CN116011636A - Wind power resource prediction method and system based on sea wave coupling effect - Google Patents

Abstract

The invention provides a wind power resource prediction method and a wind power resource prediction system based on sea wave coupling effect, and relates to the technical field of digital processing; the existing ocean, atmosphere and sea wave motions have uncertainty, and the offshore wind power prediction precision is low; the method comprises the following steps: acquiring sea wind parameter information; constructing a coupling information interaction processing platform through a cloud processor, carrying out regional distributed division, and determining regional ocean sea wind parameter sets; acquiring regional sea wave coupling data; carrying out data decomposition to obtain scale atmosphere mode component data, regional ocean mode component data and regional ocean mode component data; inputting a wind power resource prediction model to obtain regional wind power resource prediction results; and carrying out distributed reduction to obtain a wind power resource prediction result, and synchronizing the wind power resource prediction result to a wind power resource prediction system. According to the technical scheme, the sea-air-wave coupling effect analysis is performed efficiently, the component reliability of ocean, atmosphere and sea waves is guaranteed, and the technical effect of the offshore wind power resource prediction accuracy is improved.

Description

Wind power resource prediction method and system based on sea wave coupling effect

Technical Field

The invention relates to the technical field of digital processing, in particular to a wind power resource prediction method and system based on sea wave coupling effect.

Background

The coupling action of sea waves, namely the interaction between sea, atmosphere and sea waves, specifically, the sea waves, namely the short for sea, atmosphere and sea waves, are all tropical cyclones, generally formed on warmer ocean surfaces by hurricanes and typhoons (different production places), and warm sea water in a low-pressure area of the sea surface is a key factor for the formation of the tropical cyclones, moves along the warmest sea water path, weakens when moving to a colder sea surface, and obvious cold water areas appear near the passing sea area after the tropical cyclones pass through.

Sea wind is an important source of wind power resources, deep analysis and prediction are carried out on the sea wind through sea wave coupling action, and technical support is provided for output precision of wind power resource prediction.

In the prior art, the technical problems of low offshore wind power prediction precision caused by uncertainty of motions of sea, atmosphere and sea waves exist.

Disclosure of Invention

The wind power resource prediction method and system based on the sea wave coupling effect solve the technical problem that the offshore wind power prediction precision is low due to uncertainty of the motions of the sea, the atmosphere and the sea wave, and achieve the technical effects of efficiently analyzing the sea wave coupling effect, guaranteeing the component reliability of the sea, the atmosphere and the sea wave and improving the offshore wind power resource prediction precision through a cloud processor.

In view of the above problems, the application provides a wind power resource prediction method and a wind power resource prediction system based on sea wave coupling effect.

In a first aspect, the present application provides a wind power resource prediction method based on sea-air wave coupling, where the method is applied to a wind power resource prediction system, the system is communicatively connected to a cloud processor, and the method includes: acquiring data through a data acquisition device to acquire sea wind parameter information; building a coupling information interaction processing platform through the cloud processor; based on the sea wind parameter information, carrying out regional distributed division on the coupling information interaction processing platform, and determining regional sea wind parameter sets; in the coupling information interaction processing platform, carrying out distributed pattern matching on elements in the regional ocean sea wind parameter set one by one to obtain regional sea wave coupling data; carrying out data decomposition through the regional sea wave coupling data to obtain scale atmosphere mode component data, regional sea mode component data and regional sea wave mode component data; the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data are used as input data and are input into a wind power resource prediction model, and regional wind power resource prediction results are obtained; and carrying out distribution reduction on the regional wind power resource estimation result, obtaining a wind power resource estimation result, and synchronizing the wind power resource estimation result to the wind power resource prediction system.

In a second aspect, the present application provides a wind power resource prediction system based on sea wave coupling, where the system is communicatively connected to a cloud processor, and the system includes: the data acquisition unit is used for carrying out data acquisition through the data acquisition device to acquire sea wind parameter information; the processing platform building unit is used for building a coupling information interaction processing platform through the cloud processor; the regional distributed dividing unit is used for carrying out regional distributed division on the coupling information interaction processing platform based on the sea wind parameter information to determine regional sea wind parameter sets; the pattern matching unit is used for carrying out distributed pattern matching on elements in the regional ocean sea wind parameter set one by one in the coupling information interaction processing platform to obtain regional sea wave coupling data; the data decomposition unit is used for performing data decomposition through the regional sea wave coupling data to obtain scale atmospheric mode component data, regional sea mode component data and regional sea wave mode component data; the prediction result acquisition unit is used for inputting the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data into a wind power resource prediction model to acquire regional wind power resource prediction results; and the distribution reduction unit is used for carrying out distribution reduction on the wind power resource estimated result of the region, obtaining the wind power resource estimated result and synchronizing the wind power resource estimated result to the wind power resource prediction system.

One or more technical solutions provided in the present application have at least the following technical effects or advantages:

the sea wind parameter information is acquired due to the adoption of data acquisition by the data acquisition device; constructing a coupling information interaction processing platform through a cloud processor; based on sea wind parameter information, carrying out regional distributed division on a coupling information interaction processing platform, and determining regional sea wind parameter sets; in the coupling information interaction processing platform, carrying out distributed pattern matching on elements in the regional ocean sea wind parameter set one by one to obtain regional sea wave coupling data; carrying out data decomposition to obtain scale atmosphere mode component data, regional ocean mode component data and regional ocean mode component data; inputting a wind power resource prediction model to obtain regional wind power resource prediction results; and carrying out distributed reduction to obtain a wind power resource prediction result, and synchronizing the wind power resource prediction result to a wind power resource prediction system. The method and the device achieve the technical effects of efficiently analyzing the sea wave coupling action through the cloud processor, guaranteeing the component reliability of ocean, atmosphere and sea wave and improving the prediction precision of offshore wind power resources.

Drawings

FIG. 1 is a schematic flow chart of the present invention;

FIG. 2 is a schematic flow chart of a platform for determining coupling information interaction processing according to the present invention;

fig. 3 is a schematic structural view of the present invention.

In the figure: 11. the system comprises a data acquisition unit 12, a processing platform building unit 13, a region distributed dividing unit 14, a pattern matching unit 15, a data decomposition unit 16, an estimated result acquisition unit 17 and a distributed reduction unit.

Detailed Description

The wind power resource prediction method and system based on the sea wave coupling effect solve the technical problem that the offshore wind power prediction precision is low due to uncertainty of the motions of the sea, the atmosphere and the sea wave, and achieve the technical effects of efficiently analyzing the sea wave coupling effect, guaranteeing the component reliability of the sea, the atmosphere and the sea wave and improving the offshore wind power resource prediction precision through a cloud processor.

Example 1

As shown in fig. 1, the present application provides a wind power resource prediction method based on sea-air wave coupling, where the method is applied to a wind power resource prediction system, the system is in communication connection with a cloud processor, and the method includes:

step S100: acquiring data through a data acquisition device to acquire sea wind parameter information;

specifically, the motion of the sea water has a multi-scale phenomenon, and the sea water motion such as tide, wave, ocean current and the like can all influence the mass of the offshore wind power, so that the mass of the offshore wind power resources is unstable, and the reasonable resource planning and utilization are greatly influenced.

Further specifically, the data acquisition device may be other relevant sea wind parameter measurement devices such as a fusion anemometer, an ultrasonic anemometer (measurement of wind speed and wind direction through ultrasonic time difference), and the sea wind parameter may be acquired in real time, and the sea wind parameter information includes, but is not limited to, wind direction information (including deflection angle), wind index information, wind speed index information, and wind temperature index information, and performs data acquisition, so as to provide a data basis for subsequent data analysis.

Step S200: building a coupling information interaction processing platform through the cloud processor;

further, as shown in fig. 2, a coupling information interaction processing platform is built by the cloud processor, and the step S200 includes:

step S210: based on wind power resource energy indexes, serial port setting is carried out in the cloud processor, and an index information interaction unit is obtained;

step S220: setting a coupling unit matching switch in the index information interaction unit by combining a preset coupling form;

step S230: parameter matching setting is carried out on the index information interaction unit through the coupling unit matching switch, and coupling conditions are set;

step S240: and after the parameter matching setting of the index information interaction unit is completed, determining a coupling information interaction processing platform.

Specifically, the cloud processor is a cloud computing device, can assist the wind power resource prediction system in parameter computing analysis, and provides technical support for guaranteeing the computing efficiency of the wind power resource prediction system.

Further specifically, the wind power resource energy index includes a heat flux (heat induction flux, latent heat flux, long wave radiation, short wave radiation), and momentum flux (wind stress), based on a parameter type of the wind power resource energy index, serial port setting is performed in the cloud processor, the serial port setting is a matching setting of the parameter type and a serial port mark, an index information interaction unit corresponding to the serial port is determined, the preset coupling form includes tight coupling, moderate coupling, and loose coupling, in the index information interaction unit, parameter matching setting is performed on the index information interaction unit, a preset coupling form is combined, a coupling unit matching switch is set, a coupling condition can be flexibly set by the coupling unit matching switch, after the parameter matching setting of the index information interaction unit is completed, a coupling information interaction processing platform is determined, a logic frame is provided for subsequent parameter analysis by building the coupling information interaction processing platform, and support is provided for efficient data processing.

Step S300: based on the sea wind parameter information, carrying out regional distributed division on the coupling information interaction processing platform, and determining regional sea wind parameter sets;

further, based on the sea wind parameter information, performing regional distributed division on the coupling information interaction processing platform to determine a regional sea wind parameter set, and step S300 further includes:

step S310: based on the sea wind parameter information, carrying out data area grading to obtain a sea wind area parameter information set;

step S320: and based on the sea wind regional parameter information set, carrying out regional distributed division on index information interaction units of the coupling information interaction processing platform, and determining a regional sea wind regional parameter set.

Specifically, region division is performed, a basis is provided for performing fine analysis, data region class division is performed based on the sea wind parameter information and combined with sea area information, a sea wind region parameter information set is obtained, elements of the sea wind region parameter information set are a plurality of sea wind region parameter information, the sea wind region parameter information is sea wind parameter information in a limited region, the sea wind region parameter information is default set to be sea wind parameter information of a central position of the limited region, index information interaction units of the coupling information interaction processing platform are subjected to region distributed division, a state of a coupling unit matching switch is determined, the plurality of coupling units are matched with the state of the switch, namely, regional sea wind parameters, analysis is repeatedly performed on the sea wind region parameter information, a regional sea wind parameter set is determined, region division is performed on data, the data is avoided, the predicted obtained data is difficult to accurately predict and characterize wind power resources of the region, and stability of wind power resource prediction system output is reduced.

Further, the wind power index information is used for carrying out exemplary explanation, wind stress analysis is carried out based on the wind power index information, stress parameter association analysis is carried out on a serial port corresponding to momentum flux of a wind power resource energy index, a correlation coefficient is determined, the correlation coefficient is used as a state of a momentum flux coupling unit matching switch, parameter association matching setting is carried out, the scheme can be implemented for explanation, and a state analysis scheme of a plurality of coupling unit matching switches is consistent with the scheme in the above example and is not repeated here.

Step S400: in the coupling information interaction processing platform, carrying out distributed pattern matching on elements in the regional ocean sea wind parameter set one by one to obtain regional sea wave coupling data;

step S500: carrying out data decomposition through the regional sea wave coupling data to obtain scale atmosphere mode component data, regional sea mode component data and regional sea wave mode component data;

step S600: the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data are used as input data and are input into a wind power resource prediction model, and regional wind power resource prediction results are obtained;

step S700: and carrying out distribution reduction on the regional wind power resource estimation result, obtaining a wind power resource estimation result, and synchronizing the wind power resource estimation result to the wind power resource prediction system.

Specifically, in the coupling information interaction processing platform, based on the states of a plurality of coupling unit matching switches, a plurality of modes corresponding to serial ports of a cloud processor are provided for mode switching, support is provided for improving data operation processing efficiency, distributed mode matching is carried out on elements in the regional ocean sea wind parameter set one by one, regional ocean wave coupling data is obtained, the regional ocean wave coupling data is namely an atmospheric mode component, an ocean wave mode component and an ocean-air-wave coupling parameter corresponding to the modes, parameter decomposition is carried out on the ocean-air-wave coupling parameter, adaptability analysis is carried out on the ocean-air-wave coupling parameter and the atmospheric mode component, the adaptability analysis can be combined with PSO (Particle Swarm Optimization, a particle swarm optimization algorithm) or other adaptability analysis algorithms, an adaptation value obtained by the adaptability analysis is determined to be a weight of the ocean-air-wave coupling parameter, the ocean-air-wave coupling parameter is corrected, and the atmospheric mode component is combined, and dimensional atmospheric mode component data is obtained, and regional ocean mode component data and regional ocean mode data are obtained according to the steps; the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data are used as input data and are input into a wind power resource prediction model, and the wind power resource prediction model is output as a regional wind power resource prediction result; and carrying out distributed reduction on the regional wind power resource estimation result through regional distributed division, determining the distributed reduction result as a wind power resource estimation result, synchronizing the wind power resource estimation result to the wind power resource prediction system, providing data support for comprehensively carrying out parameter evaluation, ensuring the operation processing efficiency of the wind power resource prediction system, and improving the accuracy of wind power resource prediction.

Further, the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data are used as input data, and are input into a wind power resource prediction model to obtain a regional wind power resource prediction result, and step S600 includes:

step S610: acquiring historical scale atmospheric mode component data, historical area ocean mode component data and historical area ocean mode component data;

step S620: generating a component data matrix and a matrix vector by the historical scale atmospheric mode component data, the historical region ocean mode component data and the historical region ocean mode component data;

step S630: based on the component data matrix and the matrix vector, establishing a wind power resource prediction model;

step S640: and inputting the scale atmosphere mode component data, the regional ocean mode component data and the regional ocean mode component data into a wind power resource prediction model to obtain regional wind power resource prediction results.

Further, generating a component data matrix and a matrix vector from the historical scale atmospheric mode component data, the historical region ocean mode component data, and the historical region ocean mode component data, step S620 includes:

step S621: setting the historical scale atmospheric mode component data, the historical region ocean mode component data and the historical region ocean mode component data as original series of numbers, and accumulating to obtain component data accumulated values;

step S622: and performing matrix reduction based on the accumulation operation equation and the component data accumulation value, and calculating to obtain a component data matrix and a matrix vector.

Further, based on the component data matrix and the matrix vector, a wind power resource prediction model is established, and step S630 includes:

step S631: based on the component data matrix and matrix vector, differential equation parameters are calculated

And->

Step S632: parameters of differential equation

And->

Substituting, calculating an original sequence, and establishing a grey prediction model;

step S633: and carrying out error evaluation on the gray prediction model by presetting an original error index, and determining a wind power resource prediction model if the error evaluation meets a model preset precision index.

Specifically, an information storage module, commonly known as a register, is integrated in the wind power resource prediction system, and information retrieval and extraction are carried out through a marker based on the information of the relevant data of the regional sea wave coupling data recorded by the register to obtain historical scale atmosphere mode component data, historical regional sea mode component data and historical regional sea wave mode component data; setting the historical scale atmospheric mode component data, the historical region ocean mode component data and the historical region ocean mode component data as original number columns, and accumulating to obtain component data accumulated values; based on an accumulation operation equation and the component data accumulation value, performing matrix form conversion and reduction, and calculating to obtain a component data matrix and a matrix vector; substituting the component data matrix and the matrix vector into the original sequence of conversion and reduction for calculation to obtain differential equation parameters

And->

Differential equation parameters +.>

And->

Substituting the gray prediction model into a differential equation, and establishing a gray prediction model; performing error evaluation on the gray prediction model through preset original error indexes, wherein the preset original error indexes comprise, but are not limited to, residual error average values, historical data variances, historical data residual variances, posterior difference ratios and small probability errors, and if the error evaluation meets a model preset precision index, determining the gray prediction model as a wind power resource prediction model, wherein the model preset precision index is a parameter index preset by a relevant manager of a wind power resource prediction system; and taking the scale atmosphere mode component data, the regional ocean mode component data and the regional ocean mode component data as input data, inputting a wind power resource prediction model, and obtaining wind power resource prediction model output, wherein the wind power resource prediction model output is a regional wind power resource prediction result.

Further specifically, the gray prediction model is preferably obtained by establishing the gray prediction model prediction, the gray prediction model has the characteristics of ambiguity of hierarchical and structural relation, randomness of dynamic change and imperfection or uncertainty of index data, the system change rule is searched through the generation processing of the original data, a data sequence with stronger regularity is generated, then a corresponding differential equation model is established, so that the future development trend of things is predicted, the accuracy of the model is limited through the preset original error index and the preset model accuracy index, and support is provided for guaranteeing the stability of the wind power resource prediction model.

In summary, the wind power resource prediction method and system based on the sea wave coupling effect provided by the application have the following technical effects:

the sea wind parameter information is acquired due to the adoption of data acquisition by the data acquisition device; constructing a coupling information interaction processing platform through a cloud processor; based on sea wind parameter information, carrying out regional distributed division on a coupling information interaction processing platform, and determining regional sea wind parameter sets; in the coupling information interaction processing platform, carrying out distributed pattern matching on elements in the regional ocean sea wind parameter set one by one to obtain regional sea wave coupling data; carrying out data decomposition to obtain scale atmosphere mode component data, regional ocean mode component data and regional ocean mode component data; inputting a wind power resource prediction model to obtain regional wind power resource prediction results; the wind power resource prediction method and system based on the sea wave coupling effect achieve the technical effects of efficiently analyzing the sea wave coupling effect through a cloud processor, guaranteeing the component reliability of ocean, atmosphere and sea waves and improving the prediction accuracy of the offshore wind power resource.

Because the energy index based on wind power resources is adopted, serial port setting is carried out in the cloud processor, an index information interaction unit is obtained, a coupling unit matching switch is set by combining a preset coupling form, parameter matching setting is carried out on the index information interaction unit, and coupling conditions are set; and after the parameter matching setting of the index information interaction unit is completed, determining the coupling information interaction processing platform. And the cloud processor assists the wind power resource prediction system in carrying out parameter operation analysis, so that technical support is provided for guaranteeing the operation processing efficiency of the wind power resource prediction system.

Because the matrix based on the component data and the matrix vector are adopted, the differential equation parameters are calculated

And->

Substituting the original sequence to calculate, and establishing a grey prediction model; and carrying out error evaluation on the gray prediction model by presetting an original error index, and determining the wind power resource prediction model if the error evaluation meets the model preset precision index. Paired modelsThe precision of (3) is limited, and support is provided for guaranteeing the stability of the wind power resource prediction model.

Example two

Based on the same inventive concept as the wind power resource prediction method based on the sea-air wave coupling effect in the foregoing embodiment, as shown in fig. 3, the present application provides a wind power resource prediction system based on the sea-air wave coupling effect, where the system is communicatively connected with a cloud processor, and the system includes:

the data acquisition unit 11 is used for carrying out data acquisition through the data acquisition device to acquire sea wind parameter information;

the processing platform building unit 12 is used for building a coupling information interaction processing platform through the cloud processor;

the regional distributed dividing unit 13 is used for carrying out regional distributed division on the coupled information interaction processing platform based on the sea wind parameter information, and determining regional sea wind parameter sets;

the pattern matching unit 14 is configured to perform distributed pattern matching on elements in the regional ocean sea wind parameter set one by one in the coupling information interaction processing platform, so as to obtain regional ocean wave coupling data;

the data decomposition unit 15 is used for performing data decomposition through the regional sea wave coupling data to obtain scale atmospheric mode component data, regional sea mode component data and regional sea wave mode component data;

the estimated result obtaining unit 16, where the estimated result obtaining unit 16 is configured to input the scale atmospheric mode component data, the regional ocean mode component data, and the regional ocean mode component data as input data into a wind power resource prediction model to obtain a regional wind power resource estimated result;

and the distribution reduction unit 17 is used for carrying out distribution reduction on the wind power resource estimated result of the area, obtaining the wind power resource estimated result and synchronizing the wind power resource estimated result to the wind power resource prediction system.

Further, the processing platform construction unit includes:

the serial port setting unit is used for carrying out serial port setting in the cloud processor based on wind power resource energy indexes to obtain an index information interaction unit;

the coupling unit matching unit is used for setting a coupling unit matching switch in the index information interaction unit by combining a preset coupling form;

the coupling condition setting unit is used for carrying out parameter matching setting on the index information interaction unit through the coupling unit matching switch to set coupling conditions;

and the parameter matching setting unit is used for determining the coupling information interaction processing platform after the parameter matching setting of the index information interaction unit is completed.

Further, the area distributed dividing unit includes:

the region grading unit is used for grading the data region based on the sea wind parameter information to obtain a sea wind region parameter information set;

the regional distributed dividing unit is used for carrying out regional distributed division on the index information interaction unit of the coupling information interaction processing platform based on the sea wind regional parameter information set to determine a regional sea wind parameter set.

Further, the estimation result obtaining unit includes:

the component data acquisition unit is used for acquiring historical scale atmosphere mode component data, historical area ocean mode component data and historical area ocean mode component data;

the matrix characteristic parameter generation unit is used for generating a component data matrix and a matrix vector through the history scale atmospheric mode component data, the history area ocean mode component data and the history area ocean mode component data;

the model building unit is used for building a wind power resource prediction model based on the component data matrix and the matrix vector;

the prediction result output unit is used for inputting the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data into a wind power resource prediction model to obtain a regional wind power resource prediction result.

Further, the matrix characteristic parameter generating unit includes:

the original sequence setting unit is used for setting the historical scale atmospheric mode component data, the historical area ocean mode component data and the historical area ocean mode component data into original sequence, and accumulating to obtain component data accumulated values;

the matrix restoration unit is used for carrying out matrix restoration based on an accumulation operation equation and the component data accumulation value, and calculating and obtaining a component data matrix and a matrix vector.

Further, the model building unit includes:

a differential equation parameter calculation unit for calculating differential equation parameters based on the component data matrix and matrix vector

And->

A grey prediction model establishing unit for establishing differential equation parameters

And->

The substitution is carried out in such a way that,calculating an original sequence, and establishing a grey prediction model;

and the error evaluation unit is used for carrying out error evaluation on the gray prediction model through presetting an original error index, and determining a wind power resource prediction model if the error evaluation meets a model preset precision index.

The specification and drawings are merely exemplary of the present application and various modifications and combinations may be made thereto without departing from the spirit and scope of the application. Such modifications and variations of the present application are intended to be included herein within the scope of the following claims and the equivalents thereof.

Claims (10)

1. The wind power resource prediction method based on the sea wave coupling effect is characterized by being applied to a wind power resource prediction system, wherein the wind power resource prediction system is in communication connection with a cloud processor, and the wind power resource prediction method comprises the following steps:

100 Data acquisition is carried out through a data acquisition device, and sea wind parameter information is acquired;

200 Building a coupling information interaction processing platform through the cloud processor;

300 Based on the sea wind parameter information, carrying out regional distributed division on the coupling information interaction processing platform to determine regional sea wind parameter sets;

400 In the coupling information interaction processing platform, carrying out distributed pattern matching on elements in the regional ocean sea wind parameter set one by one to obtain regional sea wave coupling data;

500 Data decomposition is carried out on the regional sea wave coupling data to obtain scale atmosphere mode component data, regional sea mode component data and regional sea wave mode component data;

600 Inputting the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data into a wind power resource prediction model to obtain regional wind power resource prediction results;

700 And carrying out distribution reduction on the wind power resource estimated result of the region to obtain the wind power resource estimated result, and synchronizing the wind power resource estimated result to the wind power resource prediction system.

2. The wind power resource prediction method based on the sea wave coupling effect according to claim 1, wherein in step 200), a coupling information interaction processing platform is built through the cloud processor, and the method comprises the following steps:

210 Based on wind power resource energy indexes, serial port setting is carried out in the cloud processor, and an index information interaction unit is obtained;

220 In the index information interaction unit, a coupling unit matching switch is set in combination with a preset coupling form;

230 The parameter matching setting is carried out on the index information interaction unit through the coupling unit matching switch, and the coupling condition is set;

240 After the parameter matching setting of the index information interaction unit is completed, determining a coupling information interaction processing platform.

3. The method for predicting wind power resources based on sea wave coupling according to claim 1, wherein in step 300), based on the sea wind parameter information, regional distributed division is performed on the coupling information interaction processing platform, and a regional sea wind parameter set is determined, comprising the steps of:

310 Based on the sea wind parameter information, carrying out data area grading to obtain a sea wind area parameter information set;

320 Based on the sea wind regional parameter information set, carrying out regional distributed division on index information interaction units of the coupling information interaction processing platform, and determining regional sea wind regional parameter sets.

4. The wind power resource prediction method based on the sea-wave coupling effect according to claim 1, wherein in step 600), the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data are used as input data, and are input into a wind power resource prediction model to obtain regional wind power resource prediction results, and the method comprises the following steps:

610 Acquiring historical scale atmospheric mode component data, historical area ocean mode component data and historical area ocean mode component data;

620 Generating a component data matrix and a matrix vector through the historical scale atmospheric mode component data, the historical area ocean mode component data and the historical area ocean mode component data;

630 Based on the component data matrix and the matrix vector, establishing a wind power resource prediction model;

640 Inputting the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data into a wind power resource prediction model to obtain regional wind power resource prediction results.

5. The method for predicting wind power resources based on sea-wave coupling according to claim 4, wherein in step 620), a component data matrix and a matrix vector are generated by the historical scale atmospheric mode component data, the historical area ocean mode component data, and the method comprises the steps of:

621 Setting the historical scale atmospheric mode component data, the historical region ocean mode component data and the historical region ocean mode component data as original series of numbers, and accumulating to obtain component data accumulated values;

622 Based on the accumulated operation equation and the component data accumulated value, performing matrix reduction, and calculating to obtain a component data matrix and a matrix vector.

6. The method for predicting wind power resources based on sea-wave coupling according to claim 4, wherein in step 630), a wind power resource prediction model is built based on the component data matrix and the matrix vector, comprising the steps of:

631 Based on the component data matrixMatrix vector, calculating differential equation parameters

And->

632 To be differential equation parameters

And->

Substituting, calculating an original sequence, and establishing a grey prediction model;

633 And (3) carrying out error evaluation on the gray prediction model by presetting an original error index, and determining a wind power resource prediction model if the error evaluation meets a model preset precision index.

7. A wind power resource prediction system adopting the wind power resource prediction method based on sea wave coupling effect as claimed in any one of claims 1 to 6, characterized by comprising:

the data acquisition unit is used for carrying out data acquisition through the data acquisition device to acquire sea wind parameter information;

the processing platform building unit is used for building a coupling information interaction processing platform through the cloud processor;

the regional distributed dividing unit is used for carrying out regional distributed division on the coupling information interaction processing platform based on the sea wind parameter information to determine regional sea wind parameter sets;

the pattern matching unit is used for carrying out distributed pattern matching on the elements in the regional ocean sea wind parameter set one by one in the coupling information interaction processing platform to obtain regional ocean wave coupling data;

the data decomposition unit is used for carrying out data decomposition through the regional sea wave coupling data to obtain the scale atmosphere mode component data, the regional sea mode component data and the regional sea wave mode component data;

the estimated result obtaining unit is used for taking the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data as input data, inputting the input data into the wind power resource prediction model, and obtaining a regional wind power resource estimated result;

the distribution reduction unit is used for carrying out distribution reduction on the regional wind power resource estimation result, obtaining a wind power resource estimation result, and synchronizing the wind power resource estimation result to the wind power resource prediction system.

8. The wind power resource prediction system of claim 7, wherein: the processing platform building unit comprises:

the serial port setting unit is used for setting serial ports in the cloud processor based on wind power resource energy indexes to obtain an index information interaction unit;

the coupling unit matching unit is used for setting a coupling unit matching switch by combining a preset coupling form in the index information interaction unit;

the coupling condition setting unit is used for carrying out parameter matching setting on the index information interaction unit through the coupling unit matching switch, and setting coupling conditions;

the parameter matching setting unit is used for determining a coupling information interaction processing platform after the parameter matching setting of the index information interaction unit is completed;

the area distribution type dividing unit includes:

the region grading unit is used for grading the data region based on the sea wind parameter information to obtain a sea wind region parameter information set;

the regional distributed dividing unit is used for carrying out regional distributed division on the index information interaction unit of the coupling information interaction processing platform based on the sea wind regional parameter information set to determine a regional sea wind parameter set;

the estimated result acquisition unit includes:

the component data acquisition unit is used for acquiring historical scale atmospheric mode component data, historical area ocean mode component data and historical area ocean mode component data;

the matrix characteristic parameter generation unit is used for generating a component data matrix and a matrix vector through the history scale atmospheric mode component data, the history area ocean mode component data and the history area ocean mode component data;

the model building unit is used for building a wind power resource prediction model based on the component data matrix and the matrix vector;

and the estimated result output unit is used for inputting the scale atmospheric mode component data, the regional ocean mode component data and the regional ocean mode component data into a wind power resource prediction model to obtain a regional wind power resource estimated result.

9. The wind power resource prediction system according to claim 8, wherein the matrix characteristic parameter generating unit includes:

the original number sequence setting unit is used for setting the historical scale atmospheric mode component data, the historical region ocean mode component data and the historical region ocean mode component data into an original number sequence, and accumulating the original number sequence to obtain a component data accumulated value;

and the matrix reduction unit is used for carrying out matrix reduction based on the accumulation operation equation and the component data accumulation value, and calculating and obtaining a component data matrix and a matrix vector.

10. The wind power resource prediction system according to claim 7, wherein the model building unit includes:

a differential equation parameter calculation unit for calculating differential equation parameters based on the component data matrix and matrix vector

And->

A gray prediction model establishing unit for establishing differential equation parameters

And->

Substituting, calculating an original sequence, and establishing a grey prediction model;

and the error evaluation unit is used for carrying out error evaluation on the gray prediction model through presetting an original error index, and determining a wind power resource prediction model if the error evaluation meets a model preset precision index.

Images