Wind power generation area power generation numerical prediction system

Abstract

The present invention relates to a numerical prediction system for power generation in a wind power generation area, comprising: a power generation prediction mechanism, which is used to intelligently predict the power generation value of the wind power generation area in the future time interval based on the duration of the future time interval, various regional configuration data of the wind power generation area, and the power generation values ​​corresponding to the set number of historical time intervals before the future time interval; an information transmission mechanism, which is used to send the intelligent prediction value to a remote power generation dispatching server. Through the present invention, multiple learning devices can be introduced to output the deconvolution neural network after multiple learning as an AI intelligent prediction body, and multiple basic data can be introduced to perform the subsequent intelligent prediction of the power generation of the wind power generation area in the future time interval, thereby replacing the original rough estimation mechanism and ensuring the stability and effectiveness of the intelligent prediction results.

Description

Technical Field

[0001] The present invention relates to the field of power generation management, and in particular to a numerical prediction system for power generation in a wind power generation area. Background Art

[0002] Wind power generation refers to the conversion of wind kinetic energy into electrical energy. Wind energy is a clean, pollution-free renewable energy source that has been used by people for a long time, mainly through windmills to pump water and grind flour. People are interested in how to use wind to generate electricity. Using wind power to generate electricity is very environmentally friendly, and the wind energy reserves are huge, so it is increasingly valued by countries around the world. Wind is one of the pollution-free energy sources. And it is inexhaustible. For coastal islands, grassland pastoral areas, mountainous areas and plateau areas that are short of water, fuel and have inconvenient transportation, it is very suitable to use wind power generation according to local conditions, and there is a lot of room for development. Offshore wind power is an important field for the development of renewable energy, an important force to promote the advancement of wind power technology and industrial upgrading, and an important measure to promote the adjustment of energy structure.

[0003] However, in the process of power generation management in wind power generation areas, only the power generation in past time periods can be counted and analyzed, and the power generation in future time periods can be roughly estimated based on the results of statistics and analysis. However, it is impossible to perform a detailed prediction of the power generation in the future time period of the set wind power generation area, resulting in a lack of key reference data for subsequent power distribution and energy storage deployment. Summary of the invention

[0004] In order to solve the technical problems in the prior art, the present invention provides a numerical prediction system for power generation in a wind power generation area, which introduces multiple learning devices to output a deconvolution neural network after multiple learning as an AI intelligent prediction body, wherein different AI intelligent prediction bodies are built for different set wind power generation areas, and multiple basic data are introduced to perform intelligent prediction of power generation in future time intervals of subsequent set wind power generation areas, wherein the multiple basic data are various regional configuration data of the set wind power generation area and various power generation values ​​corresponding to a set number of historical time intervals before the future time interval of the set wind power generation area, the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude and the spacing between adjacent wind turbines, and the value of the set number is positively correlated with the regional occupied area of ​​the set wind power generation area, thereby ensuring the stability and effectiveness of the intelligent prediction results.

[0005] According to the present invention, a numerical prediction system for power generation in a wind power generation area is provided, the system comprising:

[0006] A multiple learning device, used to output the deconvolution neural network after multiple learning as an AI intelligent prediction body, wherein the deconvolution neural network is learned multiple times to obtain the deconvolution neural network after multiple learning;

[0007] A configuration input device is used to obtain various regional configuration data of a set wind power generation area, wherein the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude and the spacing between adjacent wind turbines;

[0008] A network downloading device, connected to a remote weather forecast server network and electrically connected to the configuration input device, for downloading the wind direction code value and wind force amplitude of the set wind power generation area provided by the weather forecast server, wherein the wind direction code value and wind force amplitude of the set wind power generation area provided by the weather forecast server are both for a future time interval;

[0009] A content analysis mechanism, used to obtain power generation values ​​corresponding to a set number of historical time intervals before a future time interval of a set wind power generation area, wherein the value of the set number is positively correlated with the area occupied by the set wind power generation area;

[0010] A power generation prediction mechanism is connected to the multiple learning device, the configuration input device and the content analysis mechanism respectively, and is used to input the duration of the future time interval, the various regional configuration data of the set wind power generation area and the power generation values ​​corresponding to the set number of historical time intervals before the future time interval of the set wind power generation area into the AI ​​intelligent prediction body, so as to obtain the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body;

[0011] An information transmission mechanism, connected to a remote power generation dispatching server, for sending the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body to the remote power generation dispatching server through a time division duplex communication link;

[0012] The content analysis mechanism is used to obtain the power generation values ​​corresponding to the set number of historical time intervals before the future time interval of the set wind power generation area, and the value of the set number is positively correlated with the area occupied by the set wind power generation area, including: the future time interval and the set number of historical time intervals before the future time interval form a complete time segment on the time axis and the duration of each time interval is equal;

[0013] The deconvolution neural network is subjected to multiple learning to obtain a deconvolution neural network after multiple learning, comprising: the number of times the deconvolution neural network is subjected to learning is proportional to the number of wind turbines in the set wind power generation area;

[0014] Among them, the configuration input device is used to obtain various regional configuration data of the set wind power generation area, and the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude and the distance between adjacent wind turbines, including: in the set wind power generation area, the distance between every two adjacent wind turbines is equal.

[0015] Therefore, the present invention has at least the following three important invention points:

[0016] Important invention point A: Introducing a multiple learning device for outputting a deconvolution neural network after multiple learning as an AI intelligent prediction body, wherein the deconvolution neural network is learned multiple times to obtain a deconvolution neural network after multiple learning, and the number of times the deconvolution neural network is learned is proportional to the number of wind turbines in a set wind power generation area, thereby building different AI intelligent prediction bodies for different set wind power generation areas;

[0017] Important invention point B: multiple basic data are introduced to perform intelligent prediction of power generation in the future time interval of the subsequent set wind power generation area. The multiple basic data are various regional configuration data of the set wind power generation area and the power generation values ​​corresponding to the set number of historical time intervals of the set wind power generation area before the future time interval, thereby ensuring the stability and effectiveness of the intelligent prediction results;

[0018] Important invention point C: Specifically, the various regional configuration data of the wind power generation area are set to set the regional occupied area of ​​the wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude and the spacing between adjacent wind turbines, and the value of the set number is positively correlated with the regional occupied area of ​​the set wind power generation area, thereby further ensuring the stability and effectiveness of the intelligent prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0020] Figure 1 Schematic diagram of the internal structure of a numerical prediction system for power generation in a wind power generation area according to implementation A of the present invention.

[0021] Figure 2Schematic diagram of the internal structure of a numerical prediction system for power generation in a wind power generation area according to implementation scheme B of the present invention.

[0022] Figure 3 Schematic diagram of the internal structure of a numerical prediction system for power generation in a wind power generation area according to implementation scheme C of the present invention. DETAILED DESCRIPTION

[0023] The implementation scheme of the numerical prediction system for power generation in a wind power generation area of ​​the present invention will be described in detail below with reference to the accompanying drawings.

[0024] Figure 1 This is a schematic diagram of the internal structure of a numerical prediction system for wind power generation area according to Embodiment A of the present invention, wherein the system comprises:

[0025] A multiple learning device, used to output the deconvolution neural network after multiple learning as an AI intelligent prediction body, wherein the deconvolution neural network is learned multiple times to obtain the deconvolution neural network after multiple learning;

[0026] Specifically, a multiple learning device is used to output a deconvolution neural network after multiple learning as an AI intelligent prediction body, wherein the deconvolution neural network is learned multiple times to obtain a deconvolution neural network after multiple learning, including: a SOC chip can be selected to implement the multiple learning device, which is used to output the deconvolution neural network after multiple learning as an AI intelligent prediction body, wherein the deconvolution neural network is learned multiple times to obtain a deconvolution neural network after multiple learning;

[0027] A configuration input device is used to obtain various regional configuration data of a set wind power generation area, wherein the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude and the spacing between adjacent wind turbines;

[0028] A network downloading device, connected to a remote weather forecast server network and electrically connected to the configuration input device, for downloading the wind direction code value and wind force amplitude of the set wind power generation area provided by the weather forecast server, wherein the wind direction code value and wind force amplitude of the set wind power generation area provided by the weather forecast server are both for a future time interval;

[0029] A content analysis mechanism, used to obtain power generation values ​​corresponding to a set number of historical time intervals before a future time interval of a set wind power generation area, wherein the value of the set number is positively correlated with the area occupied by the set wind power generation area;

[0030] A power generation prediction mechanism is connected to the multiple learning device, the configuration input device and the content analysis mechanism respectively, and is used to input the duration of the future time interval, the various regional configuration data of the set wind power generation area and the power generation values ​​corresponding to the set number of historical time intervals before the future time interval of the set wind power generation area into the AI ​​intelligent prediction body, so as to obtain the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body;

[0031] An information transmission mechanism, connected to a remote power generation dispatching server, for sending the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body to the remote power generation dispatching server through a time division duplex communication link;

[0032] The content analysis mechanism is used to obtain the power generation values ​​corresponding to the set number of historical time intervals before the future time interval of the set wind power generation area, and the value of the set number is positively correlated with the area occupied by the set wind power generation area, including: the future time interval and the set number of historical time intervals before the future time interval form a complete time segment on the time axis and the duration of each time interval is equal;

[0033] The deconvolution neural network is subjected to multiple learning to obtain a deconvolution neural network after multiple learning, comprising: the number of times the deconvolution neural network is subjected to learning is proportional to the number of wind turbines in the set wind power generation area;

[0034] The configuration input device is used to obtain various regional configuration data of the set wind power generation area, wherein the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude and the distance between adjacent wind turbines, including: in the set wind power generation area, the distance between every two adjacent wind turbines is equal;

[0035] The configuration input device is used to obtain various regional configuration data of the set wind power generation area, wherein the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude, and the spacing between adjacent wind turbines, and also include: different wind directions have different wind direction code values ​​represented by different binary values, and the wind amplitude is the maximum wind value of the set wind power generation area in the future time interval;

[0036] And wherein, the duration of the future time interval, the various regional configuration data of the set wind power generation area, and the power generation values ​​corresponding to a set number of multiple historical time intervals of the set wind power generation area before the future time interval are input into the AI ​​intelligent prediction body to obtain the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body, including: performing binary value conversion on the duration of the future time interval, the various regional configuration data of the set wind power generation area, and the power generation values ​​corresponding to a set number of multiple historical time intervals of the set wind power generation area before the future time interval, and then inputting them into the AI ​​intelligent prediction body.

[0037] Figure 2 Schematic diagram of the internal structure of a numerical prediction system for power generation in a wind power generation area according to implementation scheme B of the present invention.

[0038] Compared with implementation scheme A, the numerical prediction system for wind power generation area power generation shown in implementation scheme B may also include the following components:

[0039] A voltage measuring mechanism, connected to the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, respectively, for measuring the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism respectively;

[0040] Wherein, the voltage measuring mechanism is respectively connected with the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, and is used to respectively measure the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, including: the voltage measuring mechanism includes a plurality of voltage measuring units, which are respectively connected with the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, so as to complete the measurement of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism;

[0041] Wherein, the voltage measurement mechanism includes a plurality of voltage measurement units, which are used to respectively connect with the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism to complete the measurement of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism respectively, including: the plurality of voltage measurement units are a plurality of voltage sensing circuits, which are used to respectively connect with the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism to complete the measurement of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism respectively;

[0042] Wherein, the plurality of voltage measurement units are a plurality of voltage sensing circuits, which are used to be connected to the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism respectively, so as to complete the measurement of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism respectively, including: the structures of the plurality of voltage sensing circuits are the same;

[0043] And wherein, the multiple voltage measurement units are multiple voltage sensing circuits, which are used to respectively connect with the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism to complete the respective measurements of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, and also include: the multiple voltage sensing circuits have the same voltage measurement upper limit value and voltage measurement lower limit value.

[0044] Figure 3 Schematic diagram of the internal structure of a numerical prediction system for power generation in a wind power generation area according to implementation scheme C of the present invention.

[0045] Compared with implementation scheme A, the numerical prediction system for wind power generation area power generation shown in implementation scheme C may also include the following components:

[0046] A field configuration interface, connected to the power generation prediction mechanism, the multiple learning device, the configuration entry device and the multiple voltage sensing circuits of the content analysis mechanism, respectively, for real-time configuration of the operation configuration parameters of the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism;

[0047] Wherein, the field configuration interface is respectively connected to the power generation prediction mechanism, the multiple learning device, the configuration entry device and the multiple voltage sensing circuits of the content analysis mechanism, and is used for real-time configuration of the operation configuration parameters of the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, including: the field configuration interface is a serial configuration interface;

[0048] And wherein, the on-site configuration interface is respectively connected to the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, and is used to configure the operating configuration parameters of the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism in real time. The configuration parameters include: for the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, the on-site configuration interface uses different configuration addresses to configure the operating configuration parameters of the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism in real time.

[0049] In addition, in the wind power generation area power generation value prediction system, the duration of the future time interval, the various regional configuration data of the set wind power generation area, and the power generation values ​​corresponding to a set number of historical time intervals of the set wind power generation area before the future time interval are input into the AI ​​intelligent prediction body to obtain the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body, which also includes: the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body is represented in the form of a binary value.

[0050] The numerical prediction system for power generation in a wind power generation area of ​​the present invention solves the technical problem of insufficient prediction accuracy of power generation in future time intervals in a wind power generation area in the prior art by introducing multiple learning devices to output a deconvolution neural network after multiple learning as an AI intelligent prediction body and introducing multiple basic data to perform subsequent intelligent prediction of power generation in future time intervals in the wind power generation area, thereby replacing the original rough estimation mechanism and ensuring the stability and effectiveness of the intelligent prediction results.

[0051] The foregoing description of the exemplary embodiments of the present invention is provided for the purpose of illustration and description. It is not intended to be exhaustive or to limit the present invention to the exact form disclosed. Obviously, many modifications and variations are obvious to those skilled in the art. The exemplary embodiments are selected and described in order to best illustrate the principles of the present invention and its practical application, so that other persons skilled in the art can understand the various embodiments and various variations of the present invention applicable to the specific purpose contemplated. It is intended that the scope of the present invention be limited by the appended claims and their equivalents.

Claims

1. A numerical prediction system for wind power generation area, characterized in that: The system comprises: A multiple learning device, used to output the deconvolution neural network after multiple learning as an AI intelligent prediction body, wherein the deconvolution neural network is learned multiple times to obtain the deconvolution neural network after multiple learning; A configuration input device is used to obtain various regional configuration data of a set wind power generation area, wherein the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude and the spacing between adjacent wind turbines; A network downloading device, connected to a remote weather forecast server network and electrically connected to the configuration input device, for downloading the wind direction code value and wind force amplitude of the set wind power generation area provided by the weather forecast server, wherein the wind direction code value and wind force amplitude of the set wind power generation area provided by the weather forecast server are both for a future time interval; A content analysis mechanism, used to obtain power generation values ​​corresponding to a set number of historical time intervals before a future time interval of a set wind power generation area, wherein the value of the set number is positively correlated with the area occupied by the set wind power generation area; A power generation prediction mechanism is connected to the multiple learning device, the configuration input device and the content analysis mechanism respectively, and is used to input the duration of the future time interval, the various regional configuration data of the set wind power generation area and the power generation values ​​corresponding to the set number of historical time intervals before the future time interval of the set wind power generation area into the AI ​​intelligent prediction body, so as to obtain the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body; An information transmission mechanism, connected to a remote power generation dispatching server, for sending the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body to the remote power generation dispatching server through a time division duplex communication link; The content analysis mechanism is used to obtain the power generation values ​​corresponding to the set number of historical time intervals before the future time interval of the set wind power generation area, and the value of the set number is positively correlated with the area occupied by the set wind power generation area, including: the future time interval and the set number of historical time intervals before the future time interval form a complete time segment on the time axis and the duration of each time interval is equal; The deconvolution neural network is subjected to multiple learning to obtain a deconvolution neural network after multiple learning, comprising: the number of times the deconvolution neural network is subjected to learning is proportional to the number of wind turbines in the set wind power generation area; Among them, the configuration input device is used to obtain various regional configuration data of the set wind power generation area, and the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude and the distance between adjacent wind turbines, including: in the set wind power generation area, the distance between every two adjacent wind turbines is equal.

2. The numerical prediction system for wind power generation area according to claim 1, characterized in that: The configuration input device is used to obtain various regional configuration data of the set wind power generation area, wherein the various regional configuration data of the set wind power generation area are the regional occupied area of ​​the set wind power generation area, the number of wind turbines, the wind direction code value, the wind amplitude, and the spacing between adjacent wind turbines, and also include: different wind directions have different wind direction code values ​​represented by different binary values, and the wind amplitude is the maximum wind value of the set wind power generation area in the future time interval; Among them, the duration of the future time interval, the various regional configuration data of the set wind power generation area, and the power generation values ​​corresponding to the set number of historical time intervals of the set wind power generation area before the future time interval are input into the AI ​​intelligent prediction body to obtain the power generation value of the set wind power generation area in the future time interval output by the AI ​​intelligent prediction body, including: performing binary value conversion on the duration of the future time interval, the various regional configuration data of the set wind power generation area, and the power generation values ​​corresponding to the set number of historical time intervals of the set wind power generation area before the future time interval, and then inputting them into the AI ​​intelligent prediction body.

3. The numerical prediction system for wind power generation area according to claim 2, characterized in that: The system further comprises: A voltage measuring mechanism, connected to the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, respectively, for measuring the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism respectively; Among them, the voltage measuring mechanism is respectively connected to the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, and is used to respectively measure the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism. The voltage measuring mechanism includes multiple voltage measuring units, which are respectively connected to the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism to complete the respective measurements of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism.

4. The numerical prediction system for wind power generation area according to claim 3, characterized in that: The voltage measuring mechanism includes a plurality of voltage measuring units, which are used to respectively connect with the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism to complete the respective measurements of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism. The plurality of voltage measuring units are a plurality of voltage sensing circuits, which are used to respectively connect with the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism to complete the respective measurements of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism.

5. The numerical prediction system for wind power generation area according to claim 4, characterized in that: The multiple voltage measurement units are multiple voltage sensing circuits, which are used to be connected to the power generation prediction mechanism, the multiple learning devices, the configuration entry device and the content analysis mechanism respectively, so as to complete the respective measurements of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning devices, the configuration entry device and the content analysis mechanism, including: the structures of the multiple voltage sensing circuits are the same.

6. The numerical prediction system for wind power generation area according to claim 5, characterized in that: The multiple voltage measurement units are multiple voltage sensing circuits, which are used to be connected to the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism respectively, so as to complete the respective measurements of the current real-time voltage values ​​of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, and also include: the multiple voltage sensing circuits have the same voltage measurement upper limit value and voltage measurement lower limit value.

7. The numerical prediction system for wind power generation area according to any one of claims 3 to 6, characterized in that: The system further comprises: The field configuration interface is respectively connected to the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, and is used for real-time configuration of the operating configuration parameters of the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism.

8. The numerical prediction system for wind power generation area according to claim 7, characterized in that: The field configuration interface is respectively connected to the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, and is used for real-time configuration of the operating configuration parameters of the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, including: the field configuration interface is a serial configuration interface.

9. The numerical prediction system for wind power generation area according to claim 7, characterized in that: The field configuration interface is respectively connected to the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism, and is used for real-time configuration of the operating configuration parameters of the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism. The field configuration interface uses different configuration addresses to configure the operating configuration parameters of the multiple voltage sensing circuits of the power generation prediction mechanism, the multiple learning device, the configuration entry device and the content analysis mechanism in real time.

Images