Offshore wind power environmental element coupling forecasting method and device

Abstract

The invention discloses an offshore wind power environmental element coupling forecasting method and equipment, belongs to the technical field of offshore wind power environmental forecasting, and aims to provide an offshore wind power environmental element coupling forecasting method and equipment based on a wind-wave-flow depth coupling mechanism of an MCT coupler and a power dependence design of sea ice and storm surge on a coupling result. Full-chain coupling of five elements of wind, wave, flow, ice and tide from data assimilation, cooperative calculation to result output is achieved, the overall precision and physical consistency of multi-element association forecasting in a complex marine environment are remarkably improved, accurate adaptation of forecasting data and actual application is achieved through customized output module design for offshore wind power multi-scene requirements, and the method is suitable for the offshore wind power multi-scene requirement. Sea ice and storm surge forecast is innovatively established on a wind-wave-flow coupled driving power frame, and the limitation of a traditional empirical model is overcome.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of offshore wind power environment prediction, and particularly relates to an offshore wind power environment element coupling prediction method and device. BACKGROUND

[0002] The construction, operation and maintenance, power prediction and disaster warning of offshore wind power are highly dependent on the accurate prediction of meteorological and marine environmental elements. The dynamic changes of wind, wave, current, sea ice, storm surge and other elements directly affect the operation safety of wind turbines, the planning of the operation window period and the decision-making of power transactions, and require comprehensive technical support through multi-element collaborative prediction.

[0003] In the prior art, the prediction of offshore environmental elements is characterized by "single element isolation and multi-element fragmentation". On the one hand, there is a lack of integrated prediction platform that can simultaneously cover wind, wave, current, ice and tide, the element prediction systems are independent of each other, and the data cannot be cooperated and coupled, resulting in the neglect of the correlation between elements and the limitation of prediction accuracy. On the other hand, the existing prediction systems are designed for large-scale sea areas, and the coverage accuracy of local key areas (such as the surrounding area of a specific wind farm) is insufficient, and the layout of the subsystems lacks flexibility, making it difficult to meet the needs of refined prediction. In addition, the existing technology has three major defects: first, the prediction of wind, wave, current and other dynamic elements does not form an effective coupling mechanism, and is only based on single model independent calculation, which is not consistent with the physical law of multi-element interaction in the actual marine environment; second, the resolution of the prediction data is fixed, and cannot be flexibly adjusted according to different application scenarios of the wind farm (such as high-resolution local data for construction and operation and maintenance, and large-scale data for power transactions); third, there is a lack of customized data output capability for the specific needs of wind farms, and the prediction results are mostly general data, which is difficult to directly serve the power prediction, disaster warning and other special applications. SUMMARY

[0004] The purpose of the present application is to provide an offshore wind power environment element coupling prediction method and device to solve the technical problems of multi-element isolation and poor coupling and cooperation in the prior art offshore wind power environment prediction.

[0005] To achieve the above-mentioned purpose, the following technical solutions are adopted: An offshore wind power environment element coupling prediction method, comprising the following steps: Obtaining multi-element observation data and performing preprocessing; The MCT model coupler is used to establish a wind-wave-current coupling calculation model and an ice-tide coupling calculation model, the preprocessed multi-element observation data are input into the wind-wave-current coupling calculation model to generate coupled wind, wave and current prediction parameters, and the preprocessed multi-element observation data and the output of the wind-wave-current coupling calculation model are used as inputs of the ice-tide coupling calculation model to output coupled ice and tide prediction parameters. The outputs of the two sets of coupling calculation models are encrypted for the core area of the wind farm. According to the requirements of different application scenarios, corresponding prediction parameter outputs are selected for display.

[0006] Further, the multi-element observation data are preprocessed by using a 3DVAR three-dimensional variation assimilation technology.

[0007] Further, the preprocessed multi-element observation data are input into the wind-wave-current coupling calculation model to generate coupled wind, wave and current prediction parameters, including: The preprocessed multi-element observation data are input into a wind element subsystem to output wind prediction parameters. The preprocessed multi-element observation data and the first prediction parameters are input into a wave element subsystem to output wave prediction parameters. The preprocessed multi-element observation data and the second prediction parameters are input into a current element subsystem to output current prediction parameters. The preprocessed multi-element observation data and the output of the wind-wave-current coupling calculation model are used as inputs of the ice-tide coupling calculation model to output coupled ice and tide prediction parameters, including: The preprocessed multi-element observation data, the wind prediction parameters and the current prediction parameters are input into an ice element subsystem to output ice prediction parameters. The preprocessed multi-element observation data, the wind prediction parameters and the wave prediction parameters are input into a tide element subsystem to output tide prediction parameters.

[0008] Further, the wave prediction parameters and the current prediction parameters are used as underlying surface boundary conditions of the wind element subsystem.

[0009] Further, a machine learning algorithm is used to correct the wind-wave-current coupling calculation model and the ice-tide coupling calculation model based on prediction errors.

[0010] Further, the outputs of the two sets of coupling calculation models are encrypted for the core area of the wind farm, including: A spatial interpolation encryption algorithm is used to increase encrypted grid points on the basis of existing grids, and interpolation calculation is performed in combination with surrounding observation data.

[0011] Further, according to the requirements of different application scenarios, corresponding prediction parameter output display is selected, including: Power prediction scenario: output wind speed and wind direction data within 80-200m height; Electricity transaction scenario: output global wind speed and sea wave significant wave height statistical data; Disaster warning scenario: output storm surge, sea ice thickness and extreme wind speed warning indicators, and real-time push of abnormal data; Construction and operation scenario: output wind, wave and current data in a local area.

[0012] In a second aspect, the application provides a marine wind power environment element coupling prediction system, comprising an acquisition module, a coupling calculation module, an encryption module and an output module, wherein: The acquisition module is used for acquiring and preprocessing multi-element observation data; The coupling calculation module is used for adopting an MCT model coupler to establish a wind-wave-current coupling calculation model and an ice-tide coupling calculation model, inputting the preprocessed multi-element observation data into the wind-wave-current coupling calculation model to generate coupled wind, wave and current prediction parameters, and inputting the preprocessed multi-element observation data and the output of the wind-wave-current coupling calculation model into the ice-tide coupling calculation model as inputs to output coupled ice and tide prediction parameters; The encryption module is used for encrypting the outputs of the two sets of coupling calculation models for the core area of the wind farm; The output module is used for selecting corresponding prediction parameter output display according to the requirements of different application scenarios.

[0013] In a third aspect, a terminal device is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

[0014] In a fourth aspect, a computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0015] Compared with the prior art, the application has the following beneficial technical effects: The marine wind power environment element coupling prediction method of the application realizes the whole-chain coupling of five elements of wind, wave, current, ice and tide from data assimilation, cooperative calculation to result output based on the wind-wave-current deep coupling mechanism of the MCT coupler and the dynamic dependence of sea ice and storm surge on the coupling results, significantly improves the overall accuracy and physical consistency of multi-element correlation prediction in complex marine environment, and realizes the precise adaptation of prediction data to actual application through the design of customized output module for multiple scenarios of marine wind power.

[0016] Preferably, the application realizes high-precision output of prediction data by fusing 3DVAR assimilation technology and double-data optimization scheme of feedback correction of measured data, combined with local area encryption algorithm.

[0017] Preferably, the application realizes the dual goals of "global coverage + local precision" through partition fine simulation and overlapping area fusion based on the global coverage design of multi-local subsystem collaborative networking.

[0018] Preferably, the application innovatively establishes sea ice and storm surge prediction on the dynamic framework of wind-wave-current coupling driving, overcoming the limitations of traditional empirical models.

[0019] The technical solution effectively solves the core defects of isolated, fragmented, insufficient precision and poor practicability of marine environmental element prediction in the prior art by constructing an integrated prediction platform of "multi-local subsystem collaborative networking-wind-wave-current deep dynamic coupling-encryption based on measured data correction-dynamic resolution adjustment-scenario customization output". BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 A marine wind power environmental element coupling prediction method flowchart in the embodiments of the application; Figure 2 An element subsystem collaborative coverage schematic diagram; Figure 3 A multi-element coupling calculation flowchart; Figure 4 An overall front-end schematic diagram of the environmental prediction platform. DETAILED DESCRIPTION

[0021] In order to enable personnel in the technical field to better understand the application scheme, the technical solutions in the embodiments of the application will be described clearly and completely below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the application.

[0022] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and in the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] Term explanation: MCT: Model Coupling Toolkit, a core tool for realizing data interaction and collaborative calculation between different numerical models.

[0025] WRF: Weather Research and Forecasting Model, a limited-area forecasting model for numerical simulation of atmospheric environmental factors.

[0026] SWAN: Simulating Waves Nearshore, a professional model for simulating the generation and propagation process of nearshore sea waves.

[0027] ADCIRC: Advanced Circulation Model, a numerical model for simulating ocean circulation such as storm surge and tidal current.

[0028] FVCOM: Finite Volume Coastal Ocean Model, a cross-scale model for simulating fine ocean dynamic factors such as ocean current and water temperature.

[0029] 3DVAR: Three-Dimensional Variational Assimilation, a kind of assimilation technology that integrates multi-source observation data and optimizes the initial field of the model.

[0030] High resolution: fine data output standard with horizontal resolution ≤1km and time resolution ≤15min (atmospheric factors), ≤1h (ocean factors).

[0031] Technical problems to be solved: (1) Multi-element collaborative prediction is missing, and the accuracy is insufficient due to isolated calculation of each element In the prior art, wind, wave, current, ice, tide and other elements are predicted by independent systems respectively, without considering the physical coupling relationship between elements (such as wind driving sea waves, sea waves affecting sea currents, and sea ice interacting with tidal currents), resulting in a large deviation between the predicted results and the actual marine environment. At the same time, there is a lack of an integrated platform to integrate multi-element data, which cannot provide comprehensive and collaborative environmental support for wind farms, affecting the scientificity of operation decision-making.

[0032] (2) Local sea coverage is insufficient, and the accuracy of global and local prediction is difficult to balance Most existing prediction systems use a single model to cover a large range of sea areas, resulting in insufficient depiction of fine features such as terrain and coastline in local key areas (such as the surrounding area of a wind farm), insufficient prediction resolution and accuracy. If the resolution of the global model is simply increased, the calculation cost will be greatly increased, the timeliness of the prediction will be reduced, and it will be difficult to achieve the dual requirements of "global coverage + local precision".

[0033] (3) Coupling mechanism is not perfect, and the prediction of sea ice and storm surge lacks dynamic support In the prior art, some multi-element predictions only achieve data-level superposition and do not establish a deep coupling mechanism for wind, wave, and current; the prediction of sea ice and storm surge is mostly based on empirical models or static data deduction, lacking dynamic support based on wind-wave-current coupling results, resulting in limited prediction accuracy due to the quality of initial data, and the inability to adapt to complex changes in marine environment.

[0034] (4) Fixed resolution and lack of data correction, unable to meet the needs of fine-grained requirements The output resolution of existing prediction systems is mostly fixed, and cannot be flexibly adjusted according to different application scenarios of wind farms (such as the need for high resolution below 1km for construction and operation, and the need for medium resolution for a large range for power trading). At the same time, the prediction results are not corrected and encrypted in combination with the measured data of the wind farm, resulting in large prediction errors in local areas and difficulty in meeting the needs of high-precision applications.

[0035] (5) General data output, lack of customized service capability The prediction results of the existing technology are mostly standardized general data, without customized output for the individual needs of different application scenarios of wind farms such as power prediction, power trading, disaster warning, construction and operation. Different scenarios have different requirements for element types, time scales, and accuracy indicators, and general data is difficult to directly adapt, increasing the cost of secondary data processing for wind farms.

[0036] The invention will be described in further detail below with reference to the accompanying drawings: As Figure 1As shown, a marine wind power environment element coupling prediction method comprises the following steps: Step one, obtain multi-element observation data and pre-process; The multi-element observation data at least includes satellite remote sensing data, wind farm observation data, ocean station / buoy observation data and conventional meteorological observation data, and the 3DVAR three-dimensional variation assimilation technology is used to pre-process the multi-element observation data, so as to provide high-quality initial field for subsystem calculation.

[0037] Step two, adopt the MCT model coupling device to establish a wind-wave-current coupling calculation model and an ice-tide coupling calculation model, input the pre-processed multi-element observation data into the wind-wave-current coupling calculation model to generate coupled wind, wave and flow prediction parameters, and input the pre-processed multi-element observation data and the output of the wind-wave-current coupling calculation model into the ice-tide coupling calculation model as input, and output coupled ice and tide prediction parameters; Based on the MCT coupling device, the wind-wave-current coupling calculation model is established, the driving mechanism of the wind field to the sea wave and the energy exchange mechanism of the sea wave and the sea current are established, and the bidirectional coupling calculation of the three elements is realized, including: The pre-processed multi-element observation data is input into the wind element subsystem, and the wind prediction parameter is output; The pre-processed multi-element observation data and the first prediction parameter are input into the wave element subsystem, and the wave prediction parameter is output; The pre-processed multi-element observation data and the second prediction parameter are input into the flow element subsystem, and the flow prediction parameter is output.

[0038] The sea ice subsystem takes the coupled wind field and flow field data as input, simulates the influence of wind stress and flow stress on sea ice movement and thickness change, and the storm surge subsystem fuses the coupled wind field and wave field data, combines astronomical tide data, calculates the storm surge process, realizes accurate prediction under dynamic driving, including: The pre-processed multi-element observation data, wind prediction parameter and flow prediction parameter are input into the ice element subsystem, and the ice prediction parameter is output; The pre-processed multi-element observation data, wind prediction parameter and wave prediction parameter are input into the tide element subsystem, and the tide prediction parameter is output.

[0039] Among them, the wind element subsystem: based on WRF model, time resolution can reach 15min, horizontal resolution can reach 1km, vertical output is not less than 35 layers (not less than 8 layers within 80-200m height), output wind speed, wind direction, temperature and other parameters.

[0040] The wave element subsystem: based on SWAN model, time resolution can reach 1h, horizontal resolution can reach 1km, output effective wave height, average period and other parameters.

[0041] The flow element subsystem is based on the FVCOM model, and has a time resolution of 1h, a horizontal resolution of 1km, and at least 10 vertical outputs, and outputs parameters such as sea current and sea temperature.

[0042] The ice element subsystem is based on an elastic-viscoplastic sea ice model, and has a time resolution of 1h, a horizontal resolution of 1km, and outputs parameters such as sea ice thickness and outer edge length.

[0043] The tide element subsystem (storm surge) is based on the ADCIRC model, and has a horizontal resolution of 500m and a time resolution of 1h, and outputs parameters such as storm surge.

[0044] Step three, for the core area of the wind farm, the outputs of the two coupled calculation models are encrypted; For the core area of the wind farm, a spatial interpolation encryption algorithm is used to increase the encryption grid points on the basis of the existing grid, and the surrounding observation data is used for interpolation calculation, so that the effective data point density of the local area is improved by 3-5 times, and the fine degree is further improved.

[0045] Step four, according to the requirements of different application scenarios, select the corresponding prediction parameter output display; The power prediction scene outputs the wind speed and wind direction data within the height of 80-200m, with a time resolution of 15min and a prediction validity of 7 days.

[0046] The power transaction scene outputs the statistical data (such as average value and extreme value) of the global wind speed and wave effective height, with a time resolution of 1h and a prediction validity of 7 days.

[0047] The disaster warning scene outputs warning indicators such as storm surge, sea ice thickness and extreme wind speed, and pushes the abnormal data in real time.

[0048] The construction and operation scene outputs high-resolution (≤1km) wind, wave and flow data in the local area, with a prediction validity of 7 days and support for operation window period evaluation data output.

[0049] In another embodiment of the application, a marine wind power environment element coupling prediction system is provided, comprising an acquisition module, a coupling calculation module, an encryption module and an output module, wherein: The acquisition module is used for acquiring and preprocessing multi-element observation data; The coupling calculation module is used for adopting an MCT model coupler to establish a wind-wave-flow coupling calculation model and an ice-tide coupling calculation model, inputting the preprocessed multi-element observation data into the wind-wave-flow coupling calculation model to generate coupled wind, wave and flow prediction parameters, and inputting the preprocessed multi-element observation data and the output of the wind-wave-flow coupling calculation model into the ice-tide coupling calculation model as inputs to output coupled ice and tide prediction parameters. Encryption module: used for encrypting the output of the two groups of coupled calculation models for the core area of the wind farm; Output module: used for selecting corresponding prediction parameter output display according to the requirements of different application scenarios.

[0050] Optionally, the application provides an offshore wind power environment element coupling prediction system platform. The platform adopts a "layered architecture + modular design", and is divided into five core levels of data input layer, subsystem calculation layer, coupling calculation layer, data processing layer and display output layer, and each level cooperates to realize multi-element integrated prediction: 1) Data input layer: integrate satellite remote sensing data, wind farm observation data, ocean station / buoy observation data, conventional meteorological observation data and other multi-source data, and pre-process the data through 3DVAR three-dimensional variational assimilation technology to provide high-quality initial field for subsystem calculation.

[0051] 2) Subsystem calculation layer: for wind, wave, current, ice and tide, build a special prediction subsystem for each element, and each element is composed of multiple local subsystems, each local subsystem covers a specific area, and the target sea area is covered through cooperative networking, as shown in Figure 2 .

[0052] The system provides a subsystem cooperative coverage mechanism, each environmental element is composed of multiple local subsystems, and the coverage range of the local subsystem is divided according to the topographic features and wind farm distribution of the target sea area, so as to ensure that the fine topography, coastline and other features of each local area are fully described. Each local subsystem cooperates through a data interaction interface: The calculation areas of adjacent local subsystems have an overlapping zone, and the prediction results of the overlapping zone are fused by a weighted average algorithm to avoid data faults.

[0053] The calculation parameters (such as grid size and integration step) of each local subsystem are adaptively configured according to the environmental characteristics of the area, such as finer grid in the nearshore area and relatively coarse grid in the open sea area, to balance accuracy and calculation cost.

[0054] After the subsystem networking, a unified time synchronization mechanism is used to ensure that the calculation results of each subsystem are consistent in the time dimension, providing synchronous data support for subsequent coupling calculation 3) Coupling calculation layer: use MCT model coupler to realize deep coupling calculation of wind, wave and current three major dynamic elements, simulate the interaction mechanism between elements through flux exchange and calculation scheme optimization; the sea ice and storm surge subsystems take the wind-wave-current coupling calculation results as the dynamic input to realize accurate prediction based on dynamic support, as shown in Figure 3 .

[0055] Wind-wave-current coupling: Based on the MCT coupler, the driving mechanism of wind field on sea waves, the energy exchange mechanism of sea waves and sea currents are established to realize the two-way coupling calculation of the three elements. The specific process is as follows: the near-surface wind field data output by the WRF wind field model is used as the forcing field of the SWAN wave model, the wave parameters calculated by the SWAN model are fed back to the FVCOM current model, and the current data output by the FVCOM model is used to adjust the underlying surface boundary conditions of the WRF model to form a closed loop coupling.

[0056] Sea ice-storm surge coupling support: The sea ice subsystem takes the coupled wind field and current field data as input to simulate the influence of wind stress and current stress on sea ice movement and thickness change; the storm surge subsystem integrates the coupled wind field and wave field data, combines with the astronomical tide data, calculates the storm surge process, and realizes accurate prediction under the driving of power.

[0057] 4) Data processing layer: including two core modules of data correction and encryption, and dynamic resolution adjustment.

[0058] Data correction and encryption: Compare the results of subsystem and coupling calculation with the measured data of wind farm, use error feedback correction algorithm for data correction, and at the same time, carry out data encryption processing on local key areas (such as wind farm core area) to improve the local prediction accuracy: Data correction: Build an "measured data-predicted data" error database, use machine learning correction algorithm, and correct real-time prediction results based on historical error law. For example, wind speed prediction error is trained and corrected by wind speed measurement tower measured data to effectively reduce systematic error.

[0059] Data encryption: For the core area of the wind farm, use spatial interpolation encryption algorithm to increase the encryption grid points on the basis of the existing grid, and combine with the surrounding observation data for interpolation calculation, so that the effective data point density of the local area is improved by 3-5 times, and the fine degree is further improved.

[0060] Dynamic resolution adjustment: Support adjusting the output resolution of each element according to application requirements, the horizontal resolution can be switched in the range of 500m-5km, the time resolution can be adjusted in the range of 15min-1h, and the precision and calculation efficiency are considered.

[0061] 5) Display output layer: integrated comprehensive display and customized output function, realizing integrated display and personalized output of multi-element data.

[0062] Comprehensive display function: The platform has the ability of comprehensive visualization display of global multi-element data, supports single-point query of any coordinate point (outputs the time series data of each element at the point), and custom area query (outputs the element distribution atlas of the specified area), and the display interface includes element distribution heat map, time change curve, numerical statistics table and other forms, such asFigure 4 The output function is customized according to different application scenarios.

[0063] Customized output function: design special output module for different application scenarios Power prediction scenario: output wind speed and direction data within 80-200m height, time resolution 15min, prediction validity 7 days.

[0064] Electricity trading scenario: output statistical data (such as average value, extreme value) of global wind speed and wave significant height, time resolution 1h, prediction validity 7 days.

[0065] Disaster warning scenario: output warning indicators such as storm surge, sea ice thickness, and extreme wind speed, and push real-time abnormal data.

[0066] Construction and operation scenario: output high-resolution (≤1km) wind, wave, and current data in local area, prediction validity 7 days, and support operation window period evaluation data output.

[0067] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD ROM, optical storage, etc.) containing computer-usable program code.

[0068] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in one or more flows and / or blocks.

[0069] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 an apparatus that implements the functions specified in one or more flows and / or blocks.

[0070] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are generated to realize the computer-implemented processes in the computer or other programmable devices, and the instructions executed in the computer or other programmable devices provide operational steps for implementing the functions specified in the flowchart Figure 1 one flow or multiple flows and / or the functions specified in one block or multiple blocks. Figure 1 one flow or multiple flows and / or the functions specified in one block or multiple blocks.

[0071] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit the scope of protection, although the present application has been described in detail with reference to the above examples, those skilled in the art should understand that: after reading the present application, the skilled person can make various changes, modifications or equivalent replacements to the specific embodiments of the present application, but these changes, modifications or equivalent replacements are all within the scope of protection of the claims of the present application.

Claims

1. A coupled forecasting method for offshore wind power environmental factors, characterized in that, Includes the following steps: Acquire multivariate observation data and perform preprocessing; Using the MCT model coupler, a wind-wave-current coupled calculation model and an ice-tide coupled calculation model are established. The preprocessed multivariate observation data is input into the wind-wave-current coupled calculation model to generate coupled wind, wave and current prediction parameters. The preprocessed multivariate observation data and the output of the wind-wave-current coupled calculation model are used as the input of the ice-tide coupled calculation model to output coupled ice and tide prediction parameters. For the core area of ​​the wind farm, the outputs of the two sets of coupled calculation models are encrypted; Select the corresponding prediction parameters for output and display based on the needs of different application scenarios.

2. The method for coupled forecasting of offshore wind power environmental factors according to claim 1, characterized in that, The multivariate observation data were preprocessed using 3DVAR three-dimensional variational assimilation technology.

3. The method for coupled forecasting of offshore wind power environmental factors according to claim 1, characterized in that, The preprocessed multivariate observation data is input into the wind-wave-current coupled calculation model to generate coupled wind, wave, and current prediction parameters, including: The preprocessed multivariate observation data is input into the wind element subsystem, and wind prediction parameters are output. The preprocessed multivariate observation data and the first prediction parameters are input into the wave element subsystem, and the wave prediction parameters are output. The preprocessed multivariate observation data and the second prediction parameter are input into the flow element subsystem, and the flow prediction parameter is output. The preprocessed multivariate observation data and the output of the wind-wave-current coupled calculation model are used as inputs to the ice-tide coupled calculation model, which outputs coupled ice and tide prediction parameters, including: The preprocessed multivariate observation data, wind prediction parameters, and flow prediction parameters are input into the ice element subsystem, and the ice prediction parameters are output. The preprocessed multivariate observation data, wind prediction parameters, and wave prediction parameters are input into the tide element subsystem, and the tide prediction parameters are output.

4. The method for coupled forecasting of offshore wind power environmental factors according to claim 3, characterized in that, The wave prediction parameters and flow prediction parameters are used as the underlying surface boundary conditions of the wind element subsystem.

5. The method for coupled forecasting of offshore wind power environmental factors according to claim 1, characterized in that, Machine learning algorithms are used to correct the wind-wave-current coupling calculation model and the ice-tide coupling calculation model based on the prediction error.

6. The method for coupled forecasting of offshore wind power environmental factors according to claim 1, characterized in that, For the core area of ​​the wind farm, the outputs of the two sets of coupled calculation models are encrypted, including: A spatial interpolation encryption algorithm is adopted to add encrypted grid points on the basis of the existing grid and perform interpolation calculations in combination with surrounding observation data.

7. The method for coupled forecasting of offshore wind power environmental factors according to claim 6, characterized in that, Based on the requirements of the different application scenarios, the corresponding prediction parameters are selected for output and display, including: Power prediction scenario: Output wind speed and direction data within an altitude range of 80-200m; Power trading scenario: Output statistical data on global wind speed and significant wave height; Disaster early warning scenario: Output storm surge, sea ice thickness, and extreme wind speed warning indicators, and push abnormal data in real time; Construction and maintenance scenario: Output wind, wave, and current data for local areas.

8. A coupled forecasting system for offshore wind power environmental elements, characterized in that, It includes an acquisition module, a coupled calculation module, an encryption module, and an output module, wherein: Acquisition module: Used to acquire multivariate observation data and perform preprocessing; Coupled Calculation Module: Used with the MCT model coupler to establish wind-wave-current coupled calculation models and ice-tide coupled calculation models. It inputs preprocessed multivariate observation data into the wind-wave-current coupled calculation model to generate coupled wind, wave, and current prediction parameters. It uses the preprocessed multivariate observation data and the output of the wind-wave-current coupled calculation model as input to the ice-tide coupled calculation model, and outputs coupled ice and tide prediction parameters. Encryption module: Used to encrypt the output of two sets of coupled calculation models in the core area of ​​the wind farm; Output module: Used to select and display the corresponding prediction parameters according to the needs of different application scenarios.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements as claimed in claim 1.

7. The steps of any of the methods described.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements as described in claim 1.

7. The steps of any of the methods described.

Images