CN118349855A - Multi-model photovoltaic power prediction method, equipment and storage medium - Google Patents

Abstract

The application discloses a multi-model photovoltaic power prediction method, equipment and a storage medium. The method comprises the following steps: carrying out data sampling on a power station database based on a preset sampling frequency, and carrying out data screening and standardization processing on the obtained data to obtain a data set; inputting the data set into a preset time sequence model to output a first target prediction result; inputting the data set into a preset cyclic neural network model to output a second target prediction result; outputting a third target prediction result to the data set through a preset support vector regression model; weight is distributed to the first, second and third target prediction results, and model fusion is carried out through a preset weighting operation model; correcting through the photovoltaic module aging model to obtain final photovoltaic predicted power; the method solves the technical problem that the photovoltaic power prediction is inaccurate and cannot meet the power grid dispatching requirement due to inaccurate prediction of a single power prediction model.

Description

Multi-model photovoltaic power prediction method, equipment and storage medium

Technical Field

The application relates to the technical field of photovoltaic power generation power prediction, in particular to a multi-model photovoltaic power prediction method, multi-model photovoltaic power prediction equipment and a storage medium.

Background

Solar energy is an ideal renewable energy source, solar photovoltaic power generation is an important solar energy utilization mode, and various environmental problems caused by traditional energy sources can be relieved while the existing energy crisis is relieved. The photovoltaic power generation has intermittence, randomness and volatility, and the more accurate the photovoltaic power prediction is, the smaller the influence of the photovoltaic grid connection on the safe operation of the power grid is; the existing power prediction model does not consider component aging, and single power prediction model predicts inaccurately, so that photovoltaic power prediction inaccurately cannot meet power grid scheduling requirements.

Disclosure of Invention

The embodiment of the application provides a method, equipment and a storage medium for predicting multi-model photovoltaic power, which solve the technical problem that the photovoltaic power prediction is inaccurate and cannot meet the power grid dispatching requirement due to inaccurate prediction of a single power prediction model.

In a first aspect, an embodiment of the present application provides a method for predicting multi-model photovoltaic power, where data sampling is performed on a power station database based on a preset sampling frequency, and data screening and standardization processing are performed on data obtained by the data sampling, so as to obtain a data set; inputting the data set into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power; inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power; carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power; weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain photovoltaic power to be corrected; and correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain the final photovoltaic predicted power.

In one implementation of the present application, the data sampling of the power station database based on a preset sampling frequency specifically includes: determining a sampling data type and a sampling frequency of data sampling; wherein the sampling data types include: time, instantaneous irradiance, wind speed, wind direction, temperature, pressure, humidity, instantaneous power; and carrying out data sampling on the power station database based on the sampling data type and the sampling frequency.

In one implementation of the application, the weighted algorithm model is represented by the following formula:

y＝a*model_informer+b*model_lstm+c*model_svr

Model_ informer is a time sequence Informer model, model_ LSTM is a recurrent neural network LSTM model, and model_ SVR is a support vector regression SVR model; y is the photovoltaic power after model fusion; a. b and c are weights of the models, respectively, and a+b+c=1.

In one implementation of the application, the photovoltaic power to be corrected is corrected by the photovoltaic module aging model, and the method specifically comprises the following steps: calculating the aging rate of the photovoltaic module through a photovoltaic aging curve; based on the aging rate, carrying out model correction on the model to be corrected through a preset photovoltaic power correction model.

In one implementation of the application, the photovoltaic aging curve is represented by the following formula:

wherein x is the years of use of the photovoltaic module; f (x) is the aging rate.

In one implementation of the application, the photovoltaic power correction model is represented by the following formula:

y′＝model_power*(1-α)

wherein α is the value of f (x), i.e., the aging rate; model_power is the photovoltaic power to be corrected; y' is the final photovoltaic predicted power.

In one implementation manner of the present application, the data filtering method for data obtained by sampling data specifically includes: screening the data obtained by sampling the data according to preset screening conditions, wherein the preset screening conditions comprise: deleting the record with 0 or empty in the data, and eliminating the repetition of the repeated data sample; deleting records with negative values in the instantaneous irradiance and the instantaneous power; and deleting the record of the numerical abnormality in the data.

In one implementation of the present application, the normalization process specifically includes: normalization processing is performed by a Z-Score normalization formula; the Z-Score normalization formula is:

wherein μ is the mean of the data; x is the standard deviation of the data; σ is the observation of a single datum.

In a second aspect, an embodiment of the present application further provides a multi-model photovoltaic power prediction apparatus, where the apparatus includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to: carrying out data sampling on a power station database based on a preset sampling frequency, and carrying out data screening and standardization processing on data obtained by data sampling to obtain a data set; inputting the data set into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power; inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power; carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power; weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain photovoltaic power to be corrected; and correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain the final photovoltaic predicted power.

In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions for a multi-model photovoltaic power prediction method, where the computer executable instructions are configured to: carrying out data sampling on a power station database based on a preset sampling frequency, and carrying out data screening and standardization processing on data obtained by data sampling to obtain a data set; inputting the data set into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power; inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power; carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power; weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain photovoltaic power to be corrected; and correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain the final photovoltaic predicted power.

The embodiment of the application provides a method, equipment and a storage medium for predicting multi-model photovoltaic power, which are used for improving the prediction accuracy through fusion of a multi-power prediction model; the method solves the technical problem that the single power prediction model is inaccurate in prediction, so that the photovoltaic power cannot meet the power grid dispatching requirement due to inaccurate prediction.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

FIG. 1 is a flowchart of a method for predicting multi-model photovoltaic power according to an embodiment of the present application;

fig. 2 is a schematic diagram of an internal structure of a multi-model photovoltaic power prediction apparatus according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The embodiment of the application provides a method, equipment and a storage medium for predicting multi-model photovoltaic power, which solve the technical problem that the photovoltaic power prediction is inaccurate and cannot meet the power grid dispatching requirement due to inaccurate prediction of a single power prediction model.

The following describes the technical scheme provided by the embodiment of the application in detail through the attached drawings.

Fig. 1 is a flowchart of a method for predicting multi-model photovoltaic power according to an embodiment of the present application. As shown in fig. 1, the method for predicting multi-model photovoltaic power provided by the embodiment of the application specifically includes the following steps:

Step 101, performing data sampling on a power station database based on a preset sampling frequency, and performing data screening and standardization processing on data obtained by data sampling to obtain a data set;

Determining the sampling data type and the sampling frequency of data sampling according to the historical meteorological data and the generating power data of the power station; wherein the sampling data types include: time, instantaneous irradiance, wind speed, wind direction, temperature, pressure, humidity, instantaneous power; data sampling is carried out on the power station database based on the sampling data type and the sampling frequency;

Screening the data obtained by sampling the data according to preset screening conditions, wherein the preset screening conditions comprise: deleting the record with 0 or empty in the data, and eliminating the repetition of the repeated data sample; deleting records with negative values in the instantaneous irradiance and the instantaneous power; deleting records with abnormal values in the data;

Normalization processing is performed by a Z-Score normalization formula; the Z-Score normalization formula is:

wherein μ is the mean of the data; x is the standard deviation of the data; sigma is the observed value of a single datum;

wherein the sampling frequency is set to 15 minutes each time.

102, Inputting a dataset into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power;

To implement step 102, a preset time series Informer model is constructed, and a time series Informer model is trained on the dataset consisting of the eight data types, and the model regards power prediction as a periodically changing time series. Because photovoltaic power prediction has close relation with time, the power generation power changes periodically with the time of each day (the solar irradiance is received in the morning to start power generation, the power generation power in noon is maximum, the power generation power gradually reduces to 0 in the evening, and no power is generated at night); the time sequence Informer model is based on the input of time data, represents the time data after position coding, reduces the computational complexity through the multi-head self-attention and self-attention distillation mechanism of the encoder, enables the model to learn the time dependence of the long-time sequence data, and finally forms an intermediate representation form of the data information through the multi-head attention and the characteristics. Then the result is input into a decoder of a time sequence Informer model, the decoder fuses meteorological data corresponding to the power time to be predicted, the decoder of the time sequence Informer model adopts an occlusion attention mechanism, and finally a final prediction result is directly output once by a full connection layer of the decoder. The objective function of the time series Informer model is the mean square error, defined as:

Wherein, l _ij and The true value and the predicted value at the j moment in the ith input sequence are respectively represented and are the length of the sequence to be detected; training of the time series Informer model parameters is achieved through MSE minimization, and a first target prediction result is obtained.

Step 103, inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power;

In order to realize step 103, a preset cyclic neural network LSTM model is required to be constructed, the cyclic neural network LSTM model is trained by using the data set consisting of the eight data types, firstly, the data characteristic extraction is carried out on the data set, and the result is input into the shared neuron for training. And then establishing a shared learning layer, and inputting the output of the LSTM into the shared learning layer for training, thereby extracting the periodicity rule of the generated power for power prediction and obtaining a second target prediction result.

104, Carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power;

In order to implement step 104, a preset support vector regression SVR model needs to be constructed, the support vector regression SVR model is trained by using the data set composed of the eight data types, and according to the formula:

And carrying out regression analysis on the characteristic information to obtain a result output by the SVR model, thereby obtaining the power prediction, wherein x represents the characteristic information. The characteristic information and the electricity data sequence are fitted by using a support vector machine (SVR) in advance, and a Gaussian kernel function is adopted by K, and the formula is as follows:

Fitting the x and the y, calculating a SVR long plane by using a dual method, training a SVR model to obtain fitting results of the parameters alpha and b, extracting characteristic information of an electricity data sequence for predicting electricity consumption, inputting the extracted characteristic information into the SVR model with the determined parameters alpha and b, and obtaining a third target prediction result, namely a prediction result of the generated power.

Step 105, weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain the photovoltaic power to be corrected;

According to the prediction results of the three prediction models, the prediction accuracy of each model is judged and confirmed, then the weight matched with each model is distributed to each model, and then the weighting fusion is carried out through the following formula:

y＝a*model_informer+b*model_lstm+c*model_svr

Model_ informer is a time sequence Informer model, model_ LSTM is a recurrent neural network LSTM model, and model_ SVR is a support vector regression SVR model; y is the photovoltaic power after model fusion; a. b and c are weights of the models, respectively, and a+b+c=1.

Step 106, correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain final photovoltaic predicted power;

Calculating the aging rate of the photovoltaic module through a photovoltaic aging curve; based on the aging rate, carrying out model correction on the model to be corrected through a preset photovoltaic power correction model, and a photovoltaic aging curve is represented by the following formula:

wherein x is the years of use of the photovoltaic module; f (x) is the aging rate.

A photovoltaic power correction model, represented by the following formula:

y′＝model_power*(1-α)

wherein α is the value of f (x), i.e., the aging rate; model_power is the photovoltaic power to be corrected; y' is the final photovoltaic predicted power.

The above is a method embodiment of the present application. Based on the same inventive concept, the embodiment of the application also provides a device, and the structure of the device is shown in fig. 2.

Fig. 2 is a schematic diagram of an internal structure of a multi-model photovoltaic power prediction apparatus according to an embodiment of the present application. As shown in fig. 2, the apparatus includes:

at least one processor 201;

And a memory 202 communicatively coupled to the at least one processor;

Wherein the memory 202 stores instructions executable by the at least one processor, the instructions being executable by the at least one processor 201 to enable the at least one processor 201 to:

Carrying out data sampling on a power station database based on a preset sampling frequency, and carrying out data screening and standardization processing on data obtained by data sampling to obtain a data set; inputting the data set into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power; inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power; carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power; weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain photovoltaic power to be corrected; and correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain the final photovoltaic predicted power.

Some embodiments of the application provide a non-volatile computer storage medium corresponding to the multi-model photovoltaic power prediction method of fig. 1, storing computer executable instructions configured to:

Carrying out data sampling on a power station database based on a preset sampling frequency, and carrying out data screening and standardization processing on data obtained by data sampling to obtain a data set; inputting the data set into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power; inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power; carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power; weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain photovoltaic power to be corrected; and correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain the final photovoltaic predicted power.

The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the internet of things device and the medium embodiment, since they are substantially similar to the method embodiment, the description is relatively simple, and the relevant points are referred to in the description of the method embodiment.

The system, the medium and the method provided by the embodiment of the application are in one-to-one correspondence, so that the system and the medium also have similar beneficial technical effects to the corresponding method, and the beneficial technical effects of the method are explained in detail above, so that the beneficial technical effects of the system and the medium are not repeated here.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims (10)

1. A method of multimodal photovoltaic power prediction, the method comprising:

carrying out data sampling on a power station database based on a preset sampling frequency, and carrying out data screening and standardization processing on data obtained by the data sampling to obtain a data set;

Inputting the data set into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power; and

Inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power; and

Carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power;

weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain photovoltaic power to be corrected;

And correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain the final photovoltaic predicted power.

2. A method for predicting multi-model photovoltaic power according to claim 1, wherein the data sampling of the power station database is based on a preset sampling frequency, specifically comprising:

determining a sampling data type and a sampling frequency of data sampling; wherein the sampling data types include: time, instantaneous irradiance, wind speed, wind direction, temperature, pressure, humidity, instantaneous power;

and carrying out data sampling on the power station database based on the sampling data type and the sampling frequency.

3. A multi-model photovoltaic power prediction method according to claim 1, characterized in that the weighted algorithm model is represented by the following formula:

y＝a*model_informer+b*model_lstm+c*model_svr

model_ informer is the time sequence Informer model, model_ LSTM is the recurrent neural network LSTM model, and model_ SVR is the support vector regression SVR model;

y is the photovoltaic power after the model fusion;

a. b and c are weights of the models, respectively, and a+b+c=1.

4. The multi-model photovoltaic power prediction method according to claim 1, wherein the photovoltaic power to be corrected is corrected by a photovoltaic module aging model, specifically comprising:

calculating the aging rate of the photovoltaic module through a photovoltaic aging curve;

And based on the aging rate, carrying out model correction on the model to be corrected through a preset photovoltaic power correction model.

5. The method of claim 4, wherein the photovoltaic aging curve is represented by the formula:

wherein x is the years of use of the photovoltaic module;

f (x) is the aging rate.

6. The method of claim 5, wherein the photovoltaic power correction model is represented by the following formula:

y′＝model_power*(1-α)

wherein α is the value of f (x), i.e., the aging rate;

the model_power is the photovoltaic power to be corrected;

y' is the final photovoltaic predicted power.

7. The method for predicting the multi-model photovoltaic power according to claim 1, wherein the data obtained by sampling the data is subjected to data screening, and specifically comprises the following steps:

screening the data obtained by sampling the data according to preset screening conditions, wherein the preset screening conditions comprise:

deleting the record which is 0 or empty in the data, and eliminating the repetition of repeated data samples;

deleting records of values of the instantaneous irradiance and the instantaneous power that are negative;

And deleting records of numerical value anomalies in the data.

8. A method of predicting multi-model photovoltaic power according to claim 1, characterized in that the normalization process comprises in particular:

the normalization processing is performed through a Z-Score normalization formula;

The Z-Score normalization formula is:

Wherein μ is the mean of the data;

x is the standard deviation of the data;

σ is the observation of a single said data.

9. A multi-model photovoltaic power prediction apparatus, the apparatus comprising:

At least one processor;

and a memory communicatively coupled to the at least one processor;

Wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:

carrying out data sampling on a power station database based on a preset sampling frequency, and carrying out data screening and standardization processing on data obtained by the data sampling to obtain a data set;

Inputting the data set into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power; and

Inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power; and

Carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power;

weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain photovoltaic power to be corrected;

And correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain the final photovoltaic predicted power.

10. A non-transitory computer storage medium storing computer executable instructions for a multimodal photovoltaic power prediction method, the computer executable instructions configured to:

carrying out data sampling on a power station database based on a preset sampling frequency, and carrying out data screening and standardization processing on data obtained by the data sampling to obtain a data set;

Inputting the data set into a preset time sequence Informer model to output a first target prediction result corresponding to the instantaneous power; and

Inputting the data set into a preset cyclic neural network LSTM model to output a second target prediction result corresponding to the instantaneous power; and

Carrying out regression analysis and parameter fitting on the data set through a preset Support Vector Regression (SVR) model, and outputting a third target prediction result corresponding to the instantaneous power;

weight is distributed to the first target prediction result, the second target prediction result and the third target prediction result, and model fusion is carried out through a preset weighting operation model to obtain photovoltaic power to be corrected;

And correcting the photovoltaic power to be corrected through the photovoltaic module aging model to obtain the final photovoltaic predicted power.