Photovoltaic module performance prediction method and system based on real-time data analysis

Abstract

The invention relates to a photovoltaic module performance prediction method and system based on real-time data analysis, and belongs to the technical field of photovoltaic power generation. The method comprises the following steps: acquiring real-time environment data, illumination intensity data, real-time power data of a photovoltaic module and area data of the photovoltaic module; calculating the conversion efficiency of the photovoltaic module according to the area data, the real-time power data and the illumination intensity data of the photovoltaic module, and adding a timestamp to the conversion efficiency of the photovoltaic module to obtain the time sequence conversion efficiency; performing parallel splicing according to the real-time environment data and the illumination intensity data to obtain an environment feature vector, obtaining a historical environment feature vector, and determining a weather type label of the environment feature vector according to the historical environment feature vector; and storing the time sequence conversion efficiency according to the weather type to obtain a conversion efficiency sequence, performing preprocessing according to the conversion efficiency sequence to obtain preprocessed data, and performing prediction according to the preprocessed data to obtain a conversion efficiency prediction value. According to the invention, the conversion efficiency prediction of the photovoltaic module is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of photovoltaic power generation, and in particular relates to a photovoltaic component performance prediction method and system based on real-time data analysis. Background Art

[0002] As a clean and renewable energy source, the development and utilization of solar energy is increasingly valued. As the core component of the solar power generation system, the stability and efficiency of the performance of photovoltaic modules directly affect the power generation capacity and economic benefits of the entire system. Therefore, accurate prediction of the performance of photovoltaic modules is of great significance for optimizing system design, improving power generation efficiency, and reducing operation and maintenance costs.

[0003] With the continuous advancement of the Internet of Things, big data and artificial intelligence technologies, more and more people are using artificial intelligence, big data and other technologies in industrial production. After the installation of photovoltaic modules, under the same external environment, as the service life of photovoltaic modules increases, the conversion efficiency of photovoltaic modules will gradually decrease. Predicting the conversion efficiency of photovoltaic modules under the same external environment can clearly understand the scrapping time of photovoltaic modules and make preparations for the scrapping of photovoltaic modules in advance. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a photovoltaic module performance prediction method and system based on real-time data analysis.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: A photovoltaic module performance prediction method based on real-time data analysis, comprising: Collect real-time environmental data and light intensity data through sensors, obtain real-time power data of photovoltaic modules through power sensors, and obtain photovoltaic module area data; Calculate the photovoltaic module conversion efficiency according to the photovoltaic module area data, the real-time power data, and the light intensity data, and add a timestamp according to the photovoltaic module conversion efficiency to obtain a time series conversion efficiency; Parallel splicing is performed to obtain an environmental feature vector according to the real-time environmental data and the light intensity data, a historical environmental feature vector is obtained, and a weather type label of the environmental feature vector is determined according to the historical environmental feature vector; The time series conversion efficiency is stored according to the weather type label to obtain a conversion efficiency sequence, preprocessing data is calculated through a preprocessing model according to the conversion efficiency sequence, and conversion efficiency prediction values ​​are calculated through an LSTM model according to the preprocessing data.

[0006] A further improvement of the present invention is that the real-time environmental data includes environmental humidity, cloud opacity, environmental temperature data, and wind speed.

[0007] A further improvement of the present invention is that determining the weather type of the environmental feature vector according to the historical environmental feature vector comprises: The historical environmental feature vector carries the weather type label, and the cosine similarity is calculated based on the historical environmental feature vector and the environmental feature vector to obtain a similarity value. The most similar historical environmental feature vector is determined based on the similarity value, and the weather type label of the most similar historical environmental feature vector is used as the weather type of the environmental feature vector.

[0008] A further improvement of the present invention is that the specific steps of the preprocessing model include: A sliding window is preset, and the conversion efficiency sequence is intercepted according to the sliding window to obtain a prediction sequence; Obtaining decomposed modes through CEEMDAN empirical mode decomposition according to the predicted sequence; According to the decomposed mode, an integrated sequence is obtained by integrating sample entropy; Obtaining normalized data by maximum and minimum value normalization according to the integrated sequence; The preprocessed data is obtained by decomposing the normalized data through an adaptive VMD algorithm.

[0009] A further improvement of the present invention is that the specific steps of sample entropy integration are: Reconstructing the phase space according to the decomposed mode to obtain a vector sequence; Calculating the distances between the vector sequences at different times; Preset an acceptance matrix tolerance, obtain a matching point probability by calculation according to the distance and the acceptance matrix tolerance, and calculate sample entropy according to the matching point probability; A sample entropy threshold is preset, the decomposition modes are screened according to the sample entropy threshold and the sample entropy to obtain screened decomposition modes, and the decomposition modes are added to obtain the integrated sequence.

[0010] A further improvement of the present invention is that the specific steps of the adaptive VMD algorithm include: S201: Acquire the number of decomposed eigenfunctions, and decompose the normalized data through VMD according to the number of decomposed eigenfunctions to obtain an eigenmode function; S202: Add each of the intrinsic mode functions to obtain a reconstructed signal; S203: Obtain a reconstruction error by calculating a mean square error according to the reconstructed signal; S204: Obtain the minimum error and determine whether the reconstruction error is less than the minimum error. If yes, set the reconstruction error to the minimum error and output the preprocessing result and the number of decomposed eigenfunctions. If no, increase the number of decomposed eigenfunctions by one and repeat steps S201-S204.

[0011] A further improvement of the present invention is that the LSTM model includes transmitting the preprocessed data to the first convolution layer through the input layer, the first convolution layer performs causal convolution according to the preprocessed data to obtain a causal convolution result, performing dilated convolution through the second convolution layer according to the causal convolution result to obtain a first dilated result, performing dilated convolution through the third convolution layer according to the first dilated result to obtain a second dilated result, transmitting the causal convolution result, the first dilated result, and the second dilated result to the first LSTM layer, the second LSTM layer, and the third LSTM layer respectively to calculate the first feature, the second feature, and the third feature, and fusing the first feature, the second feature, and the third feature through the fully connected layer to obtain the conversion efficiency prediction value.

[0012] A photovoltaic module performance prediction system based on real-time data analysis, comprising: a data acquisition module, a data processing module, a data classification module and a data prediction module; The data acquisition module is used to collect real-time environmental data and light intensity data through sensors, obtain real-time power data of photovoltaic modules through power sensors, and obtain photovoltaic module area data; The data processing module is used to calculate the photovoltaic module conversion efficiency according to the photovoltaic module area data, the real-time power data, and the light intensity data, and to add a timestamp according to the photovoltaic module conversion efficiency to obtain a time series conversion efficiency; The data classification module is used to obtain an environmental feature vector by parallel splicing of the real-time environmental data and the light intensity data, obtain a historical environmental feature vector, and determine a weather type label of the environmental feature vector according to the historical environmental feature vector; The data prediction module is used to store the time series conversion efficiency according to the weather type label to obtain a conversion efficiency sequence, calculate preprocessing data through a preprocessing model according to the conversion efficiency sequence, and calculate a conversion efficiency prediction value through an LSTM model according to the preprocessing data.

[0013] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for predicting photovoltaic component performance based on real-time data analysis is implemented.

[0014] A storage medium containing computer executable instructions, characterized in that the computer executable instructions are used to execute the photovoltaic component performance prediction method based on real-time data analysis when executed by a computer processor.

[0015] Compared with the prior art, the present invention has at least the following beneficial technical effects: The present invention provides a photovoltaic module performance prediction method and system based on real-time data analysis, (1) historical environmental data matching based on cosine similarity: in order to make full use of the information in the historical data, the method uses the cosine similarity algorithm to compare the real-time environmental data with the historical environmental data to find the historical environmental data that is most similar to the real-time environment. Cosine similarity is an indicator that measures the cosine value of the angle between two vectors, which can effectively reflect the degree of similarity between data. Through this step, the weather type label corresponding to the historical environmental data can be assigned to the real-time environmental data, thereby providing more accurate background information for subsequent performance prediction. (2) Classification storage and prediction sequence selection of conversion efficiency data: according to the weather type label of the real-time environmental data, the real-time conversion efficiency data is classified and stored. This step helps to reduce data noise and improve the accuracy of the prediction model. At the same time, according to the prediction requirements, a suitable conversion efficiency prediction sequence is selected from the classified stored data as the input of the LSTM prediction model. (3) An LSTM prediction model is provided. By predicting the conversion efficiency of photovoltaic modules under the same external environment, the scrapping time of photovoltaic modules can be clearly understood, and the preliminary preparations for the scrapping of photovoltaic modules can be made in advance, and photovoltaic modules can be replaced in time to effectively ensure the continuous operation of photovoltaic modules. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 The present invention is a schematic flow chart of a photovoltaic module performance prediction method based on real-time data analysis.

[0018] Figure 2 The present invention is a structural block diagram of a photovoltaic module performance prediction system based on real-time data analysis. DETAILED DESCRIPTION

[0019] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0020] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0021] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0023] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0024] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] Example 1 like Figure 1 As shown, the present invention provides a photovoltaic module performance prediction method based on real-time data analysis, comprising the following steps: Collect real-time environmental data and light intensity data through sensors, obtain real-time power data of photovoltaic modules through power sensors, and obtain photovoltaic module area data; Calculate the photovoltaic module conversion efficiency according to the photovoltaic module area data, the real-time power data, and the light intensity data, and add a timestamp according to the photovoltaic module conversion efficiency to obtain a time series conversion efficiency; Parallel splicing is performed to obtain an environmental feature vector according to the real-time environmental data and the light intensity data, a historical environmental feature vector is obtained, and a weather type label of the environmental feature vector is determined according to the historical environmental feature vector; The time series conversion efficiency is stored according to the weather type label to obtain a conversion efficiency sequence, preprocessing data is calculated through a preprocessing model according to the conversion efficiency sequence, and conversion efficiency prediction values ​​are calculated through an LSTM model according to the preprocessing data.

[0026] The real-time environmental data includes environmental humidity, cloud opacity, environmental temperature data, and wind speed.

[0027] Specifically, the photovoltaic module conversion efficiency calculation formula is: , in, n is the photovoltaic module conversion efficiency, P For real-time power data, A is the photovoltaic module area data, I The light intensity data.

[0028] Specifically, determining the weather type of the environmental feature vector according to the historical environmental feature vector includes: The historical environment feature vector carries the weather type label, and a cosine similarity is calculated based on the historical environment feature vector and the environment feature vector to obtain a similarity value, and a most similar historical environment feature vector is determined based on the similarity value, and the weather type label of the most similar historical environment feature vector is used as the weather type of the environment feature vector; The cosine similarity expression is: , in, K is the similarity value, n is a variable parameter, indicating the first n parameters, N is the number of parameters in the feature vector, y i Indicates i A historical environment feature vector, y is the environmental feature vector.

[0029] Specifically, the weather type labels include sunny day, cloudy day, and rainy day.

[0030] Specifically, the preprocessing model comprises the following steps: A sliding window is preset, and the conversion efficiency sequence is intercepted according to the sliding window to obtain a prediction sequence; Obtaining decomposed modes through CEEMDAN empirical mode decomposition according to the predicted sequence; According to the decomposed mode, an integrated sequence is obtained by integrating sample entropy; Obtaining normalized data by maximum and minimum value normalization according to the integrated sequence; The preprocessed data is obtained by decomposing the normalized data through an adaptive VMD algorithm.

[0031] Specifically, the sample entropy integration steps are as follows: Reconstructing the phase space according to the decomposed mode to obtain a vector sequence; The vector sequence expression is: , in, Ym(i) The length is m A vector sequence starting at the data point i , n is the total number of data points, Y（*） To decompose the mode; Calculating the distances between the vector sequences at different times; The distance calculation formula is: , Among them, dm[Ym(i),Ym(x)] is the distance between Ym(i) and Ym(x), Ym(i) The length is m A vector sequence starting at the data point i , Ym(x) The length is m A vector sequence starting at the data point x , k is a variable parameter; Preset an acceptance matrix tolerance, obtain a matching point probability by calculation according to the distance and the acceptance matrix tolerance, and calculate sample entropy according to the matching point probability; The matching point probability calculation formula is: , Among them, A m (r) is the length of m, the probability of the matching point with acceptance matrix tolerance r, r is the acceptance matrix tolerance, A m is the distance, m is the length of the vector sequence, and n is the total number of data points; The sample entropy calculation formula is: , Among them, SE (m, r, n) is the sample entropy, r is the acceptance matrix tolerance, A m(r) is the probability of matching points with a length of m and an acceptance matrix tolerance of r, m is the length of the vector sequence, and n is the total number of data points; A sample entropy threshold is preset, the decomposition modes are screened according to the sample entropy threshold and the sample entropy to obtain screened decomposition modes, and the decomposition modes are added to obtain the integrated sequence.

[0032] Specifically, the specific steps of the adaptive VMD algorithm include: S201: Acquire the number of decomposed eigenfunctions, and decompose the normalized data by VMD decomposition according to the number of decomposed eigenfunctions to obtain an eigenmode function; S202: Add each of the intrinsic mode functions to obtain a reconstructed signal; S203: Obtain a reconstruction error by calculating a mean square error according to the reconstructed signal; S204: Obtain the minimum error and determine whether the reconstruction error is less than the minimum error. If yes, set the reconstruction error to the minimum error and output the preprocessing result and the number of decomposed eigenfunctions. If no, increase the number of decomposed eigenfunctions by one and repeat steps S201-S204.

[0033] In this embodiment, when the preprocessed data is obtained by decomposing the normalized data through an adaptive VMD algorithm, the number of decomposed eigenfunctions is calculated to be 10.

[0034] Specifically, the LSTM model includes transmitting the preprocessed data to the first convolution layer through the input layer, the first convolution layer performing causal convolution according to the preprocessed data to obtain a causal convolution result, performing dilated convolution through the second convolution layer according to the causal convolution result to obtain a first dilated result, performing dilated convolution through the third convolution layer according to the first dilated result to obtain a second dilated result, transmitting the causal convolution result, the first dilated result, and the second dilated result to the first LSTM layer, the second LSTM layer, and the third LSTM layer respectively to calculate the first feature, the second feature, and the third feature, and fusing the first feature, the second feature, and the third feature through the fully connected layer to obtain the conversion efficiency prediction value.

[0035] In this embodiment, the LSTM model includes an input layer, three convolutional layers, three LSTM layers, and a fully connected layer, and the input layer contains ten neurons.

[0036] Example 2 like Figure 2 As shown, the present invention provides a photovoltaic module performance prediction system based on real-time data analysis, including: a data acquisition module, a data processing module, a data classification module and a data prediction module.

[0037] The data acquisition module is used to collect real-time environmental data and light intensity data through sensors, obtain real-time power data of photovoltaic modules through power sensors, and obtain photovoltaic module area data; The data processing module is used to calculate the photovoltaic module conversion efficiency according to the photovoltaic module area data, the real-time power data, and the light intensity data, and to add a timestamp according to the photovoltaic module conversion efficiency to obtain a time series conversion efficiency; The data classification module is used to obtain an environmental feature vector by parallel splicing of the real-time environmental data and the light intensity data, obtain a historical environmental feature vector, and determine a weather type label of the environmental feature vector according to the historical environmental feature vector; The data prediction module is used to store the time series conversion efficiency according to the weather type label to obtain a conversion efficiency sequence, calculate preprocessing data through a preprocessing model according to the conversion efficiency sequence, and calculate a conversion efficiency prediction value through an LSTM model according to the preprocessing data.

[0038] Example 3 The present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the photovoltaic module performance prediction method based on real-time data analysis as described above is implemented.

[0039] The electronic device may also include one or more of a multimedia component, an input / output (I / O) interface, and a communication component.

[0040] The processor is used to control the overall operation of the electronic device to complete all or part of the steps in the storage medium sharing method. The memory is used to store various types of data to support the operation of the electronic device, which may include instructions for any application or method used to operate on the electronic device, as well as application-related data, such as contact data, messages sent and received, pictures, audio, video, etc. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving an external audio signal. The received audio signal may be further stored in a memory or sent through a communication component. The audio component also includes at least one speaker for outputting an audio signal. The I / O interface provides an interface between the processor and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component is used for wired or wireless communication between the electronic device and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component may include: Wi-Fi module, Bluetooth module, NFC module.

[0041] In an exemplary embodiment, the electronic device can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the storage medium sharing method.

[0042] Example 4 The present invention provides a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute the photovoltaic module performance prediction method based on real-time data analysis as described above.

[0043] The working principle and use process of the present invention: The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0044] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0045] The program code contained on the computer-readable medium can be transmitted with any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, and the programming language includes an object-oriented programming language-such as Java, Smalltalk, C++, and also includes a conventional procedural programming language-such as "C" language or similar programming language. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN, or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0046] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0047] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A photovoltaic module performance prediction method based on real-time data analysis, characterized in that: include: Collect real-time environmental data and light intensity data through sensors, obtain real-time power data of photovoltaic modules through power sensors, and obtain photovoltaic module area data; Calculate the photovoltaic module conversion efficiency according to the photovoltaic module area data, the real-time power data, and the light intensity data, and add a timestamp according to the photovoltaic module conversion efficiency to obtain a time series conversion efficiency; Parallel splicing is performed to obtain an environmental feature vector according to the real-time environmental data and the light intensity data, a historical environmental feature vector is obtained, and a weather type label of the environmental feature vector is determined according to the historical environmental feature vector; The time series conversion efficiency is stored according to the weather type label to obtain a conversion efficiency sequence, preprocessing data is calculated through a preprocessing model according to the conversion efficiency sequence, and conversion efficiency prediction values ​​are calculated through an LSTM model according to the preprocessing data.

2. The photovoltaic module performance prediction method based on real-time data analysis according to claim 1, characterized in that: The real-time environmental data includes environmental humidity, cloud opacity, environmental temperature data, and wind speed.

3. The photovoltaic module performance prediction method based on real-time data analysis according to claim 1, characterized in that: The step of determining the weather type of the environmental feature vector according to the historical environmental feature vector comprises: The historical environmental feature vector carries the weather type label, and the cosine similarity is calculated based on the historical environmental feature vector and the environmental feature vector to obtain a similarity value. The most similar historical environmental feature vector is determined based on the similarity value, and the weather type label of the most similar historical environmental feature vector is used as the weather type of the environmental feature vector.

4. The photovoltaic module performance prediction method based on real-time data analysis according to claim 1, characterized in that: The specific steps of the preprocessing model include: A sliding window is preset, and the conversion efficiency sequence is intercepted according to the sliding window to obtain a prediction sequence; Obtaining decomposed modes through CEEMDAN empirical mode decomposition according to the predicted sequence; According to the decomposed mode, an integrated sequence is obtained by integrating sample entropy; Obtaining normalized data by maximum and minimum value normalization according to the integrated sequence; The preprocessed data is obtained by decomposing the normalized data through an adaptive VMD algorithm.

5. The photovoltaic module performance prediction method based on real-time data analysis according to claim 4 is characterized in that: The specific steps of sample entropy integration are: Reconstructing the phase space according to the decomposed mode to obtain a vector sequence; Calculating the distances between the vector sequences at different times; Preset an acceptance matrix tolerance, obtain a matching point probability by calculation according to the distance and the acceptance matrix tolerance, and calculate sample entropy according to the matching point probability; A sample entropy threshold is preset, the decomposition modes are screened according to the sample entropy threshold and the sample entropy to obtain screened decomposition modes, and the decomposition modes are added to obtain the integrated sequence.

6. The photovoltaic module performance prediction method based on real-time data analysis according to claim 4, characterized in that: The specific steps of the adaptive VMD algorithm include: S201: Acquire the number of decomposed eigenfunctions, and decompose the normalized data through VMD according to the number of decomposed eigenfunctions to obtain an eigenmode function; S202: Add each of the intrinsic mode functions to obtain a reconstructed signal; S203: Obtain a reconstruction error by calculating a mean square error according to the reconstructed signal; S204: Obtain the minimum error and determine whether the reconstruction error is less than the minimum error. If yes, set the reconstruction error to the minimum error and output the preprocessing result and the number of decomposed eigenfunctions. If no, increase the number of decomposed eigenfunctions by one and repeat steps S201-S204.

7. The photovoltaic module performance prediction method based on real-time data analysis according to claim 1, characterized in that: The LSTM model includes transmitting the preprocessed data to the first convolution layer through the input layer, the first convolution layer performing causal convolution according to the preprocessed data to obtain a causal convolution result, performing dilated convolution through the second convolution layer according to the causal convolution result to obtain a first dilated result, performing dilated convolution through the third convolution layer according to the first dilated result to obtain a second dilated result, transmitting the causal convolution result, the first dilated result, and the second dilated result to the first LSTM layer, the second LSTM layer, and the third LSTM layer respectively to calculate the first feature, the second feature, and the third feature, and fusing the first feature, the second feature, and the third feature through the fully connected layer to obtain the conversion efficiency prediction value.

8. A photovoltaic module performance prediction system based on real-time data analysis, characterized in that: include: Data collection module, data processing module, data classification module, data prediction module; The data acquisition module is used to collect real-time environmental data and light intensity data through sensors, obtain real-time power data of photovoltaic modules through power sensors, and obtain photovoltaic module area data; The data processing module is used to calculate the photovoltaic module conversion efficiency according to the photovoltaic module area data, the real-time power data, and the light intensity data, and to add a timestamp according to the photovoltaic module conversion efficiency to obtain a time series conversion efficiency; The data classification module is used to obtain an environmental feature vector by parallel splicing of the real-time environmental data and the light intensity data, obtain a historical environmental feature vector, and determine a weather type label of the environmental feature vector according to the historical environmental feature vector; The data prediction module is used to store the time series conversion efficiency according to the weather type label to obtain a conversion efficiency sequence, calculate preprocessing data through a preprocessing model according to the conversion efficiency sequence, and calculate a conversion efficiency prediction value through an LSTM model according to the preprocessing data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the photovoltaic component performance prediction method based on real-time data analysis as described in any one of claims 1 to 7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the photovoltaic component performance prediction method based on real-time data analysis as described in any one of claims 1 to 7 when executed by a computer processor.

Images