Generated power prediction system and method for mountain photovoltaic power station

Abstract

The invention discloses a generation power prediction system and method of a photovoltaic power station for a mountain land, relates to the technical field of photovoltaic power generation, and solves the technical problem that the generation power is predicted through meteorological prediction data and an artificial intelligence model in the prior art and is not suitable for being arranged in a photovoltaic power station with a complex terrain environment. The method comprises the following steps: establishing environment time sequence data of each photovoltaic panel based on irradiance time sequence data and meteorological time sequence data, and inputting the environment time sequence data into a power prediction model to obtain power generation power of a target power station; the irradiance time sequence data is used for determining whether each photovoltaic panel in the target power station is shielded or not, the meteorological time sequence data is the meteorological data of each photovoltaic panel at the moment, the irradiance time sequence data and the meteorological time sequence data are combined to determine the environment time sequence data of each photovoltaic panel, and the power generation environment of each photovoltaic panel at each moment can be determined according to the environment time sequence data. According to the method, the influence of the micrometeorological effect is fully considered, so that the prediction precision of the generated power is improved.

Description

Technical Field

[0001] This application belongs to the field of photovoltaic power generation, and relates to the power generation power prediction technology of a photovoltaic power station, specifically a power generation power prediction system and method for a mountain photovoltaic power station. Background Art

[0002] With the continuous development of clean energy, the proportion of photovoltaic power generation has increased rapidly. Since photovoltaic power stations require a large amount of land, sunny slopes that are difficult to utilize are gradually used for the construction of photovoltaic power stations.

[0003] The mountain terrain fluctuates greatly, the photovoltaic arrays are scattered and the zoning is complex, and the installation angles of the photovoltaic power stations in different regions are different. This leads to the fact that as the solar azimuth angle changes, the photovoltaic power station is easily blocked, and the blocked area is also different. Moreover, there is a high probability of micro-meteorological effects in the mountain slope. The micro-meteorological effects will make the local meteorological conditions significantly different from the surrounding areas, thus affecting the surrounding areas. Existing solutions predict the power generation power of photovoltaic power stations based on predicted meteorological data, which is obviously not applicable to predicting photovoltaic power stations in mountainous areas.

[0004] This application provides a power generation power prediction system and method for a mountain photovoltaic power station to solve the above technical problems. Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art; for this purpose, this application proposes a power generation power prediction system and method for a mountain photovoltaic power station, which is used to solve the technical problem that the existing technology cannot be applied to a photovoltaic power station set in a complex terrain environment by predicting meteorological data and an artificial intelligence model to predict power generation power.

[0006] To achieve the above object, the first aspect of this application provides a power generation power prediction method for a mountain photovoltaic power station, including:

[0007] Collect and obtain the position feature information of the target power station, model the target power station based on the position feature information, and simulate the solar movement trajectory to determine the irradiance time series data of each photovoltaic panel in the target power station; wherein, the position feature information includes the positions, altitudes, angles and surrounding environment data of each photovoltaic panel.

[0008] Detect the coverage area of the micro-meteorological phenomenon in the area where the target power station is located, and mark it as meteorological area one; predict and obtain the meteorological prediction data of the target power station and the micro-meteorological data of meteorological area one; construct the meteorological time series data of each photovoltaic panel based on the meteorological prediction data and the micro-meteorological data.

[0009] Establish the environmental time series data of each photovoltaic panel based on the irradiance time series data and meteorological time series data, and input the environmental time series data into the power prediction model to obtain the power generation of the target power station; among them, the power prediction model is constructed based on the artificial intelligence model.

[0010] Preferably, model the target power station based on the location feature information, including:

[0011] Preprocess the location feature information and then input it into the modeling software to construct a virtual model of the target power station; among them, the modeling software includes Pvsyst or SketchUp;

[0012] By simulating the sun's movement trajectory in different seasons, identify the affected situation of each photovoltaic panel in the virtual model during the sun's movement, and convert the affected situation into the irradiance time series data of each photovoltaic panel.

[0013] Preferably, detect the coverage area of the micro-meteorological phenomenon in the area where the target power station is located, including:

[0014] Extract the historical meteorological data of the target power station; classify the historical meteorological data according to meteorological elements to obtain data of each element; among them, the meteorological elements include temperature, wind speed, humidity and solar irradiance;

[0015] Based on the change trend of each element data, judge whether there is a micro-meteorological phenomenon; if yes, determine the coverage area of the micro-meteorological phenomenon according to the change trend; if not, there is no need to determine the coverage area.

[0016] Preferably, judge whether there is a micro-meteorological phenomenon based on the change trend of each element data, including:

[0017] Based on the element data, establish a three-dimensional change diagram of the corresponding meteorological element, and respectively identify the abnormal areas in the three-dimensional change diagram; among them, the three-dimensional change diagram is used to represent the change of the meteorological element at different positions;

[0018] When there is an overlap in the abnormal areas corresponding to at least one meteorological element, it is judged that there is a micro-meteorological phenomenon in the area where the target power station is located.

[0019] Preferably, determine the coverage area of the micro-meteorological phenomenon according to the change trend, including:

[0020] Select at least one target element from the meteorological elements according to the influence weight on the photovoltaic power generation; among them, the target elements are screened from large to small according to the influence weight;

[0021] Take the abnormal area of the target element as the coverage area of the micro-meteorological phenomenon, or take the combination of the abnormal areas corresponding to several target elements as the coverage area of the micro-meteorological phenomenon.

[0022] Preferably, meteorological time-series data of each photovoltaic panel is constructed based on meteorological prediction data and micro-meteorological data, including:

[0023] Extract meteorological prediction data and micro-meteorological data;

[0024] Successively take the positions of the photovoltaic panels in the target power station as the target positions, and extract the meteorological data corresponding to the target positions from the meteorological prediction data or micro-meteorological data;

[0025] Construct meteorological time-series data based on the meteorological data and their corresponding times, and associate it with the photovoltaic panels.

[0026] Preferably, environmental time-series data of each photovoltaic panel is established based on irradiance time-series data and meteorological time-series data, including:

[0027] Extract the irradiance time-series data and environmental time-series data of each photovoltaic panel in the target power station; among them, the irradiance time-series data refers to the ability of the photovoltaic panel to receive light at each moment;

[0028] Align the irradiance time-series data and environmental time-series data in time to obtain the environmental time-series data of the photovoltaic panel.

[0029] Preferably, before obtaining the environmental time-series data of the photovoltaic panel, detect whether there is cloud and fog affecting the target power station;

[0030] If it exists, predict the cloud and fog movement trajectory, and adjust the data obtained by time alignment based on the cloud and fog movement trajectory to obtain the environmental time-series data of each photovoltaic panel;

[0031] If it does not exist, no adjustment is made, and the environmental time-series data of each photovoltaic panel is directly obtained.

[0032] Preferably, input the environmental time-series data into the power prediction model, including:

[0033] Determine a number of prediction times; among them, the prediction times are extracted at a set interval from the set prediction period;

[0034] Extract the data of the photovoltaic panel at a number of prediction times from the environmental time-series data, and mark it as the basic model data; integrate the basic model data of each photovoltaic panel into the model input data;

[0035] Input the model input data into the power prediction model to obtain the power generation power of the target power station at a number of prediction times; construct a power prediction curve based on the power generation power at a number of prediction times.

[0036] The second aspect of the present application provides a power generation power prediction system for a mountain photovoltaic power station, including a power prediction module and a data acquisition module connected thereto;

[0037] Data acquisition module: used to collect and obtain the location feature information of the target power station; among them, the location feature information includes the locations, altitudes, angles of each photovoltaic panel, and surrounding environment data;

[0038] Power prediction module: used to build a model for the target power station based on the location feature information, and simulate the solar movement trajectory to determine the irradiance time series data of each photovoltaic panel in the target power station;

[0039] Detect the coverage area of the micro-meteorological phenomenon in the area where the target power station is located, and mark it as meteorological area one; predict and obtain the meteorological prediction data of the target power station and the micro-meteorological data of meteorological area one; construct the meteorological time series data of each photovoltaic panel based on the meteorological prediction data and the micro-meteorological data; and,

[0040] Establish the environmental time series data of each photovoltaic panel based on the irradiance time series data and the meteorological time series data, and input the environmental time series data into the power prediction model to obtain the power generation power of the target power station; among them, the power prediction model is constructed based on the artificial intelligence model.

[0041] Compared with the prior art, the beneficial effects of this application are:

[0042] 1. This application builds a model for the target power station based on the location feature information, simulates the solar movement trajectory to determine the irradiance time series data of each photovoltaic panel in the target power station; predicts and obtains the meteorological prediction data of the target power station and the micro-meteorological data of meteorological area one; constructs the meteorological time series data of each photovoltaic panel based on the meteorological prediction data and the micro-meteorological data; establishes the environmental time series data of each photovoltaic panel based on the irradiance time series data and the meteorological time series data, and input the environmental time series data into the power prediction model to obtain the power generation power of the target power station; the irradiance time series data in this application is to clarify whether each photovoltaic panel in the target power station is blocked, and the meteorological time series data is the meteorological data of each photovoltaic panel at each moment. The combination of the two can determine the environmental time series data of each photovoltaic panel. According to the environmental time series data, the power generation environment of the photovoltaic panel at each moment can be determined, so as to determine the power generation power of the target power station at each moment. This application fully considers the influence of the micro-meteorological effect to improve the prediction accuracy of the power generation power.

[0043] 2. Before obtaining the environmental time series data of the photovoltaic panel, this application detects whether there is cloud and fog affecting the target power station; if so, predicts the movement trajectory of the cloud and fog, and adjusts the data obtained by time alignment based on the movement trajectory of the cloud and fog to obtain the environmental time series data of each photovoltaic panel; if not, no adjustment is made, and the environmental time series data of each photovoltaic panel is directly obtained; this application considers the randomness of cloud and fog, detects whether there is cloud and fog affecting the target power station before determining the environmental time series data. If so, the data is adjusted according to the predicted movement trajectory of the cloud and fog, which can solve the influence of randomly appearing cloud and fog in the mountains on the target power station, and further improve the prediction accuracy of the power generation power of the target power station. Description of the Drawings

[0044] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0045] Figure 1 It is a schematic diagram of the method steps of the power generation prediction method in the first embodiment of the present application;

[0046] Figure 2 It is a schematic diagram of the system principle of the power generation prediction system in the first embodiment of the present application;

[0047] Figure 3 It is a schematic diagram of the method steps of the adjustment based on the cloud and fog movement trajectory in the second embodiment of the present application. Specific implementation manners

[0048] The following will clearly and completely describe the technical solutions of the present application in combination with the embodiments. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0049] When a photovoltaic power station is set on a hillside, compared with being set on a plain, its power generation is additionally affected by the following factors: 1) Terrain and orientation: Different hillside orientations, slopes, and the safe angles of photovoltaic modules will affect the amount of light received; 2) Occluded areas and areas: Mountain shadows and the occlusion between photovoltaic modules will cause power generation losses; 3) Local climate and micro-meteorological effects: The local climate and micro-meteorological effects in mountainous areas are more significant, such as valley winds and airflow changes caused by terrain. These factors will affect parameters such as solar irradiance and temperature, and thus affect the power generation.

[0050] Most of the existing technical solutions predict the power generation of a photovoltaic power station by predicting future meteorological data and combining the sun's movement trajectory and the installation angle of the photovoltaic panels. The existing solutions do not disclose the solutions corresponding to the above factors. In order to accurately predict the power generation of a photovoltaic power station for mountain use, the present application provides a power generation prediction system and method for a photovoltaic power station for mountain use.

[0051] Embodiment 1:

[0052] Please refer to Figure 1 - Figure 2 , the first aspect embodiment of the present application provides a power generation prediction method for a photovoltaic power station for mountain use, including:

[0053] Collect the location feature information of the target power station, model the target power station based on the location feature information, simulate the sun's movement trajectory to determine the irradiance time series data of each photovoltaic panel in the target power station; detect the coverage area of the micro-meteorological phenomena in the area where the target power station is located and label it as Meteorological Area 1; predict and obtain the meteorological prediction data of the target power station and the micro-meteorological data of Meteorological Area 1; construct the meteorological time series data of each photovoltaic panel based on the meteorological prediction data and the micro-meteorological data; establish the environmental time series data of each photovoltaic panel based on the irradiance time series data and the meteorological time series data, and input the environmental time series data into the power prediction model to obtain the power generation of the target power station.

[0054] To clarify and solve the problem of occlusion of each photovoltaic panel of a photovoltaic power station by the complex terrain of a mountain, in this embodiment, the location feature information of the target power station is first collected. The location feature information mainly includes the location, altitude, angle, and surrounding environment data of each photovoltaic panel. The surrounding environment data mainly refers to factors that affect the photovoltaic panel's reception of light, such as tall trees, rocks, and cliffs around the photovoltaic panel. Based on the location feature information, the target power station can be modeled, and then the sun's movement trajectory can be simulated to determine which photovoltaic panels can receive light at which times, laying a data foundation for subsequent prediction of the power generation of the target power station.

[0055] To solve the influence of the micro-meteorological effect on the target power station, in this embodiment, it is determined whether the area where the target power station is located is affected by the micro-meteorological effect. If it is affected, the coverage area of the micro-meteorological effect is identified, and then the meteorological data of the coverage area is predicted to assist in predicting the power generation of the target power station. Considering the influence of the micro-meteorological effect, the prediction accuracy of the power generation can be improved.

[0056] Next, the specific implementation process of this embodiment will be elaborated.

[0057] First, model the target power station based on the location feature information, including:

[0058] After preprocessing the location feature information, input it into the modeling software to construct a virtual model of the target power station; by simulating the sun's movement trajectory in different seasons, identify the affected situation of each photovoltaic panel in the virtual model during the sun's movement, and convert the affected situation into the irradiance time series data of each photovoltaic panel. There are many related modeling software, such as Pvsyst or SketchUp.

[0059] Exemplarily, taking the Pvsyst software as an example to obtain the irradiance time series data:

[0060] 1. Set up the project site and meteorological data: After creating a new project in the software, select the site file of the target power station. Of course, a new site can also be created directly. Then, input the location information of the target power station, such as longitude and latitude, and import it after confirmation. Next, import the relevant information of the environmental data around the target power station determined through on-site investigation into the software to build a virtual model of the target power station.

[0061] 2. Simulate the sun's movement trajectory: After entering the simulation interface, set the corresponding parameters according to the season and time range to be simulated, and run the simulation to simulate the sun's movement trajectory in different seasons.

[0062] 3. Analyze the affected situation: After the simulation is completed, the software will generate a detailed report document. The affected situation of each photovoltaic panel can be identified through the report document. Convert the affected situation of each photovoltaic panel into irradiance time series data, which serves as the typical data basis for predicting the power generation of the target power station in the future.

[0063] It should be noted that the irradiance time series data mainly includes when a corresponding photovoltaic panel will receive sunlight during a day. This period may be a complete period or multiple discontinuous periods. Moreover, the irradiance time series data is actually closely related to the location of the target power station and the surrounding environment. Without human intervention, the location and environment generally do not change. Due to the relatively stable location characteristic information, the irradiance time series data of each photovoltaic panel in the target power station is also relatively stable, and the data obtained after one modeling and simulation can be used for a long time. When the target power station or the surrounding environmental data changes, targeted modeling and simulation can be carried out.

[0064] Secondly, detect the coverage area of the micro-meteorological phenomenon in the area where the target power station is located, including: extracting the historical meteorological data of the target power station; classifying the historical meteorological data according to meteorological elements to obtain data for each element; judging whether there is a micro-meteorological phenomenon based on the change trend of each element's data; if yes, determine the coverage area of the micro-meteorological phenomenon according to the change trend; if no, there is no need to determine the coverage area.

[0065] The micro-meteorological effect refers to the meteorological characteristics at a small spatial scale ranging from a few meters to a few kilometers. Such characteristics may make the local meteorological conditions significantly different from the surrounding areas, but will not cause significant changes to the large-scale climate characteristics. The micro-meteorological effect will affect temperature, humidity, wind speed, and solar radiation, and the changes in these parameters will affect the power generation of the photovoltaic power station.

[0066] The micro-meteorological effect can be analyzed by using the historical meteorological data of the area where the target power station is located. This historical meteorological data can be obtained through research before the construction of the target power station. According to the characteristics of the micro-meteorological effect, it is possible to judge whether there is a micro-meteorological phenomenon by analyzing the changing trends of various meteorological elements. After obtaining the historical meteorological data, the historical meteorological data is first classified according to meteorological elements to obtain several data groups, and each data group corresponds to a meteorological element.

[0067] Judging whether there is a micro-meteorological phenomenon based on the changing trends of the data of each element includes:

[0068] Based on the element data, a three-dimensional change diagram of the corresponding meteorological element is established, and the abnormal areas in the three-dimensional change diagram are respectively identified; when there is an overlap in the abnormal areas corresponding to at least one meteorological element, it is judged that there is a micro-meteorological phenomenon in the area where the target power station is located.

[0069] The three-dimensional change diagram is used to represent the changes of meteorological elements at different positions. The three-dimensional change diagram can be generated by importing the data group into Matlab software. Each three-dimensional change diagram is associated with a meteorological element. In the three-dimensional change diagram, the X and Y axes represent positions, and the Z axis represents the specific values of the meteorological element.

[0070] Exemplarily, taking temperature as an example, the construction of the three-dimensional change diagram and the judgment of the micro-meteorological phenomenon are described as follows:

[0071] Extract the data group corresponding to temperature from the historical meteorological data. This data group includes temperature values and their corresponding position information. The position information can be longitude and latitude, or can be determined according to other set coordinate systems.

[0072] Import the data group into Matlab software, and call the relevant image generation function to generate the three-dimensional change diagram of temperature; if there is an area in the three-dimensional change diagram that is significantly different from the surrounding area, the abnormal area is identified (there is a function in Matlab software to identify mutation points). At this time, it can also be determined that there is a micro-meteorological phenomenon in the area where the target power station is located.

[0073] It should be noted that the identification of the abnormal area is mainly through judging whether the temperature changes suddenly. If the temperature changes suddenly at some points and the degree of mutation exceeds the set threshold, the area enclosed by these points is taken as the abnormal area. Here, the set threshold can be set based on the experience of relevant meteorological experts.

[0074] When it is determined that there is a micro-meteorological phenomenon, it is also necessary to determine the coverage area of this micro-meteorological phenomenon. In this example, by determining which meteorological factors have a greater impact on the photovoltaic power generation, the coverage area is determined according to the corresponding abnormal area. Specifically:

[0075] Select at least one target factor from meteorological factors according to the influence weight on the photovoltaic power generation; take the abnormal area of the target factor as the coverage area of the micro-meteorological phenomenon, or take the combination of the abnormal areas corresponding to several target factors as the coverage area of the micro-meteorological phenomenon.

[0076] The influence weight of each meteorological factor on the photovoltaic power generation can be determined by weight analysis methods such as the principal component analysis method. Sort the meteorological factors according to the influence weight from large to small, and select the meteorological factor with the largest influence weight as the target factor. If there is only one target factor, take its abnormal area as the coverage area of the micro-meteorological phenomenon; if there are multiple target factors, take the combination of the abnormal areas of the multiple target factors as the coverage area of the micro-meteorological phenomenon.

[0077] The reason for determining the target factor by the influence weight in this embodiment is that in the micro-meteorological effect, the changes of some meteorological factors will not affect the power generation power of the photovoltaic power station, or the influence on the power generation power is small and not analyzed to avoid increasing the data processing volume. For example, the micro-meteorological effect may affect the humidity in the area, but this humidity mainly affects the ground and the plants on the ground, and the influence on the power generation power is relatively small compared with the temperature; the wind speed in the area will also change greatly, but the influence of the wind speed on the power generation power is also relatively small. On the basis of considering the data processing volume, meteorological factors with small influence on the power generation power such as humidity and wind speed can be analyzed according to the influence weight of the specific area.

[0078] After determining that there is a micro-meteorological effect in the area where the target power station is located, predict the meteorological prediction data and micro-meteorological data of the area where the target power station is located based on historical meteorological data. When obtaining the meteorological prediction data and micro-meteorological data, the photovoltaic panel should be used as the benchmark, that is, obtain the historical meteorological data corresponding to the photovoltaic panel, and use this historical meteorological data and the meteorological prediction model to obtain the meteorological prediction data. If the photovoltaic panel is in the coverage area of the micro-meteorological phenomenon, the meteorological prediction data is the micro-meteorological data.

[0079] It should be noted that the prediction of the meteorological prediction data and micro-meteorological data can be realized through time series models, such as through autoregressive moving average models or long short-term memory network models, etc. These models for predicting meteorological data have been publicly disclosed in the existing solutions, and the specific training and prediction processes will not be elaborated here.

[0080] Next, it is necessary to construct the meteorological time series data of each photovoltaic panel in the target power station, specifically:

[0081] Extract the meteorological prediction data and micro-meteorological data; sequentially take the position of the photovoltaic panel in the target power station as the target position, and extract the meteorological data corresponding to the target position from the meteorological prediction data or micro-meteorological data; construct the meteorological time series data based on the meteorological data and its corresponding time, and associate it with the photovoltaic panel.

[0082] Extract the meteorological prediction data and micro-meteorological data obtained by the foregoing scheme prediction, and then use the positions of the photovoltaic panels as the target positions; extract the meteorological data of the target positions from the meteorological prediction data and the micro-meteorological data, and then integrate them in chronological order to obtain meteorological time-series data.

[0083] Exemplarily, assume that there are photovoltaic panel A and photovoltaic panel B in the target power station. Photovoltaic panel A is in the normal area, and photovoltaic panel B is in the coverage area of the micro-meteorological phenomenon;

[0084] Take the position of photovoltaic panel A as the target position, and extract the meteorological time-series data corresponding to the target position from the meteorological prediction data, that is, the meteorological data corresponding to each moment; take the position of photovoltaic panel B as the target position, and extract the meteorological time-series data corresponding to the target position from the micro-meteorological data.

[0085] A photovoltaic power station is set up on the hillside, and its photovoltaic panels may be set in different areas and are far apart. Therefore, some photovoltaic panels may not be in the coverage area of the micro-meteorological phenomenon, while some photovoltaic panels are in the coverage area of the micro-meteorological phenomenon. Moreover, the positions of each photovoltaic panel are different, so the meteorological time-series data corresponding to each photovoltaic panel are also different. The changes of various meteorological factors in the meteorological time-series data affect the power generation power of the photovoltaic panels, thus affecting the power generation power of the entire photovoltaic power station.

[0086] It is necessary to combine the meteorological time-series data with the irradiance time-series data to determine the environmental time-series data of each photovoltaic panel, specifically as follows: extract the irradiance time-series data and environmental time-series data of each photovoltaic panel in the target power station; align the irradiance time-series data and the environmental time-series data in time to obtain the environmental time-series data of the photovoltaic panel.

[0087] The irradiance time-series data refers to the ability of the photovoltaic panel to receive light at each moment. During the daily solar movement, the photovoltaic panel may not receive light due to the occlusion of the surrounding environmental data in some periods. Since it cannot receive light, it naturally cannot generate electricity. The meteorological time-series data does not consider the problem of the photovoltaic panel being occluded when it is obtained, and it represents whether the photovoltaic panel can receive light at a certain moment without considering the influence of the surrounding environmental data.

[0088] Combine the irradiance time-series data and the meteorological time-series data, that is, judge whether the photovoltaic panel is occluded at each moment through the irradiance time-series data. If it is not occluded at a certain moment, extract the meteorological data corresponding to that moment from the meteorological time-series data. Therefore, the meteorological data at each moment, that is, the environmental time-series data, can be obtained after processing. It should be noted that if the photovoltaic panel is occluded at a certain moment, there is no need to extract the meteorological data, and the corresponding meteorological data can be set to be empty and not considered in the subsequent process of predicting the power generation power.

[0089] It should be noted that part of the photovoltaic panel may be shaded. If the remaining part of the photovoltaic panel can still generate electricity, it is necessary to match the meteorological data at each moment for it. However, when predicting the power generation power of the target power station subsequently, it is necessary to introduce the actual power generation area of each photovoltaic panel in order to accurately predict the power generation power of the target power station.

[0090] Input the environmental time-series data of each photovoltaic panel in the target power station into the power prediction model, and the power generation power of the target power station at each moment can be obtained. Before input, it is necessary to perform necessary processing on the environmental time-series data, normalize the environmental time-series data and insert the label (which can be a number) of the photovoltaic panel. If part of the photovoltaic panel is shaded, it is also necessary to insert the actual working area of the photovoltaic panel.

[0091] The power prediction model is trained based on an artificial intelligence model, including:

[0092] Construct an artificial intelligence model; train the artificial intelligence model with standard training data, and mark the trained artificial intelligence model as the power prediction model; among them, the artificial intelligence model includes a BP neural network model or an RBF neural network model;

[0093] The standard training data can be obtained through actual measurement or simulation. The standard training data mainly includes the power generation power of the target power station, as well as the meteorological data and actual working area corresponding to each photovoltaic panel therein; after normalizing the meteorological data and actual working area of each photovoltaic panel, insert the label of the photovoltaic panel therein; in this way, at the same moment, each photovoltaic panel corresponds to a piece of data including meteorological data, actual working area, and label. Integrate the data corresponding to each photovoltaic panel at the same moment into the model input data, and integrate the power generation power of the target power station at the corresponding moment into the model output data. Train the constructed artificial intelligence model through the model input data and model output data to obtain the power prediction model. The model training process will not be elaborated here.

[0094] Inputting the environmental time-series data into the power prediction model includes:

[0095] Determine several prediction moments; extract the data of the photovoltaic panel at several prediction moments from the environmental time-series data, and mark it as the basic model data; integrate the basic model data of each photovoltaic panel into the model input data; input the model input data into the power prediction model to obtain the power generation power of the target power station at several prediction moments; construct a power prediction curve based on the power generation power at several prediction moments.

[0096] The prediction moments are extracted from the set prediction period at a set interval. For example, if the prediction period is the next week and the set interval is one hour, then several prediction moments can be extracted from the prediction period according to the set interval.

[0097] After obtaining the power generation powers at several prediction moments, a power prediction curve can be fitted and constructed. This power prediction curve represents the change curve of the power generation power within the prediction period, and can be used to assist the staff in dispatching the distribution network. Of course, integral calculation can also be performed to determine the power generation amount of the target power station within a certain period.

[0098] The second aspect of the embodiments of the present application provides a power generation power prediction system for a mountain photovoltaic power station, including a power prediction module and a data acquisition module connected thereto;

[0099] Data acquisition module: used to collect and obtain the location feature information of the target power station; wherein, the location feature information includes the locations, altitudes, angles of each photovoltaic panel, and surrounding environment data;

[0100] Power prediction module: used to model the target power station based on the location feature information, and simulate the solar movement trajectory to determine the irradiance time series data of each photovoltaic panel in the target power station;

[0101] Detect the coverage area of the micro-meteorological phenomenon in the area where the target power station is located, and mark it as meteorological area one; predict and obtain the meteorological prediction data of the target power station and the micro-meteorological data of meteorological area one; construct the meteorological time series data of each photovoltaic panel based on the meteorological prediction data and the micro-meteorological data; and,

[0102] Based on the irradiance time series data and the meteorological time series data, establish the environmental time series data of each photovoltaic panel, and input the environmental time series data into the power prediction model to obtain the power generation power of the target power station; wherein, the power prediction model is constructed based on an artificial intelligence model.

[0103] The data acquisition module is connected to the meteorological platform and various types of meteorological sensors.

[0104] Embodiment 2: Compared with Embodiment 1, this embodiment provides a solution for the influence of clouds on the power generation power. Please refer to Figure 3 : Before obtaining the environmental time series data of the photovoltaic panel, detect whether there are clouds affecting the target power station; if so, predict the cloud movement trajectory, and adjust the data obtained by time alignment based on the cloud movement trajectory to obtain the environmental time series data of each photovoltaic panel; if not, no adjustment is made, and the environmental time series data of each photovoltaic panel is directly obtained.

[0105] The appearance of clouds is quite random, and it is also difficult to predict based on historical data. In this embodiment, cloud detection equipment, such as satellite images or other image data set around the target power station, is first used to identify clouds, and the existing cloud trajectory prediction model is used to predict the future movement trajectory of the clouds, and determine whether the movement trajectory of the clouds will affect each photovoltaic panel in the target power station. If it will have an impact, the environmental time series data of each photovoltaic panel is adjusted according to the cloud movement trajectory.

[0106] The appearance of clouds and fog will cause the photovoltaic panels to be blocked and unable to receive sunlight, resulting in the inability of the photovoltaic panels to generate electricity. Therefore, clouds and fog can be understood as dynamic obstacles, which will block the photovoltaic panels during their movement. After predicting and obtaining the movement trajectory of clouds and fog, it is possible to determine when the clouds and fog will affect which photovoltaic panel. By setting the meteorological data of the corresponding moment of the photovoltaic panel to be empty, it means that the photovoltaic panel does not generate electricity at that moment.

[0107] In this embodiment, it is first detected whether clouds and fog are formed, and then combined with meteorological data analysis to determine whether the clouds and fog will affect the target power station. Then, the existing cloud and fog tracking platform is used to predict the movement trajectory of the clouds and fog. It should be noted that if clouds and fog appear during the prediction of the power generation power of the target power station, the movement trajectory of the clouds and fog can be analyzed in real time to adjust the environmental time series data of each photovoltaic panel. Of course, it is also possible to introduce the clouds and fog after prediction to adjust the prediction results. The cloud and fog tracking platform can be NVIDIA Earth-2, RayCloudSim, etc.

[0108] It should be noted that if the appearance of clouds and fog can be accurately predicted, it is also possible to first predict the clouds and fog and their movement trajectories, so as to adjust the environmental time series data.

[0109] Embodiment 3: Compared with Embodiment 1, this embodiment uses an artificial intelligence model to predict micro-meteorological data.

[0110] First, obtain the meteorological prediction data of the area where the target power station is located through a meteorological platform, and then preprocess the meteorological prediction data and input it into the trained artificial intelligence model to obtain the meteorological prediction data of the area covered by the micro-meteorological phenomenon, that is, micro-meteorological data.

[0111] The artificial intelligence model in this embodiment is trained with the historical meteorological data of the target power station. Extract the meteorological data of the area covered by the micro-meteorological phenomenon from the historical meteorological data as the micro-meteorological historical data; use the historical meteorological data as the model input data and the micro-meteorological historical data as the model output data to train the artificial intelligence model. The trained artificial intelligence model can establish the mapping relationship between the meteorological data and the micro-meteorological data.

[0112] Of course, in order to achieve accurate prediction of micro-meteorological data, several feature points can be selected from the coverage area, and the meteorological data of these feature points can be integrated into micro-meteorological data. The meteorological platform can be a third-party meteorological prediction platform or the data given by a meteorological station set in the area where the target power station is located.

[0113] The above embodiments are only used to illustrate the technical solutions of the present application and not to limit them. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for predicting the power generation of a photovoltaic power station for mountainous areas, characterized in that: include: Acquire location characteristic information of the target power station, model the target power station based on the location characteristic information, and simulate the sun's motion trajectory to determine the irradiance time series data of each photovoltaic panel in the target power station; wherein the location characteristic information includes the location, altitude, angle and surrounding environment data of each photovoltaic panel; Detecting the coverage area of ​​the micro-meteorological phenomenon in the area where the target power station is located, marking it as meteorological area one; predicting and obtaining meteorological forecast data of the target power station and micro-meteorological data of the meteorological area one; constructing meteorological time series data of each photovoltaic panel based on the meteorological forecast data and the micro-meteorological data; Based on the irradiance time series data and the meteorological time series data, the environmental time series data of each photovoltaic panel is established, and the environmental time series data is input into the power prediction model to obtain the power generation power of the target power station; wherein the power prediction model is constructed based on an artificial intelligence model.

2. The method for predicting power generation of a photovoltaic power station for mountainous areas according to claim 1, characterized in that: Modeling the target power station based on the location feature information includes: Preprocessing the location feature information and inputting it into a modeling software to construct a virtual model of the target power station; wherein the modeling software includes Pvsyst or SketchUp; By simulating the movement trajectory of the sun in different seasons, the impact of each photovoltaic panel in the virtual model during the movement of the sun can be identified, and the impact is converted into irradiance time series data of each photovoltaic panel.

3. The method for predicting power generation of a photovoltaic power station for mountainous areas according to claim 1, characterized in that: The coverage area for detecting micro-meteorological phenomena in the area where the target power station is located includes: Extracting historical meteorological data of the target power station; classifying the historical meteorological data according to meteorological elements to obtain data of each element; wherein the meteorological elements include temperature, wind speed, humidity and solar irradiance; Based on the change trend of each of the element data, it is judged whether there is a micro-meteorological phenomenon; if yes, the coverage area of ​​the micro-meteorological phenomenon is determined according to the change trend; if not, there is no need to determine the coverage area.

4. The method for predicting power generation of a photovoltaic power station for mountainous areas according to claim 3, characterized in that: Judging whether there is a micro-meteorological phenomenon based on the change trend of each element data includes: A three-dimensional change map of the corresponding meteorological element is established based on the element data, and abnormal areas in the three-dimensional change map are respectively identified; wherein the three-dimensional change map is used to represent the change of meteorological elements at different locations; When the abnormal areas corresponding to at least one of the meteorological elements overlap, it is determined that micro-meteorological phenomena exist in the area where the target power station is located.

5. The method for predicting power generation of a photovoltaic power station for mountainous areas according to claim 4, characterized in that: Determine the coverage area of ​​micro-meteorological phenomena based on the changing trends, including: Selecting at least one target element from the meteorological elements according to the weight of influence on photovoltaic power generation; wherein the target elements are selected from large to small according to the weight of influence; The abnormal area of ​​the target element is used as the coverage area of ​​the micro-meteorological phenomenon, or the abnormal areas corresponding to several target elements are combined as the coverage area of ​​the micro-meteorological phenomenon.

6. The method for predicting power generation of a photovoltaic power station for mountainous areas according to claim 5, characterized in that: The meteorological time series data of each photovoltaic panel is constructed based on the meteorological forecast data and the micro-meteorological data, including: Extracting the meteorological forecast data and the micro-meteorological data; The positions of the photovoltaic panels in the target stations are sequentially taken as target positions, and the meteorological data corresponding to the target positions are extracted from the meteorological forecast data or the micro-meteorological data; Meteorological time series data is constructed based on the meteorological data and its corresponding time, and is associated with the photovoltaic panel.

7. A method for predicting power generation of a photovoltaic power station for mountainous areas according to claim 6, characterized in that: Establishing environmental time series data of each photovoltaic panel based on the irradiance time series data and the meteorological time series data includes: Extracting the irradiance time series data and the environment time series data of each photovoltaic panel in the target power station; wherein the irradiance time series data refers to the light that the photovoltaic panel can receive at each moment; The irradiance time series data and the environment time series data are time-aligned to obtain the environment time series data of the photovoltaic panel.

8. The method for predicting power generation of a photovoltaic power station for mountainous areas according to claim 7, characterized in that: Before obtaining the environmental time series data of the photovoltaic panel, detecting whether there is fog that affects the target power station; If it exists, predict the cloud and fog movement trajectory, and adjust the data obtained by the time alignment based on the cloud and fog movement trajectory to obtain the environmental time series data of each photovoltaic panel; If it does not exist, no adjustment is performed and the environmental timing data of each photovoltaic panel is directly obtained.

9. The method for predicting power generation of a photovoltaic power station for mountainous areas according to claim 8, characterized in that: Inputting the environmental time series data into a power prediction model includes: Determining a number of prediction moments; wherein the prediction moments are extracted from a set prediction period at set intervals; Extracting data of photovoltaic panels at a number of prediction moments from the environmental time series data and marking them as basic model data; integrating the basic model data of each photovoltaic panel as model input data; The model input data is input into the power prediction model to obtain the power generation of the target power station at several prediction moments; and a power prediction curve is constructed based on the power generation at several prediction moments.

10. A power generation prediction system for a photovoltaic power station for use in mountainous areas, used to execute a power generation prediction method for a photovoltaic power station for use in mountainous areas as claimed in any one of claims 1 to 9, characterized in that: It includes a power prediction module and a data acquisition module connected thereto; Data acquisition module: used to acquire location characteristic information of the target power station; the location characteristic information includes the location, altitude, angle and surrounding environment data of each photovoltaic panel; Power prediction module: used to model the target power station based on the location feature information, and simulate the sun's motion trajectory to determine the irradiance time series data of each photovoltaic panel in the target power station; Detecting the coverage area of ​​the micro-meteorological phenomenon in the area where the target power station is located, marked as meteorological area one; predicting and acquiring the meteorological forecast data of the target power station and the micro-meteorological data of the meteorological area one; constructing the meteorological time series data of each photovoltaic panel based on the meteorological forecast data and the micro-meteorological data; and, Establishing environmental time series data of each photovoltaic panel based on the irradiance time series data and the meteorological time series data According to the environmental time series data, the environmental time series data is input into a power prediction model to obtain the power generation power of the target power station; Among them, the power prediction model is built based on the artificial intelligence model.

Images