A method, system and device for photovoltaic power prediction in high altitude mountainous areas

Abstract

The present application discloses a method, system and device for photovoltaic power prediction in high altitude mountains, and relates to the field of photovoltaic power prediction technology. The present application discloses a method for photovoltaic power prediction in high altitude mountains, comprising the following steps: grouping photovoltaic panels; obtaining historical power prediction data and corresponding actual power data of each group of photovoltaic panels and calculating error data of each group of photovoltaic panels; dividing all photovoltaic panel groups into a first photovoltaic cluster and a second photovoltaic cluster according to the error data; responding to a photovoltaic power prediction request; inputting a first characteristic parameter through a first prediction model to obtain first power prediction data; inputting a second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data through a second prediction model to obtain second power prediction data; obtaining power prediction data of photovoltaic panels in a target area according to the first power prediction data and the second power prediction data.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic power prediction, and in particular to a method, system and device for photovoltaic power prediction in high-altitude mountainous areas. Background Art

[0002] Due to the complex and changeable climate conditions in high-altitude areas, the power output of photovoltaic power stations is affected by many factors, such as temperature, humidity, wind speed, light intensity, etc. Therefore, how to accurately predict the power output of high-altitude mountain photovoltaic power stations is of great significance to improving the operation efficiency and energy management of power stations.

[0003] Photovoltaic panels at different locations in high-altitude mountainous areas have different power generation capacities due to environmental factors. Using the same model to predict photovoltaic panels at different locations has low prediction accuracy, which is not conducive to grid connection or power dispatch control of all photovoltaic panels. Summary of the invention

[0004] The main purpose of this application is to provide a high-precision management system for high-altitude mountain photovoltaic power prediction, aiming to solve the problem of low prediction accuracy when predicting the power generation power of photovoltaic panels at different locations in high-altitude mountainous areas through the same model in the prior art.

[0005] To achieve the above objectives, in a first aspect, the present application provides a method for predicting photovoltaic power in high-altitude mountainous areas, comprising the following steps:

[0006] The photovoltaic panels are grouped according to the label information of the photovoltaic panels in the target area;

[0007] Obtaining historical power prediction data and corresponding actual power data of each group of photovoltaic panels, and calculating error data of each group of photovoltaic panels according to the historical power prediction data and the corresponding actual power data;

[0008] According to the error data, all photovoltaic panel groups are divided into a first photovoltaic cluster whose error data is within a first preset interval and a second photovoltaic cluster whose error data is within a second preset interval;

[0009] responding to a photovoltaic power forecast request;

[0010] By using a first prediction model, a first characteristic parameter related to the power generation of the first photovoltaic cluster is input to obtain first power prediction data;

[0011] By using a second prediction model, inputting a second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data, obtaining second power prediction data;

[0012] Power prediction data of the photovoltaic panels in the target area is obtained according to the first power prediction data and the second power prediction data.

[0013] Optionally, the tag information includes number information and / or location information of the photovoltaic panels, and the photovoltaic panels located at the same height are divided into the same group.

[0014] Optionally, the step of inputting a first characteristic parameter related to the power generation power of the first photovoltaic cluster through a first prediction model to obtain first power prediction data includes:

[0015] Obtaining a first characteristic parameter related to the power generation of the first photovoltaic cluster according to the tag information of the photovoltaic panels in the first photovoltaic cluster;

[0016] By using a first prediction model, a first characteristic parameter related to the power generation of the first photovoltaic cluster is input to obtain first power prediction data;

[0017] The step of inputting a second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data through a second prediction model to obtain second power prediction data includes:

[0018] Obtaining a second characteristic parameter related to the power generation of the second photovoltaic cluster according to the tag information of the photovoltaic panels in the second photovoltaic cluster;

[0019] A second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data are input through a second prediction model to obtain second power prediction data.

[0020] Optionally, according to the tag information, identifying whether there are abnormal photovoltaic panel groups in the first photovoltaic cluster and the second photovoltaic cluster;

[0021] If so, the cluster of the abnormal photovoltaic panel group is corrected.

[0022] Optionally, the step of obtaining the second prediction model includes:

[0023] The historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster is used as input, and the corresponding actual power data is used as output to train the first prediction model to obtain the second prediction model.

[0024] Optionally, before taking the historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster as input, the method further includes:

[0025] Sorting the photovoltaic panel groups in the first photovoltaic cluster and the second photovoltaic cluster in descending order of error data;

[0026] adding photovoltaic panel groups of a first preset proportion before sorting in the second photovoltaic cluster to the first photovoltaic cluster;

[0027] The photovoltaic panel groups with a second preset ratio after sorting in the first photovoltaic cluster are added to the second photovoltaic cluster.

[0028] Optionally, the first preset interval is smaller than the second preset interval.

[0029] Optionally, the error data is obtained according to a root mean square error, and a calculation formula for the root mean square error is as follows:

[0030] Wherein, di is the difference between the historical power prediction data and the corresponding actual power data, and n is the number of historical power prediction data.

[0031] In a second aspect, the present application provides a system for high-altitude mountain photovoltaic power prediction, comprising:

[0032] A grouping module is configured to group the photovoltaic panels according to the tag information of the photovoltaic panels in the target area;

[0033] A data acquisition module is configured to acquire historical power prediction data and corresponding actual power data of each group of photovoltaic panels;

[0034] A data processing module, configured to calculate error data of each group of photovoltaic panels according to the historical power prediction data and the corresponding actual power data;

[0035] a data analysis module configured to divide all photovoltaic panel groups into a first photovoltaic cluster whose error data is within a first preset interval and a second photovoltaic cluster whose error data is within a second preset interval according to the error data;

[0036] a response module configured to respond to the photovoltaic power prediction request;

[0037] a characteristic parameter acquisition module, configured to acquire a first characteristic parameter related to the power generation of the first photovoltaic cluster and a second characteristic parameter related to the power generation of the second photovoltaic cluster;

[0038] The power prediction module is configured to obtain first power prediction data by inputting a first characteristic parameter through a first prediction model, and obtain second power prediction data by inputting a second characteristic parameter and the first power prediction data through a second prediction model;

[0039] The power prediction data acquisition module is configured to obtain power prediction data of the photovoltaic panels in the target area according to the first power prediction data and the second power prediction data.

[0040] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0041] Beneficial effects that this application can achieve:

[0042] A method, system and device for photovoltaic power prediction in high-altitude mountains proposed in an embodiment of the present application include the following steps: grouping photovoltaic panels according to label information of photovoltaic panels in a target area; obtaining historical power prediction data and corresponding actual power data of each group of photovoltaic panels, and calculating error data of each group of photovoltaic panels according to the historical power prediction data and the corresponding actual power data; dividing all photovoltaic panel groups into a first photovoltaic cluster whose error data is located in a first preset interval and a second photovoltaic cluster whose error data is located in a second preset interval according to the error data; responding to a photovoltaic power prediction request; inputting a first characteristic parameter related to the power generation power of the first photovoltaic cluster through a first prediction model to obtain first power prediction data; inputting a second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data through a second prediction model to obtain second power prediction data; and obtaining power prediction data of photovoltaic panels in the target area according to the first power prediction data and the second power prediction data. At least the problem in the prior art is that photovoltaic panels at different heights in high-altitude mountainous areas have different solar radiation in the same time period, photovoltaic panel groups at lower positions are easily blocked by mountains or trees, and the prediction accuracy of photovoltaic groups at different heights is different. By processing historical power prediction data and corresponding actual power data, the first photovoltaic cluster with high prediction accuracy is screened out, and the model is optimized with the first photovoltaic cluster as the anchor point to improve the prediction accuracy of the second photovoltaic cluster. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of the process of the photovoltaic power prediction method for high altitude mountain areas in this application;

[0044] Figure 2 A schematic diagram of a computer device in the present application.

[0045] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0048] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0050] Example 1

[0051] like Figure 1 As shown, a method for predicting photovoltaic power in high-altitude mountainous areas comprises the following steps:

[0052] S1. Group the photovoltaic panels according to the label information of the photovoltaic panels in the target area.

[0053] Optionally, after the photovoltaic panels in the target area are grouped, the photovoltaic panel groups are numbered to facilitate acquisition or recording of corresponding data.

[0054] S2. Obtain historical power prediction data and corresponding actual power data of each group of photovoltaic panels, and calculate error data of each group of photovoltaic panels based on the historical power prediction data and the corresponding actual power data.

[0055] Optionally, the error data is used to characterize the accuracy of historical power prediction of the photovoltaic panel group.

[0056] S3. According to the error data, divide all photovoltaic panel groups into a first photovoltaic cluster whose error data is within a first preset interval and a second photovoltaic cluster whose error data is within a second preset interval.

[0057] Optionally, the historical photovoltaic power prediction accuracy of the photovoltaic panel groups in the first photovoltaic cluster is higher than the historical photovoltaic power prediction accuracy of the photovoltaic panel groups in the second photovoltaic cluster.

[0058] S4. Responding to a photovoltaic power prediction request.

[0059] S5. Using a first prediction model, input a first characteristic parameter related to the power generation of the first photovoltaic cluster to obtain first power prediction data.

[0060] S6. Using a second prediction model, input a second characteristic parameter related to the power generation of the second photovoltaic cluster and the first power prediction data to obtain second power prediction data.

[0061] S7. Obtain power prediction data of the photovoltaic panels in the target area according to the first power prediction data and the second power prediction data.

[0062] Example 2

[0063] This embodiment, based on the first embodiment, provides a method for predicting photovoltaic power in a high altitude mountain area, comprising the following steps:

[0064] S1. Group the photovoltaic panels according to the label information of the photovoltaic panels in the target area.

[0065] Specifically, according to the topographic trend of high-altitude mountainous areas, when photovoltaic panels are installed in high-altitude mountainous areas, all photovoltaic panels present different heights in space, and the spatial coordinates or height positions of the photovoltaic panels can be recorded in the label information of the photovoltaic panels. According to the label information of the photovoltaic panels, the label information may include the location height or spatial coordinate information of the photovoltaic panels to group photovoltaic panels at different heights, divide photovoltaic panels at the same height into the same group, and number the photovoltaic panel groups in the order of gradually increasing or gradually decreasing relative heights.

[0066] Optionally, the tag information includes serial number information and / or location information of the photovoltaic panels, and the photovoltaic panels at the same height are divided into the same group.

[0067] Optionally, the tag information may include only the number information of the photovoltaic panel, or only the location information of the photovoltaic panel, or may include both the number information and the location information of the photovoltaic panel; when the tag information includes only the number information of the photovoltaic panel, the number information should include the relative height of the installation position of the photovoltaic panel, that is, all photovoltaic panels are based on the same height, so as to obtain the relative height information of all photovoltaic panels. Photovoltaic panels at the same height are divided into the same group, and each photovoltaic panel group is numbered to facilitate subsequent error analysis and model application.

[0068] Specifically, an example is shown in the following table:

[0069]

[0070] S2. Obtain historical power prediction data and corresponding actual power data of each group of photovoltaic panels, and calculate error data of each group of photovoltaic panels based on the historical power prediction data and the corresponding actual power data.

[0071] Optionally, the error data is used to characterize the prediction accuracy of the historical power generation of the photovoltaic panel. When the error data value is too large, the power prediction accuracy is low; when the error data value is too small, the power prediction accuracy is high. Photovoltaic panel groups are installed at different heights in high-altitude mountainous areas. At the same time, the photovoltaic panel group at a relatively low position may be blocked by mountains or trees, and the area of ​​the photovoltaic panel directly shining on the sun is small, while the photovoltaic panel at a relatively high position is not blocked, and the sun can directly shine on the photovoltaic panel. Using the same prediction model, the theoretical prediction data of the photovoltaic panel group at a lower position deviates from the actual data, which may lead to lower prediction accuracy for the photovoltaic panel group at a lower position.

[0072] Optionally, the error data is obtained based on the root mean square error, and the root mean square error is calculated as follows:

[0073] Wherein, di is the difference between the historical power prediction data and the corresponding actual power data, and n is the number of historical power prediction data.

[0074] S3. According to the error data, divide all photovoltaic panel groups into a first photovoltaic cluster whose error data is within a first preset interval and a second photovoltaic cluster whose error data is within a second preset interval.

[0075] Optionally, the first preset interval is smaller than the second preset interval, and the maximum value of the error data in the first preset interval is smaller than the minimum value of the second preset interval, that is, the deviation between the historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster and the corresponding actual power data is smaller than the deviation between the historical power prediction data of the photovoltaic panel group of the second photovoltaic cluster and the corresponding actual power data, indicating that the historical power prediction accuracy of the first photovoltaic cluster is higher than that of the second photovoltaic cluster.

[0076] Optionally, the preset interval can be a ratio or an accuracy, such as sorting all the error numbers in ascending order, dividing the photovoltaic panel groups in the first 20%-30% of the sort into the first photovoltaic cluster, and dividing the remaining photovoltaic panel groups into the second photovoltaic cluster. The specific ratio can be 20%, 22%, 25%, 28% or 30%, preferably 25%.

[0077] Optionally, identifying whether there is an abnormal photovoltaic panel group in the first photovoltaic cluster and the second photovoltaic cluster according to the label information of the photovoltaic panels;

[0078] If present, the cluster of abnormal photovoltaic panel groups is corrected.

[0079] Optionally, the method for abnormality identification is that when the error data of a photovoltaic panel group is different from the clusters of photovoltaic panel groups adjacent to the photovoltaic panel group, the photovoltaic panel group is recorded as an abnormal photovoltaic panel group, and if the abnormality occurs continuously, a warning message is issued or manual marking is performed.

[0080] When an abnormal photovoltaic panel group appears in the first photovoltaic cluster, the error data of the abnormal photovoltaic panel group is outside the first preset interval, that is, the power prediction data of the photovoltaic panel group deviates greatly from the actual power data. At this time, some photovoltaic panels in the abnormal photovoltaic panel group fail, or the surface cleanliness of the photovoltaic panels is low, and an alarm message is issued to remind the administrator to deal with the abnormal photovoltaic panels.

[0081] When an abnormal photovoltaic panel group appears in the second photovoltaic cluster, the error data of the abnormal photovoltaic panel group is outside the second preset interval.

[0082] S4. Responding to a photovoltaic power prediction request.

[0083] Optionally, the photovoltaic power prediction request may be issued regularly by the photovoltaic power station to coordinate power allocation of the photovoltaic power station, and the photovoltaic power prediction request may also be issued by a background administrator.

[0084] S5. Using a first prediction model, inputting a first characteristic parameter related to the power generation of the first photovoltaic cluster to obtain first power prediction data;

[0085] Optionally, the first prediction model may be a model for obtaining historical power prediction data of photovoltaic panels in a preset area.

[0086] Optionally, the step of obtaining first power prediction data by inputting a first characteristic parameter related to the power generation power of the first photovoltaic cluster through a first prediction model includes:

[0087] Obtaining a first characteristic parameter related to the power generation of the first photovoltaic cluster according to the tag information of the photovoltaic panels in the first photovoltaic cluster;

[0088] By using a first prediction model, a first characteristic parameter related to the power generation of the first photovoltaic cluster is input to obtain first power prediction data;

[0089] The step of inputting a second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data through a second prediction model to obtain second power prediction data includes:

[0090] Obtaining a second characteristic parameter related to the power generation of the second photovoltaic cluster according to the tag information of the photovoltaic panels in the second photovoltaic cluster;

[0091] The second power prediction data is obtained by inputting a second characteristic parameter related to the power generation of the second photovoltaic cluster and the first power prediction data through the second prediction model.

[0092] Optionally, the first characteristic parameter is obtained through the photovoltaic panel tag information of the first cluster and historical meteorological data, and the first characteristic parameter may be one or more of parameters such as solar irradiance, temperature, type of photovoltaic panel, and installation angle of photovoltaic panel. The second characteristic parameter is obtained through the photovoltaic panel tag information of the second cluster and historical meteorological data, and the second characteristic parameter may be one or more of parameters such as solar irradiance, temperature, type of photovoltaic panel, installation angle of photovoltaic panel, wind speed, wind direction, etc.

[0093] Optionally, the first prediction model is used to input a first characteristic parameter related to the power generation of the first photovoltaic cluster, and the specific steps of obtaining the first power prediction data include:

[0094] According to the label information of the photovoltaic panels in the first photovoltaic cluster (such as number, location, installation angle, inclination, photovoltaic panel type, etc.), first characteristic parameters related to the power generation of these photovoltaic panels are collected. These parameters may include historical weather data (such as solar radiation, temperature, cloud thickness, etc.), equipment status data (such as photovoltaic panel temperature, inverter efficiency, etc.) and other external factors that may affect the power generation.

[0095] The collected first feature parameters are preprocessed to eliminate noise, outliers or missing values ​​in the data. This may include steps such as data cleaning, standardization, and normalization to ensure the quality and consistency of the input data.

[0096] The preprocessed first feature parameter is passed as input data to the first prediction model. This can be achieved through a programming interface, database query or other data exchange mechanism.

[0097] After receiving the input data, the first prediction model will perform calculations based on its internal algorithms and parameters.

[0098] After the first prediction model is calculated, the power generation prediction data of the first photovoltaic cluster will be generated. These data can be presented in numerical values, charts or other visual forms so that users or systems can intuitively understand the prediction results.

[0099] Optionally, before taking the historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster as input, the method further includes:

[0100] The photovoltaic panel groups in the first photovoltaic cluster and the second photovoltaic cluster are sorted in descending order according to the error data;

[0101] adding the photovoltaic panel groups of the first preset proportion before sorting in the second photovoltaic cluster to the first photovoltaic cluster;

[0102] The photovoltaic panel groups with a second preset ratio after being sorted in the first photovoltaic cluster are added to the second photovoltaic cluster.

[0103] Optionally, the first preset ratio and the second preset ratio can both be 5%-10%, such as 5%, 6%, 7%, 8%, 9% or 10%, preferably 7%. Through the above steps, the photovoltaic panel groups in the first photovoltaic cluster and the second photovoltaic cluster can be dynamically optimized to improve the photovoltaic power prediction accuracy.

[0104] S6. Using a second prediction model, inputting a second characteristic parameter related to the power generation of the second photovoltaic cluster and the first power prediction data to obtain second power prediction data;

[0105] Optionally, the first power prediction data is the result obtained after inputting the first characteristic parameter of the first photovoltaic cluster into the first prediction model. The power data accuracy of the photovoltaic panel group of the first photovoltaic cluster is higher than the prediction accuracy of the photovoltaic panel group of the second photovoltaic cluster. When obtaining the second power prediction data, the first power prediction data is used as an anchor point, and the second characteristic parameter of the second photovoltaic cluster is input into the second prediction model to output the second power prediction data. In high-altitude mountainous areas, when sunlight shines on photovoltaic panels, affected by the incident angle of sunlight, photovoltaic panel groups located at lower positions are easily blocked by other mountains or trees, forming shadows on the photovoltaic panels, while photovoltaic panel groups located at higher positions are not easily blocked by other mountains. The coverage of shadows should be normal power generation of photovoltaic panels. The position of shadow coverage and the impact it causes are greatly affected by the position of the sun, but the parameters of the sun's position are not easy to collect. The sun's position will also affect the power of photovoltaic panels at higher positions. Photovoltaic panels at higher positions are less affected by shadows, and their photovoltaic power prediction accuracy is high. We introduce the power of photovoltaic panels at higher positions into the second prediction model, establish the connection between photovoltaic panels at lower positions and the position of the sun, and improve the accuracy of power prediction for photovoltaic panels at lower positions.

[0106] Through the above steps, the prediction accuracy of the power generation of the photovoltaic panel group of the second photovoltaic cluster is improved.

[0107] Optionally, the step of obtaining the second prediction model includes:

[0108] The historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster is used as input, and the corresponding actual power data is used as output to train the first prediction model and obtain the second prediction model.

[0109] Optional, include the following steps:

[0110] The historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster is collected, and the historical power prediction data may come from the output of a previous prediction model or algorithm.

[0111] At the same time, actual power data within the time period corresponding to these historical prediction data are collected, and these data usually come from real-time monitoring or recording of the photovoltaic power generation system.

[0112] Ensure that historical power forecast data is aligned with actual power data in time, that is, each forecast value has a corresponding actual value for comparison.

[0113] Carry out necessary cleaning and organization of data, remove outliers, process missing data, etc., to ensure data quality.

[0114] Select a suitable prediction model as the first prediction model. This can be a statistical-based method, a machine learning algorithm, or a deep learning model, etc.

[0115] The first prediction model is trained using the historical power prediction data and the corresponding actual power data as training data.

[0116] The prediction performance of the model is optimized by continuously adjusting the parameters and structure of the model. This usually involves iteratively updating the weights and bias terms of the model to minimize the prediction error.

[0117] S7. Obtain power prediction data of the photovoltaic panels in the target area according to the first power prediction data and the second power prediction data.

[0118] Optionally, by comparing the historical photovoltaic power prediction data of the photovoltaic panel group in the target area with the corresponding actual photovoltaic power data, the photovoltaic panel group in the target area is divided into a first photovoltaic cluster and a second photovoltaic cluster. The first photovoltaic cluster obtains the first power prediction data through the first characteristic parameter and the first prediction model, and the second photovoltaic cluster obtains the second power prediction data through the second characteristic parameter, the first power prediction data and the second prediction model. The first prediction model focuses on processing the first photovoltaic cluster with a smaller error, while the second prediction model uses the first power prediction data as one of the inputs to make a more detailed prediction of the second photovoltaic cluster with a larger error. This progressive prediction method helps to improve the accuracy of the overall prediction.

[0119] Example 3

[0120] Based on Embodiment 1, this embodiment provides a system for predicting photovoltaic power in high-altitude mountainous areas, including:

[0121] A grouping module is configured to group the photovoltaic panels according to the tag information of the photovoltaic panels in the target area;

[0122] A data acquisition module is configured to acquire historical power prediction data and corresponding actual power data of each group of photovoltaic panels;

[0123] A data processing module is configured to calculate error data of each group of photovoltaic panels based on historical power prediction data and corresponding actual power data;

[0124] a data analysis module configured to divide all photovoltaic panel groups into a first photovoltaic cluster whose error data is within a first preset interval and a second photovoltaic cluster whose error data is within a second preset interval according to the error data;

[0125] a response module configured to respond to the photovoltaic power prediction request;

[0126] A characteristic parameter acquisition module, configured to acquire a first characteristic parameter related to the power generation of the first photovoltaic cluster and a second characteristic parameter related to the power generation of the second photovoltaic cluster;

[0127] The power prediction module is configured to obtain first power prediction data by inputting a first characteristic parameter through a first prediction model, and obtain second power prediction data by inputting a second characteristic parameter and the first power prediction data through a second prediction model;

[0128] The power prediction data acquisition module is configured to obtain power prediction data of the photovoltaic panels in the target area according to the first power prediction data and the second power prediction data.

[0129] Example 4

[0130] Based on Embodiment 1, this embodiment provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0131] Specifically, Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage; the processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0132] Those skilled in the art will understand that Figure 2 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0133] like Figure 2As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and a method for implementing photovoltaic power prediction for high-altitude mountain areas.

[0134] exist Figure 2 In the electronic device shown, the network interface 103 is mainly used for data communication with a network server; the user interface 104 is mainly used for data interaction with a user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the application program for the method for high-altitude mountain photovoltaic power prediction stored in the memory 105 through the processor 101 to implement any of the above methods.

[0135] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for predicting photovoltaic power in high-altitude mountainous areas, characterized in that: include: The photovoltaic panels are grouped according to the label information of the photovoltaic panels in the target area; The tag information includes the number information and / or location information of the photovoltaic panels, and the photovoltaic panels at the same height are divided into the same group; Obtaining historical power prediction data and corresponding actual power data of each group of photovoltaic panels, and calculating error data of each group of photovoltaic panels according to the historical power prediction data and the corresponding actual power data; According to the error data, all photovoltaic panel groups are divided into a first photovoltaic cluster whose error data is within a first preset interval and a second photovoltaic cluster whose error data is within a second preset interval; The first preset interval is smaller than the second preset interval; responding to a photovoltaic power forecast request; By using a first prediction model, a first characteristic parameter related to the power generation of the first photovoltaic cluster is input to obtain first power prediction data; By using a second prediction model, inputting a second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data, obtaining second power prediction data; The step of obtaining the second prediction model comprises: Taking the historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster as input and the corresponding actual power data as output, training the first prediction model to obtain the second prediction model; Power prediction data of the photovoltaic panels in the target area is obtained according to the first power prediction data and the second power prediction data.

2. The method for predicting photovoltaic power in high altitude mountainous areas according to claim 1, characterized in that: The step of inputting a first characteristic parameter related to the power generation power of the first photovoltaic cluster through a first prediction model to obtain first power prediction data includes: Obtaining a first characteristic parameter related to the power generation of the first photovoltaic cluster according to the tag information of the photovoltaic panels in the first photovoltaic cluster; By using a first prediction model, a first characteristic parameter related to the power generation of the first photovoltaic cluster is input to obtain first power prediction data; The step of inputting a second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data through a second prediction model to obtain second power prediction data includes: Obtaining a second characteristic parameter related to the power generation of the second photovoltaic cluster according to the tag information of the photovoltaic panels in the second photovoltaic cluster; A second characteristic parameter related to the power generation power of the second photovoltaic cluster and the first power prediction data are input through a second prediction model to obtain second power prediction data.

3. The method for predicting photovoltaic power in high altitude mountainous areas according to claim 1, characterized in that: include: According to the tag information, identifying whether there is an abnormal photovoltaic panel group in the first photovoltaic cluster and the second photovoltaic cluster; If so, the first photovoltaic cluster or the second photovoltaic cluster where the abnormal photovoltaic panel group is located is corrected.

4. The method for predicting photovoltaic power in high altitude mountainous areas according to claim 1, characterized in that: Before taking the historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster as input, the method further includes: Sorting the photovoltaic panel groups in the first photovoltaic cluster and the second photovoltaic cluster in descending order of error data; adding photovoltaic panel groups of a first preset proportion before sorting in the second photovoltaic cluster to the first photovoltaic cluster; The photovoltaic panel groups with a second preset ratio after sorting in the first photovoltaic cluster are added to the second photovoltaic cluster.

5. The method for predicting photovoltaic power in high altitude mountain areas according to claim 1, characterized in that: The error data is obtained according to the root mean square error, and the calculation formula of the root mean square error is as follows: Wherein, di is the difference between the historical power prediction data and the corresponding actual power data, and n is the number of historical power prediction data.

6. A system for predicting photovoltaic power in high-altitude mountainous areas, characterized in that: include: A grouping module is configured to group the photovoltaic panels according to the tag information of the photovoltaic panels in the target area; The tag information includes the number information and / or location information of the photovoltaic panels, and the photovoltaic panels at the same height are divided into the same group; A data acquisition module is configured to acquire historical power prediction data and corresponding actual power data of each group of photovoltaic panels; A data processing module, configured to calculate error data of each group of photovoltaic panels according to the historical power prediction data and the corresponding actual power data; a data analysis module configured to divide all photovoltaic panel groups into a first photovoltaic cluster whose error data is within a first preset interval and a second photovoltaic cluster whose error data is within a second preset interval according to the error data; The first preset interval is smaller than the second preset interval; a response module configured to respond to the photovoltaic power prediction request; a characteristic parameter acquisition module, configured to acquire a first characteristic parameter related to the power generation of the first photovoltaic cluster and a second characteristic parameter related to the power generation of the second photovoltaic cluster; The power prediction module is configured to obtain first power prediction data by inputting a first characteristic parameter through a first prediction model, and obtain second power prediction data by inputting a second characteristic parameter and the first power prediction data through a second prediction model; The step of obtaining the second prediction model comprises: Taking the historical power prediction data of the photovoltaic panel group of the first photovoltaic cluster as input and the corresponding actual power data as output, training the first prediction model to obtain the second prediction model; The power prediction data acquisition module is configured to obtain power prediction data of the photovoltaic panels in the target area according to the first power prediction data and the second power prediction data.

7. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 5.

Images