind turbine in the offshore wind farm to be allocated is the largest among the plurality of third simulated total power generation amounts. The processor performs the steps of determining the steering angle of each wind turbine based on the measured orientation and the third orientation of each wind turbine, The processor performs the steps of determining the adjustment time for each wind turbine based on the target layout and the measured position, The method according to 6, wherein the processor includes the step of determining the target steering rate for each wind turbine based on the adjustment time and steering angle of each wind turbine.

8. A resource allocation device for an offshore wind power plant, An acquisition module for obtaining the initial measured wind energy dataset, initial measured wind turbine dataset, and initial forecast wind energy dataset for offshore wind farms to be allocated, A construction module for constructing a predictive twin model based on wind power generation, based on the initial measured wind energy dataset, the initial measured wind turbine dataset, and the initial forecasted wind energy dataset, wherein the predictive twin model based on wind power generation includes a construction module for obtaining the total simulated power generated by various wind turbine layouts within the offshore wind farm to be allocated, under the conditions of the forecasted wind energy dataset. A determination module for determining the adjustment rate based on the aforementioned predicted wind energy dataset and a preset adjustment period, An offshore wind farm resource allocation device, characterized in that, in the aforementioned preset adjustment period, it adjusts the layout of each wind turbine in the predictive twin model based on the wind power generation based on the predicted wind energy dataset and the adjustment rate, and includes an adjustment module for obtaining a target layout of the wind turbine group within the offshore wind farm to be allocated and a target orientation of each wind turbine until the total simulated power generation generated by the offshore wind farm to be allocated is maximized.

9. A computer device, A computer device comprising memory and a processor, wherein the memory and the processor are communicately connected, computer instructions are stored in the memory, and the processor executes the computer instructions to perform the resource allocation method for an offshore wind power plant described in any one of claims 1 to 7.

10. A computer-readable storage medium characterized by storing computer instructions for causing a computer to execute the resource allocation method for an offshore wind power plant described in any one of claims 1 to 7.