Speed regulator control method and system in water-light complementary environment

Abstract

The invention provides a speed regulator control method and system in a water-light complementary environment. The method comprises the following steps: determining a corresponding cloud picture region based on a photovoltaic power generation region; acquiring historical cloud picture data of the cloud picture area; segmenting the cloud image of the historical cloud data into a plurality of sub-images, determining the cloud layer coverage and the cloud layer thickness of each sub-image, and determining the cloud layer coverage and the cloud layer thickness of the sub-image at the prediction time point based on the cloud layer coverage and the cloud layer thickness of each sub-image; calculating an illumination subtraction degree based on the cloud layer coverage degree and the cloud layer thickness of each sub-image at the prediction time point, determining predicted illumination intensity of a cloud picture region corresponding to a region covered by photovoltaic power generation at the prediction time point based on the illumination subtraction degree, and determining corresponding photovoltaic power generation power; and determining corresponding hydroelectric generation power based on the photovoltaic generation power at the predicted time point and the target generation power, and controlling a speed regulator based on the hydroelectric generation power.

Description

Technical Field

[0001] The present invention relates to the field of energy supply technology, and in particular to a speed regulator control method and system in a water-photovoltaic complementary environment. Background Art

[0002] The synergy of hydropower and photovoltaic power generation helps optimize the energy structure and improve the utilization rate of renewable energy. Both hydropower and photovoltaic power generation are clean and renewable forms of energy. Their use can reduce dependence on fossil fuels, reduce greenhouse gas emissions, and help address global climate change. By working together, these two energy sources can be used more efficiently, reducing energy waste and improving overall energy efficiency.

[0003] In addition, this collaborative work can also reduce energy development and operating costs. Hydropower and photovoltaic power generation often have certain complementarity in terms of geographical location. For example, areas with abundant rivers often also have abundant solar energy resources. Therefore, building hydropower stations and photovoltaic power stations in the same area can share infrastructure and operation and maintenance resources, reducing construction and operating costs. At the same time, water-photovoltaic complementarity can also make full use of the existing hydropower transmission channels and power grid facilities to reduce duplication of construction and investment.

[0004] However, photovoltaic power generation is greatly affected by weather conditions. Cloud cover can cause fluctuations in its power generation. The existing hydraulic system is difficult to predict the actual situation, and the synergy between water and light is poor.

[0005] In view of this, the present invention is proposed. Summary of the invention

[0006] The purpose of the present invention is to provide a speed regulator control method and system in a water-photovoltaic complementary environment. This scheme determines the load of hydropower generation by predicting the photovoltaic power generation power at the predicted time point, and then predetermines how to control the operation of the speed regulator to ensure the synergy of water-photovoltaic complementary power generation.

[0007] The present invention provides a speed regulator control method in a water-photovoltaic complementary environment, the method comprising the following steps:

[0008] The coordinate correspondence between the ground surface and the cloud map is constructed based on the pre-constructed earth model, and the corresponding cloud map area is determined based on the area covered by photovoltaic power generation;

[0009] Acquire historical cloud map data of the cloud map area, wherein the historical cloud map data includes cloud map images of the cloud map area at multiple historical time points;

[0010] The cloud image is divided into a plurality of sub-images, each sub-image is analyzed, the cloud coverage and cloud thickness of each sub-image are determined, and the cloud coverage and cloud thickness of the sub-image at the prediction time point are determined based on the cloud coverage and cloud thickness of each sub-image;

[0011] Calculate the light reduction degree based on the cloud coverage and cloud thickness of each sub-image at the predicted time point, determine the predicted light intensity of the cloud map area corresponding to the area covered by photovoltaic power generation at the predicted time point based on the light reduction degree, and determine the corresponding photovoltaic power generation power;

[0012] The corresponding hydroelectric power generation power is determined based on the photovoltaic power generation power and the target power generation power at the predicted time point, and the speed regulator is controlled based on the hydroelectric power generation power.

[0013] The above scheme is adopted. Since cloud obstruction factors will cause fluctuations in the power of photovoltaic power generation in a water-photovoltaic complementary environment, this scheme determines the cloud map area corresponding to the photovoltaic power generation area based on the pre-built earth model, and predicts the cloud map data at the predicted time point based on the historical data of the cloud map area, determines the degree of light reduction, and then determines the predicted light intensity and the corresponding photovoltaic power generation power. This scheme determines the load of hydropower generation by predicting the photovoltaic power generation power at the predicted time point, and then predetermines how to control the operation of the speed regulator to ensure the synergy of water-photovoltaic complementary power generation.

[0014] In some embodiments of the present invention, the steps of dividing the cloud image into a plurality of sub-images, analyzing each sub-image, and determining the cloud coverage and cloud thickness of each sub-image include:

[0015] Determine a cloud-free area based on the pixel value of each pixel point in the cloud image, render the cloud-free area of ​​the cloud image as a first pixel value, and update the cloud image;

[0016] The proportion of cloud-free areas of sub-images obtained by segmenting the cloud image is calculated based on the number of the first pixel values, so as to obtain the cloud coverage of each sub-image.

[0017] Using the above scheme, this scheme first performs a preliminary screening of the cloud map image. Since the cloudless area will not affect the photovoltaic equipment's reception of light, the cloudless area in the cloud map image is determined through preliminary screening and rendered as a first pixel value. The updated cloud map image is then segmented. The proportion of the cloudy area can be efficiently determined through the number of first pixel values, and then the cloud coverage of the sub-image can be efficiently determined.

[0018] In some embodiments of the present invention, the cloud map image is divided into multiple sub-images, and each sub-image is analyzed. The step of determining the cloud coverage and cloud thickness of each sub-image also includes analyzing each pixel point in the area outside the cloud-free area in each sub-image, determining the corresponding cloud thickness value based on the pixel value of each pixel point in the area outside the cloud-free area, and determining the cloud thickness of the sub-image based on the cloud thickness value of each pixel point in the sub-image.

[0019] In some embodiments of the present invention, in the step of determining the cloud coverage and cloud thickness of a sub-image at a prediction time point based on the cloud coverage and cloud thickness of each sub-image, the cloud coverage and cloud thickness of each of the sub-images at multiple time points are respectively constructed as a coverage prediction vector and a thickness prediction vector, and the coverage prediction vector and the thickness prediction vector are respectively input into a preset coverage prediction model and a thickness prediction model to obtain the cloud coverage and cloud thickness of each of the sub-images at the prediction time point.

[0020] Adopting the above scheme, this scheme performs a refined analysis of the photovoltaic power generation area by dividing the overall image into multiple sub-images, and analyzes the cloud coverage and cloud thickness of each sub-image separately, taking into account multiple influencing factors of photovoltaic power generation, and predicting the cloud coverage and cloud thickness of each sub-image separately, to ensure the calculation accuracy of the final light reduction.

[0021] In some embodiments of the present invention, in the step of calculating the illumination reduction degree based on the cloud coverage and cloud thickness of each sub-image at the prediction time point:

[0022] Calculating the sub-reduction degree of each sub-image based on the cloud coverage and cloud thickness of each sub-image at the prediction time point;

[0023] Based on the position of each sub-image in the cloud image, a decision matrix composed of sub-attenuation degrees of the sub-images is constructed, and the decision matrix is ​​input into a pre-trained calculation model, and the calculation model outputs the illumination attenuation degree.

[0024] Using the above scheme, this scheme first completes the refined processing by dividing the whole image into sub-images, and in the final illumination reduction calculation of this scheme, a judgment matrix composed of the sub-reduction degrees of the sub-images is constructed based on the positions of the sub-images, taking into account the fact that the area corresponding to the edge sub-image has a smaller impact on the illumination, while the central area has a greater impact on the illumination, and the position factor of the sub-image is incorporated into the calculation to ensure the calculation accuracy of the illumination reduction degree.

[0025] In some embodiments of the present invention, in the step of determining the predicted light intensity of the cloud map area corresponding to the area covered by photovoltaic power generation at the predicted time point based on the light attenuation degree, the basic light intensity of the area covered by photovoltaic power generation is obtained, and the predicted light intensity is calculated based on the basic light intensity and the light attenuation degree.

[0026] In some embodiments of the present invention, in the step of determining the corresponding hydroelectric power based on the photovoltaic power generation power and the target power generation power at the predicted time point, the difference between the target power generation power and the photovoltaic power generation power is calculated, and the difference is the required hydroelectric power corresponding to the predicted time point.

[0027] In some embodiments of the present invention, in the step of constructing a coordinate correspondence between the ground surface and the cloud map based on a pre-constructed earth model and determining the corresponding cloud map area based on the area covered by photovoltaic power generation:

[0028] Constructing a bounding box of a three-dimensional earth model, evenly dividing each face of the bounding box using dividing lines, and connecting the intersection of the dividing lines with the center of gravity of the three-dimensional earth model;

[0029] The lines connecting the center point of the three-dimensional earth model that pass through the area covered by photovoltaic power generation are screened, and the area enclosed when the lines pass through the height of the cloud layer is determined as the cloud map area corresponding to the area covered by photovoltaic power generation.

[0030] Adopting the above scheme, this scheme evenly divides each face of the bounding box with a dividing line, and constructs a line connecting the intersection of the dividing lines and the center of gravity of the three-dimensional earth model. The line passes through the surface covered by photovoltaic power generation and the position of the cloud height in the three-dimensional earth model to determine the cloud map area corresponding to the area covered by photovoltaic power generation.

[0031] In some embodiments of the present invention, in the step of determining the area enclosed by the line when it passes through the height of the cloud layer;

[0032] The point where the connecting line passes through the cloud layer height is taken as a marking point;

[0033] Calculate the coordinate center point of each marked point, draw a circle with the coordinate center point as the center, and calculate the marked point farthest from the coordinate center point in each central angle direction of the circle;

[0034] The marked points farthest from the coordinate center point in the direction of each central angle of the circle are sequentially connected to obtain the cloud map area.

[0035] Adopting the above scheme, this scheme makes a circle with the coordinate center point in the marked point as the center, and divides it into multiple central angles. In the opening and closing area of ​​each central angle, the marked point farthest from the coordinate center point in the direction of each central angle of the circle is determined. The cloud map area is further obtained by connecting the marked points corresponding to each central angle, which can efficiently and accurately determine the corresponding cloud map area.

[0036] Another aspect of the present invention also relates to a speed regulator control system in a water-photovoltaic complementary environment, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method.

[0037] In summary, the present invention has the following beneficial effects:

[0038] 1. In the water-photovoltaic complementary environment, cloud cover factors will cause fluctuations in photovoltaic power generation. This solution determines the cloud map area corresponding to the photovoltaic power generation area based on the pre-built earth model, predicts the cloud map data at the predicted time point based on the historical data of the cloud map area, determines the light reduction degree, and then determines the predicted light intensity and the corresponding photovoltaic power generation power. This solution determines the load of hydropower generation by predicting the photovoltaic power generation power at the predicted time point, and then predetermines how to control the speed regulator operation to ensure the synergy of water-photovoltaic complementary power generation;

[0039] 2. This scheme first performs a preliminary screening of the cloud image. Since the cloudless area will not affect the light reception of the photovoltaic equipment, the cloudless area in the cloud image is determined through preliminary screening and rendered as the first pixel value. The updated cloud image is then segmented. The proportion of the cloud area can be efficiently determined by the number of first pixel values, and then the cloud coverage of the sub-image can be efficiently determined;

[0040] 3. This solution divides the overall image into multiple sub-images to perform a detailed analysis of the photovoltaic power generation area, and analyzes the cloud coverage and cloud thickness of each sub-image separately. It takes into account multiple influencing factors of photovoltaic power generation, and predicts the cloud coverage and cloud thickness of each sub-image separately to ensure the calculation accuracy of the final light reduction degree;

[0041] 4. This scheme first completes the refined processing by dividing the whole image into sub-images. In the final calculation of the illumination reduction degree of this scheme, a decision matrix composed of the sub-reduction degrees of the sub-images is constructed based on the positions of the sub-images. The factors that the area corresponding to the edge sub-image has a smaller impact on the illumination, while the central area has a greater impact on the illumination are taken into consideration. The position factor of the sub-image is incorporated into the calculation to ensure the calculation accuracy of the illumination reduction degree. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 It is a schematic diagram of a first implementation mode of the speed regulator control method in a water-photovoltaic complementary environment of the present invention;

[0044] Figure 2 It is a schematic diagram of a second implementation mode of the speed regulator control method in a water-photovoltaic complementary environment of the present invention. DETAILED DESCRIPTION

[0045] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0046] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0047] like Figure 1 As shown, the present invention provides a speed regulator control method in a water-photovoltaic complementary environment, the method comprising the steps of:

[0048] Step S100, constructing a coordinate correspondence between the ground surface and the cloud map based on a pre-constructed earth model, and determining a corresponding cloud map area based on an area covered by photovoltaic power generation;

[0049] In a specific implementation process, the earth model is a pre-constructed three-dimensional model.

[0050] Step S200, obtaining historical cloud map data of the cloud map area, wherein the historical cloud map data includes cloud map images of multiple historical time points of the cloud map area;

[0051] During the specific implementation process, the historical cloud map data is acquired via satellite.

[0052] Step S300, dividing the cloud image into a plurality of sub-images, analyzing each sub-image, determining the cloud coverage and cloud thickness of each sub-image, and determining the cloud coverage and cloud thickness of the sub-image at a predicted time point based on the cloud coverage and cloud thickness of each sub-image;

[0053] In a specific implementation process, in the step of dividing the cloud image into a plurality of sub-images, the cloud image is evenly divided into a plurality of sub-images of rectangular areas of the same size.

[0054] Step S400, calculating the light reduction degree based on the cloud coverage and cloud thickness of each sub-image at the prediction time point, determining the predicted light intensity of the cloud map area corresponding to the area covered by photovoltaic power generation at the prediction time point based on the light reduction degree, and determining the corresponding photovoltaic power generation power;

[0055] In the specific implementation process, in the step of determining the predicted light intensity of the cloud map area corresponding to the area covered by photovoltaic power generation at the predicted time point based on the light reduction degree, the basic light intensity corresponding to the current longitude and latitude position and the current solar term of the area covered by photovoltaic power generation is calculated, and the predicted light intensity is calculated by combining the basic light intensity with the predicted light reduction degree.

[0056] Step S500, determining the corresponding hydroelectric power generation power based on the photovoltaic power generation power and the target power generation power at the predicted time point, and controlling the speed regulator based on the hydroelectric power generation power.

[0057] In some embodiments of the present invention, the hydroelectric power is sent to a control end of a speed regulator, and a staff at the control end adjusts the parameters of the speed regulator accordingly according to the target hydroelectric power.

[0058] The above scheme is adopted. Since cloud obstruction factors will cause fluctuations in the power of photovoltaic power generation in a water-photovoltaic complementary environment, this scheme determines the cloud map area corresponding to the photovoltaic power generation area based on the pre-built earth model, and predicts the cloud map data at the predicted time point based on the historical data of the cloud map area, determines the degree of light reduction, and then determines the predicted light intensity and the corresponding photovoltaic power generation power. This scheme determines the load of hydropower generation by predicting the photovoltaic power generation power at the predicted time point, and then predetermines how to control the operation of the speed regulator to ensure the synergy of water-photovoltaic complementary power generation.

[0059] like Figure 2 As shown, in some embodiments of the present invention, the cloud image is divided into a plurality of sub-images, each sub-image is analyzed, and the steps of determining the cloud coverage and cloud thickness of each sub-image include:

[0060] Step S310, determining a cloud-free area based on the pixel value of each pixel point in the cloud image, rendering the cloud-free area of ​​the cloud image as a first pixel value, and updating the cloud image;

[0061] In the specific implementation process, in the step of determining the cloud-free area based on the pixel value of each pixel point in the cloud map image, the pixel grids within the pixel range can be identified as the area where clouds exist by setting the pixel range, and the pixel grids no longer in the pixel range can be set as the cloud-free area; the non-cloud area can also be identified by means of a neural network model, specifically, the CN32s and FCN8s models can be used.

[0062] Step S320: Calculate the proportion of cloud-free areas of sub-images obtained by segmenting the cloud image based on the number of the first pixel values, and then obtain the cloud coverage of each sub-image.

[0063] In the specific implementation process, the ratio of the number of pixels of the first pixel value to all pixels is calculated as the cloud-free area ratio of the sub-image, and the cloud coverage of the sub-image = 1-the cloud-free area ratio of the sub-image.

[0064] Using the above scheme, this scheme first performs a preliminary screening of the cloud map image. Since the cloudless area will not affect the photovoltaic equipment's reception of light, the cloudless area in the cloud map image is determined through preliminary screening and rendered as a first pixel value. The updated cloud map image is then segmented. The proportion of the cloudy area can be efficiently determined through the number of first pixel values, and then the cloud coverage of the sub-image can be efficiently determined.

[0065] In some embodiments of the present invention, the cloud map image is divided into multiple sub-images, and each sub-image is analyzed. The step of determining the cloud coverage and cloud thickness of each sub-image also includes, step S330, analyzing each pixel point in the area outside the cloud-free area in each sub-image, determining the corresponding cloud thickness value based on the pixel value of each pixel point in the area outside the cloud-free area, and determining the cloud thickness of the sub-image based on the cloud thickness value of each pixel point in the sub-image.

[0066] In some embodiments of the present invention, in the step of analyzing each pixel point in the area outside the cloud-free area in each sub-image and determining the corresponding cloud thickness value based on the pixel value of each pixel point in the area outside the cloud-free area, a pixel range setting method can be adopted to determine the pixel range in which each pixel value is located, and the cloud thickness corresponding to the pixel range is used, and then the average value of the cloud thickness corresponding to each pixel value is calculated as the cloud thickness value of the sub-image; the cloud thickness value of each sub-image can also be identified through a pre-trained neural network model.

[0067] In some embodiments of the present invention, the step of determining the cloud coverage and cloud thickness of a sub-image at a prediction time point based on the cloud coverage and cloud thickness of each sub-image includes: step S340, constructing the cloud coverage and cloud thickness of each of the sub-images at multiple time points into a coverage prediction vector and a thickness prediction vector, respectively, inputting the coverage prediction vector and the thickness prediction vector into a preset coverage prediction model and a thickness prediction model, respectively, to obtain the cloud coverage and cloud thickness of each of the sub-images at the prediction time point.

[0068] In some embodiments of the present invention, the coverage prediction model and the thickness prediction model are both pre-trained long short-term memory network models (LSTM, Long Short-Term Memory).

[0069] Adopting the above scheme, this scheme performs a refined analysis of the photovoltaic power generation area by dividing the overall image into multiple sub-images, and analyzes the cloud coverage and cloud thickness of each sub-image separately, taking into account multiple influencing factors of photovoltaic power generation, and predicting the cloud coverage and cloud thickness of each sub-image separately, to ensure the calculation accuracy of the final light reduction.

[0070] In some embodiments of the present invention, in the step of calculating the illumination reduction degree based on the cloud coverage and cloud thickness of each sub-image at the prediction time point:

[0071] Calculating the sub-reduction degree of each sub-image based on the cloud coverage and cloud thickness of each sub-image at the prediction time point;

[0072] Based on the position of each sub-image in the cloud image, a decision matrix composed of sub-attenuation degrees of the sub-images is constructed, and the decision matrix is ​​input into a pre-trained calculation model, and the calculation model outputs the illumination attenuation degree.

[0073] In the specific implementation process, in the step of calculating the sub-reduction degree of each sub-image based on the cloud coverage and cloud thickness of each sub-image at the predicted time point, the cloud coverage and cloud thickness of the sub-image are weightedly calculated to obtain the sub-reduction degree of the sub-image.

[0074] In the specific implementation process, the pre-trained computing model can be a pre-trained convolutional neural network model.

[0075] Using the above scheme, this scheme first completes the refined processing by dividing the whole image into sub-images, and in the final illumination reduction calculation of this scheme, a judgment matrix composed of the sub-reduction degrees of the sub-images is constructed based on the positions of the sub-images, taking into account the fact that the area corresponding to the edge sub-image has a smaller impact on the illumination, while the central area has a greater impact on the illumination, and the position factor of the sub-image is incorporated into the calculation to ensure the calculation accuracy of the illumination reduction degree.

[0076] In some embodiments of the present invention, in the step of determining the predicted light intensity of the cloud map area corresponding to the area covered by photovoltaic power generation at the predicted time point based on the light attenuation degree, the basic light intensity of the area covered by photovoltaic power generation is obtained, and the predicted light intensity is calculated based on the basic light intensity and the light attenuation degree.

[0077] In some embodiments of the present invention, in the step of calculating the predicted light intensity based on the basic light intensity and the light reduction degree, the predicted light intensity is calculated using the following formula:

[0078] Predicted light intensity = basic light intensity * (1-light reduction).

[0079] In some embodiments of the present invention, in the step of determining the corresponding hydroelectric power based on the photovoltaic power generation power and the target power generation power at the predicted time point, the difference between the target power generation power and the photovoltaic power generation power is calculated, and the difference is the required hydroelectric power corresponding to the predicted time point.

[0080] In the specific implementation process, the target power generation is achieved through hydroelectric power generation and photovoltaic power generation. The target power generation can be calculated by statistically analyzing the historical power consumption data of a region.

[0081] In some embodiments of the present invention, in the step of constructing a coordinate correspondence between the ground surface and the cloud map based on a pre-constructed earth model and determining the corresponding cloud map area based on the area covered by photovoltaic power generation:

[0082] Constructing a bounding box of a three-dimensional earth model, evenly dividing each face of the bounding box using dividing lines, and connecting the intersection of the dividing lines with the center of gravity of the three-dimensional earth model;

[0083] The lines connecting the center point of the three-dimensional earth model that pass through the area covered by photovoltaic power generation are screened, and the area enclosed when the lines pass through the height of the cloud layer is determined as the cloud map area corresponding to the area covered by photovoltaic power generation.

[0084] In a specific implementation process, in the three-dimensional earth model, the area covered by photovoltaic power generation and the cloud layer are in different layers, the cloud layer wraps the surface of the three-dimensional earth model, and the area covered by photovoltaic power generation is on the surface.

[0085] In the specific implementation process, the intersection of the dividing lines is connected to the center of gravity of the three-dimensional earth model. The line passes through the clouds and the surface. The corresponding cloud area is determined based on the line passing through the area covered by photovoltaic power generation, and the cloud map required for analysis in this scheme is accurately positioned.

[0086] Adopting the above scheme, this scheme evenly divides each face of the bounding box with a dividing line, and constructs a line connecting the intersection of the dividing lines and the center of gravity of the three-dimensional earth model. The line passes through the surface covered by photovoltaic power generation and the position of the cloud height in the three-dimensional earth model to determine the cloud map area corresponding to the area covered by photovoltaic power generation.

[0087] In some embodiments of the present invention, in the step of determining the area enclosed by the line when it passes through the height of the cloud layer;

[0088] The point where the connecting line passes through the cloud layer height is taken as a marking point;

[0089] Calculate the coordinate center point of each marked point, draw a circle with the coordinate center point as the center, and calculate the marked point farthest from the coordinate center point in each central angle direction of the circle;

[0090] The marked points farthest from the coordinate center point in the direction of each central angle of the circle are sequentially connected to obtain the cloud map area.

[0091] In a specific implementation process, in the step of taking the point where the connecting line passes through the cloud layer height as a marking point, the point where the connecting line passes through the cloud layer surface when passing through the cloud layer is taken as the marking point;

[0092] In the specific implementation process, in the step of drawing a circle with the coordinate center point as the center and calculating the mark point among the mark points that is farthest from the coordinate center point in the direction of each center angle of the circle, a circle is drawn on the surface of the cloud layer; the angle of the center angle can be 1 degree, and the two sides of each center angle are extended, and the mark points within the area surrounded by the two sides are judged, and a mark point is selected for each center angle range, and the mark points corresponding to each center angle are connected in a clockwise or counterclockwise order to obtain the cloud map area.

[0093] Adopting the above scheme, this scheme makes a circle with the coordinate center point in the marked point as the center, and divides it into multiple central angles. In the opening and closing area of ​​each central angle, the marked point farthest from the coordinate center point in the direction of each central angle of the circle is determined. The cloud map area is further obtained by connecting the marked points corresponding to each central angle, which can efficiently and accurately determine the corresponding cloud map area.

[0094] Another aspect of the present invention also relates to a speed regulator control system in a water-photovoltaic complementary environment, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method.

[0095] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the speed regulator control method in the water-light complementary environment is implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0096] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0097] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0098] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0099] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A speed regulator control method in a water-photovoltaic complementary environment, characterized in that: The steps of the method include: The coordinate correspondence between the ground surface and the cloud map is constructed based on the pre-constructed earth model, and the corresponding cloud map area is determined based on the area covered by photovoltaic power generation; Acquire historical cloud map data of the cloud map area, wherein the historical cloud map data includes cloud map images of the cloud map area at multiple historical time points; The cloud image is divided into a plurality of sub-images, each sub-image is analyzed, the cloud coverage and cloud thickness of each sub-image are determined, and the cloud coverage and cloud thickness of the sub-image at the prediction time point are determined based on the cloud coverage and cloud thickness of each sub-image; Calculate the light reduction degree based on the cloud coverage and cloud thickness of each sub-image at the predicted time point, determine the predicted light intensity of the cloud map area corresponding to the area covered by photovoltaic power generation at the predicted time point based on the light reduction degree, and determine the corresponding photovoltaic power generation power; The corresponding hydroelectric power generation power is determined based on the photovoltaic power generation power and the target power generation power at the predicted time point, and the speed regulator is controlled based on the hydroelectric power generation power.

2. The speed regulator control method in a water-photovoltaic complementary environment according to claim 1 is characterized in that: The steps of dividing the cloud image into a plurality of sub-images, analyzing each sub-image, and determining the cloud coverage and cloud thickness of each sub-image include: Determine a cloud-free area based on the pixel value of each pixel point in the cloud image, render the cloud-free area of ​​the cloud image as a first pixel value, and update the cloud image; The proportion of cloud-free areas of sub-images obtained by segmenting the cloud image is calculated based on the number of the first pixel values, so as to obtain the cloud coverage of each sub-image.

3. The speed regulator control method in a water-photovoltaic complementary environment according to claim 2 is characterized in that: The steps of dividing the cloud map image into a plurality of sub-images, analyzing each sub-image, and determining the cloud coverage and cloud thickness of each sub-image also include analyzing each pixel point in an area outside a cloud-free area in each sub-image, determining a corresponding cloud thickness value based on a pixel value of each pixel point in the area outside the cloud-free area, and determining the cloud thickness of the sub-image based on the cloud thickness value of each pixel point in the sub-image.

4. The speed regulator control method in a water-light complementary environment according to claim 1, characterized in that: In the step of determining the cloud coverage and cloud thickness of a sub-image at a prediction time point based on the cloud coverage and cloud thickness of each sub-image, the cloud coverage and cloud thickness of each sub-image at multiple time points are respectively constructed as a coverage prediction vector and a thickness prediction vector, and the coverage prediction vector and the thickness prediction vector are respectively input into a preset coverage prediction model and a thickness prediction model to obtain the cloud coverage and cloud thickness of each sub-image at the prediction time point.

5. The speed regulator control method in a water-photovoltaic complementary environment according to any one of claims 1 to 4, characterized in that: In the step of calculating the illumination reduction based on the cloud coverage and cloud thickness of each sub-image at the prediction time point: Calculating the sub-reduction degree of each sub-image based on the cloud coverage and cloud thickness of each sub-image at the prediction time point; Based on the position of each sub-image in the cloud image, a decision matrix composed of sub-attenuation degrees of the sub-images is constructed, and the decision matrix is ​​input into a pre-trained calculation model, and the calculation model outputs the illumination attenuation degree.

6. The speed regulator control method in a water-photovoltaic complementary environment according to claim 5, characterized in that: In the step of determining the predicted light intensity of the cloud map area corresponding to the area covered by photovoltaic power generation at the predicted time point based on the light reduction degree, the basic light intensity of the area covered by photovoltaic power generation is obtained, and the predicted light intensity is calculated based on the basic light intensity and the light reduction degree.

7. The speed regulator control method in a water-photovoltaic complementary environment according to claim 1 or 6, characterized in that: In the step of determining the corresponding hydroelectric power based on the photovoltaic power and the target power at the predicted time point, the difference between the target power and the photovoltaic power is calculated, and the difference is the required hydroelectric power corresponding to the predicted time point.

8. The speed regulator control method in a water-photovoltaic complementary environment according to claim 1, characterized in that: In the step of constructing the coordinate correspondence between the ground surface and the cloud map based on the pre-constructed earth model and determining the corresponding cloud map area based on the area covered by photovoltaic power generation: Constructing a bounding box of a three-dimensional earth model, evenly dividing each face of the bounding box using dividing lines, and connecting the intersection of the dividing lines with the center point of the three-dimensional earth model; The lines connecting the center point of the three-dimensional earth model that pass through the area covered by photovoltaic power generation are screened, and the area enclosed when the lines pass through the height of the cloud layer is determined as the cloud map area corresponding to the area covered by photovoltaic power generation.

9. The speed regulator control method in a water-photovoltaic complementary environment according to claim 8, characterized in that: In the step of determining the area enclosed by the line when it passes through the height of the cloud layer; The point where the connecting line passes through the cloud layer height is taken as a marking point; Calculate the coordinate center point of each marked point, draw a circle with the coordinate center point as the center, and calculate the marked point farthest from the coordinate center point in each central angle direction of the circle; The marked points farthest from the coordinate center point in the direction of each central angle of the circle are sequentially connected to obtain the cloud map area.

10. A speed regulator control system in a water-light complementary environment, characterized in that: The system includes a computer device, which includes a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method described in any one of claims 1 to 9.

Images