Photovoltaic generating capacity prediction method and system based on solar radiation model

Abstract

The invention discloses a photovoltaic power generation capacity prediction method and system based on a solar radiation model, and the method comprises the steps: obtaining and preprocessing the historical meteorological data of a region where photovoltaic power generation is located, analyzing the historical meteorological data, and determining the key features related to solar radiation in the historical meteorological data; building a solar radiation model based on the data corresponding to the key features and a preset neural network model, and predicting solar radiation prediction data in a period of time in the future through the solar radiation model; standard electric energy conversion characteristics of the photovoltaic cell under solar radiation are obtained, and stage electric energy conversion characteristics of the photovoltaic cell in different solar radiation stages are determined based on the solar radiation prediction data and the standard electric energy conversion characteristics; and predicting the photovoltaic generating capacity of different solar radiation stages based on the stage electric energy conversion characteristics and the solar radiation prediction data. The photovoltaic generating capacity is predicted based on the solar radiation model, the photovoltaic generating capacity in a period of time in the future can be accurately predicted, and important support is provided for energy planning and management.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to a photovoltaic power generation prediction method and system based on a solar radiation model. Background Art

[0002] As the demand for renewable energy continues to grow, photovoltaic power generation, as an important source of clean energy, has received widespread attention. In the planning and management of photovoltaic power generation systems, accurate prediction of photovoltaic power generation is of great significance for optimizing energy utilization, improving power generation efficiency, and rationally arranging grid dispatch. The prediction of photovoltaic power generation needs to consider multiple factors, among which solar radiation is one of the key factors affecting photovoltaic power generation. Changes in solar radiation will directly affect the power generation efficiency of photovoltaic cells. Therefore, predicting solar radiation is crucial to accurately predicting photovoltaic power generation.

[0003] However, traditional prediction methods usually cannot fully consider the impact of solar radiation on photovoltaic power generation, because they often rely on simple statistical features in meteorological data, and ignore the impact of changes in solar radiation on power generation, resulting in inaccurate prediction results. In addition, traditional prediction methods usually ignore the power conversion characteristics of photovoltaic cells under different solar radiation conditions. The output of photovoltaic cells is affected by multiple factors such as light intensity and temperature, and traditional methods fail to fully consider the impact of these factors on different radiation stages, resulting in a large deviation between the prediction results and the actual power generation. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a photovoltaic power generation prediction method and system based on a solar radiation model, comprising:

[0005] Obtain historical meteorological data of the area where photovoltaic power generation is located and pre-process the historical meteorological data;

[0006] Analyze the preprocessed historical meteorological data to determine the key features related to solar radiation in the historical meteorological data;

[0007] A solar radiation model is constructed based on the data corresponding to the key features and the preset neural network model, and the solar radiation forecast data for a period of time in the future is predicted through the solar radiation model;

[0008] Obtaining the standard power conversion characteristics of photovoltaic cells under solar radiation, and determining the stage power conversion characteristics of photovoltaic cells in different solar radiation stages based on solar radiation prediction data and the standard power conversion characteristics;

[0009] The photovoltaic power generation in different solar radiation stages is predicted based on the stage power conversion characteristics and solar radiation prediction data.

[0010] Furthermore, the acquisition of historical meteorological data of the region where the photovoltaic power generation is located and preprocessing of the historical meteorological data include:

[0011] Obtain historical meteorological data in the area where photovoltaic power generation is located, clean the historical meteorological data, and remove noise, missing values, and outliers in the data;

[0012] The cleaned historical meteorological data are normalized.

[0013] Furthermore, the pre-processed historical meteorological data is analyzed to determine key features related to solar radiation in the historical meteorological data, including:

[0014] The pre-processed historical meteorological data are parsed into several parameter data groups according to parameter types, and the correlation between each parameter data group and solar radiation is analyzed;

[0015] The average value of the correlation between all parameter data groups and solar radiation is calculated, and the parameter data groups that exceed the average value are screened out and identified as the key features related to solar radiation in the historical meteorological data.

[0016] Furthermore, the analysis of the correlation between each parameter data group and solar radiation includes:

[0017] Acquire existing solar radiation prediction data, and aggregate the solar radiation prediction data to obtain a solar radiation prediction data group;

[0018] Calculating the correlation between each parameter data set and the solar radiation prediction data set, and calculating the sum of the correlations between all parameter data sets and the solar radiation prediction data set;

[0019] Calculate the ratio of each correlation to the total, and use the ratio as the weight corresponding to each parameter data group;

[0020] The inter-data group standard deviation between each parameter data group and the solar radiation prediction data group is calculated, and the inter-data group standard deviation is evaluated and valued to obtain the associated evaluation value of each parameter data group. The calculation formula of the associated evaluation value is as follows:

[0021]

[0022] Among them, S is the correlation evaluation value of each parameter data group, α is the data difference coefficient, Mi is the i-th data in the parameter data group, Ni is the i-th data in the solar radiation prediction data group, and n is the number of data in the data group;

[0023] The correlation evaluation value of each parameter data group is weightedly added to the corresponding weight to obtain the correlation degree between each parameter data group and solar radiation.

[0024] Furthermore, the solar radiation model is constructed based on the data corresponding to the key features and the preset neural network model, and the solar radiation prediction data for a period of time in the future is predicted by the solar radiation model, including:

[0025] The data corresponding to the key features are used as a data set, and the data set is input into a preset neural network model to construct an initial solar radiation model;

[0026] The data set is divided into a training set and a test set according to a certain ratio, and the training set and the test set are input into the solar radiation initial model, and the relationship initial model is trained and tested until the solar radiation initial model meets the preset convergence conditions, thereby obtaining a solar radiation model;

[0027] Real-time meteorological data of the photovoltaic power generation area is obtained, and the real-time meteorological data is input into the solar radiation model, and the solar radiation model is used to predict the solar radiation forecast data for a period of time in the future.

[0028] Furthermore, the step of obtaining the standard power conversion characteristics of the photovoltaic cell and determining the stage power conversion characteristics of the photovoltaic cell at different solar radiation stages based on the solar radiation prediction data and the standard power conversion characteristics includes:

[0029] Obtain solar radiation prediction data, and draw a solar radiation curve graph based on the solar radiation prediction data;

[0030] Calculate the average radiation value of the solar radiation prediction data, determine the valley points in the solar radiation curve that are lower than the average radiation value, and divide the solar radiation prediction data into several solar radiation stages according to the valley points;

[0031] Determine the total solar radiation in each solar radiation stage, and calculate the difference between the total solar radiation in each solar radiation stage and the standard solar radiation;

[0032] The adjustment coefficient of each solar radiation stage is determined according to the difference in radiation amount, and the standard electric energy conversion characteristic is adjusted according to the adjustment coefficient to obtain the stage electric energy conversion characteristic of each solar radiation stage.

[0033] Furthermore, determining the adjustment coefficient of each solar radiation stage according to the radiation difference includes:

[0034] The preset adjustment coefficient-radiation difference interval correspondence relationship is that the adjustment coefficient-radiation difference interval correspondence relationship is associated with a corresponding adjustment coefficient for each radiation difference interval;

[0035] The radiation difference is obtained, and based on the mapping relationship between the radiation difference interval to which the radiation difference belongs and the adjustment coefficient corresponding to the radiation difference interval is selected as the adjustment coefficient for each solar radiation stage.

[0036] Furthermore, the photovoltaic power generation in different solar radiation stages is predicted based on the stage power conversion characteristics and solar radiation prediction data, including:

[0037] The solar radiation prediction data is divided into several solar radiation stage data groups according to the solar radiation stage, and a photovoltaic power generation physical model is established according to the stage power conversion characteristics;

[0038] The data sets of each solar radiation stage are input into the photovoltaic power generation physical model to obtain the photovoltaic power generation in different solar radiation stages.

[0039] The present invention also provides a photovoltaic power generation prediction system based on a solar radiation model, comprising:

[0040] A preprocessing module is used to obtain historical meteorological data of the area where photovoltaic power generation is located and preprocess the historical meteorological data;

[0041] An analysis module is used to analyze the pre-processed historical meteorological data and determine the key features related to solar radiation in the historical meteorological data;

[0042] A modeling module is used to build a solar radiation model based on the data corresponding to the key features and a preset neural network model, and to predict the solar radiation forecast data for a period of time in the future through the solar radiation model;

[0043] A determination module is used to obtain the standard power conversion characteristics of the photovoltaic cell under solar radiation, and determine the stage power conversion characteristics of the photovoltaic cell in different solar radiation stages based on the solar radiation prediction data and the standard power conversion characteristics;

[0044] The prediction module is used to predict the photovoltaic power generation in different solar radiation stages based on the stage power conversion characteristics and solar radiation prediction data.

[0045] Compared with the prior art, the photovoltaic power generation prediction method and system based on the solar radiation model in the embodiment of the present invention has the following beneficial effects:

[0046] The present invention can ensure the good quality of data used for modeling and analysis by acquiring historical meteorological data of the area where photovoltaic power generation is located and effectively preprocessing the data, thereby improving the accuracy and reliability of the model;

[0047] The present invention analyzes historical meteorological data to determine key features related to solar radiation, which helps to accurately capture the factors that affect changes in solar radiation and provides effective input variables for modeling;

[0048] The present invention constructs a solar radiation model based on determined key features and historical meteorological data, which can help predict solar radiation forecast data for a period of time in the future and provide support for the operation and power generation forecast of photovoltaic power generation systems;

[0049] The present invention can improve the accuracy of photovoltaic power generation prediction by obtaining the standard power conversion characteristics of photovoltaic cells and determining the stage power conversion characteristics of photovoltaic cells in different solar radiation stages based on solar radiation prediction data and the standard power conversion characteristics;

[0050] The present invention can predict photovoltaic power generation in different solar radiation stages by combining the stage power conversion characteristics and solar radiation prediction data, and provide a reference for the operation of photovoltaic power generation system and power generation prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 Schematic diagram of the process structure of a photovoltaic power generation prediction method based on a solar radiation model in an embodiment of the present invention;

[0052] Figure 2 It is a schematic diagram of the composition of a photovoltaic power generation prediction system based on a solar radiation model in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0054] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are the orientation or position relationship shown in the accompanying drawings, which are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0055] The terms "second" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined with "second" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "multiple" means two or more.

[0056] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it 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 it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0057] like Figure 1 As shown, in an embodiment of the present application, a method for predicting photovoltaic power generation based on a solar radiation model is provided, including: S100: obtaining historical meteorological data of the area where photovoltaic power generation is located, and preprocessing the historical meteorological data; S200: analyzing the preprocessed historical meteorological data to determine key features related to solar radiation in the historical meteorological data; S300: constructing a solar radiation model based on data corresponding to the key features and a preset neural network model, and predicting solar radiation prediction data for a period of time in the future through the solar radiation model; S400: obtaining standard electric energy conversion characteristics of photovoltaic cells under solar radiation, and determining the stage electric energy conversion characteristics of photovoltaic cells in different solar radiation stages based on the solar radiation prediction data and the standard electric energy conversion characteristics; S500: predicting photovoltaic power generation in different solar radiation stages based on the stage electric energy conversion characteristics and the solar radiation prediction data.

[0058] Furthermore, the present invention can ensure the good quality of data used for modeling and analysis by obtaining historical meteorological data of the area where photovoltaic power generation is located and effectively preprocessing the data, thereby improving the accuracy and reliability of the model; the present invention determines the key features related to solar radiation by analyzing historical meteorological data, which helps to accurately capture the factors affecting the change of solar radiation and provides effective input variables for modeling; the present invention constructs a solar radiation model based on the determined key features and historical meteorological data, which can help predict the solar radiation forecast data for a period of time in the future, and provide support for the operation and power generation forecast of the photovoltaic power generation system; the present invention obtains the standard power conversion characteristics of photovoltaic cells, and determines the stage power conversion characteristics of photovoltaic cells in different solar radiation stages based on the solar radiation forecast data and the standard power conversion characteristics, so as to improve the accuracy of photovoltaic power generation forecast; the present invention can predict the photovoltaic power generation in different solar radiation stages by combining the stage power conversion characteristics and solar radiation forecast data, and provide a reference for the operation and power generation forecast of the photovoltaic power generation system.

[0059] In an embodiment of the present application, a method for predicting photovoltaic power generation based on a solar radiation model is provided, wherein historical meteorological data of the region where photovoltaic power generation is located is obtained and the historical meteorological data is preprocessed, including: obtaining historical meteorological data of the region where photovoltaic power generation is located, cleaning the historical meteorological data to remove noise, missing values ​​and outliers in the data; and performing data normalization on the cleaned historical meteorological data.

[0060] Specifically, obtain these data from local meteorological stations, meteorological departments or professional meteorological data service providers; remove noise from the data, which may come from sensor errors, data transmission problems or other interference sources. By using filtering technology or smoothing algorithms, you can try to remove these noises to ensure the accuracy of the data; check whether there are missing values ​​in the data (such as blank data or NaN), and decide how to deal with these missing values, choose to fill the missing values ​​(such as using interpolation methods), or discard these missing values ​​(if the missing values ​​account for a small proportion); detect and handle outliers, which may be caused by equipment failure or other abnormal conditions, and use statistical methods (such as the 3σ principle) or methods based on domain knowledge to identify and handle outliers; after cleaning the data, you can then perform data normalization to unify data with different features into a smaller range to avoid the impact of numerical differences between different features on modeling. By cleaning historical meteorological data and performing data normalization, a high-quality data foundation can be provided for the subsequent construction of solar radiation models and photovoltaic power generation prediction modeling.

[0061] In an embodiment of the present application, a method for predicting photovoltaic power generation based on a solar radiation model is provided, wherein the preprocessed historical meteorological data is analyzed to determine key features related to solar radiation in the historical meteorological data, including: parsing the preprocessed historical meteorological data into several parameter data groups according to parameter type, and analyzing the degree of correlation between each parameter data group and solar radiation; calculating the average value of the degree of correlation between all parameter data groups and solar radiation, screening out parameter data groups that exceed the average value, and determining them as key features related to solar radiation in the historical meteorological data.

[0062] Specifically, the pre-processed historical meteorological data are parsed according to parameter types, such as temperature, humidity, wind speed, air pressure, and solar radiation intensity, and they are divided into different parameter data groups; the correlation degree between each parameter data group and solar radiation is analyzed, and a higher correlation degree indicates a stronger correlation between the parameter data group and solar radiation; the average value of the correlation degree between all parameter data groups and solar radiation is calculated, and the parameter data groups that exceed the average value, that is, the parameter data groups with a higher correlation with solar radiation, are determined as the key features related to solar radiation in the historical meteorological data. This step can determine the key features related to solar radiation in the historical meteorological data, which will provide important input variables for building solar radiation models and photovoltaic power generation prediction models.

[0063] In an embodiment of the present application, a photovoltaic power generation prediction method based on a solar radiation model is provided, wherein the analysis of the correlation between each parameter data group and solar radiation includes: obtaining existing solar radiation prediction data, and aggregating the solar radiation prediction data to obtain a solar radiation prediction data group; calculating the correlation between each parameter data group and the solar radiation prediction data group, and calculating the sum of the correlations between all parameter data groups and the solar radiation prediction data groups; calculating the ratio of each correlation to the sum, and using the ratio as the weight corresponding to each parameter data group; calculating the standard deviation between each parameter data group and the solar radiation prediction data group, and evaluating the standard deviation between each data group to obtain the correlation evaluation value of each parameter data group, and the calculation formula of the correlation evaluation value is as follows:

[0064]

[0065] Among them, S is the correlation evaluation value of each parameter data group, α is the data difference coefficient, Mi is the i-th data in the parameter data group, Ni is the i-th data in the solar radiation prediction data group, and n is the number of data in the data group; the correlation evaluation value of each parameter data group is weightedly added to the corresponding weight to obtain the degree of correlation between each parameter data group and solar radiation.

[0066] Specifically, solar radiation prediction data is obtained and integrated into a solar radiation prediction data group; the correlation between each parameter data group and the solar radiation prediction data group is obtained, and the sum of the correlations between all parameter data groups and the solar radiation prediction data group is calculated; the ratio of each correlation to the sum is calculated, and the ratio is used as the weight corresponding to each parameter data group, indicating the importance of each parameter data group for solar radiation prediction; the standard deviation between each parameter data group and the solar radiation prediction data group is calculated; the standard deviation between each data group is evaluated and the associated evaluation value of each parameter data group is obtained to indicate the data quality and stability of each parameter data group; the associated evaluation value of each parameter data group is weighted and added to the corresponding weight to obtain the degree of association between each parameter data group and solar radiation. This step can obtain the degree of association between each parameter data group and solar radiation, which can provide an important feature selection basis for the photovoltaic power generation prediction model.

[0067] In an embodiment of the present application, a method for predicting photovoltaic power generation based on a solar radiation model is provided, wherein a solar radiation model is constructed based on data corresponding to key features and a preset neural network model, and solar radiation prediction data for a period of time in the future is predicted through the solar radiation model, including: taking the data corresponding to the key features as a data set, and inputting the data set into a preset neural network model to construct an initial solar radiation model; dividing the data set into a training set and a test set according to a certain ratio, and inputting the training set and the test set into the initial solar radiation model, training and testing the initial solar radiation model until the initial solar radiation model meets the preset convergence conditions, and obtaining a solar radiation model; acquiring real-time meteorological data in the area where photovoltaic power generation is located, and inputting the real-time meteorological data into the solar radiation model, and predicting the solar radiation prediction data for a period of time in the future by the solar radiation model.

[0068] Specifically, the data corresponding to the key features are used as a data set, and then the data set is input into a preset neural network model to build an initial solar radiation model; the data set is divided into a training set and a test set according to a certain ratio. The common division ratio is 80% of the data for training and 20% of the data for testing. The training set and the test set are input into the initial solar radiation model to train and test the model. During the training process, the model parameters are continuously adjusted through the back propagation algorithm and the optimizer until the model meets the preset convergence conditions; the trained model is the solar radiation model, which can be used to predict solar radiation data for a period of time in the future, obtain real-time meteorological data in the area where photovoltaic power generation is located, and input the real-time meteorological data into the solar radiation model. The model will process the real-time meteorological data and then predict solar radiation data for a period of time in the future.

[0069] In an embodiment of the present application, a method for predicting photovoltaic power generation based on a solar radiation model is provided, wherein the standard power conversion characteristics of a photovoltaic cell are obtained, and the stage power conversion characteristics of the photovoltaic cell in different solar radiation stages are determined based on the solar radiation prediction data and the standard power conversion characteristics, including: obtaining solar radiation prediction data, and drawing a solar radiation curve diagram according to the solar radiation prediction data; calculating the radiation average value of the solar radiation prediction data, and determining the valley points in the solar radiation curve diagram that are lower than the radiation average value, and dividing the solar radiation prediction data into several solar radiation stages according to the valley points; determining the total solar radiation of each solar radiation stage, and calculating the radiation difference between the total solar radiation of each solar radiation stage and the standard solar radiation; determining the adjustment coefficient of each solar radiation stage according to the radiation difference, and adjusting the standard power conversion characteristics according to the adjustment coefficient to obtain the stage power conversion characteristics of each solar radiation stage.

[0070] Specifically, obtain solar radiation forecast data from the meteorological department or a reliable meteorological data provider and use it for subsequent processing; use data visualization tools (such as matplotlib) to draw a solar radiation curve based on the obtained solar radiation forecast data, so as to intuitively understand the changing trend of solar radiation; calculate the average value of the solar radiation forecast data to obtain the average value of the solar radiation, determine the valley points below the radiation average, and divide the solar radiation forecast data into several solar radiation stages based on these valley points; determine the total solar radiation of each solar radiation stage, and calculate the radiation difference between the total solar radiation of each solar radiation stage and the standard solar radiation; determine the adjustment coefficient of each solar radiation stage based on the radiation difference; adjust the standard electric energy conversion characteristics according to the adjustment coefficient to obtain the stage electric energy conversion characteristics of each solar radiation stage.

[0071] In an embodiment of the present application, a photovoltaic power generation prediction method based on a solar radiation model is provided, and the adjustment coefficient of each solar radiation stage is determined according to the radiation difference, including: a preset adjustment coefficient-radiation difference interval correspondence relationship, and the adjustment coefficient-radiation difference interval correspondence relationship is associated with a corresponding adjustment coefficient for each radiation difference interval; the radiation difference is obtained, and based on a mapping relationship between the radiation difference interval to which the radiation difference belongs within the adjustment coefficient-radiation difference interval correspondence relationship, the adjustment coefficient corresponding to the radiation difference interval is selected as the adjustment coefficient for each solar radiation stage.

[0072] Specifically, a preset adjustment coefficient-radiation amount difference interval correspondence is defined, and the preset adjustment coefficient-radiation amount difference interval correspondence is defined as a mapping table or function, and a specific value is obtained from the calculated radiation amount difference of each solar radiation stage; based on the interval to which the radiation amount difference belongs, mapping is performed within the preset adjustment coefficient-radiation amount difference interval correspondence, and the adjustment coefficient corresponding to the radiation amount difference interval is selected as the adjustment coefficient for each solar radiation stage; the selected adjustment coefficient is applied to the corresponding solar radiation stage to adjust the standard electric energy conversion characteristics, so as to obtain the stage electric energy conversion characteristics of each solar radiation stage.

[0073] In an embodiment of the present application, a method for predicting photovoltaic power generation based on a solar radiation model is provided, wherein the photovoltaic power generation in different solar radiation stages is predicted based on the stage power conversion characteristics and the solar radiation prediction data, comprising: dividing the solar radiation prediction data into a number of solar radiation stage data groups according to the solar radiation stage, and establishing a photovoltaic power generation physical model according to the stage power conversion characteristics; inputting each solar radiation stage data group into the photovoltaic power generation physical model to obtain the photovoltaic power generation in different solar radiation stages.

[0074] Specifically, according to the solar radiation stage obtained in the previous steps, the solar radiation prediction data is divided into corresponding solar radiation stage data groups, and each data group corresponds to a solar radiation stage; according to the stage power conversion characteristics, a photovoltaic power generation physical model is established. This model can be based on existing physical principles and characteristic curves of photovoltaic cells, such as I-V curves and P-V curves; each solar radiation stage data group is input into the photovoltaic power generation physical model, and the photovoltaic power generation in different solar radiation stages is obtained according to the model calculation. For each solar radiation stage, the corresponding photovoltaic power generation is obtained.

[0075] like Figure 2 As shown, in an embodiment of the present application, a photovoltaic power generation prediction system based on a solar radiation model is provided, including: a preprocessing module, used to obtain historical meteorological data of the area where photovoltaic power generation is located, and preprocess the historical meteorological data; an analysis module, used to analyze the preprocessed historical meteorological data, and determine the key features related to solar radiation in the historical meteorological data; a modeling module, used to build a solar radiation model based on data corresponding to the key features and a preset neural network model, and predict solar radiation prediction data for a period of time in the future through the solar radiation model; a determination module, used to obtain the standard power conversion characteristics of photovoltaic cells under solar radiation, and determine the stage power conversion characteristics of photovoltaic cells in different solar radiation stages based on the solar radiation prediction data and the standard power conversion characteristics; a prediction module, used to predict photovoltaic power generation in different solar radiation stages based on the stage power conversion characteristics and the solar radiation prediction data.

[0076] In summary, the embodiment of the present invention provides a method and system for predicting photovoltaic power generation based on a solar radiation model, which includes: obtaining and preprocessing historical meteorological data of the area where photovoltaic power generation is located, analyzing it, and determining key features related to solar radiation in the historical meteorological data; constructing a solar radiation model based on data corresponding to the key features and a preset neural network model, and using it to predict solar radiation prediction data for a period of time in the future; obtaining the standard power conversion characteristics of photovoltaic cells under solar radiation, and determining the stage power conversion characteristics of photovoltaic cells in different solar radiation stages based on the solar radiation prediction data and the standard power conversion characteristics; predicting photovoltaic power generation in different solar radiation stages based on the stage power conversion characteristics and the solar radiation prediction data. The present invention predicts photovoltaic power generation based on a solar radiation model, and can accurately predict photovoltaic power generation in a period of time in the future, providing important support for energy planning and management.

[0077] Finally, it should be noted that it is obvious that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0078] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0079] The term "comprises" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0080] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0081] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A photovoltaic power generation prediction method based on a solar radiation model, characterized in that: include: Obtain historical meteorological data of the area where photovoltaic power generation is located and pre-process the historical meteorological data; Analyze the preprocessed historical meteorological data to determine the key features related to solar radiation in the historical meteorological data; A solar radiation model is constructed based on the data corresponding to the key features and the preset neural network model, and the solar radiation forecast data for a period of time in the future is predicted through the solar radiation model; Obtaining the standard power conversion characteristics of photovoltaic cells under solar radiation, and determining the stage power conversion characteristics of photovoltaic cells in different solar radiation stages based on solar radiation prediction data and the standard power conversion characteristics; The photovoltaic power generation in different solar radiation stages is predicted based on the stage power conversion characteristics and solar radiation prediction data.

2. The photovoltaic power generation prediction method based on the solar radiation model according to claim 1 is characterized in that: The obtaining of historical meteorological data of the region where the photovoltaic power generation is located and preprocessing of the historical meteorological data include: Obtain historical meteorological data in the area where photovoltaic power generation is located, clean the historical meteorological data, and remove noise, missing values, and outliers in the data; The cleaned historical meteorological data are normalized.

3. The photovoltaic power generation prediction method based on the solar radiation model according to claim 1 is characterized in that: The pre-processed historical meteorological data is analyzed to determine key features related to solar radiation in the historical meteorological data, including: The pre-processed historical meteorological data are parsed into several parameter data groups according to parameter types, and the correlation between each parameter data group and solar radiation is analyzed; The average value of the correlation between all parameter data groups and solar radiation is calculated, and the parameter data groups that exceed the average value are screened out and identified as the key features related to solar radiation in the historical meteorological data.

4. The photovoltaic power generation prediction method based on the solar radiation model according to claim 3 is characterized in that: The analysis of the correlation between each parameter data group and solar radiation includes: Acquire existing solar radiation prediction data, and aggregate the solar radiation prediction data to obtain a solar radiation prediction data group; Calculating the correlation between each parameter data set and the solar radiation prediction data set, and calculating the sum of the correlations between all parameter data sets and the solar radiation prediction data set; Calculate the ratio of each correlation to the total, and use the ratio as the weight corresponding to each parameter data group; The inter-data group standard deviation between each parameter data group and the solar radiation prediction data group is calculated, and the inter-data group standard deviation is evaluated and valued to obtain the associated evaluation value of each parameter data group. The calculation formula of the associated evaluation value is as follows: Among them, S is the correlation evaluation value of each parameter data group, α is the data difference coefficient, Mi is the i-th data in the parameter data group, Ni is the i-th data in the solar radiation prediction data group, and n is the number of data in the data group; The correlation evaluation value of each parameter data group is weightedly added to the corresponding weight to obtain the correlation degree between each parameter data group and solar radiation.

5. The photovoltaic power generation prediction method based on the solar radiation model according to claim 3 is characterized in that: The solar radiation model is constructed based on the data corresponding to the key features and the preset neural network model, and the solar radiation prediction data for a period of time in the future is predicted by the solar radiation model, including: The data corresponding to the key features are used as a data set, and the data set is input into a preset neural network model to construct an initial solar radiation model; The data set is divided into a training set and a test set according to a certain ratio, and the training set and the test set are input into the solar radiation initial model, and the relationship initial model is trained and tested until the solar radiation initial model meets the preset convergence conditions, thereby obtaining a solar radiation model; Real-time meteorological data of the photovoltaic power generation area is obtained, and the real-time meteorological data is input into the solar radiation model, and the solar radiation model is used to predict the solar radiation forecast data for a period of time in the future.

6. A photovoltaic power generation prediction method based on a solar radiation model according to claim 5, characterized in that: The step of obtaining the standard power conversion characteristics of the photovoltaic cell and determining the stage power conversion characteristics of the photovoltaic cell at different solar radiation stages based on the solar radiation prediction data and the standard power conversion characteristics includes: Obtain solar radiation prediction data, and draw a solar radiation curve graph based on the solar radiation prediction data; Calculate the average radiation value of the solar radiation prediction data, determine the valley points in the solar radiation curve that are lower than the average radiation value, and divide the solar radiation prediction data into several solar radiation stages according to the valley points; Determine the total solar radiation in each solar radiation stage, and calculate the difference between the total solar radiation in each solar radiation stage and the standard solar radiation; The adjustment coefficient of each solar radiation stage is determined according to the difference in radiation amount, and the standard electric energy conversion characteristic is adjusted according to the adjustment coefficient to obtain the stage electric energy conversion characteristic of each solar radiation stage.

7. The photovoltaic power generation prediction method based on the solar radiation model according to claim 6 is characterized in that: Determining the adjustment coefficient of each solar radiation stage according to the radiation difference includes: The preset adjustment coefficient-radiation difference interval correspondence relationship is that the adjustment coefficient-radiation difference interval correspondence relationship is associated with a corresponding adjustment coefficient for each radiation difference interval; The radiation difference is obtained, and based on the mapping relationship between the radiation difference interval to which the radiation difference belongs and the adjustment coefficient corresponding to the radiation difference interval is selected as the adjustment coefficient for each solar radiation stage.

8. The photovoltaic power generation prediction method based on the solar radiation model according to claim 6 is characterized in that: The method of predicting photovoltaic power generation in different solar radiation stages based on the stage power conversion characteristics and solar radiation prediction data includes: The solar radiation prediction data is divided into several solar radiation stage data groups according to the solar radiation stage, and a photovoltaic power generation physical model is established according to the stage power conversion characteristics; The data sets of each solar radiation stage are input into the photovoltaic power generation physical model to obtain the photovoltaic power generation in different solar radiation stages.

9. A photovoltaic power generation prediction system based on a solar radiation model, characterized in that: include: A preprocessing module is used to obtain historical meteorological data of the area where photovoltaic power generation is located and preprocess the historical meteorological data; An analysis module is used to analyze the pre-processed historical meteorological data and determine the key features related to solar radiation in the historical meteorological data; A modeling module is used to build a solar radiation model based on the data corresponding to the key features and a preset neural network model, and to predict the solar radiation forecast data for a period of time in the future through the solar radiation model; A determination module is used to obtain the standard power conversion characteristics of the photovoltaic cell under solar radiation, and determine the stage power conversion characteristics of the photovoltaic cell in different solar radiation stages based on the solar radiation prediction data and the standard power conversion characteristics; The prediction module is used to predict the photovoltaic power generation in different solar radiation stages based on the stage power conversion characteristics and solar radiation prediction data.

Images