Distributed new energy power generation data prediction method and device, equipment and medium

Abstract

The invention discloses a distributed new energy power generation data prediction method and device, equipment and a medium, and the method comprises the steps: obtaining a power station region where a distributed photovoltaic power station is located; acquiring a plurality of first two-dimensional shot images shot by different unmanned aerial vehicles on the sky area from different angles at the target time; performing three-dimensional reconstruction to obtain a plurality of target cloud cluster three-dimensional models in the sky area; the power station area and the multiple target cloud cluster three-dimensional models are projected on a first plane, a power station projection area corresponding to the power station area and multiple cloud cluster projection areas corresponding to the multiple target cloud cluster three-dimensional models are obtained, and the first plane is perpendicular to the sunlight irradiation direction; determining cloud cluster overall influence parameters of the distributed photovoltaic power station based on a position relationship between the cloud cluster projection area and a power station projection area of the distributed photovoltaic power station; and determining the predicted power generation power of the distributed photovoltaic power station based on the cloud cluster overall influence parameter. According to the invention, the power generation prediction accuracy of distributed new energy can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence processing technology, and specifically to a method, device, equipment and medium for predicting power generation data of distributed renewable energy. Background Art

[0002] With the development of the photovoltaic power generation industry, photovoltaic power generation has been connected to the power grid in large quantities. Photovoltaic power generation is random and volatile due to the influence of weather, which makes it difficult to achieve stable output of photovoltaic power generation. At present, the electricity generated in the photovoltaic base is usually consumed on-site, that is, directly used in the surrounding areas of the photovoltaic base, thereby improving the reliability of photovoltaic power supply, reducing transmission costs and improving the resilience of the power grid. Clouds have a great impact on photovoltaic power generation, resulting in a low accuracy rate in the prediction of distributed renewable energy power generation. Summary of the invention

[0003] The embodiments of the present application provide a method, device, equipment and medium for predicting power generation data of distributed renewable energy, which can improve the accuracy of power generation prediction of distributed renewable energy.

[0004] In a first aspect, the distributed renewable energy power generation data prediction method provided by the present application includes:

[0005] Get the power station area where the distributed photovoltaic power station is located;

[0006] Acquire a plurality of first two-dimensional images of the sky area taken by different drones from different angles at a target time, wherein the distributed photovoltaic power station corresponds to a drone cluster, and the drone cluster flies and takes pictures within an area centered on the distributed power station;

[0007] Performing three-dimensional reconstruction based on the multiple first two-dimensional captured images to obtain three-dimensional models of multiple target cloud clusters in the sky area;

[0008] Get the sun's direction of sunlight at the target time;

[0009] Projecting the power station area and the plurality of target cloud cluster three-dimensional models onto a first plane respectively, to obtain a power station projection area corresponding to the power station area and a plurality of cloud cluster projection areas corresponding to the plurality of target cloud cluster three-dimensional models, wherein the first plane is perpendicular to the sunlight irradiation direction;

[0010] Determine the overall cloud impact parameter of the distributed photovoltaic power station based on the positional relationship between the cloud projection area and the power station projection area of ​​the distributed photovoltaic power station;

[0011] The predicted power generation of the distributed photovoltaic power station is determined based on the overall cloud cluster impact parameter of the distributed photovoltaic power station.

[0012] Optionally, the determining the predicted power generation power of the distributed photovoltaic power station based on the overall cloud cluster impact parameter of the distributed photovoltaic power station includes:

[0013] Respectively calculating overall cloud impact parameters of the distributed photovoltaic power station at multiple different times within a preset time period;

[0014] Respectively obtaining meteorological parameters of the distributed photovoltaic power station at multiple different times within a preset time period, wherein the meteorological parameters include at least one of temperature, wind speed, and humidity;

[0015] The cloud overall impact parameters at multiple different times and the meteorological parameters at multiple different times are combined to obtain the input parameters at multiple different times;

[0016] Input parameters at multiple different times are input into a preset power generation prediction model to obtain the predicted power generation power of the distributed photovoltaic power station.

[0017] Optionally, the determining the cloud cluster overall impact parameter of the distributed photovoltaic power station based on the positional relationship between the cloud cluster projection area and the power station projection area of ​​the distributed photovoltaic power station includes:

[0018] If there is an overlapping area between the power station projection area and the cloud cluster projection area of ​​the target cloud cluster three-dimensional model, then based on the overlapping area and the cloud cluster projection area of ​​the target cloud cluster three-dimensional model, determine the influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station; if there is no overlapping area between the power station projection area and the cloud cluster projection area, then determine the preset influence parameter value as the influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station;

[0019] The average value of the cloud cluster monomer influencing parameters of each of the target cloud cluster three-dimensional models on the distributed photovoltaic power station is determined as the cloud cluster overall influencing parameter of the distributed photovoltaic power station.

[0020] Optionally, the determining, based on the overlapping area and the cloud projection area of ​​the target cloud three-dimensional model, an influence parameter of the target cloud three-dimensional model on a cloud cell of the distributed photovoltaic power station includes:

[0021] Obtaining an area ratio of the overlapping area to the power station projection area;

[0022] Generate a plurality of first straight lines passing through the target cloud three-dimensional model and the overlapping area and parallel to the sunlight irradiation direction;

[0023] Cutting the first straight line on the surface of the target cloud three-dimensional model to generate a first line segment, thereby obtaining a plurality of first line segments of the first straight line;

[0024] The influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station is determined based on the average value of the area ratio of the region and the lengths of the multiple first line segments, wherein the larger the average value of the lengths of the multiple first line segments, the larger the cloud cluster monomer influence parameter, and the larger the area ratio, the larger the cloud cluster monomer influence parameter.

[0025] Optionally, the determining, based on the area ratio and the average value of the lengths of the plurality of first line segments, an influence parameter of the target cloud cluster three-dimensional model on a cloud cluster monomer of the distributed photovoltaic power station comprises:

[0026] Obtaining a centroid distance between the centroid of the overlapping area and the centroid of the cloud projection area;

[0027] The influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station is determined based on the average value of the area ratio of the region, the centroid distance and the length of multiple first line segments, wherein the larger the average value of the length of multiple first line segments, the larger the cloud cluster monomer influence parameter, the larger the area ratio, the larger the cloud cluster monomer influence parameter, and the larger the centroid distance, the smaller the cloud cluster monomer influence parameter.

[0028] Optionally, the performing three-dimensional reconstruction based on the plurality of first two-dimensional captured images to obtain the three-dimensional models of the plurality of target clouds in the sky area includes:

[0029] Use the SFM algorithm to perform three-dimensional reconstruction on the multiple first two-dimensional photographed images to obtain initial point cloud data;

[0030] Selecting a preset ratio of first two-dimensional photographed images from the plurality of first two-dimensional photographed images as second two-dimensional photographed images to obtain a plurality of second two-dimensional photographed images, wherein the preset ratio is less than 1;

[0031] performing cloud segmentation on the plurality of the second two-dimensional photographed images to obtain a plurality of cloud segmentation regions on the plurality of the second two-dimensional photographed images;

[0032] Determine the point cloud data located in each of the cloud cluster segmentation areas in the initial point cloud data as cloud cluster point cloud data;

[0033] A plurality of target cloud three-dimensional models are determined based on the cloud point cloud data.

[0034] Optionally, generating a plurality of target cloud three-dimensional models based on the cloud point cloud data includes:

[0035] Clustering the cloud point cloud data to obtain a plurality of first three-dimensional point clusters;

[0036] The target cloud three-dimensional model is determined based on the first three-dimensional point cluster, and a plurality of target cloud three-dimensional models corresponding to the plurality of the first three-dimensional point clusters are obtained.

[0037] In a second aspect, the distributed renewable energy power generation data prediction device provided by the present application includes:

[0038] The first acquisition module is used to acquire the power station area where the distributed photovoltaic power station is located;

[0039] A second acquisition module is used to acquire a plurality of first two-dimensional images captured by different drones of a sky area from different angles at a target time, wherein the distributed photovoltaic power station corresponds to a drone cluster, and the drone cluster flies and takes pictures within an area centered on the distributed power station;

[0040] A three-dimensional reconstruction module, used for performing three-dimensional reconstruction based on the plurality of first two-dimensional photographed images to obtain three-dimensional models of a plurality of target cloud clusters in the sky area;

[0041] The third acquisition module is used to obtain the sunlight direction of the sun at the target time;

[0042] A projection module, used to project the power station area and the plurality of target cloud group three-dimensional models onto a first plane respectively, to obtain a power station projection area corresponding to the power station area and a plurality of cloud group projection areas corresponding to the plurality of target cloud group three-dimensional models, wherein the first plane is perpendicular to the sunlight irradiation direction;

[0043] A first determination module is used to determine the overall cloud impact parameter of the distributed photovoltaic power station based on the positional relationship between the cloud projection area and the power station projection area of ​​the distributed photovoltaic power station;

[0044] The second determination module is used to determine the predicted power generation of the distributed photovoltaic power station based on the overall cloud cluster impact parameter of the distributed photovoltaic power station.

[0045] On the third aspect, the electronic device provided in the present application includes a memory and a processor, the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the distributed new energy power generation data prediction method provided in the present application.

[0046] In a fourth aspect, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the distributed renewable energy power generation data prediction method provided in the present application.

[0047] In a fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implement the steps in the method for predicting power generation data of distributed renewable energy provided in the present application.

[0048] In this application, compared with the related art, the power station area where the distributed photovoltaic power station is located is obtained; multiple first two-dimensional images taken by different drones from different angles of the sky area at the target time are obtained, wherein the distributed photovoltaic power station corresponds to a drone cluster, and each drone cluster flies and takes pictures within the area centered on the distributed power station; three-dimensional reconstruction is performed based on multiple first two-dimensional images to obtain multiple target cloud group three-dimensional models in the sky area; the sunlight exposure direction of the sun at the target time is obtained; the power station area and multiple target cloud group three-dimensional models are projected on the first plane respectively, and the power station projection area corresponding to the power station area and multiple cloud group projection areas corresponding to the multiple target cloud group three-dimensional models are obtained, wherein the first plane is perpendicular to the sunlight exposure direction; the overall cloud group influencing parameters of the distributed photovoltaic power station are determined based on the positional relationship between the cloud group projection area and the power station projection area of ​​the distributed photovoltaic power station; the predicted power generation power of the distributed photovoltaic power station is determined based on the overall cloud group influencing parameters of the distributed photovoltaic power station. This application can improve the accuracy of distributed new energy power generation prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 This is a schematic diagram of a scenario of a distributed renewable energy power generation data prediction system provided in an embodiment of the present application;

[0051] Figure 2 It is a flow chart of an embodiment of a method for predicting power generation data of distributed renewable energy provided in an embodiment of the present application;

[0052] Figure 3 It is a schematic diagram of a target cloud group three-dimensional model and a power station area projection in one embodiment of a distributed renewable energy power generation data prediction method provided in an embodiment of the present application;

[0053] Figure 4 It is a schematic diagram of a cloud projection area and a power station projection area in one embodiment of a distributed renewable energy power generation data prediction method provided in an embodiment of the present application;

[0054] Figure 5It is a structural schematic diagram of a distributed renewable energy power generation data prediction device provided in an embodiment of the present application;

[0055] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] It should be noted that the principles of the present application are illustrated by implementing them in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application and should not be considered as limiting other specific embodiments of the present application that are not described in detail herein.

[0057] In the following description of the present application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0058] In the following description of the present application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0060] In order to improve the effect of distributed renewable energy power generation data prediction, the embodiments of the present application provide a distributed renewable energy power generation data prediction method, a distributed renewable energy power generation data prediction device, an electronic device, a computer-readable storage medium, and a computer program product. The distributed renewable energy power generation data prediction method can be executed by the distributed renewable energy power generation data prediction device, or by an electronic device integrated with the distributed renewable energy power generation data prediction device.

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0062] Please refer to Figure 1 , the present application also provides a distributed renewable energy power generation data prediction system, such as Figure 1 As shown, the distributed renewable energy power generation data prediction system electronic device 100, the distributed renewable energy power generation data prediction device provided by the present application is integrated in the electronic device 100.

[0063] Among them, the electronic device 100 can be any device equipped with a processor and has processing capabilities, such as mobile electronic devices with processors such as smart phones, tablet computers, PDAs, laptops, smart speakers, or fixed electronic devices with processors such as desktop computers, televisions, servers, industrial equipment, etc.

[0064] In addition, if Figure 1 As shown, the distributed renewable energy power generation data prediction system may further include a memory 200 for storing original data, intermediate data and result data.

[0065] In the embodiment of the present application, the memory 200 can be a cloud storage. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of different types of storage devices (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.

[0066] At present, the storage method of the storage system is: create a logical volume, and when creating a logical volume, allocate physical storage space for each logical volume. The physical storage space may be composed of disks of a storage device or several storage devices. The client stores data on a logical volume, that is, stores the data on the file system. The file system divides the data into many parts, each of which is an object. The object contains not only data but also additional information such as data identification (ID, ID entity). The file system writes each object into the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object.

[0067] The process of the storage system allocating physical storage space to a logical volume is as follows: based on the estimated capacity of the objects stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the grouping of independent redundant disk arrays (RAID, Redundant Array of Independent Disks), the physical storage space is pre-divided into stripes. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0068] It should be noted that Figure 1 The scenario diagram of the distributed renewable energy power generation data prediction system shown is merely an example. The distributed renewable energy power generation data prediction system and scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can know that with the evolution of the distributed renewable energy power generation data prediction system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0069] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0070] Please refer to Figure 2 , Figure 2 FIG. 1 is a flow chart of an embodiment of a method for predicting power generation data of distributed renewable energy provided in an embodiment of the present application. Figure 2 As shown, the process of the distributed renewable energy power generation data prediction method provided in this application is as follows:

[0071] 201. Obtain the power station area where the distributed photovoltaic power station is located.

[0072] In the embodiment of the present application, the power station area is the area where the distributed photovoltaic power station is located.

[0073] 202. Acquire a plurality of first two-dimensional images of a sky area captured by a plurality of different drones from different angles at a target time.

[0074] Among them, a distributed photovoltaic power station corresponds to a drone cluster, and each drone cluster flies and takes pictures within an area centered on the distributed power station.

[0075] In an embodiment of the present application, a ground station is provided in the distributed photovoltaic power station, and the ground station is connected to a network of multiple drones in the drone cluster. The ground station controls the multiple drones in the drone cluster to fly and take pictures within an area centered on the distributed power station.

[0076] Specifically, a third two-dimensional image is obtained by the depth camera of the drone shooting the sky vertically upward at the ground station, and a sky reference image is obtained by the drone shooting the sky vertically upward at the ground station, wherein the sky reference image is marked with the angle between each pixel and the vertical direction, and the third two-dimensional image is detected to obtain the first cloud cluster segmentation area on the third two-dimensional image and the power station cloud cluster distance between each pixel in the first cloud cluster segmentation area and the distributed photovoltaic power station. Specifically, a cloud cluster segmentation model is pre-trained, and the cloud cluster segmentation model can be a Unet model or other model, which can be set according to specific circumstances. The third two-dimensional image is input into the cloud cluster segmentation model for detection to obtain the first cloud cluster segmentation area on the third two-dimensional image. The current depth cameras can be divided into three types according to their working principles: TOF, RGB binocular, and structured light. The power station cloud cluster distance between each pixel in the first cloud cluster segmentation area and the distributed photovoltaic power station is obtained according to the depth information collected by the depth camera.

[0077] The sky reference image and the third two-dimensional image are aligned to obtain the angle between each pixel point on the first cloud segmentation area on the third two-dimensional image and the vertical direction. Based on the power station cloud cluster distance between each pixel point on the first cloud segmentation area and the distributed photovoltaic power station, and the angle between each pixel point on the first cloud segmentation area and the vertical direction, the physical distance between each pixel point on the first cloud segmentation area and the image center of the third two-dimensional image is determined, and the average value of the physical distance between each pixel point on the first cloud segmentation area and the image center of the third two-dimensional image is determined as the power station cloud cluster horizontal distance. The physical distance between the pixel point and the image center of the third two-dimensional image can be determined by trigonometric functions.

[0078] The longitude and latitude of the distributed photovoltaic power station are obtained, and a preset minimum solar illumination angle and a preset cloud cluster height are determined based on the longitude and latitude of the distributed photovoltaic power station. A first distance threshold is determined based on the preset cloud cluster height and the preset minimum solar illumination angle, and a first cloud cluster segmentation area whose horizontal distance from the power station cloud cluster is less than the first distance threshold is determined as a second cloud cluster segmentation area, and multiple second cloud cluster segmentation areas are obtained.

[0079] Project the multiple second cloud cluster segmentation areas on the third two-dimensional image onto the second plane where the distributed photovoltaic power station is located, and obtain multiple detection projection areas and regional centroids of the multiple detection projection areas corresponding to the multiple second cloud cluster segmentation areas. Determine the first polygon based on the regional centroids of the multiple detection projection areas, wherein the regional centroids of the multiple detection projection areas are all located within the first polygon, and the vertices of the first polygon are all regional centroids of the detection projection areas. Enlarge the first polygon according to a preset ratio to obtain a second polygon, wherein the first polygon and the second polygon have the same shape and centroid, and the multiple detection projection areas are all located within the second polygon. Determine the spatial area enclosed by the second polygon as the regional range of activities of each drone in the drone cluster.

[0080] 203. Perform three-dimensional reconstruction based on the multiple first two-dimensional captured images to obtain three-dimensional models of multiple target cloud clusters in the sky area.

[0081] In a specific embodiment, the SFM algorithm is used to perform three-dimensional reconstruction on multiple first two-dimensional images to obtain three-dimensional models of multiple target clouds in the sky area. In computer vision, three-dimensional reconstruction refers to the process of reconstructing three-dimensional information based on single-view or multi-view images. Since the information of a single video is incomplete, three-dimensional reconstruction requires the use of empirical knowledge. The three-dimensional reconstruction of multiple views (similar to human binocular positioning) is relatively easy. The method is to first calibrate the camera, that is, calculate the relationship between the camera's image coordinate system and the world coordinate system. Then use the information in multiple two-dimensional images to reconstruct the three-dimensional information.

[0082] In another specific embodiment, three-dimensional reconstruction is performed based on the multiple first two-dimensional captured images to obtain three-dimensional models of multiple target clouds in the sky area, including:

[0083] (1) Use the SFM algorithm to perform three-dimensional reconstruction on multiple first two-dimensional images to obtain initial point cloud data.

[0084] Structure From Motion (SFM) is a technique for estimating 3D structures from a series of 2D image sequences containing visual motion information. Specifically, the SFM algorithm includes the following steps: extracting image feature points, extracting key points, and calculating descriptors; matching features between two images; obtaining the spatial pose transformation between two images; and performing sparse reconstruction based on the matched feature points to obtain point cloud data.

[0085] (2) Selecting a preset ratio of first two-dimensional photographed images from the plurality of first two-dimensional photographed images as second two-dimensional photographed images to obtain a plurality of second two-dimensional photographed images, wherein the preset ratio is less than 1.

[0086] The preset ratio may be 0.5 or other values, which may be set according to specific circumstances.

[0087] In a specific embodiment, selecting a preset proportion of first two-dimensional captured images from a plurality of first two-dimensional captured images as second two-dimensional captured images to obtain a plurality of second two-dimensional captured images includes:

[0088] Step 1-1, determine the first two-dimensional captured image as the image to be detected, perform optical flow calculation based on the image to be detected and the historical two-dimensional captured images of the drone that captured the image to be detected before the image to be detected was captured, and obtain the optical flow vector of each pixel point on the image to be detected.

[0089] In the real world, everything is moving, and the speed and direction of movement may be different, which constitutes a motion field. The projection of the motion of an object on the image reflects the movement of pixels. Optical flow is the instantaneous speed of the pixel movement of a spatial moving object on the observation imaging plane. This instantaneous movement speed of pixels is the optical flow. The optical flow method is a method that uses the changes in the pixels in the image sequence in the time domain and the correlation between adjacent frames to find the corresponding relationship between the previous frame and the current frame, and calculates the motion information of objects between adjacent frames.

[0090] The optical flow method uses the change of pixels in the image sequence in the time domain and the correlation between adjacent frames to find the corresponding relationship between the previous frame and the current frame, thereby calculating the motion information of objects between adjacent frames. The instantaneous change rate of grayscale at a specific coordinate point on the two-dimensional image plane is usually defined as an optical flow vector.

[0091] Optical flow methods can be divided into gradient-based methods, matching-based methods, energy-based methods, phase-based methods, etc. according to different implementation methods. Among them, the gradient-based method is the Farnback optical flow method. The premise assumptions of the optical flow method include: the brightness between adjacent frames is constant; the time between adjacent frames is continuous or the motion changes are small; the pixels in the same sub-image have the same motion.

[0092] Step 1-2, based on the optical flow vector of each pixel on the image to be detected, the magnitude and direction of the optical flow vector of each pixel are calculated.

[0093] Specifically, the optical flow vector size of the pixel is calculated according to each optical flow vector (ui, vi), where the calculation formula for the optical flow vector size magi of the i-th pixel is as follows:

[0094] magi=sqrt(ui^2+vi^2),

[0095] Specifically, the optical flow vector direction of the pixel is calculated according to each optical flow vector (ui, vi), where the calculation formula for the optical flow vector direction angi of the i-th pixel is as follows:

[0096] angi=arctan(vi / ui),

[0097] Step 1-3, calculate the average value of the optical flow vector size of each pixel point to obtain the amplitude average value.

[0098] Specifically, the calculation formula for the amplitude average value μ is as follows:

[0099] μ=mean(mag),

[0100] Among them, mag represents the set of optical flow vector sizes magi of each pixel point on the image to be detected.

[0101] Step 1-4, calculate the standard deviation of the optical flow vector size of each pixel point to obtain the direction change parameter.

[0102] Specifically, the calculation formula of the direction change parameter σ is as follows:

[0103] σ=std(mag),

[0104] Among them, μ represents the average amplitude, and σ represents the direction change parameter. A smaller μ means a smaller motion amplitude, and a smaller σ means that the magnitudes of the vectors are more uniform.

[0105] Step 1-5, calculate the variance of the optical flow vector direction of each pixel point to obtain the vector direction change degree parameter.

[0106] Specifically, the calculation formula of the vector direction change degree parameter varθ is as follows:

[0107] varθ=var(ang),

[0108] Among them, ang represents the set of optical flow vector directions angi of each pixel point on the image to be detected. varθ represents the degree of dispersion of the main direction. A smaller varθ means that the main direction is more concentrated, and a larger varθ means that the main direction is more dispersed.

[0109] Step 1-6, determining the image vibration parameters of the image to be detected based on the amplitude average value, the direction change parameter and the vector direction change degree parameter, and obtaining the image vibration parameters of each first two-dimensional captured image.

[0110] The image vibration parameter decreases with the increase of the amplitude average value, the image vibration parameter increases with the increase of the direction change parameter, and the image vibration parameter decreases with the increase of the vector direction change degree parameter.

[0111] In a specific embodiment, the image vibration parameter G score Satisfies the following calculation formula,

[0112] G score =exp(-μ / σ)*exp(-varθ),

[0113] Among them, μ represents the average amplitude, σ represents the direction change parameter, varθ represents the vector direction change degree parameter, G score Represents image vibration parameters.

[0114] Among them, the image vibration parameter G score The value is between 0 and 1. The closer it is to 1, the more stable the image is.

[0115] Step 1-7: determining the first two-dimensional captured image whose image vibration parameter is greater than the preset vibration parameter as the second two-dimensional captured image.

[0116] Furthermore, multiple photos taken by the same drone are obtained.

[0117] (3) Perform cloud segmentation on the plurality of second two-dimensional captured images to obtain a plurality of cloud segmentation regions on the plurality of second two-dimensional captured images.

[0118] Specifically, a pre-trained cloud segmentation model is used to perform cloud segmentation on the plurality of second two-dimensional captured images to obtain a plurality of cloud segmentation regions on the plurality of second two-dimensional captured images.

[0119] (4) The point cloud data located in each cloud cluster segmentation area in the initial point cloud data is determined as cloud cluster point cloud data.

[0120] Since the initial point cloud data is reconstructed from multiple second two-dimensional images, each three-dimensional point cloud in the initial point cloud data can find a corresponding mapping pixel point in the multiple second two-dimensional images. Specifically, the mapping pixel points corresponding to each three-dimensional point cloud in the initial point cloud data in the second two-dimensional images are obtained, and the three-dimensional point clouds whose mapping pixels are located in each cloud segmentation area are determined as cloud point cloud data.

[0121] (5) Determine multiple target cloud 3D models based on the cloud point cloud data.

[0122] In a specific embodiment, the cloud point cloud data is clustered to obtain a plurality of first three-dimensional point clusters; a target cloud three-dimensional model is determined based on the first three-dimensional point clusters to obtain a plurality of target cloud three-dimensional models corresponding to the plurality of first three-dimensional point clusters. Specifically, a solid formed by enclosing a plurality of three-dimensional point clouds in the first three-dimensional point cluster is determined as the target cloud three-dimensional model.

[0123] In another specific embodiment, image matching is performed on the cloud segmentation areas on multiple second two-dimensional captured images to obtain multiple cloud segmentation areas of the same cloud on different second two-dimensional captured images. Multiple cloud segmentation areas of the same cloud on different second two-dimensional captured images are determined as a segmentation area group to obtain multiple segmentation area groups. In the initial point cloud data, the three-dimensional point cloud enclosed by multiple cloud segmentation areas in the segmentation area group is determined as a first cloud three-dimensional model to obtain multiple first cloud three-dimensional models corresponding to the multiple segmentation area groups. The number of segmentation area groups is determined as a preset number, and the cloud point cloud data is clustered based on the preset number to obtain a preset number of first three-dimensional point clusters. The second cloud three-dimensional model is determined based on the first three-dimensional point cluster, and a preset number of second cloud three-dimensional models corresponding to the preset number of first three-dimensional point clusters are obtained. Specifically, the three-dimensional point cloud enclosed by multiple three-dimensional point clouds in the first three-dimensional point cluster is determined as a second cloud three-dimensional model. The first cloud three-dimensional model and the second cloud three-dimensional model are matched to obtain the first cloud three-dimensional model and the corresponding second cloud three-dimensional model. The intersection of the first cloud cluster 3D model and the second cloud cluster 3D model is determined as the target cloud cluster 3D model to obtain multiple target cloud cluster 3D models. Specifically, the union of the first cloud cluster 3D model and the second cloud cluster 3D model is determined as the target cloud cluster 3D model.

[0124] Image matching refers to identifying points of the same name between two or more images through a certain matching algorithm. For example, in two-dimensional image matching, by comparing the correlation coefficients of windows of the same size in the target area and the search area, the center point of the window with the largest correlation coefficient in the search area is taken as the point of the same name. Its essence is the optimal search problem using matching criteria under the condition of primitive similarity.

[0125] Specifically, clustering the cloud point cloud data based on a preset number to obtain a preset number of first three-dimensional point clusters includes:

[0126] (1) Obtain point cloud features of H 3D points in the cloud point cloud data. The point cloud features include the 3D coordinates and color values ​​of the 3D points.

[0127] (2) Randomly divide the H 3D points into Q 3D point sets, where each 3D point set contains H / Q 3D points.

[0128] (3) Clustering the Q three-dimensional point sets respectively to obtain a preset number of second three-dimensional point clusters in each three-dimensional point set.

[0129] In a specific embodiment, the k-means clustering algorithm is used to cluster the Q three-dimensional point sets respectively to obtain a preset number of second three-dimensional point clusters in each three-dimensional point set.

[0130] (4) Determine each second three-dimensional point cluster as a target three-dimensional point cluster, and calculate the three-dimensional point cluster similarity between the target three-dimensional point cluster and the second three-dimensional point clusters in the Q three-dimensional point sets.

[0131] Specifically, the similarity between the cluster average vector of the target three-dimensional point cluster and the cluster average vector of the second three-dimensional point cluster is calculated; the similarity between the cluster average vector of the target three-dimensional point cluster and the cluster average vector of the second three-dimensional point cluster is determined as the three-dimensional point cluster similarity between the target three-dimensional point cluster and the second three-dimensional point cluster.

[0132] (5) merging the second three-dimensional point clusters with the greatest similarity to the target three-dimensional point cluster in each three-dimensional point set to obtain the first three-dimensional point cluster corresponding to the target three-dimensional point cluster, and obtaining a preset number of first three-dimensional point clusters corresponding to a preset number of second three-dimensional point clusters.

[0133] 204. Obtain the sunlight direction of the sun at a target time.

[0134] In the embodiment of the present application, the direction of sunlight can be obtained based on the weather forecast of the location of the distributed photovoltaic power station. Figure 3 shown.

[0135] 205. Project the power station area and the multiple target cloud cluster three-dimensional models onto the first plane respectively to obtain a power station projection area corresponding to the power station area and multiple cloud cluster projection areas corresponding to the multiple target cloud cluster three-dimensional models.

[0136] The first plane is perpendicular to the direction of sunlight. The first plane, power station area, power station projection area, target cloud group three-dimensional model, cloud group projection area are as follows: Figure 3 and Figure 4 shown.

[0137] 206. Determine the overall cloud impact parameter of the distributed photovoltaic power station based on the positional relationship between the cloud projection area and the power station projection area of ​​the distributed photovoltaic power station.

[0138] In an embodiment of the present application, the overall influencing parameters of the cloud cluster of the distributed photovoltaic power station are determined based on the positional relationship between the cloud cluster projection area and the power station projection area of ​​the distributed photovoltaic power station, including: if there is an overlapping area between the power station projection area and the cloud cluster projection area of ​​the target cloud cluster three-dimensional model, then the influencing parameters of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station are determined based on the overlapping area and the cloud cluster projection area of ​​the target cloud cluster three-dimensional model; if there is no overlapping area between the power station projection area and the cloud cluster projection area, then the preset influencing parameter value is determined as the influencing parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station; the average value of the influencing parameters of each target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station is determined as the overall influencing parameter of the cloud cluster of the distributed photovoltaic power station.

[0139] The preset influencing parameter value can be 1 or other values, which can be set according to the specific situation. Figure 4 shown.

[0140] In the embodiment of the present application, the influence parameters of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station are determined based on the overlapping area and the cloud cluster projection area of ​​the target cloud cluster three-dimensional model, including:

[0141] (1) Obtain the area ratio of the overlapping area to the power station projection area.

[0142] In the embodiment of the present application, the area ratio is the area ratio of the overlapping area to the power station projection area.

[0143] (2) Generate multiple first straight lines that pass through the target cloud 3D model and the overlapping area and are parallel to the direction of sunlight.

[0144] In an embodiment of the present application, the centroid of the overlapping area is obtained, and multiple rays are generated with the centroid of the overlapping area as the starting point, which intersect with the boundaries of the overlapping area at multiple intersection points respectively, to obtain multiple second line segments with the centroid of the overlapping area as the starting point and the multiple intersection points as the end points, and multiple equally divided points on the second line segments are obtained, and a straight line parallel to the direction of sunlight is drawn through each equally divided point on each second line segment to obtain multiple first straight lines.

[0145] (3) The first straight line is cut off on the surface of the target cloud three-dimensional model to generate a first line segment, thereby obtaining a plurality of first line segments of the first straight line.

[0146] (4) Determine the influence parameters of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station based on the area ratio and the average value of the lengths of the multiple first line segments.

[0147] Among them, the larger the average value of the lengths of the multiple first line segments is, the larger the cloud cluster monomer influence parameter is, and the larger the regional area ratio is, the smaller the cloud cluster monomer influence parameter is.

[0148] In a specific embodiment, the influence parameters of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station are determined based on the average value of the area ratio and the length of multiple first line segments, including: normalizing the average value of the length of multiple first line segments to obtain a normalized length average, weighted averaging the area ratio and the normalized length average to obtain a weighted average, multiplying the weighted average and a preset influence parameter value and adding the weighted average to the preset influence parameter value to obtain the cloud cluster monomer influence parameter.

[0149] In another specific embodiment, determining the influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station based on the area ratio and the average value of the lengths of the plurality of first line segments includes:

[0150] (1) Obtain the centroid distance between the centroid of the overlapping area and the centroid of the cloud projection area.

[0151] (2) Determine the influencing parameters of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station based on the area ratio, the centroid distance and the average value of the lengths of multiple first line segments.

[0152] Among them, the larger the average value of the lengths of the multiple first line segments, the larger the cloud cluster monomer influence parameter, the larger the regional area ratio, the larger the cloud cluster monomer influence parameter, and the larger the centroid distance, the smaller the cloud cluster monomer influence parameter.

[0153] Specifically, the average value of the lengths of the multiple first line segments is normalized to obtain a normalized length average value, the inverse of the average value of the lengths of the multiple first line segments is determined as the inverse of the spacing average value, the inverse of the spacing average value is normalized to obtain a normalized inverse spacing average value, the normalized inverse spacing average value, the area ratio and the normalized length average value are weighted averaged to obtain a weighted average value, the weighted average value is multiplied by a preset influencing parameter value and added to the preset influencing parameter value to obtain the cloud cluster monomer influencing parameter.

[0154] Specifically, the cloud cluster monomer influence parameter P2 satisfies the following formula:

[0155] P2=(a1*L+a2*A+a3*J+1)*P1,

[0156] Among them, P1 is the preset influencing parameter value, which can be determined according to manual experience, L is the normalized length average, a1 is the weight of the normalized length average L, A is the area ratio, a2 is the weight of the area ratio A, J is the normalized reciprocal mean of the spacing, and a3 is the weight of the normalized reciprocal mean of the spacing J.

[0157] 207. Determine the predicted power generation of the distributed photovoltaic power station based on the overall cloud cluster influencing parameters of the distributed photovoltaic power station.

[0158] In the embodiment of the present application, the predicted power generation of the distributed photovoltaic power station is determined based on the overall impact parameters of the cloud cluster of the distributed photovoltaic power station, including:

[0159] (1) Calculate the overall impact parameters of clouds on distributed photovoltaic power stations at multiple different times within a preset time period.

[0160] Specifically, different times are determined as target times, and overall cloud impact parameters at multiple different times are obtained.

[0161] The multiple different times may be multiple time points arranged at preset time intervals, for example, the preset time interval is 1 minute, and the multiple time points are 12:01, 12:02, 12:03, 12:04, etc. For example, the overall cloud impact parameters at multiple different times are 1, 1.1, 1.2, 1.2, and 1.5, respectively.

[0162] (2) respectively obtaining meteorological parameters of the distributed photovoltaic power station at multiple different times within a preset time period, wherein the meteorological parameters include at least one of temperature, wind speed, and humidity.

[0163] Specifically, meteorological parameters can be obtained through weather forecasts.

[0164] (3) The cloud overall impact parameters at multiple different times and the meteorological parameters at multiple different times are spliced ​​together to obtain the input parameters at multiple different times.

[0165] The output parameters at each time include meteorological parameters and cloud overall impact parameters.

[0166] (4) Inputting multiple input parameters at different times into a preset power generation prediction model to obtain the predicted power generation power of the distributed photovoltaic power station.

[0167] The preset power generation prediction model can be a pre-trained long short-term memory network. Input parameters at different times are input as a sequence data into the preset power generation prediction model to obtain the predicted power generation of the distributed photovoltaic power station. The long short-term memory network (LSTM) is an improved recurrent neural network that can solve the problem that RNN cannot handle long-distance dependencies.

[0168] In order to facilitate better implementation of the distributed renewable energy power generation data prediction method provided in the embodiment of the present application, the embodiment of the present application also provides a distributed renewable energy power generation data prediction device based on the above distributed renewable energy power generation data prediction method. The meanings of the terms are the same as those in the above distributed renewable energy power generation data prediction method. For specific implementation details, please refer to the description in the above method embodiment.

[0169] Please refer to Figure 5 , Figure 5 A schematic diagram of the structure of a distributed renewable energy power generation data prediction device provided in an embodiment of the present application, wherein the distributed renewable energy power generation data prediction device may include:

[0170] The first acquisition module 701 is used to acquire the power station area where the distributed photovoltaic power station is located;

[0171] The second acquisition module 702 is used to acquire a plurality of first two-dimensional images captured by different drones at a target time from different angles of the sky area, wherein a distributed photovoltaic power station corresponds to a drone cluster, and the drone cluster flies and takes pictures within an area centered on the distributed power station;

[0172] A three-dimensional reconstruction module 703 is used to perform three-dimensional reconstruction based on the multiple first two-dimensional captured images to obtain three-dimensional models of multiple target clouds in the sky area;

[0173] The third acquisition module 704 is used to obtain the sunlight radiation direction of the sun at the target time;

[0174] The projection module 705 is used to project the power station area and the multiple target cloud group three-dimensional models onto the first plane respectively, to obtain a power station projection area corresponding to the power station area and multiple cloud group projection areas corresponding to the multiple target cloud group three-dimensional models, wherein the first plane is perpendicular to the sunlight irradiation direction;

[0175] A first determination module 706 is used to determine the overall cloud impact parameter of the distributed photovoltaic power station based on the positional relationship between the cloud projection area and the power station projection area of ​​the distributed photovoltaic power station;

[0176] The second determination module 707 is used to determine the predicted power generation of the distributed photovoltaic power station based on the overall impact parameters of the cloud cluster of the distributed photovoltaic power station.

[0177] The specific implementation of each of the above modules can be found in the previous embodiments and will not be described in detail here.

[0178] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the processor is used to execute the steps in the distributed new energy power generation data prediction method provided in this embodiment by calling a computer program stored in the memory.

[0179] Please refer to Figure 6 , Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0180] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0181] The processor 101 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102. Optionally, the processor 101 may include one or more processing cores; optionally, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 101.

[0182] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0183] The electronic device also includes a power supply 103 for supplying power to each component. Optionally, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 103 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0184] The electronic device may further include an input unit 104, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0185] Although not shown, the electronic device may also include a display unit, an image acquisition component, etc., which will not be described in detail here. Specifically in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps in the distributed renewable energy power generation data prediction method provided in this application, such as:

[0186] Acquire the power station area where the distributed photovoltaic power station is located; acquire multiple first and second-dimensional images of the sky area taken by different drones from different angles at a target time, wherein the distributed photovoltaic power station corresponds to a drone cluster, and each drone cluster flies and takes pictures within an area centered on the distributed power station; perform three-dimensional reconstruction based on the multiple first and second-dimensional images to obtain multiple three-dimensional models of target clouds in the sky area; acquire the sunlight direction of the sun at the target time; project the power station area and the multiple target cloud cluster three-dimensional models onto a first plane respectively, to obtain a power station projection area corresponding to the power station area and multiple cloud cluster projection areas corresponding to the multiple target cloud cluster three-dimensional models, wherein the first plane is perpendicular to the sunlight direction; determine the overall cloud cluster influencing parameters of the distributed photovoltaic power station based on the positional relationship between the cloud cluster projection area and the power station projection area of ​​the distributed photovoltaic power station; determine the predicted power generation power of the distributed photovoltaic power station based on the overall cloud cluster influencing parameters of the distributed photovoltaic power station.

[0187] It should be noted that the electronic device provided in the embodiment of the present application belongs to the same concept as the distributed renewable energy power generation data prediction method in the above embodiment. The specific implementation process is detailed in the above related embodiments and will not be repeated here.

[0188] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program stored therein is executed on a processor of an electronic device provided in an embodiment of the present application, the processor of the electronic device executes the steps in the distributed renewable energy power generation data prediction method provided in the present application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0189] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes various optional implementations of the above-mentioned distributed renewable energy power generation data prediction method.

[0190] The above is a detailed introduction to the distributed renewable energy power generation data prediction method, device, equipment and medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0191] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, the relevant data of the user is involved, and the user's permission or consent is required, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A method for predicting power generation data of distributed renewable energy, characterized in that: The distributed renewable energy power generation data prediction method comprises: Get the power station area where the distributed photovoltaic power station is located; Acquire a plurality of first two-dimensional images of the sky area taken by different drones from different angles at a target time, wherein the distributed photovoltaic power station corresponds to a drone cluster, and each drone cluster flies and takes pictures within an area centered on the distributed power station; Performing three-dimensional reconstruction based on the multiple first two-dimensional captured images to obtain three-dimensional models of multiple target cloud clusters in the sky area; Get the sun's direction of sunlight at the target time; Projecting the power station area and the plurality of target cloud cluster three-dimensional models onto a first plane respectively, to obtain a power station projection area corresponding to the power station area and a plurality of cloud cluster projection areas corresponding to the plurality of target cloud cluster three-dimensional models, wherein the first plane is perpendicular to the sunlight irradiation direction; Determine the overall cloud impact parameter of the distributed photovoltaic power station based on the positional relationship between the cloud projection area and the power station projection area of ​​the distributed photovoltaic power station; The predicted power generation of the distributed photovoltaic power station is determined based on the overall cloud cluster impact parameter of the distributed photovoltaic power station.

2. The distributed renewable energy power generation data prediction method according to claim 1, characterized in that: The step of determining the predicted power generation power of the distributed photovoltaic power station based on the cloud cluster overall impact parameter of the distributed photovoltaic power station comprises: Respectively calculating overall cloud impact parameters of the distributed photovoltaic power station at multiple different times within a preset time period; Respectively obtaining meteorological parameters of the distributed photovoltaic power station at multiple different times within a preset time period, wherein the meteorological parameters include at least one of temperature, wind speed, and humidity; The cloud overall impact parameters at multiple different times and the meteorological parameters at multiple different times are combined to obtain the input parameters at multiple different times; Input parameters at multiple different times are input into a preset power generation prediction model to obtain the predicted power generation power of the distributed photovoltaic power station.

3. The distributed renewable energy power generation data prediction method according to claim 1, characterized in that: The determining of the cloud cluster overall impact parameter of the distributed photovoltaic power station based on the positional relationship between the cloud cluster projection area and the power station projection area of ​​the distributed photovoltaic power station comprises: If there is an overlapping area between the power station projection area and the cloud cluster projection area of ​​the target cloud cluster three-dimensional model, then based on the overlapping area and the cloud cluster projection area of ​​the target cloud cluster three-dimensional model, determine the influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station; if there is no overlapping area between the power station projection area and the cloud cluster projection area, then determine the preset influence parameter value as the influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station; The average value of the influencing parameters of each target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station is determined as the overall influencing parameter of the cloud cluster of the distributed photovoltaic power station.

4. The distributed renewable energy power generation data prediction method according to claim 3 is characterized in that: The determining, based on the overlapping area and the cloud projection area of ​​the target cloud three-dimensional model, an influence parameter of the target cloud three-dimensional model on the cloud monomer of the distributed photovoltaic power station comprises: Obtaining an area ratio of the overlapping area to the power station projection area; Generate a plurality of first straight lines passing through the target cloud three-dimensional model and the overlapping area and parallel to the sunlight irradiation direction; Cutting the first straight line on the surface of the target cloud three-dimensional model to generate a first line segment, thereby obtaining a plurality of first line segments of the first straight line; The influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station is determined based on the average value of the area ratio of the region and the lengths of the multiple first line segments, wherein the larger the average value of the lengths of the multiple first line segments, the larger the cloud cluster monomer influence parameter, and the larger the area ratio, the larger the cloud cluster monomer influence parameter.

5. The distributed renewable energy power generation data prediction method according to claim 4 is characterized in that: The determining, based on the area ratio and the average value of the lengths of the plurality of first line segments, the influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station comprises: Obtaining a centroid distance between the centroid of the overlapping area and the centroid of the cloud projection area; The influence parameter of the target cloud cluster three-dimensional model on the cloud cluster monomer of the distributed photovoltaic power station is determined based on the average value of the area ratio of the region, the centroid distance and the length of multiple first line segments, wherein the larger the average value of the length of multiple first line segments, the larger the cloud cluster monomer influence parameter, the larger the area ratio, the larger the cloud cluster monomer influence parameter, and the larger the centroid distance, the smaller the cloud cluster monomer influence parameter.

6. The distributed renewable energy power generation data prediction method according to claim 1, characterized in that: The three-dimensional reconstruction based on the multiple first two-dimensional captured images to obtain the three-dimensional models of multiple target clouds in the sky area includes: Use the SFM algorithm to perform three-dimensional reconstruction on the multiple first two-dimensional photographed images to obtain initial point cloud data; Selecting a preset ratio of first two-dimensional photographed images from the plurality of first two-dimensional photographed images as second two-dimensional photographed images to obtain a plurality of second two-dimensional photographed images, wherein the preset ratio is less than 1; performing cloud segmentation on the plurality of the second two-dimensional photographed images to obtain a plurality of cloud segmentation regions on the plurality of the second two-dimensional photographed images; Determine the point cloud data located in each of the cloud cluster segmentation areas in the initial point cloud data as cloud cluster point cloud data; A plurality of target cloud three-dimensional models are determined based on the cloud point cloud data.

7. The distributed renewable energy power generation data prediction method according to claim 6, characterized in that: The generating a plurality of target cloud group three-dimensional models based on the cloud group point cloud data comprises: Clustering the cloud point cloud data to obtain a plurality of first three-dimensional point clusters; The target cloud three-dimensional model is determined based on the first three-dimensional point cluster, and a plurality of target cloud three-dimensional models corresponding to the plurality of the first three-dimensional point clusters are obtained.

8. A distributed new energy power generation data prediction device, characterized in that: include: The first acquisition module is used to acquire the power station area where the distributed photovoltaic power station is located; A second acquisition module is used to acquire a plurality of first two-dimensional images captured by different drones of a sky area from different angles at a target time, wherein the distributed photovoltaic power station corresponds to a drone cluster, and the drone cluster flies and takes pictures within an area centered on the distributed power station; A three-dimensional reconstruction module, used for performing three-dimensional reconstruction based on the plurality of first two-dimensional photographed images to obtain three-dimensional models of a plurality of target cloud clusters in the sky area; The third acquisition module is used to obtain the sunlight direction of the sun at the target time; A projection module, used to project the power station area and the plurality of target cloud group three-dimensional models onto a first plane respectively, to obtain a power station projection area corresponding to the power station area and a plurality of cloud group projection areas corresponding to the plurality of target cloud group three-dimensional models, wherein the first plane is perpendicular to the sunlight irradiation direction; A first determination module is used to determine the overall cloud impact parameter of the distributed photovoltaic power station based on the positional relationship between the cloud projection area and the power station projection area of ​​the distributed photovoltaic power station; The second determination module is used to determine the predicted power generation of the distributed photovoltaic power station based on the overall cloud cluster impact parameter of the distributed photovoltaic power station.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the steps in the distributed renewable energy power generation data prediction method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the method for predicting power generation data of distributed renewable energy as described in any one of claims 1 to 7.

Images