Photovoltaic power generation prediction method, equipment and medium based on ground-based cloud map
By combining the data of the foundation cloud map and satellite cloud map, the dynamics of cloud cluster motion are simulated and the photovoltaic power generation power is predicted, which solves the problem of unstable power generation power in the photovoltaic power generation system, and improves the prediction accuracy and management efficiency of the power system.
Patent Information
- Application Number
- CN202411259594.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-10
AI Technical Summary
Due to the randomness and volatility of the weather, photovoltaic power generation systems lead to unstable power generation power, making it difficult to accurately predict, affecting the toughness of the power grid and power transmission efficiency.
Using the photovoltaic power prediction method based on foundation cloud map and satellite cloud map, the outline, movement speed, thickness and types of cloud clusters are obtained, combined with atmospheric data and solar motion trajectory, the motion dynamic map of cloud clusters is simulated, and the occlusion area and radiation reduction are calculated. Small amounts predict the similarity of the sky color value, and then predict the photovoltaic power generation.
It improves the accuracy of photovoltaic power generation prediction, helps staff understand future power generation situations in advance, optimizes the management of power grids and transmission lines, and improves the stability and efficiency of the power system.
Smart Images

Figure CN118801370B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of photovoltaic power generation, and in particular to a photovoltaic power generation power prediction method, device and medium based on ground-based cloud maps. 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 affected by the weather and has randomness and volatility, which makes it difficult to achieve stable output of photovoltaic power generation. At present, the electric energy generated in the photovoltaic base is usually consumed on-site, that is, it is directly used in the surrounding areas of the photovoltaic base, so as to improve the reliability of photovoltaic power supply, reduce transmission costs and enhance the resilience of the power grid. On-site consumption can effectively solve the problem of energy loss in the process of power transmission and improve the overall system efficiency. However, due to the randomness and volatility of photovoltaic power generation, it is necessary to predict the power generation of the photovoltaic base in the future in order to know the quality and effect of power generation in the future, and then judge whether there is a low power or abnormal situation based on the predicted power generation to make corresponding treatment. Therefore, it becomes a problem to accurately predict the power of photovoltaic power generation in the short term in the future. Summary of the invention
[0003] In order to improve the accuracy of photovoltaic power generation prediction, the present application provides a photovoltaic power generation power prediction method, device and medium based on ground-based cloud map.
[0004] In the first aspect, the present application provides a photovoltaic power generation power prediction method based on ground-based cloud maps, which adopts the following technical solutions:
[0005] The photovoltaic power generation power prediction method based on ground-based cloud map includes:
[0006] Obtain ground-based cloud images, satellite cloud images, atmospheric data, and solar movement trajectories of photovoltaic bases;
[0007] Determine from the ground-based cloud map and the satellite cloud map the cloud clusters that can move to a preset area within a preset future time period, the preset area being the lighting area corresponding to the photovoltaic base;
[0008] Determine the outline, moving speed, thickness and type of each cloud cluster based on the satellite cloud image;
[0009] Simulating a motion dynamic diagram of each cloud based on the contour, movement speed, type and atmospheric data of each cloud;
[0010] Determine a target cloud cluster based on the sun's motion trajectory and the motion dynamic graph of each cloud cluster, and determine a first variation graph of the sun-blocking area and the sun-blocking time of each target cloud cluster, wherein the target cloud cluster is a cloud cluster that can block the sun;
[0011] Determine the sky color value of the sky area from the ground-based cloud map, calculate the similarity between the sky color value and multiple historical sky color values at the same time, and determine the target historical sky color value and a third change graph of the target historical sky color value, wherein the sky color value is an RGB value, the target historical sky color value is the historical sky color value with the highest similarity, each historical sky color value corresponds to a second change graph of photovoltaic power generation over time, and each historical sky color value corresponds to a third change graph of radiation over time;
[0012] Determine, based on the thickness, type, first variation graph, and third variation graph of the target cloud cluster, a radiation reduction amount of the sun when each target cloud cluster blocks the sun;
[0013] A photovoltaic power generation power prediction diagram is determined and output based on the radiation reduction amount and the second change diagram of the target historical sky color value.
[0014] By adopting the above technical scheme, the cloud clusters that will move to the lighting area within a preset future time period can be accurately determined from the ground-based cloud map and the satellite cloud map, and the outline, moving speed, thickness and type of the cloud cluster can be determined based on the satellite cloud map, so as to facilitate the simulation of the motion state diagram of each cloud cluster according to the above attributes and atmospheric data. In combination with the sun's motion trajectory and the cloud cluster's motion state diagram, the target cloud cluster and the first change diagram can be determined, the sky color value can be determined from the ground-based cloud map, and the similarity between the sky color value and the historical sky color value can be calculated, so as to determine the target historical sky color value with the highest similarity, that is, the current sky color value is closest to the target historical sky color value, and the change of the current sky color value over time is similar to the change of the target historical sky color value over time. The changes in are also close, so the second change graph and the third change graph of the target historical sky color value can be used to predict the power generation power in the current preset future time period, and the radiation reduction amount is determined according to the thickness, type, first change graph and third change graph of the target cloud group. There is an influence relationship between the radiation reduction amount and the power generation power, so according to the radiation reduction amount and the second change graph of the target historical sky color value, the photovoltaic power generation power prediction graph can be accurately determined and output, so as to facilitate the staff to know the prediction situation, and according to the sky color value, the target historical sky color value with a high degree of proximity is determined from the historical sky color values, and the second change graph and the third change graph of the target historical sky color value and the relevant data of the target cloud group are used to comprehensively predict the power generation power more accurately.
[0015] Preferably, the atmospheric data includes wind direction, and the motion dynamic diagram of each cloud group simulated based on the outline, moving speed, type and atmospheric data of each cloud group includes:
[0016] Inputting the outline, moving speed, type and atmospheric data of each cloud group into the trained first network model for dynamic simulation to obtain a candidate motion dynamic graph of each cloud group;
[0017] Determine an associated area of each cloud cluster based on the wind direction and the position of each cloud cluster, and obtain atmospheric data of the associated area;
[0018] The atmospheric data of the associated area and the candidate motion dynamic graph are input into the trained second network model for deep simulation to obtain the motion dynamic graph of each cloud cluster.
[0019] Preferably, the determining the reduction in solar radiation when each target cloud blocks the sun based on the thickness, type, first variation graph, and third variation graph of the target cloud group includes:
[0020] determining a spectrum of each target cloud based on the type of each target cloud;
[0021] Determining the light shielding rate of each target cloud cluster based on the thickness and spectrum of the target cloud cluster;
[0022] Determine the shielding area at each shielding moment from the first variation graph of each target cloud cluster, and determine the radiation amount at each moment from the third variation graph of the target historical sky color value;
[0023] The radiation reduction amount at each shielding moment is determined based on the shielding rate, the shielding area at each shielding moment, and the radiation amount at each moment.
[0024] Preferably, determining and outputting a photovoltaic power prediction diagram based on the radiation reduction amount and the second change diagram includes:
[0025] Determine the power value at each moment from the second change graph of the target historical sky color value, determine the radiation amount at each moment from the third change graph of the target historical sky color value, and determine the predicted power value at each shading moment in a preset future time period based on the radiation reduction amount and the power value;
[0026] Deleting the power value corresponding to each shielding moment in the second variation graph of the target historical sky color value, and mapping the predicted power value in the second variation graph according to the shielding moment to obtain the photovoltaic power generation power prediction graph;
[0027] Output the photovoltaic power generation power prediction diagram.
[0028] Preferably, the photovoltaic power generation power prediction method based on ground-based cloud map also includes:
[0029] Obtaining the atmospheric turbidity above the photovoltaic base;
[0030] Calculate a first difference between a sky color value of the photovoltaic base and a preset sky color value in each channel, wherein the preset sky color value is a sky color value when the sky above the photovoltaic base is in a clear sky state;
[0031] Determine, based on the first difference, a percentage of the atmosphere above the photovoltaic base blocking light of a preset wavelength, where the preset wavelength is light of a specific wavelength that can be used for photovoltaic power generation;
[0032] A second difference between the atmospheric turbidity and a preset turbidity is calculated, and the power generation power at each moment is corrected based on the atmospheric turbidity and the blocking percentage. The preset turbidity is the atmospheric turbidity when the sky above the photovoltaic base is in a clear sky state.
[0033] Preferably, the photovoltaic power generation power prediction method based on ground-based cloud map also includes:
[0034] Determining a target time period in which the power generation is less than a preset power from the photovoltaic power generation power prediction diagram;
[0035] Determine the total duration of all target time periods, and determine the ratio of the total duration to the preset future time period;
[0036] Determine the average power and power variance in the photovoltaic power generation power prediction graph;
[0037] A quality score is determined based on the proportion, average power, power variance and respective corresponding coefficients, and the quality score represents the power generation quality of the photovoltaic base within a preset future time period.
[0038] Preferably, the photovoltaic power generation power prediction method based on ground-based cloud map also includes:
[0039] Calculating the similarity between the photovoltaic power generation prediction graph and a plurality of historical photovoltaic power generation graphs;
[0040] Determine the most similar historical photovoltaic power generation graph;
[0041] Obtaining the strain strategy corresponding to the historical photovoltaic power generation power diagram with the highest similarity;
[0042] The transmission lines of the photovoltaic base and the transmission lines of the main power grid are controlled based on the contingency strategy.
[0043] In the second aspect, the present application provides a photovoltaic power generation prediction device based on a ground-based cloud map, which adopts the following technical solution:
[0044] The photovoltaic power generation power prediction device based on ground-based cloud map includes:
[0045] The first acquisition module is used to obtain ground cloud images, satellite cloud images, atmospheric data and solar motion tracks of the photovoltaic base;
[0046] A first determination module is used to determine, from the ground-based cloud map and the satellite cloud map, a cloud group that can move to a preset area within a preset future time period, where the preset area is a lighting area corresponding to the photovoltaic base;
[0047] A second determination module is used to determine the outline, moving speed, thickness and type of each cloud cluster based on the satellite cloud image;
[0048] A simulation module, for simulating a motion dynamic diagram of each cloud cluster based on the contour, moving speed, type and atmospheric data of each cloud cluster;
[0049] A third determination module is used to determine a target cloud cluster based on the sun's motion trajectory and the motion dynamic graph of each cloud cluster, and determine a first variation graph of the shielding area and shielding time of each target cloud cluster to the sun, wherein the target cloud cluster is a cloud cluster that can shield the sun;
[0050] a fourth determination module, for determining a sky color value of a sky area from the ground-based cloud map, calculating the similarity between the sky color value and a plurality of historical sky color values at the same time, and determining a target historical sky color value and a third change graph of the target historical sky color value, wherein the sky color value is an RGB value, the target historical sky color value is the historical sky color value with the highest similarity, each historical sky color value corresponds to a second change graph of photovoltaic power generation over time, and each historical sky color value corresponds to a third change graph of radiation over time;
[0051] a fifth determination module, configured to determine, based on the thickness, type, first variation graph, and third variation graph of the target cloud cluster, an amount of reduction in solar radiation when each target cloud cluster blocks the sun;
[0052] A prediction map output module is used to determine and output a photovoltaic power generation power prediction map based on the radiation reduction amount and the second change map of the target historical sky color value.
[0053] By adopting the above technical solution, the first acquisition module obtains the ground cloud map, satellite cloud map, atmospheric data and solar motion trajectory of the photovoltaic base, the first determination module can accurately determine the cloud group that moves to the lighting area within a preset future time period from the ground cloud map and the satellite cloud map, and the second determination module can determine the outline, moving speed, thickness and type of the cloud group according to the satellite cloud map, so that the simulation module can simulate the motion state diagram of each cloud group according to the above attributes and atmospheric data, the third determination module can determine the target cloud group and the first change diagram in combination with the solar motion trajectory and the motion state diagram of the cloud group, the fourth determination module determines the sky color value from the ground cloud map, and calculates the similarity between the sky color value and the historical sky color value, so as to determine the target historical sky color value with the highest similarity, that is, the current sky color value is closest to the target historical sky color value. The change of the current sky color value over time is similar to the change of the target historical sky color value over time. Therefore, the second change graph and the third change graph of the target historical sky color value can be used to predict the power generation power in the current preset future time period. The fifth determination module determines the radiation reduction amount according to the thickness, type, first change graph and third change graph of the target cloud group. There is an influence relationship between the radiation reduction amount and the power generation power. Therefore, the prediction graph output module can accurately determine the photovoltaic power generation power prediction graph and output it according to the radiation reduction amount and the second change graph of the target historical sky color value, so as to facilitate the staff to know the prediction situation, and determine the target historical sky color value with a high degree of proximity from the historical sky color values according to the sky color value, and use the second change graph, the third change graph of the target historical sky color value and the relevant data of the target cloud group to comprehensively predict the power generation power more accurately.
[0054] Preferably, the atmospheric data includes wind direction, and the simulation module is specifically used to:
[0055] Inputting the outline, moving speed, type and atmospheric data of each cloud group into the trained first network model for dynamic simulation to obtain a candidate motion dynamic graph of each cloud group;
[0056] Determine an associated area of each cloud cluster based on the wind direction and the position of each cloud cluster, and obtain atmospheric data of the associated area;
[0057] The atmospheric data of the associated area and the candidate motion dynamic graph are input into the trained second network model for deep simulation to obtain the motion dynamic graph of each cloud cluster.
[0058] Preferably, when determining the amount of reduction in solar radiation when each target cloud blocks the sun based on the thickness, type, first change graph and third change graph of the target cloud, the fifth determination module is specifically used to:
[0059] determining a spectrum of each target cloud based on the type of each target cloud;
[0060] Determining the light shielding rate of each target cloud cluster based on the thickness and spectrum of the target cloud cluster;
[0061] Determine the shielding area at each shielding moment from the first variation graph of each target cloud cluster, and determine the radiation amount at each moment from the third variation graph of the target historical sky color value;
[0062] The radiation reduction amount at each shielding moment is determined based on the shielding rate, the shielding area at each shielding moment, and the radiation amount at each moment.
[0063] Preferably, when the prediction map output module determines and outputs the photovoltaic power generation prediction map based on the radiation reduction amount and the second change map, it is specifically used to:
[0064] Determine the power value at each moment from the second change graph of the target historical sky color value, determine the radiation amount at each moment from the third change graph of the target historical sky color value, and determine the predicted power value at each shading moment in a preset future time period based on the radiation reduction amount and the power value;
[0065] Deleting the power value corresponding to each shielding moment in the second variation graph of the target historical sky color value, and mapping the predicted power value in the second variation graph according to the shielding moment to obtain the photovoltaic power generation power prediction graph;
[0066] Output the photovoltaic power generation power prediction diagram.
[0067] Preferably, the photovoltaic power generation power prediction device based on the ground-based cloud map further includes:
[0068] A sixth determination module, used to obtain the atmospheric turbidity above the photovoltaic base;
[0069] A difference calculation module, used to calculate a first difference between a sky color value of the photovoltaic base and a preset sky color value in each channel, wherein the preset sky color value is a sky color value when the sky above the photovoltaic base is in a clear sky state;
[0070] a seventh determination module, configured to determine, based on the first difference, a percentage of blocking of light of a preset wavelength by the atmosphere above the photovoltaic base, where the light of the preset wavelength is light of a specific wavelength that can be used for photovoltaic power generation;
[0071] The correction module is used to calculate the second difference between the atmospheric turbidity and the preset turbidity, and to correct the power generation at each moment based on the atmospheric turbidity and the blocking percentage. The preset turbidity is the atmospheric turbidity when the sky above the photovoltaic base is in a clear sky state.
[0072] Preferably, the photovoltaic power generation power prediction device based on the ground-based cloud map further includes:
[0073] A time period determination module, used to determine a target time period in which the power generation is less than a preset power from the photovoltaic power generation power prediction map;
[0074] A ratio determination module, used to determine the total duration of all target time periods, and determine the ratio of the total duration to the preset future time period;
[0075] An eighth determination module is used to determine the average power and power variance in the photovoltaic power generation power prediction map;
[0076] The score determination module is used to determine a quality score based on the proportion, average power, power variance and their corresponding coefficients, wherein the quality score represents the power generation quality of the photovoltaic base in a preset future time period.
[0077] Preferably, the photovoltaic power generation power prediction device based on the ground-based cloud map further includes:
[0078] A similarity calculation module, used to calculate the similarity between the photovoltaic power generation prediction graph and a plurality of historical photovoltaic power generation graphs;
[0079] A ninth determination module is used to determine the historical photovoltaic power generation graph with the highest similarity;
[0080] A strategy acquisition module, used to acquire the strain strategy corresponding to the historical photovoltaic power generation power diagram with the highest similarity;
[0081] A control module is used to control the transmission lines of the photovoltaic base and the transmission lines of the main power grid based on the strain strategy.
[0082] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:
[0083] An electronic device, comprising:
[0084] at least one processor;
[0085] Memory;
[0086] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one application is used to: execute the photovoltaic power generation power prediction method based on ground-based cloud maps as described in any one of the first aspects.
[0087] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:
[0088] A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute the photovoltaic power generation power prediction method based on ground-based cloud maps as described in any one of the first aspects.
[0089] In summary, the present application includes at least one of the following beneficial technical effects:
[0090] From the ground-based cloud map and the satellite cloud map, the cloud clusters that will move to the lighting area within the preset future time period can be accurately determined, and the outline, moving speed, thickness and type of the cloud clusters can be determined based on the satellite cloud map, so that the motion state diagram of each cloud cluster can be simulated according to the above attributes and atmospheric data. The target cloud cluster and the first change diagram can be determined by combining the sun's motion trajectory and the cloud cluster's motion state diagram; the sky color value is determined from the ground-based cloud map, and the similarity between the sky color value and the historical sky color value is calculated, so as to determine the target historical sky color value with the highest similarity, that is, the current sky color value is closest to the target historical sky color value, and the change of the current sky color value over time is the same as the change of the target historical sky color value over time. Therefore, the second change graph and the third change graph of the target historical sky color value can be used to predict the power generation power in the current preset future time period; the radiation reduction amount is determined according to the thickness, type, first change graph and third change graph of the target cloud group, and there is an influence relationship between the radiation reduction amount and the power generation power, so according to the radiation reduction amount and the second change graph of the target historical sky color value, the photovoltaic power generation power prediction graph can be accurately determined and output, so as to facilitate the staff to know the prediction situation; and according to the sky color value, the target historical sky color value with a high degree of proximity is determined from the historical sky color values, and the second change graph and the third change graph of the target historical sky color value and the relevant data of the target cloud group are used to comprehensively predict the power generation power for more accurate. BRIEF DESCRIPTION OF THE DRAWINGS
[0091] Figure 1 It is a flow chart of a photovoltaic power generation power prediction method based on a ground-based cloud map according to an embodiment of the present application.
[0092] Figure 2 It is a structural schematic diagram of a photovoltaic power generation power prediction device based on a ground-based cloud map according to an embodiment of the present application.
[0093] Figure 3It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0094] The following is combined with Figure 1-3 This application is described in further detail.
[0095] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.
[0096] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are 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 ordinary technicians in this field without creative work are within the scope of protection of this application.
[0097] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.
[0098] The following is attached to the instruction manual Figure 1-3 The embodiments of the present application are described in further detail.
[0099] The embodiment of the present application provides a photovoltaic power generation prediction method based on a ground-based cloud map, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104, step S105, step S106, step S107 and step S108, wherein:
[0100] S101, obtain ground cloud images, satellite cloud images, atmospheric data and solar movement trajectory of the photovoltaic base.
[0101] For the embodiments of the present application, the staff may place an all-sky imager on site at the photovoltaic base, collect ground-based cloud images above the photovoltaic base through the all-sky imager, and the electronic device is connected to the all-sky imager through a wire or wirelessly, thereby obtaining the ground-based cloud images collected by the all-sky imager. The electronic device may use a proprietary channel or interface to obtain satellite cloud images above the photovoltaic base under permission, thereby knowing the cloud conditions above the photovoltaic base. The electronic device may obtain atmospheric data at the photovoltaic base through a server or the Internet. The atmospheric data includes air pressure, temperature, wind direction, wind speed, and pollution conditions. By obtaining the above-mentioned data in various aspects, it is convenient to simulate the sky conditions within a certain period of time in the future more accurately, thereby making the power prediction more accurate.
[0102] S102, determining from ground-based cloud images and satellite cloud images the cloud clusters that can move into a preset area within a preset future time period.
[0103] Among them, the preset area is the lighting area corresponding to the photovoltaic base.
[0104] For the embodiments of the present application, the preset future time period may be the next hour, two hours, or three hours, etc., and the satellite cloud image may be a dynamic image or video from a certain time point in the past to the current time point. The electronic device may input the satellite cloud image into a trained network model for simulation, or use a proprietary large meteorological model for simulation, so as to be able to determine from the satellite cloud image the cloud clusters that will arrive at the preset area in the preset future time period. The cloud clusters in the ground-based cloud image are cloud clusters that are already in the preset area, and are still moving or passing through the preset area in the preset future time period. Cloud clusters that move in or pass through the preset area are screened out through ground-based cloud images and satellite cloud images, thereby narrowing the scope of analysis and saving computing power.
[0105] S103, determining the outline, moving speed, thickness and type of each cloud cluster based on the satellite cloud image.
[0106] For the embodiment of the present application, after the cloud cluster is determined, the electronic device performs edge detection on the satellite cloud image to obtain the outline of each cloud cluster, and because the satellite cloud image is a dynamic image or video, the moving speed of each cloud cluster can be determined. In other embodiments, the moving speed can be calculated by a meteorological satellite and obtained when the electronic device obtains the satellite cloud image.
[0107] Determining the thickness of clouds through satellite cloud images can be achieved by analyzing the hue, texture, shadows and other characteristics of clouds in visible light and infrared channel images. On satellite cloud images, the thickness of clouds is related to albedo and temperature. On visible light cloud images, bright white tones usually indicate thicker clouds, because thicker clouds reflect more solar radiation. On infrared cloud images, whiter tones represent lower temperatures, which usually means that the cloud tops are higher, which can infer that the clouds are thicker. Alternatively, the laser radar carried by meteorological satellites can be used to emit pulsed lasers to the clouds and receive the reflected signals. By analyzing and calculating these signals, the vertical structure and optical thickness of the clouds can be accurately measured. The thickness of the clouds represents the degree of shading from the sun.
[0108] Electronic devices can determine the type of cloud clusters through the outline of each cloud cluster, such as cumulus, cirrus, stratus, altocumulus, high-level cloud, cirrocumulus, etc. Different types of clouds block light to different degrees, and the cloud cluster outlines are deformed to different degrees over time and under the influence of atmospheric conditions such as wind direction, and different types of clouds block light of different wavelengths to different degrees. Therefore, combining the types of clouds can more accurately analyze the outline of the cloud cluster when it reaches the photovoltaic base, thereby improving the accuracy of analyzing the cloud cluster blocking the sun.
[0109] S104, simulating a motion dynamic diagram of each cloud cluster based on the outline, moving speed, type and atmospheric data of each cloud cluster.
[0110] For the embodiments of the present application, after knowing the outline, moving speed, type of each cloud group and the atmospheric data at the photovoltaic base, the electronic device can more accurately simulate the motion dynamic graph of each cloud group. Through the more accurate motion dynamic graph, a more accurate situation of each cloud group blocking the sun can be obtained.
[0111] S105, determining a target cloud cluster based on the sun's motion trajectory and the motion dynamic diagram of each cloud cluster, and determining a first variation diagram of the shielding area and shielding time of each target cloud cluster to the sun.
[0112] Among them, the target cloud is a cloud that can block the sun.
[0113] For the embodiment of the present application, the position of the sun also changes with time, but the change of the sun's position is regular, so the electronic device can accurately determine the movement trajectory of the sun in a preset future time period in combination with the current date, time point and the position of the sun. After determining the movement trajectory of the sun, the electronic device can use specific software or plug-ins to map and simulate the movement trajectory of the sun and the dynamic motion diagram of each cloud group, so that the target cloud group that can block the sun can be determined from all the cloud groups. And in the process of mapping simulation, the electronic device can obtain the time point when each target cloud group starts to block the sun and the time point when it completely leaves the sun, so as to obtain the change of the blocking area of each target cloud group in the process of blocking the sun over time, and the electronic device determines the first change diagram according to the change of the blocking area over time.
[0114] S106, determining the sky color value of the sky area from the ground-based cloud map, calculating the similarity between the sky color value and multiple historical sky color values at the same time, and determining the target historical sky color value and a third change map of the target historical sky color value.
[0115] Among them, the sky color value is the RGB value, the target historical sky color value is the historical sky color value with the highest similarity, each historical sky color value corresponds to the second change graph of photovoltaic power generation over time, and each historical sky color value corresponds to the third change graph of radiation over time.
[0116] In the embodiment of the present application, the electronic device determines the sky color value of the sky area from the ground-based cloud map, and the sky color value includes the colors of three channels: red, green, and blue. Different sky color values represent different amounts of radiation reaching the ground after being blocked by the atmosphere.
[0117] The electronic device's database or the server's database stores multiple historical sky color values at each moment of the daytime photovoltaic power generation working period. The electronic device calculates the time point of the current sky color value, selects the historical sky color values at the same moment from the database, and calculates the similarity between the current sky color value and each historical sky color value at the same moment, thereby determining the historical sky color value with the highest similarity, that is, the target historical sky color value. Specifically, the similarity can be calculated through a histogram, or two sky color values can be input into a trained network model for similarity calculation. Determining the target historical sky color value means that the target historical sky color value is relatively close to the current sky color value, and the radiation is also relatively close. The sky color value also changes over time, and the current sky color value changes over time and the target historical sky color value changes over time are close to each other.
[0118] In the historical photovoltaic power generation operation, the electronic device obtains the change of the power generation over time and generates a second change graph of the power generation over time, and obtains the change of the radiation over time and generates a third change graph of the radiation over time. The electronic device also obtains the change of the sky color value over time. After the electronic device determines the target historical sky color value, it determines the time period after the target historical sky color value in combination with the preset future time period, and determines the required second change graph and third change graph according to the time period.
[0119] S107, determining the reduction in solar radiation when each target cloud blocks the sun based on the thickness, type, first variation graph, and third variation graph of the target cloud.
[0120] For the embodiments of the present application, the first variation graph of the target cloud cluster's thickness, type, and blocked area over time and the third variation graph of the target cloud cluster's radiation corresponding to the historical sky color value over time are both factors that cause the target cloud cluster to reduce solar radiation. Therefore, the electronic device can comprehensively and accurately determine the amount of solar radiation reduction for each target cloud cluster when it blocks the sun based on the above factors.
[0121] S108: Determine and output a photovoltaic power prediction diagram based on the radiation reduction amount and the second variation diagram.
[0122] For the embodiment of the present application, there is a relationship between the amount of radiation reduction and the reduction in photovoltaic power generation, and the electronic device has determined a relatively close second change graph that can characterize the change of power generation over time in a preset future time period. Therefore, the electronic device can accurately determine the photovoltaic power generation power prediction graph in the preset future time period based on the amount of radiation reduction and the second change graph, and then the electronic device outputs the photovoltaic power generation power prediction graph, so that the staff can know the power prediction situation in the preset future time period, and then facilitate the adjustment of photovoltaic power generation and transmission lines.
[0123] In the embodiment of the present application, preferably, the atmospheric data includes wind direction. Step S104 simulates the motion dynamic diagram of each cloud based on the outline, moving speed, type and atmospheric data of each cloud, specifically including step S1041 (not shown in the figure), step S1042 (not shown in the figure) and step S1043 (not shown in the figure), wherein:
[0124] S1041, inputting the outline, moving speed, type and atmospheric data of each cloud cluster into the trained first network model for dynamic simulation to obtain a candidate motion dynamic graph of each cloud cluster.
[0125] For the embodiment of the present application, since the outline, moving speed, type and atmospheric data of the cloud are all important factors that affect the movement of the cloud, the electronic device inputs the outline, moving speed, type and atmospheric data of each cloud into the trained first network model for dynamic simulation, thereby obtaining the candidate motion dynamics of each cloud. The first network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models. For the first network model, the staff can collect a training sample set in advance. Taking a training sample a as an example, the input of training sample a is "the outline image of cloud a, 2m / s, cumulus, atmospheric data (temperature, air pressure, wind speed, wind direction, etc.)", and the corresponding label is "the outline image of cloud a one hour later, the outline image of cloud a two hours later, etc." After determining the training sample set, the electronic device performs supervised training and learning on the first network model according to the training sample set to obtain the trained first network model.
[0126] S1042, determining the associated area of each cloud cluster based on the wind direction and the position of each cloud cluster, and acquiring atmospheric data of the associated area.
[0127] For the embodiment of the present application, the electronic device determines the upstream area of each cloud cluster, i.e., the associated area, according to the wind direction and the preset map. The atmospheric conditions in the associated area affect the movement of each cloud cluster. Therefore, the electronic device obtains the atmospheric data of the associated area of each cloud map, and the movement of the cloud cluster is predicted more accurately based on the atmospheric data of the associated area.
[0128] S1043, inputting the atmospheric data of the associated area and the candidate motion dynamic graph into the trained second network model for deep simulation to obtain the motion dynamic graph of each cloud cluster.
[0129] For the embodiment of the present application, after the electronic device determines the atmospheric data of the associated area of each cloud cluster, the atmospheric data of the associated area of each cloud cluster and the candidate motion dynamic graph of each cloud cluster are input into the trained second network model for deep simulation, thereby obtaining the final motion state graph of each cloud cluster. After obtaining the candidate motion dynamic graph, the candidate motion dynamic graph is further corrected, learned and simulated according to the atmospheric data of the associated area of each cloud cluster, thereby obtaining a more accurate motion dynamic graph. The second network model can be a convolutional neural network model, a recurrent neural network model, or other types of network models. Similarly, the staff can collect a training sample set for the second network model in the manner of step S1041, and input the training sample set of the second network model into the initial second network model for supervised training and learning to obtain a trained second network model.
[0130] In the embodiment of the present application, preferably, in step S107, the reduction in solar radiation of each target cloud when blocking the sun is determined based on the thickness, type, first change graph and third change graph of the target cloud, and specifically includes step S1071 (not shown in the figure), step S1072 (not shown in the figure), step S1073 (not shown in the figure) and step S1074 (not shown in the figure), wherein:
[0131] S1071, determining the spectrum of each target cloud cluster based on the type of each target cloud cluster.
[0132] For the embodiment of the present application, the composition and proportion of water vapor and other substances in different types of clouds are different, so the absorption degree of light of different wavelengths is different, that is, the spectral characteristics of different types of clouds are different, and different types of clouds such as cumulus clouds and stratus clouds absorb light differently. The electronic device determines the spectrum of each target cloud according to the type of each target cloud. Specifically, the spectrum corresponding to each type of cloud can be stored in advance in the storage medium in the electronic device or in the cloud server, so that the electronic device determines the corresponding spectrum according to the type of each target cloud.
[0133] S1072, determining the shading rate of each target cloud cluster based on the thickness and spectrum of the target cloud cluster.
[0134] For the embodiment of the present application, the photovoltaic panel can convert the light energy of light of a specific wavelength into electrical energy, so the electronic device determines the transmittance, absorptivity and other properties of each target cloud cluster for light of a specific wavelength that can generate electricity based on the spectrum of each target cloud cluster. The different thicknesses of the clouds have different degrees of absorption and shielding of light, that is, the thickness of the clouds also affects the transmittance and other properties of the clouds. The thicker the cloud cluster, the stronger the light shielding and absorption effect, and vice versa, the stronger the light penetration effect. Therefore, the electronic device can input the thickness and spectrum of each target cloud cluster into the trained network model to calculate the transmittance, thereby obtaining the final transmittance of each target cloud cluster. Alternatively, the electronic equipment determines the absorptivity, transmittance or shading rate of each target cloud cluster to light of a specific wavelength for photovoltaic power generation based on the spectrum, and performs weighted calculation based on the thickness of the cloud cluster to obtain the shading rate of each target cloud cluster. Specifically, the absorptivity, transmittance and other properties of the target cloud cluster and the thickness of the cloud cluster have different effects on the shading rate. Therefore, the staff can set different coefficients for the absorptivity or transmittance and other properties of each type of cloud cluster to light of a specific wavelength and the thickness of the cloud cluster in advance. The electronic equipment performs weighted calculation based on the determined absorptivity or transmittance and other coefficients and the thickness of the cloud cluster to obtain a score, and using this score to characterize the shading rate is also more accurate.
[0135] S1073, determining the shielding area at each shielding moment from the first change graph of each target cloud group, and determining the radiation amount at each moment from the third change graph of the target historical sky color value.
[0136] For the embodiment of the present application, the electronic device can determine the shielding area at each shielding moment in the first variation graph. Since the cloud is always in a moving state, the shielding area of the sun is different at different times. The larger the shielding area, the greater the reduction in solar radiation, and vice versa. The electronic device also determines the radiation at each moment from the third variation graph of the target historical sky color value, so as to facilitate the subsequent analysis of the radiation reduction at each shielding moment in a preset future time period.
[0137] S1074, determining the radiation reduction amount at each shielding moment based on the shielding rate, the shielding area at each shielding moment, and the radiation amount at each moment.
[0138] For the embodiment of the present application, the electronic device calculates the ratio of the shading area to the area of the entire sun. After the electronic device determines the radiation at each moment, it multiplies the radiation corresponding to each shading moment by the above ratio to obtain the radiation of the shading area when it is not shading, and then multiplies it by the shading rate to obtain the radiation reduction of the shading area, that is, the radiation reduction of the sun at each shading moment. The shading rate of each target cloud is determined by the spectrum and the thickness of the cloud, and then combined with the shading area and the radiation when the atmospheric conditions in history are similar to the radiation, a more accurate radiation reduction is comprehensively determined, which is convenient for the subsequent determination of photovoltaic power generation power based on the radiation reduction.
[0139] In the embodiment of the present application, preferably, in step S108, a photovoltaic power generation power prediction diagram is determined and output based on the second change diagram of the radiation reduction amount and the target historical sky color value, which specifically includes step S1081 (not shown in the figure), step S1082 (not shown in the figure) and step S1083 (not shown in the figure), wherein:
[0140] S1081, determine the power value at each moment from the second change graph of the target historical sky color value, determine the radiation amount at each moment from the third change graph of the target historical sky color value, and determine the predicted power value at each occlusion moment in a preset future time period based on the radiation reduction amount and the power value.
[0141] For an embodiment of the present application, the electronic device determines the power value at each moment from the second change graph of the target historical sky color value, and determines the radiation amount at each moment from the third change graph of the target historical sky color value. The electronic device determines the ratio of the radiation reduction amount at each occlusion moment to the radiation amount at the corresponding moment, multiplies the ratio and the power value at the corresponding moment to obtain the power reduction value, and then subtracts the power value at the occlusion moment from the corresponding power reduction value to obtain the predicted power value at each occlusion moment.
[0142] S1082, deleting the power value corresponding to each shielding moment in the second variation graph of the target historical sky color value, and mapping the predicted power value in the second variation graph according to the shielding moment to obtain a photovoltaic power prediction graph.
[0143] For the embodiment of the present application, the electronic device deletes the original power value at the shading moment on the second change graph, and maps the predicted power value according to the shading moment on the current second change graph to obtain a photovoltaic power generation power prediction graph.
[0144] S1083, outputting a photovoltaic power generation power prediction diagram.
[0145] For the embodiment of the present application, the electronic device can send the photovoltaic power generation prediction diagram to the terminal device of the staff, so that the staff can view it through the application program on the terminal device. Alternatively, the electronic device can control a display device such as a display screen to display the photovoltaic power generation prediction diagram, so that the staff can view it easily.
[0146] In the embodiment of the present application, preferably, the photovoltaic power generation power prediction method based on the ground cloud map further includes step 1, step 2, step 3 and step 4, wherein:
[0147] Step 1: Obtain the atmospheric turbidity above the photovoltaic base.
[0148] For the embodiment of the present application, the atmospheric turbidity indicates the atmospheric turbidity above the photovoltaic base, which can be measured and calculated by a relevant professional platform and then obtained by an electronic device after being published.
[0149] Step 2: Calculate the first difference between the sky color value of the photovoltaic base and the preset sky color value in each channel.
[0150] Among them, the preset sky color value is the sky color value when the sky above the photovoltaic base is in a clear sky state.
[0151] For the embodiment of the present application, the preset sky color value represents the sky color value when the photovoltaic base can maintain a high power generation and stable power generation. The electronic device makes a corresponding difference between the current sky color value and the values of the three RGB channels of the preset sky color value to obtain the first difference of the color value of each channel. When there is a difference in the sky color values of different channels, there is a difference between the absorption of light of different wavelengths by the atmosphere. Therefore, after the electronic device calculates the first difference of each channel, it is convenient for the subsequent analysis of the absorption of light of different wavelengths by the atmosphere above the current photovoltaic base.
[0152] Step three: determining the blocking percentage of light of a preset wavelength by the atmosphere above the photovoltaic base based on the first difference.
[0153] The light of the preset wavelength is light of a specific wavelength that can be used for photovoltaic power generation.
[0154] For the embodiment of the present application, the staff can collect different sky color values and use a spectrometer to collect the corresponding atmospheric spectra, and compare the atmospheric spectra of different sky color values with the atmospheric spectra of preset sky color values, so as to obtain the blocking percentage of different sky color values to the preset wavelength of light, and then the electronic device separates the collected sky color values into three channels of RGB to obtain the corresponding values on the three channels, and then subtracts the corresponding values on the three channels from the respective values on the three channels of the preset sky color value to obtain the first difference of the color values on the three channels, and finally the electronic device determines the correspondence between the first difference of the color values on the three channels and the blocking percentage and stores it to obtain a database about the above correspondence. After the electronic device determines the first difference between the current sky color value and the preset sky color value on each channel, it matches in the above database about the corresponding relationship based on the first difference, so as to determine the matching correspondence and obtain the blocking percentage.
[0155] In other embodiments, the staff can measure the absorption rate of the preset sky color value to the preset wavelength of light, that is, the blocking percentage, based on experiments or calculations. Then the staff collects different sky color values and the corresponding blocking percentages, determines the difference between the sky color value and the preset sky color value in each channel, and generates training samples based on the difference and blocking percentage in each channel, one of the training samples is, for example, "R: 20, G: 50, B: 15; blocking percentage: 32%". After the initial network model is supervisedly trained according to the obtained training sample set, a trained network model is obtained, and the electronic device inputs the current difference into the above network model to calculate the blocking percentage.
[0156] Step 4: Calculate the second difference between the atmospheric turbidity and the preset turbidity, and correct the power generation at each moment based on the atmospheric turbidity and the blocking percentage.
[0157] Among them, the preset turbidity is the atmospheric turbidity when the sky above the photovoltaic base is in a clear state.
[0158] For the embodiment of the present application, the electronic device calculates the second difference between the atmospheric turbidity and the preset turbidity, and the second difference represents the difference between the current sky turbidity and the sky turbidity in a clear sky state. The atmospheric turbidity and the blocking percentage are both important factors affecting the radiation amount, and the degree of influence varies. Therefore, the staff can set different coefficients according to the degree of influence of the atmospheric turbidity and the blocking percentage, and then the electronic device performs weighted calculation according to the atmospheric turbidity, the blocking percentage and their respective corresponding coefficients to obtain a radiation correction value.
[0159] The electronic device corrects the power generation at each moment in the photovoltaic power generation prediction diagram according to the determined radiation correction value. The radiation correction value represents the correction value of the radiation corresponding to the power generation at each moment in the photovoltaic power generation prediction diagram under the current sky color value, so it can be corrected by adding the radiation correction value to the radiation at each moment according to the positive or negative of the second difference, or by subtracting the radiation correction value to correct the radiation in the third change diagram. After obtaining the corrected radiation at each moment, the power generation at each moment can be corrected according to the corrected radiation, so as to obtain a more accurate power generation, for example, the power correction value is determined according to the radiation correction value and the corresponding preset coefficient, and then the corrected power is obtained.
[0160] In the embodiment of the present application, preferably, step S108 further includes step Sa (not shown in the figure), step Sb (not shown in the figure), step Sc (not shown in the figure) and step Sd (not shown in the figure), wherein:
[0161] Sa, determine the target time period when the power generation power is less than the preset power from the photovoltaic power generation power prediction diagram.
[0162] For the embodiment of the present application, the preset power serves as the dividing point between power that is too high or too low. Failure to reach the preset power indicates that the power of photovoltaic power generation is too low and cannot provide sufficient power to the power consumption area. Therefore, the electronic device determines the target time period when the power generation power is less than the preset power from the photovoltaic power generation power prediction diagram.
[0163] Sb, determine the total duration of all target time periods, and determine the ratio of the total duration to the preset future time period.
[0164] For the embodiment of the present application, the electronic device calculates the sum of the duration of each target time period to obtain the total duration of all target time periods. The longer the total duration, the more time the power generation is too low and the worse the power generation quality. Therefore, the electronic device calculates the ratio of the total duration to the preset future time period. The larger the ratio, the worse the power generation quality in the preset future time period.
[0165] Sc, determines the average power and power variance in the photovoltaic power generation power prediction diagram.
[0166] For the embodiment of the present application, the electronic device uses the average value calculation formula to obtain the average power based on the power value at each moment in the photovoltaic power prediction diagram, and uses the variance calculation formula to obtain the power variance. The average power represents the overall power generation in a preset future time period. The larger the average power, the better the power generation quality. The power variance represents the stability of power generation in a preset future time period. The larger the variance, the more unstable the power generation and the worse the power generation quality.
[0167] Sd, determines the quality score based on the proportion, average power, power variance and their corresponding coefficients.
[0168] Among them, the quality score represents the power generation quality of the photovoltaic base in a preset future time period.
[0169] For the embodiments of the present application, it can be seen from the above that the proportion, average power and power variance are all important factors affecting the power generation quality of the photovoltaic base in the preset future time period, and the importance is different. Therefore, the electronic device can set different coefficients for the above three factors. Since the proportion and power variance are inversely proportional to the power generation quality, in order to facilitate calculation, the electronic device can take the inverse of the proportion and power variance and then combine them with the average power for weighted calculation to obtain a quality score. The staff can more intuitively know the power generation quality in the preset future time period through the quality score.
[0170] In the embodiment of the present application, preferably, step S108 further includes step S1 (not shown in the figure), step S2 (not shown in the figure), step S3 (not shown in the figure) and step S4 (not shown in the figure), wherein:
[0171] S1, calculating the similarity between the photovoltaic power generation prediction map and multiple historical photovoltaic power generation maps.
[0172] For the embodiment of the present application, a plurality of historical photovoltaic power generation graphs are stored in a storage medium inside the electronic device or in a server, and the historical photovoltaic power generation graph is generated by the change of power generation over time collected in real time during the historical power generation process. The electronic device calculates the similarity between the photovoltaic power generation power prediction graph and the plurality of historical photovoltaic power generation powers. Specifically, the electronic device can calculate the similarity by a structural similarity metric (SSIM), or by a cosine distance or a histogram, etc., which is not limited here.
[0173] S2, and determine the historical photovoltaic power generation graph with the highest similarity.
[0174] With respect to the embodiments of the present application, since the electric energy generated by the photovoltaic base is generally distributed to nearby power consumption areas, and photovoltaic power generation is unstable, it is sometimes necessary to connect the electricity in the main power grid to the power consumption area. Therefore, the electronic device determines the historical photovoltaic power generation power graph with the highest similarity. Such a historical photovoltaic power generation power graph is close to the currently predicted power graph. The contingency strategy for the power grid lines corresponding to the historical photovoltaic power generation power graph with the highest similarity, such as switching the lines in the power consumption area, is also suitable for application in the photovoltaic power generation process in a preset future time period.
[0175] S3, obtaining the strain strategy corresponding to the historical photovoltaic power generation power diagram with the highest similarity.
[0176] For the embodiment of the present application, in the process of historical photovoltaic power generation, the strategy for controlling the transmission lines of the photovoltaic base, the main power grid and the power consumption area is the strain strategy, and the electronic device records the operation time of each strain strategy and determines the historical photovoltaic power generation power diagram corresponding to each strain strategy according to the operation time. Therefore, the electronic device can obtain the corresponding strain strategy according to the historical photovoltaic power generation power diagram with the highest similarity.
[0177] S4, controlling the transmission lines of the photovoltaic base and the transmission lines of the main power grid based on the contingency strategy.
[0178] For the embodiment of the present application, after the electronic device determines the strain strategy, it determines the time point corresponding to the strain strategy in the photovoltaic power generation prediction diagram based on the duration from the strain strategy to the starting time point of the historical photovoltaic power generation diagram with the highest similarity. The electronic device monitors the time point. When the time point is reached, the electronic device controls the transmission lines of the photovoltaic base and the transmission lines of the main power grid according to the strain strategy.
[0179] The above-mentioned embodiment introduces the photovoltaic power prediction method based on the ground-based cloud map from the perspective of the method flow. The following embodiment introduces the photovoltaic power prediction device based on the ground-based cloud map from the perspective of the virtual module or virtual unit. For details, please refer to the following embodiment.
[0180] The embodiment of the present application provides a photovoltaic power generation prediction device 20 based on a ground-based cloud map, such as Figure 2 As shown, the photovoltaic power generation power prediction device 20 based on the ground cloud map may specifically include:
[0181] The first acquisition module 201 is used to acquire ground cloud images, satellite cloud images, atmospheric data and the sun's motion trajectory of the photovoltaic base;
[0182] The first determination module 202 is used to determine, from the ground-based cloud map and the satellite cloud map, the cloud cluster that can move to a preset area within a preset future time period, where the preset area is the lighting area corresponding to the photovoltaic base;
[0183] The second determination module 203 is used to determine the outline, moving speed, thickness and type of each cloud cluster based on the satellite cloud image;
[0184] A simulation module 204, for simulating a motion dynamic diagram of each cloud based on the contour, movement speed, type and atmospheric data of each cloud;
[0185] The third determination module 205 is used to determine the target cloud cluster based on the sun's motion trajectory and the motion dynamic graph of each cloud cluster, and determine a first variation graph of the shielding area and shielding time of each target cloud cluster to the sun, wherein the target cloud cluster is a cloud cluster that can shield the sun;
[0186] The fourth determination module 206 is used to determine the sky color value of the sky area from the ground-based cloud map, calculate the similarity between the sky color value and multiple historical sky color values at the same time, and determine the target historical sky color value and the third change graph of the target historical sky color value, the sky color value is an RGB value, the target historical sky color value is the historical sky color value with the highest similarity, each historical sky color value corresponds to the second change graph of photovoltaic power generation over time, and each historical sky color value corresponds to the third change graph of radiation over time;
[0187] A fifth determination module 207, configured to determine a reduction in solar radiation when each target cloud blocks the sun based on the thickness, type, first variation graph, and third variation graph of the target cloud;
[0188] The prediction graph output module 208 is used to determine and output a photovoltaic power generation prediction graph based on the radiation reduction amount and the second change graph of the target historical sky color value.
[0189] The embodiment of the present application discloses a photovoltaic power generation power prediction device 20 based on a ground-based cloud map, wherein a first acquisition module 201 acquires a ground-based cloud map, a satellite cloud map, atmospheric data and a solar motion trajectory of a photovoltaic base, a first determination module 202 can accurately determine the cloud clusters that move to the lighting area within a preset future time period from the ground-based cloud map and the satellite cloud map, and a second determination module 203 can determine the contour, moving speed, thickness and type of the cloud clusters according to the satellite cloud map, so that a simulation module 204 can simulate a motion state diagram of each cloud cluster according to the above attributes and atmospheric data, a third determination module 205 can determine a target cloud cluster and a first change diagram in combination with the solar motion trajectory and the motion state diagram of the cloud cluster, and a fourth determination module 206 determines a sky color value from the ground-based cloud map, and calculates the similarity between the sky color value and the historical sky color value, so as to determine the target historical sky color value with the highest similarity, that is, the current sky color value. The color value is closest to the target historical sky color value, and the change of the current sky color value over time is also close to the change of the target historical sky color value over time. Therefore, the second change graph and the third change graph of the target historical sky color value can be used to predict the power generation power in the current preset future time period. The fifth determination module 207 determines the radiation reduction amount according to the thickness, type, first change graph and third change graph of the target cloud group. There is an influence relationship between the radiation reduction amount and the power generation power. Therefore, the prediction graph output module 208 can accurately determine the photovoltaic power generation power prediction graph according to the radiation reduction amount and the second change graph of the target historical sky color value and output it, so as to facilitate the staff to know the prediction situation, and determine the target historical sky color value with a high degree of proximity from the historical sky color values according to the sky color value, and use the second change graph, the third change graph of the target historical sky color value and the relevant data of the target cloud group to comprehensively predict the power generation power more accurately.
[0190] In the embodiment of the present application, preferably, the atmospheric data includes wind direction, and the simulation module 204 is specifically used to:
[0191] Input the outline, moving speed, type and atmospheric data of each cloud cluster into the trained first network model for dynamic simulation to obtain a candidate motion dynamic graph of each cloud cluster;
[0192] Determine the associated area of each cloud cluster based on the wind direction and the position of each cloud cluster, and obtain atmospheric data of the associated area;
[0193] The atmospheric data of the associated area and the candidate motion dynamics graph are input into the trained second network model for deep simulation to obtain the motion dynamics graph of each cloud cluster.
[0194] In the embodiment of the present application, preferably, when determining the amount of solar radiation reduction of each target cloud cluster when blocking the sun based on the thickness, type, first change graph and third change graph of the target cloud cluster, the fifth determination module 207 is specifically used to:
[0195] determining a spectrum of each target cloud based on the type of each target cloud;
[0196] Determine the light-shielding rate of each target cloud based on the thickness and spectrum of the target cloud;
[0197] Determine the shielding area at each shielding moment from the first variation graph of each target cloud cluster, and determine the radiation amount at each moment from the third variation graph of the target historical sky color value;
[0198] The radiation reduction amount at each shielding moment is determined based on the shielding rate, the shielding area at each shielding moment, and the radiation amount at each moment.
[0199] In the embodiment of the present application, preferably, when the prediction diagram output module 208 determines and outputs the photovoltaic power prediction diagram based on the radiation reduction amount and the second change diagram, it is specifically used to:
[0200] Determine the power value at each moment from the second change graph of the target historical sky color value, determine the radiation amount at each moment from the third change graph of the target historical sky color value, and determine the predicted power value at each shading moment in a preset future time period based on the radiation reduction amount and the power value;
[0201] Delete the power value corresponding to each shielding moment in the second change graph of the target historical sky color value, and map the predicted power value in the second change graph according to the shielding moment to obtain a photovoltaic power prediction graph;
[0202] Output photovoltaic power generation prediction diagram.
[0203] In the embodiment of the present application, preferably, the photovoltaic power generation prediction device 20 based on the ground cloud map further includes:
[0204] The sixth determination module is used to obtain the atmospheric turbidity above the photovoltaic base;
[0205] A difference calculation module, used to calculate the first difference between the sky color value of the photovoltaic base and the preset sky color value in each channel, the preset sky color value is the sky color value when the sky above the photovoltaic base is in a clear sky state;
[0206] a seventh determination module, configured to determine, based on the first difference, a percentage of blocking of light of a preset wavelength by the atmosphere above the photovoltaic base, where the light of the preset wavelength is light of a specific wavelength that can be used for photovoltaic power generation;
[0207] The correction module is used to calculate the second difference between the atmospheric turbidity and the preset turbidity, and to correct the power generation at each moment based on the atmospheric turbidity and the blocking percentage. The preset turbidity is the atmospheric turbidity when the sky above the photovoltaic base is in a clear sky state.
[0208] In the embodiment of the present application, preferably, the photovoltaic power generation prediction device 20 based on the ground cloud map further includes:
[0209] A time period determination module, used to determine a target time period in which the power generation is less than a preset power from a photovoltaic power generation power prediction diagram;
[0210] A ratio determination module is used to determine the total duration of all target time periods and the ratio of the total duration to the preset future time period;
[0211] An eighth determination module is used to determine the average power and power variance in the photovoltaic power generation power prediction diagram;
[0212] The score determination module is used to determine the quality score based on the proportion, average power, power variance and their corresponding coefficients. The quality score represents the power generation quality of the photovoltaic base in a preset future time period.
[0213] In the embodiment of the present application, preferably, the photovoltaic power generation prediction device 20 based on the ground cloud map further includes:
[0214] A similarity calculation module is used to calculate the similarity between the photovoltaic power generation prediction diagram and multiple historical photovoltaic power generation diagrams;
[0215] A ninth determination module is used to determine the historical photovoltaic power generation graph with the highest similarity;
[0216] A strategy acquisition module is used to obtain the strain strategy corresponding to the historical photovoltaic power generation power diagram with the highest similarity;
[0217] The control module is used to control the transmission lines of the photovoltaic base and the transmission lines of the main power grid based on the strain strategy.
[0218] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the photovoltaic power prediction device 20 based on the ground cloud map described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0219] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.
[0220] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.
[0221] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.
[0222] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.
[0223] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.
[0224] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0225] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.
[0226] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0227] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. Photovoltaic power generation prediction method based on ground-based cloud map, It is characterized in that include: Obtain ground-based cloud images, satellite cloud images, atmospheric data, and solar movement trajectories of photovoltaic bases; Determine from the ground-based cloud map and the satellite cloud map the cloud clusters that can move to a preset area within a preset future time period, the preset area being the lighting area corresponding to the photovoltaic base; Determine the outline, moving speed, thickness and type of each cloud cluster based on the satellite cloud image; Simulating a motion dynamic diagram of each cloud based on the contour, movement speed, type and atmospheric data of each cloud; Determine a target cloud cluster based on the sun's motion trajectory and the motion dynamic graph of each cloud cluster, and determine a first variation graph of the sun-blocking area and the sun-blocking time of each target cloud cluster, wherein the target cloud cluster is a cloud cluster that can block the sun; Determine the sky color value of the sky area from the ground-based cloud map, calculate the similarity between the sky color value and multiple historical sky color values at the same time, and determine the target historical sky color value and a third change graph of the target historical sky color value, wherein the sky color value is an RGB value, the target historical sky color value is the historical sky color value with the highest similarity, each historical sky color value corresponds to a second change graph of photovoltaic power generation over time, and each historical sky color value corresponds to a third change graph of radiation over time; Determine, based on the thickness, type, first variation graph, and third variation graph of the target cloud cluster, a radiation reduction amount of the sun when each target cloud cluster blocks the sun; A photovoltaic power generation power prediction diagram is determined and output based on the radiation reduction amount and the second change diagram of the target historical sky color value.
2. The photovoltaic power generation prediction method based on ground-based cloud map according to claim 1, It is characterized in that The atmospheric data includes wind direction, and the motion dynamic diagram of each cloud group simulated based on the outline, moving speed, type and atmospheric data of each cloud group includes: Inputting the outline, moving speed, type and atmospheric data of each cloud group into the trained first network model for dynamic simulation to obtain a candidate motion dynamic graph of each cloud group; Determine an associated area of each cloud cluster based on the wind direction and the position of each cloud cluster, and obtain atmospheric data of the associated area; The atmospheric data of the associated area and the candidate motion dynamic graph are input into the trained second network model for deep simulation to obtain the motion dynamic graph of each cloud cluster.
3. The photovoltaic power generation prediction method based on ground-based cloud map according to claim 1, It is characterized in that The step of determining the amount of solar radiation reduction when each target cloud blocks the sun based on the thickness, type, first variation graph, and third variation graph of the target cloud group includes: determining a spectrum of each target cloud based on the type of each target cloud; Determining the light shielding rate of each target cloud cluster based on the thickness and spectrum of the target cloud cluster; Determine the shielding area at each shielding moment from the first variation graph of each target cloud cluster, and determine the radiation amount at each moment from the third variation graph of the target historical sky color value; The radiation reduction amount at each shielding moment is determined based on the shielding rate, the shielding area at each shielding moment, and the radiation amount at each moment.
4. The photovoltaic power generation prediction method based on ground-based cloud map according to claim 1, It is characterized in that The step of determining and outputting a photovoltaic power prediction diagram based on the radiation reduction amount and the second change diagram includes: Determine the power value at each moment from the second change graph of the target historical sky color value, determine the radiation amount at each moment from the third change graph of the target historical sky color value, and determine the predicted power value at each shading moment in a preset future time period based on the radiation reduction amount and the power value; Deleting the power value corresponding to each shielding moment in the second variation graph of the target historical sky color value, and mapping the predicted power value in the second variation graph according to the shielding moment to obtain the photovoltaic power generation power prediction graph; Output the photovoltaic power generation power prediction diagram.
5. The photovoltaic power generation prediction method based on ground-based cloud map according to claim 3, It is characterized in that The method further comprises: Obtaining the atmospheric turbidity above the photovoltaic base; Calculate a first difference between a sky color value of the photovoltaic base and a preset sky color value in each channel, wherein the preset sky color value is a sky color value when the sky above the photovoltaic base is in a clear sky state; Determine, based on the first difference, a percentage of the atmosphere above the photovoltaic base blocking light of a preset wavelength, where the preset wavelength is light of a specific wavelength that can be used for photovoltaic power generation; A second difference between the atmospheric turbidity and a preset turbidity is calculated, and the power generation power at each moment is corrected based on the atmospheric turbidity and the blocking percentage. The preset turbidity is the atmospheric turbidity when the sky above the photovoltaic base is in a clear sky state.
6. The photovoltaic power generation prediction method based on ground-based cloud map according to claim 1, It is characterized in that The method further comprises: Determining a target time period in which the power generation is less than a preset power from the photovoltaic power generation power prediction diagram; Determine the total duration of all target time periods, and determine the ratio of the total duration to the preset future time period; Determine the average power and power variance in the photovoltaic power generation power prediction graph; A quality score is determined based on the proportion, average power, power variance and respective corresponding coefficients, and the quality score represents the power generation quality of the photovoltaic base within a preset future time period.
7. The photovoltaic power generation prediction method based on ground-based cloud map according to claim 1, It is characterized in that The method further comprises: Calculating the similarity between the photovoltaic power generation prediction graph and a plurality of historical photovoltaic power generation graphs; Determine the most similar historical photovoltaic power generation graph; Obtaining the strain strategy corresponding to the historical photovoltaic power generation power diagram with the highest similarity; The transmission lines of the photovoltaic base and the transmission lines of the main power grid are controlled based on the contingency strategy.
8. Photovoltaic power generation prediction device based on ground-based cloud map, It is characterized in that include: The first acquisition module is used to obtain ground cloud images, satellite cloud images, atmospheric data and solar motion tracks of the photovoltaic base; A first determination module is used to determine, from the ground-based cloud map and the satellite cloud map, a cloud group that can move to a preset area within a preset future time period, where the preset area is a lighting area corresponding to the photovoltaic base; A second determination module is used to determine the outline, moving speed, thickness and type of each cloud cluster based on the satellite cloud image; A simulation module, for simulating a motion dynamic diagram of each cloud cluster based on the contour, moving speed, type and atmospheric data of each cloud cluster; A third determination module is used to determine a target cloud cluster based on the sun's motion trajectory and the motion dynamic graph of each cloud cluster, and determine a first variation graph of the shielding area and shielding time of each target cloud cluster to the sun, wherein the target cloud cluster is a cloud cluster that can shield the sun; a fourth determination module, for determining a sky color value of a sky area from the ground-based cloud map, calculating the similarity between the sky color value and a plurality of historical sky color values at the same time, and determining a target historical sky color value and a third change graph of the target historical sky color value, wherein the sky color value is an RGB value, the target historical sky color value is the historical sky color value with the highest similarity, each historical sky color value corresponds to a second change graph of photovoltaic power generation over time, and each historical sky color value corresponds to a third change graph of radiation over time; a fifth determination module, configured to determine, based on the thickness, type, first variation graph, and third variation graph of the target cloud cluster, an amount of reduction in solar radiation when each target cloud cluster blocks the sun; A prediction map output module is used to determine and output a photovoltaic power generation power prediction map based on the radiation reduction amount and the second change map of the target historical sky color value.
9. An electronic device, It is characterized in that include: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute the photovoltaic power generation power prediction method based on ground-based cloud maps as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed in a computer, the computer is caused to execute the photovoltaic power generation power prediction method based on ground-based cloud maps as described in any one of claims 1 to 7.
