Self-adaptive adjusting system for photovoltaic module

Abstract

The invention provides a self-adaptive adjustment system for a photovoltaic module, and relates to the technical field of photovoltaic power supply, and the system comprises the steps: obtaining a plurality of series equalization module sets; obtaining a plurality of first state monitoring data sets; obtaining a plurality of first abnormal indexes; if the multiple first abnormal indexes are all smaller than or equal to a preset abnormal threshold value, performance optimization is executed based on a monitoring result, and an optimal control parameter is obtained; and performing generation power adjustment on the first series equalization assembly set according to the optimal control parameter. According to the invention, the technical problem of poor control effect caused by different control performances of different components and insufficient refinement degree of control analysis in the prior art can be solved, performance balance and series connectivity are taken as constraints, a plurality of series balance component sets are obtained through division, and the control effect is improved. And performance optimization is carried out after analysis of power abnormality, so that the technical effects of ensuring safe operation of the photovoltaic module and improving the output performance of the photovoltaic module are achieved.

Description

Technical Field

[0001] The present application relates to the field of photovoltaic power supply technology, and in particular to an adaptive regulation system for photovoltaic components. Background Art

[0002] As the demand for renewable energy grows, photovoltaic power generation has been widely used as a clean energy source. However, the power generation efficiency of photovoltaic modules is affected by many factors, such as solar radiation intensity, module temperature, installation angle, etc.

[0003] At present, the existing technology often performs unified analysis and control on photovoltaic modules in a region. However, different modules have different control performances and the control analysis is not refined enough, resulting in poor control effects. Summary of the invention

[0004] The purpose of this application is to provide an adaptive regulation system for photovoltaic components to solve the technical problem in the prior art that the control performance of different components is different and the control analysis is not refined enough, resulting in poor control effect.

[0005] In view of the above problems, the present application provides an adaptive regulation system for photovoltaic components, the system comprising: an optimal division module, the optimal division module is used to obtain multiple distributed photovoltaic components in a target area, and perform multi-scenario output performance analysis on the multiple distributed photovoltaic components, and perform optimal division on the multiple distributed photovoltaic components with performance balance and series connectivity as constraints to obtain multiple series balancing component sets; an operation status monitoring module, the operation status monitoring module is used to perform operation status monitoring on multiple first components in a first series balancing component set to obtain multiple first status monitoring data sets; a power consumption anomaly identification module, the power consumption anomaly identification module is used to identify power consumption anomalies based on the multiple first status monitoring data sets to obtain multiple first anomaly indicators; a performance optimization module, the performance optimization module is used to monitor the solar radiation intensity and battery panel temperature of the first series balancing component set if the multiple first anomaly indicators are all less than or equal to a predetermined anomaly threshold, perform performance optimization based on the monitoring results, and obtain optimal control parameters; a power regulation module, the power regulation module is used to regulate the power generation power of the first series balancing component set with the optimal control parameters.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: Acquire multiple distributed photovoltaic components in the target area, and perform multi-scenario output performance analysis on the multiple distributed photovoltaic components. With performance balance and series connectivity as constraints, perform optimal division on the multiple distributed photovoltaic components to obtain multiple series balanced component sets; perform operation status monitoring on multiple first components in the first series balanced component set to obtain multiple first status monitoring data sets; perform power consumption anomaly identification based on the multiple first status monitoring data sets to obtain multiple first abnormal indicators; if the multiple first abnormal indicators are all less than or equal to the predetermined abnormal threshold, perform solar radiation intensity and panel temperature monitoring on the first series balanced component set, perform performance optimization based on the monitoring results, and obtain optimal control parameters; and adjust the power generation power of the first series balanced component set with the optimal control parameters. Thus, with performance balance and series connectivity as constraints, multiple series balanced component sets are divided, and then performance optimization is performed after power abnormality analysis, so as to achieve the technical effect of ensuring the safe operation of photovoltaic components and improving the output performance of photovoltaic components.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0009] Figure 1 This is a schematic diagram of the structure of the adaptive adjustment system for photovoltaic modules in this application; Figure 2 A schematic flow chart of the method steps executed by the adaptive adjustment system for photovoltaic components of the present application.

[0010] Explanation of the reference numerals: optimization and division module 11 , operation status monitoring module 12 , power consumption abnormality identification module 13 , performance optimization module 14 , power regulation module 15 . DETAILED DESCRIPTION

[0011] This application solves the technical problem in the prior art that the control performance of different components is different, the control analysis is not refined enough, and the control effect is poor by providing an adaptive adjustment system for photovoltaic components. With performance balance and series connectivity as constraints, multiple series balanced component sets are divided, and then power anomaly analysis is performed and performance optimization is performed to achieve the technical effect of ensuring the safe operation of photovoltaic components and improving the output performance of photovoltaic components.

[0012] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0013] Please refer to the attached Figure 1 The present application provides an adaptive regulation system for photovoltaic modules, for performing the following steps: Figure 2 The adaptive adjustment method for photovoltaic components shown in the figure comprises: An optimal partitioning module 11 is used to obtain a plurality of distributed photovoltaic components in a target area, and perform multi-scenario output performance analysis on the plurality of distributed photovoltaic components, and optimally partition the plurality of distributed photovoltaic components with performance balance and series connectivity as constraints to obtain a plurality of series balanced component sets; Specifically, multiple distributed photovoltaic modules are arranged in the target area, and multiple distributed photovoltaic modules are photovoltaic modules to be controlled and adjusted, which need to be determined in combination with actual conditions. Different distributed photovoltaic modules have different output performance in different scenarios. For example, under the same environmental conditions such as light and temperature, the output power of different modules may be different. Multiple scenarios are different operating environment conditions. Based on this, a multi-scenario output performance analysis is performed on multiple distributed photovoltaic modules. With performance balance and series connectivity as constraints, distributed photovoltaic modules with the same output performance and series connection relationship are divided together to obtain multiple series balanced component sets. In this way, the components in each series balanced component set can be uniformly controlled and analyzed, thereby improving control efficiency and accuracy.

[0014] An operation status monitoring module 12, the operation status monitoring module 12 is used to monitor the operation status of multiple first components in the first series balancing component set to obtain multiple first status monitoring data sets; Specifically, the multiple first components refer to the distributed photovoltaic components included in the first series balancing component set. The operating status of the multiple first components is monitored by installing light sensors, temperature sensors, current sensors, voltage sensors, etc. on the photovoltaic components to obtain multiple first status monitoring data sets. The multiple first status monitoring data sets include parameters such as the operating temperature, voltage, and current of the first components.

[0015] A power consumption anomaly identification module 13, wherein the power consumption anomaly identification module 13 is used to identify power consumption anomalies based on the plurality of first state monitoring data sets to obtain a plurality of first anomaly indicators; Specifically, photovoltaic modules are generally packaged by combining multiple single solar cells in series and parallel. In actual applications, some photovoltaic modules will be shaded. The shaded cells will short-circuit, causing the current to decrease, which will limit the output current of the series circuit and output negative power, that is, it will become a load, consuming power in the form of heat, and in severe cases will damage the solar cells. Therefore, power anomaly recognition of photovoltaic modules can identify abnormal modules, and the first abnormal indicator represents the degree of abnormality of the first component.

[0016] The performance optimization module 14 is used to monitor the solar radiation intensity and the temperature of the solar panels of the first series balancing component set if the multiple first abnormal indicators are all less than or equal to the predetermined abnormal threshold, and perform performance optimization based on the monitoring results to obtain the optimal control parameters; Specifically, the predetermined abnormal threshold refers to the critical value of the abnormal index that will affect the safety of the photovoltaic module, that is, exceeding the predetermined abnormal threshold will cause damage to the photovoltaic module. It is set by professional and technical personnel in this field based on actual experience, and there is no restriction on this. If the multiple first abnormal indicators are all less than or equal to the predetermined abnormal threshold, it means that the degree of abnormality is small and will not cause damage to the photovoltaic module. It is just an abnormality caused by improper setting of the control parameters. Therefore, the control parameters can be optimized. The solar radiation intensity and the temperature of the battery panel are factors that affect the output power of the photovoltaic module. Therefore, according to the influence relationship between the solar radiation intensity and the temperature of the battery panel and the output power, the control parameters are optimized to obtain the optimal control parameters. The optimal control parameters include the voltage, current and other control parameters of the photovoltaic module.

[0017] The power regulating module 15 is used to regulate the power generation of the first series balancing component set with the optimal control parameters.

[0018] Specifically, the first series balancing component set is controlled and adjusted according to the optimal control parameters to achieve power generation regulation and improve the performance of the photovoltaic components.

[0019] Furthermore, the optimization partitioning module 11 further includes: An output similarity identification module, the output similarity identification module is used to perform multi-scenario output similarity identification on the multiple distributed photovoltaic components to obtain multi-scenario output similarity; a first constraint division module, the first constraint division module is used to divide the multiple distributed photovoltaic components with the multi-scenario output similarity being greater than a preset similarity as a first constraint to generate multiple photovoltaic component sets; a second constraint division module, the second constraint division module is used to divide the multiple photovoltaic component sets again with series connectivity as a second constraint to generate the multiple series balancing component sets.

[0020] Furthermore, the optimization partitioning module 11 further includes: A power generation influencing factor extraction module, the power generation influencing factor extraction module is used to collect historical power generation records of photovoltaic components, extract power generation influencing factors based on the historical power generation records, and obtain factor intervals of the power generation influencing factors; a factor assignment module, the factor assignment module is used to perform uniform assignment based on the factor interval, and cross-combine the uniform assignment results of different power generation influencing factors to obtain multi-scenario factor assignment information; a historical data mining module, the historical data mining module is used to perform historical output power mining on the multiple distributed photovoltaic components based on the multi-scenario factor assignment information to obtain multiple historical output power record sets; a multi-scenario similarity identification module, the multi-scenario similarity identification module is used to traverse the multiple historical output power record sets to perform multi-scenario output similarity identification on the multiple distributed photovoltaic components, and generate the multi-scenario output similarity.

[0021] Specifically, the plurality of distributed photovoltaic components are optimally divided with performance balance and series connectivity as constraints, so that components with series connectivity and performance similarity can be uniformly analyzed and controlled, effectively improving control accuracy and control efficiency. The specific implementation steps are as follows: First, the multi-scenario output similarity identification is performed on the multiple distributed photovoltaic components, that is, the output power difference of different components under different environmental conditions is analyzed to obtain the multi-scenario output similarity, which is specifically as follows: based on the existing technology, the historical power generation records of the photovoltaic components are collected, and the historical power generation records include historical environmental conditions (such as temperature, solar radiation, etc.) and historical power generation output power. The existing correlation analysis method, such as gray correlation analysis, is used to analyze the environmental conditions that affect the power generation power based on the historical power generation records as the power generation influencing factors. Further, according to the user manual of the distributed photovoltaic components, the application value range of the power generation influencing factor is obtained as the factor interval. Random assignment is performed within the factor interval to ensure that the assignment result is uniformly distributed, and multiple uniformly distributed assignment results corresponding to each power generation influencing factor can be obtained, and then the uniform assignment results of different power generation influencing factors are cross-combined, that is, the uniform assignment results of different power generation influencing factors are randomly combined, and different combination results are used as multi-scenario factor assignment information.

[0022] Furthermore, the multi-scenario factor assignment information is used as index information, and the historical output power of the multiple distributed photovoltaic components is retrieved based on the existing Internet big data to obtain multiple historical output power record sets corresponding to the multi-scenario factor assignment information. The multiple historical output power record sets are traversed, and the historical output power record sets of any two distributed photovoltaic components are compared for similarity. For example, similarity recognition can be performed through the existing cosine similarity to obtain the multi-scenario output similarity between any two distributed photovoltaic components. In this way, multi-scenario similarity recognition is achieved, which provides support for the subsequent photovoltaic component division and improves the control efficiency.

[0023] Furthermore, a preset similarity is set. The preset similarity refers to a similarity reference value for determining that the multi-scenario output powers of two distributed photovoltaic components are the same, and is set by professional and technical personnel in the field. Taking the multi-scenario output similarity greater than the preset similarity as the first constraint, any two distributed photovoltaic components whose multi-scenario output similarity is greater than the preset similarity are divided together, and multiple photovoltaic component sets are generated based on the division results. Then, taking series connectivity as the second constraint, the components with series connectivity in the multiple photovoltaic component sets are divided again to generate the multiple series balanced component sets. Specifically, the series connectivity can be identified by obtaining the line connection diagram of the components in the multiple photovoltaic component sets. The division of the series balanced component set provides a basis for subsequent performance optimization and facilitates improving the efficiency of control analysis.

[0024] Furthermore, the power consumption abnormality identification module 13 also includes: An abnormal information preset module, the abnormal information preset module is used to obtain preset power abnormality type information and preset abnormal index threshold, wherein the preset abnormal index threshold represents the degree of damage to the photovoltaic component caused by the abnormal type; a sample mining module, the sample mining module is used to mine abnormal operation data samples of the photovoltaic component based on the preset power abnormality type information, the abnormal operation data samples include abnormal operation state samples and identification information identifying the degree of abnormality; a feedback optimization module, the feedback optimization module is used to construct an abnormality recognition model with the abnormal operation data samples, and use the preset abnormal index threshold as the feedback network layer to perform feedback optimization on the output of the abnormality recognition model; an indicator output module, the indicator output module is used to perform power consumption abnormality recognition on the multiple first state monitoring data sets with the abnormality recognition model, and output the multiple first abnormal indicators.

[0025] Specifically, power consumption anomaly identification is performed through an anomaly identification model, and the construction process of the anomaly identification model is as follows: first, the preset power anomaly type information and the preset anomaly index threshold are obtained, wherein the preset anomaly index threshold indicates the degree of damage of the anomaly type to the photovoltaic module, that is, different anomaly types have different effects on the photovoltaic module, such as the hot spot effect will cause the temperature to be too high and the module to burn out, and the corresponding preset anomaly index threshold is larger. Specifically, the preset power anomaly type information and the preset anomaly index threshold are set by professional and technical personnel in this field in combination with historical experience, and can be updated and adjusted in real time. Then, based on the preset power anomaly type information as an index element, the abnormal operation data sample of the photovoltaic module corresponding to the preset power anomaly type information is retrieved based on the existing Internet big data, and the abnormal operation data sample includes an abnormal operation state sample and an identification information indicating the degree of abnormality. The abnormal operation recognition model is constructed with the abnormal operation data sample, and the abnormal recognition model can be constructed based on an existing machine learning model, such as a neural network model. The abnormal operation data sample is used as training data, the abnormal operation state sample is input into the abnormal recognition model, and the output is supervised and adjusted with the identification information indicating the degree of abnormality until the abnormal recognition model is trained to converge.

[0026] Furthermore, the output of the abnormal identification model is optimized by using the preset abnormal index threshold as the feedback network layer, that is, the output result of the abnormal identification model is multiplied by the preset abnormal index threshold to achieve feedback optimization. Multiple first state monitoring data sets are input into the abnormal identification model to identify power consumption abnormalities, and multiple first abnormal indicators representing the degree of abnormality can be output. In this way, power abnormality identification is achieved, which facilitates control optimization when the degree of abnormality meets the threshold, and realizes performance optimization of photovoltaic modules.

[0027] Furthermore, the performance optimization module 14 further includes: A temperature-power impact analysis module, the temperature-power impact analysis module is used to perform an impact analysis of the correlation between the panel temperature and the output power of the first series balancing component to obtain a temperature-power impact relationship, wherein the first series balancing component is any component in the first series balancing component set; a temperature trend analysis module, the temperature trend analysis module is used to perform an impact analysis of the panel temperature and the solar radiation intensity on the first series balancing component to obtain a temperature prediction trend; a temperature control analysis module, the temperature control analysis module is used to perform an impact analysis of the panel temperature and the control parameters on the first series balancing component to generate a temperature control relationship; a power optimization module, the power optimization module is used to combine the temperature-power impact relationship, the temperature prediction trend and the temperature control relationship to optimize the power output maximization and obtain the optimal control parameters.

[0028] Furthermore, the performance optimization module 14 further includes: A power supply demand acquisition module, the power supply demand acquisition module is used to obtain the power supply demand power of the photovoltaic components in the target area; a temperature optimization prediction module, the temperature optimization prediction module is used to take the power supply demand power as the target, perform temperature optimization prediction based on the temperature-power influence relationship and the temperature prediction trend, and obtain the predicted optimized temperature; a control parameter conversion module, the control parameter conversion module is used to perform control parameter conversion on the predicted optimized temperature based on the temperature control relationship, and generate the optimal control parameter.

[0029] Specifically, the correlation influence of the panel temperature and output power of the first series balancing component is first analyzed to determine the influence of the panel temperature change on the component output power. The component output power data at different temperatures can be collected, and the existing regression analysis or machine learning algorithm is used to establish a mathematical model between temperature and power, and a function or model describing the influence of temperature change on output power is obtained as the temperature-power influence relationship. The influence of the panel temperature and solar radiation intensity is analyzed for the first series balancing component to analyze how the change of solar radiation intensity affects the panel temperature and predict the temperature trend. Specifically, the panel temperature under different solar radiation intensities can be monitored and the relationship between the two can be analyzed. Exemplarily, the existing time series analysis or prediction model is used to predict the future temperature trend as the temperature prediction trend.

[0030] Furthermore, the influence of the battery panel temperature and the control parameters is analyzed for the first series balancing component, a temperature control relationship is generated, and the relationship between the control parameters (such as voltage and current) and the battery panel temperature is analyzed. Specifically, the control parameters can be adjusted and the changes in the battery panel temperature and output power can be monitored to analyze the influence of the control parameters on the temperature and power, and a function describing the relationship between the control parameters and the battery panel temperature can be generated as the temperature control relationship.

[0031] Finally, the power output is maximized and optimized by combining the temperature-power influence relationship, the temperature prediction trend and the temperature control relationship to obtain the optimal control parameters and achieve performance optimization of the photovoltaic module. The specific method is as follows: Specifically, the power demand of photovoltaic modules can be obtained by the user through the user end input, or it can be determined according to historical demand. Taking the power demand of photovoltaic modules as the target, the power demand of photovoltaic modules is converted to temperature based on the temperature-power influence relationship, and the module temperature that meets the power demand of photovoltaic modules can be obtained. However, solar radiation will affect the temperature. Therefore, the temperature prediction trend is used to reverse the module temperature, which is to ensure that the final predicted optimization temperature can reach the module temperature that meets the power demand of photovoltaic modules after the trend change of the temperature prediction trend.

[0032] Finally, based on the temperature control relationship, we analyze how to achieve the predicted optimized temperature by adjusting the control parameters. Specifically, we can calculate the control parameter values ​​that need to be adjusted based on the predicted optimized temperature, including but not limited to voltage, current, heat dissipation parameters, etc., and use them as the optimal control parameters to improve the operating efficiency and reliability of photovoltaic modules and ensure the stability of power supply.

[0033] Furthermore, the system further comprises: An abnormality judgment module, the abnormality judgment module is used to locate the first abnormal component if any abnormal indicator among the multiple first abnormal indicators is greater than a predetermined abnormal threshold; an abnormality optimization analysis module, the abnormality optimization analysis module is used to determine whether the first abnormal component is an angle-adjustable component, and if so, collect solar incidence parameters and a preset angle adjustment range of the first abnormal component for abnormality optimization analysis to obtain a first abnormality optimization degree; a protection instruction generation module, the protection instruction generation module is used to generate a first circuit protection instruction if the first abnormal optimization degree is less than a predetermined optimization degree; a circuit protection control module, the circuit protection control module is used to start the protection circuit of the first abnormal component based on the first circuit protection instruction, and perform circuit protection control on the first abnormal component; a remaining component optimization module, the remaining component optimization module is used to perform performance optimization on the remaining series balancing components except the first abnormal component to obtain the optimal control parameters.

[0034] Furthermore, the abnormal optimization analysis module also includes: An angle iteration adjustment module, the angle iteration adjustment module is used to iteratively adjust the component angle of the first abnormal component within the preset angle adjustment range to obtain multiple iterative component angles; a power density identification module, the power density identification module is used to identify the component incident power density based on the multiple iterative component angles and the solar incidence parameters to obtain multiple iterative power densities; an operation status prediction module, the operation status prediction module is used to predict the operation status of the first abnormal component based on the multiple iterative power densities to obtain first predicted status data; an optimization degree analysis module, the optimization degree analysis module is used to compare the degree of deviation between the first predicted status data and the first status monitoring data set corresponding to the first abnormal component, and generate the first abnormal optimization degree.

[0035] Specifically, in the aforementioned performance optimization module 14, when the multiple first abnormal indicators are all less than or equal to the predetermined abnormal threshold, the performance optimization is performed, then, the situation where the multiple first abnormal indicators are greater than the predetermined abnormal threshold is analyzed next. If any abnormal indicator among the multiple first abnormal indicators is greater than the predetermined abnormal threshold, the component whose abnormal indicator is greater than the predetermined abnormal threshold is located as the first abnormal component. Some photovoltaic components can be angle-adjusted during design and installation, but some are fixed. Professionals and technicians in this field can mark each component to see if the angle can be adjusted based on actual conditions, and judge whether the first abnormal component is an angle-adjustable component based on the marking results. If so, the solar incident parameters including the incident angle and the solar radiation intensity are collected by the existing light sensor. The preset angle adjustment range of the first abnormal component refers to the angle adjustment range, which needs to be determined based on actual conditions.

[0036] Based on the solar incidence parameter and the preset angle adjustment range of the first abnormal component, an abnormal optimization analysis is performed to obtain a first abnormal optimization degree, that is, by adjusting the angle of the photovoltaic component to improve the power output of the component and reduce the occurrence of abnormalities. The first abnormal optimization degree is used to measure the effectiveness of the angle adjustment. The specific implementation steps are as follows: Within the preset angle adjustment range, the first abnormal component is iteratively adjusted, and each adjustment generates a new component angle, which constitutes a plurality of iterative component angles. For example, if the preset angle adjustment range is 20° to 60°, a series of iterative angles (such as 25°, 30°, 35°, etc.) can be set. For each iterative angle, the incident power density of the photovoltaic component is calculated using the existing optical model in combination with the solar incidence parameters. Exemplarily, the calculation method is: ,in, is the incident power density, is the solar radiation intensity, It is the effective light receiving area of ​​the component, which needs to be determined based on actual conditions. It is the incident angle of the sun's rays on the surface of the component, which can be determined by combining the incident angle in the solar incident parameter with the iterative component angle, thereby obtaining multiple iterative power densities, which reflect the solar radiation energy received by the photovoltaic component at different angles. Using multiple iterative power densities, the future operating state of the first abnormal component is predicted to generate first predicted state data, which includes the expected power output.

[0037] Specifically, the existing machine learning model can be trained by obtaining historical power density samples and corresponding historical state data samples to obtain a state prediction model, and multiple iterative power densities are analyzed through the state prediction model to obtain the first predicted state data. The first predicted state data is compared with the real-time state monitoring data set corresponding to the first abnormal component, and the degree of deviation between the two is calculated. The degree of deviation is subtracted from 1, and the result is the first abnormal optimization degree, which is used to measure the optimization effect achieved by angle adjustment. If the degree of deviation is small, it means that the predicted state is close to the actual state and the optimization effect is good; if the degree of deviation is large, it means that the optimization effect is not good. If the first abnormal optimization degree is less than the predetermined optimization degree, a first circuit protection instruction is generated, and the protection circuit of the first abnormal component is started according to the first circuit protection instruction. The protection circuit includes disconnecting the abnormal component, adjusting the current flow direction and other measures to prevent the fault from spreading to other components. The specific needs to be determined in combination with the actual situation, thereby performing circuit protection control on the first abnormal component.

[0038] For the remaining series balancing components except the first abnormal component, performance optimization is performed according to the aforementioned method for obtaining the optimal control parameters, while protecting the safety of the photovoltaic components, maximizing the energy output of the remaining components and improving the output performance of the photovoltaic components.

[0039] In summary, the adaptive adjustment system for photovoltaic modules provided by the present application has the following technical effects: Acquire multiple distributed photovoltaic components in the target area, and perform multi-scenario output performance analysis on the multiple distributed photovoltaic components. With performance balance and series connectivity as constraints, perform optimal division on the multiple distributed photovoltaic components to obtain multiple series balanced component sets; perform operation status monitoring on multiple first components in the first series balanced component set to obtain multiple first status monitoring data sets; perform power consumption anomaly identification based on the multiple first status monitoring data sets to obtain multiple first abnormal indicators; if the multiple first abnormal indicators are all less than or equal to the predetermined abnormal threshold, perform solar radiation intensity and panel temperature monitoring on the first series balanced component set, perform performance optimization based on the monitoring results, and obtain optimal control parameters; and adjust the power generation power of the first series balanced component set with the optimal control parameters. Thus, with performance balance and series connectivity as constraints, multiple series balanced component sets are divided, and then performance optimization is performed after power abnormality analysis, so as to achieve the technical effect of ensuring the safe operation of photovoltaic components and improving the output performance of photovoltaic components.

[0040] The various embodiments in this specification are described in a progressive manner, and the above description of the disclosed embodiments enables professionals and technicians in the field to implement or use the present application. Various modifications to these embodiments will be obvious to professionals and technicians in the field, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features disclosed herein.

[0041] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An adaptive regulation system for photovoltaic modules, characterized in that: include: An optimal partitioning module, the optimal partitioning module is used to obtain multiple distributed photovoltaic components in a target area, and perform multi-scenario output performance analysis on the multiple distributed photovoltaic components, and optimally partition the multiple distributed photovoltaic components with performance balance and series connectivity as constraints to obtain multiple series balanced component sets; An operation status monitoring module, the operation status monitoring module is used to monitor the operation status of multiple first components in the first series balancing component set to obtain multiple first status monitoring data sets; A power consumption anomaly identification module, the power consumption anomaly identification module is used to identify power consumption anomalies based on the multiple first state monitoring data sets to obtain multiple first anomaly indicators; A performance optimization module, wherein if the plurality of first abnormal indicators are all less than or equal to a predetermined abnormal threshold, the performance optimization module is used to monitor the solar radiation intensity and the temperature of the solar panel of the first series balancing component set, and to perform performance optimization based on the monitoring results to obtain optimal control parameters; A power regulation module is used to regulate the power generation of the first series balancing component set using the optimal control parameters.

2. The adaptive adjustment system for photovoltaic modules according to claim 1, characterized in that: Performing a multi-scenario output performance analysis on the plurality of distributed photovoltaic components, and optimizing and dividing the plurality of distributed photovoltaic components with performance balance and series connectivity as constraints, including: An output similarity identification module, wherein the output similarity identification module is used to perform multi-scenario output similarity identification on the plurality of distributed photovoltaic components to obtain multi-scenario output similarity; A first constraint division module, the first constraint division module is used to divide the plurality of distributed photovoltaic components by taking the multi-scenario output similarity being greater than a preset similarity as a first constraint to generate a plurality of photovoltaic component sets; The second constraint division module is used to divide the plurality of photovoltaic component sets again by taking series connectivity as a second constraint to generate the plurality of series balancing component sets.

3. The adaptive adjustment system for photovoltaic modules according to claim 2, characterized in that: Performing multi-scenario output similarity identification on the plurality of distributed photovoltaic components to obtain multi-scenario output similarity includes: A power generation influencing factor extraction module, the power generation influencing factor extraction module is used to collect historical power generation records of photovoltaic modules, extract power generation influencing factors based on the historical power generation records, and obtain factor intervals of the power generation influencing factors; A factor assignment module, the factor assignment module is used to perform uniform assignment based on the factor interval, and cross-combine the uniform assignment results of different power generation influencing factors to obtain multi-scenario factor assignment information; A historical data mining module, wherein the historical data mining module is used to mine the historical output power of the plurality of distributed photovoltaic components based on multi-scenario factor assignment information to obtain a plurality of historical output power record sets; A multi-scenario similarity identification module is used to traverse the multiple historical output power record sets to perform multi-scenario output similarity identification on the multiple distributed photovoltaic components to generate the multi-scenario output similarity.

4. The adaptive adjustment system for photovoltaic modules according to claim 1, characterized in that: Power consumption anomaly identification is performed based on the multiple first state monitoring data sets to obtain multiple first abnormal indicators, including: An abnormal information preset module, the abnormal information preset module is used to obtain preset power abnormality type information and preset abnormal index threshold, wherein the preset abnormal index threshold represents the degree of damage of the abnormal type to the photovoltaic module; A sample mining module, the sample mining module is used to mine abnormal operation data samples of photovoltaic components based on the preset power abnormality type information, the abnormal operation data samples include abnormal operation state samples and identification information identifying the degree of abnormality; A feedback optimization module, the feedback optimization module is used to construct an abnormality recognition model with the abnormal operation data sample, and to perform feedback optimization on the output of the abnormality recognition model with the preset abnormality index threshold as a feedback network layer; An indicator output module is used to identify power consumption anomalies of the plurality of first state monitoring data sets using the anomaly identification model, and output the plurality of first anomaly indicators.

5. The adaptive adjustment system for photovoltaic modules according to claim 1, characterized in that: The solar radiation intensity and the temperature of the solar panels are monitored for the first series balancing component set, and performance optimization is performed based on the monitoring results to obtain optimal control parameters, including: A temperature-power impact analysis module, the temperature-power impact analysis module is used to perform a correlation impact analysis between the battery panel temperature and the output power of the first series balancing component to obtain a temperature-power impact relationship, wherein the first series balancing component is any component in the first series balancing component set; A temperature trend analysis module, which is used to analyze the influence of the temperature of the solar panel and the intensity of solar radiation on the first series balancing component to obtain a temperature prediction trend; A temperature control analysis module, the temperature control analysis module is used to analyze the influence of the battery panel temperature and the control parameters on the first series balancing component, and generate a temperature control relationship; A power optimization module is used to combine the temperature-power influence relationship, the temperature prediction trend and the temperature control relationship to maximize the power output and obtain the optimal control parameters.

6. The adaptive adjustment system for photovoltaic modules according to claim 5, characterized in that: Combining the temperature-power influence relationship, the temperature prediction trend and the temperature control relationship to maximize the power output and obtain the optimal control parameters includes: A power supply demand acquisition module, which is used to obtain the power supply demand power of the photovoltaic components in the target area; A temperature optimization prediction module, wherein the temperature optimization prediction module is used to perform temperature optimization prediction based on the temperature-power influence relationship and the temperature prediction trend with the power supply demand as the target, and obtain a predicted optimized temperature; A control parameter conversion module is used to perform control parameter conversion on the predicted optimization temperature based on the temperature control relationship to generate the optimal control parameter.

7. The self-adaptive adjustment system for photovoltaic modules according to claim 4, characterized in that: The system further comprises: An abnormality judgment module, the abnormality judgment module is used to locate the first abnormal component if any abnormal indicator among the multiple first abnormal indicators is greater than a predetermined abnormal threshold; an abnormal optimization analysis module, the abnormal optimization analysis module is used to determine whether the first abnormal component is an angle-adjustable component, and if so, collect solar incidence parameters and a preset angle adjustment range of the first abnormal component to perform abnormal optimization analysis to obtain a first abnormal optimization degree; A protection instruction generation module, the protection instruction generation module is used to generate a first circuit protection instruction if the first abnormal optimization degree is less than a predetermined optimization degree; a circuit protection control module, the circuit protection control module being used to start the protection circuit of the first abnormal component based on the first circuit protection instruction, and perform circuit protection control on the first abnormal component; The remaining component optimization module is used to perform performance optimization on the remaining series balancing components except the first abnormal component to obtain the optimal control parameters.

8. The adaptive adjustment system for photovoltaic modules according to claim 7, characterized in that: Collecting solar incident parameters and a preset angle adjustment range of the first abnormal component to perform abnormal optimization analysis to obtain a first abnormal optimization degree includes: An angle iteration adjustment module, the angle iteration adjustment module is used to perform component angle iteration adjustment on the first abnormal component within the preset angle adjustment range to obtain multiple iterative component angles; A power density identification module, the power density identification module is used to identify component incident power density based on the multiple iterative component angles and the solar incidence parameters to obtain multiple iterative power densities; An operating state prediction module, the operating state prediction module is used to predict the operating state of the first abnormal component based on the multiple iterative power densities to obtain first predicted state data; An optimization degree analysis module is used to compare the degree of deviation between the first predicted state data and a first state monitoring data set corresponding to the first abnormal component to generate the first abnormal optimization degree.

Images