Distributed photovoltaic output characteristic prediction method, system and equipment in combination with health factors

Abstract

The invention belongs to the field of photovoltaic power generation prediction, and particularly relates to a distributed photovoltaic output characteristic prediction method, system and equipment combined with health factors. Determining a distributed photovoltaic system, wherein the distributed photovoltaic system comprises a plurality of photovoltaic modules; health factors of the photovoltaic modules are calculated respectively; obtaining target environment data of each photovoltaic module in the target prediction time period, and predicting nominal generation power of each photovoltaic module to obtain a nominal output prediction value of each photovoltaic module; matching the health factor of each photovoltaic module with a corresponding nominal output predicted value, and correcting the nominal output predicted value to obtain a corrected output predicted value of each photovoltaic module; and summarizing the corrected output prediction values of the photovoltaic modules to obtain a photovoltaic output prediction value of the distributed photovoltaic system. According to the invention, the health factor is introduced to represent the actual health condition of the photovoltaic module, and the health factor is combined with the nominal output prediction value, so that the output prediction precision of the distributed photovoltaic system is improved.

Description

Technical Field

[0001] The present invention belongs to the field of photovoltaic power generation prediction, and in particular to a method, system and device for predicting distributed photovoltaic output characteristics combined with health factors. Background Art

[0002] Distributed photovoltaic power generation is an important form of photovoltaic power generation. However, since distributed photovoltaic systems are composed of a large number of dispersed photovoltaic modules, they are affected by factors such as the installation environment and the performance attenuation of the modules themselves, and their actual power generation output is often difficult to accurately predict. In the prior art, distributed photovoltaic output prediction adopts a modeling method based on nominal parameters, that is, according to the factory parameters of photovoltaic modules, combined with external factors such as meteorological data, physical or statistical models are used to estimate their theoretical output. However, in actual operation, photovoltaic modules are affected by factors such as dust shielding, local hot spots, and material aging, and their performance is often significantly different from the factory state, making it impossible to accurately assess the actual health level of photovoltaic modules, and it is difficult to fully reflect their true working status in the photovoltaic output prediction, resulting in low accuracy in the output prediction of distributed photovoltaic systems. Summary of the invention

[0003] This application aims to solve the technical problem that the existing technology lacks accurate assessment of the actual health status of photovoltaic components, resulting in low accuracy in output prediction of distributed photovoltaic systems, by providing a method and device for predicting distributed photovoltaic output characteristics combined with health factors.

[0004] In view of the above problems, the present application provides a method and device for predicting distributed photovoltaic output characteristics combined with health factors.

[0005] The first aspect disclosed in the present application provides a method for predicting distributed photovoltaic output characteristics in combination with a health factor, the method comprising: determining a distributed photovoltaic system, the distributed photovoltaic system comprising a plurality of distributed photovoltaic clusters, wherein each distributed photovoltaic cluster comprises a plurality of photovoltaic modules; for each photovoltaic module, respectively calculating a health factor of each photovoltaic module, the health factor indicating the health degree of the actual working state of the photovoltaic module relative to its factory nominal state; obtaining target environmental data of each photovoltaic module within a target prediction period, predicting the nominal power generation of each photovoltaic module, and obtaining a nominal output prediction value of each photovoltaic module; matching the health factor of each photovoltaic module with the corresponding nominal output prediction value, correcting the nominal output prediction value, and obtaining a corrected output prediction value of each photovoltaic module; and summarizing the corrected output prediction values ​​of each photovoltaic module to obtain a photovoltaic output prediction value of the distributed photovoltaic system.

[0006] Furthermore, the method for calculating the health factor of each photovoltaic module described in S2 is: first, obtaining the historical operating data of the photovoltaic module, including but not limited to output voltage, current, and power parameters; second, collecting environmental data of the corresponding time period, such as light intensity, temperature, and humidity; then, comparing and analyzing these actual operating data with the factory nominal parameters of the photovoltaic module to quantify the performance of the photovoltaic module in each working link; wherein, the value range of the health factor is between 0 and 1, where 1 indicates that the module is in an ideal healthy state and fully meets the factory nominal performance, while a value close to 0 indicates that the performance of the module is severely degraded and requires maintenance or replacement.

[0007] Furthermore, the method for matching the health factor of each photovoltaic module with the corresponding nominal output prediction value in S4 is: multiplying the nominal output prediction value of each photovoltaic module with its corresponding health factor.

[0008] Furthermore, the aggregation process described in S5 is performed based on the structure of the distributed photovoltaic system. First, the corrected output prediction values ​​of the photovoltaic components belonging to the same distributed photovoltaic cluster are added together and loss correction is performed to obtain the predicted output of the distributed photovoltaic cluster; then, the predicted outputs of all distributed photovoltaic clusters are added together and loss correction is performed to obtain the overall output prediction value of the entire distributed photovoltaic system.

[0009] Furthermore, for the multi-stage energy conversion process of photovoltaic power generation, a photoelectric conversion efficiency model, a carrier collection efficiency model and a circuit conversion efficiency model are established, wherein the multi-stage energy conversion process includes multiple energy conversion stages, namely, a photoelectric conversion stage, a carrier collection stage and a circuit conversion stage;

[0010] Set a preset time period and read the historical operation data and corresponding historical environmental data of each photovoltaic module within the preset time period;

[0011] Based on the historical operation data and historical environmental data of each photovoltaic module, combined with the photoelectric conversion efficiency model, the carrier collection efficiency model and the circuit conversion efficiency model, the health of each photovoltaic module in multiple energy conversion stages is obtained;

[0012] The health of each photovoltaic module in multiple energy conversion stages is comprehensively evaluated to obtain the health factor of each photovoltaic module.

[0013] Further,

[0014] Obtain factory inspection data of standard photovoltaic modules of the same model as each photovoltaic module as nominal sample data;

[0015] The nominal sample data are grouped and labeled to obtain samples of the photoelectric conversion stage, samples of the carrier collection stage, and samples of the circuit conversion stage;

[0016] The photoelectric conversion efficiency model is constructed by taking the irradiance and temperature of the sample in the photoelectric conversion stage as input and the photogenerated carrier concentration as output;

[0017] The carrier collection efficiency model is constructed by taking the photogenerated carrier concentration in the sample during the carrier collection stage as input and the photovoltaic current and photovoltaic voltage as output;

[0018] The photovoltaic current and photovoltaic voltage in the samples of the circuit conversion stage are taken as input, and the photovoltaic power is taken as output to construct a circuit conversion efficiency model.

[0019] Further,

[0020] According to the historical operation data of each photovoltaic module and the corresponding historical environmental data, the actual photoelectric conversion efficiency, the actual carrier collection efficiency and the actual circuit conversion efficiency of each photovoltaic module are calculated;

[0021] Compare the actual photoelectric conversion efficiency, actual carrier collection efficiency and actual circuit conversion efficiency of each photovoltaic module with the standard efficiency values ​​of the photoelectric conversion efficiency model, the carrier collection efficiency model and the circuit conversion efficiency model, respectively, and calculate the difference between the two;

[0022] The difference is converted into health degree representation to obtain the health degree of each photovoltaic module in the photoelectric conversion stage, carrier collection stage and circuit conversion stage.

[0023] Further,

[0024] Obtain weight coefficients of multiple transduction stages;

[0025] The health of each photovoltaic module in the photoelectric conversion stage, carrier collection stage and circuit conversion stage is multiplied by the corresponding weight coefficient to obtain the weighted health;

[0026] The weighted health of each photovoltaic module in multiple energy conversion stages is multiplied to obtain the health factor of each photovoltaic module.

[0027] The second aspect disclosed in the present application provides a distributed photovoltaic output characteristic prediction system combined with health factors, the system comprising:

[0028] A system determination module is used to determine a distributed photovoltaic system, wherein the distributed photovoltaic system includes a plurality of distributed photovoltaic clusters, wherein each distributed photovoltaic cluster includes a plurality of photovoltaic modules;

[0029] A health factor calculation module is used to calculate the health factor of each photovoltaic module for each photovoltaic module, wherein the health factor indicates the health degree of the actual working state of the photovoltaic module relative to its factory nominal state;

[0030] The environmental data acquisition module is used to acquire the target environmental data of each photovoltaic module within the target prediction period, predict the nominal power generation of each photovoltaic module, and obtain the nominal output prediction value of each photovoltaic module;

[0031] The nominal output prediction module is used to match the health factor of each photovoltaic module with the corresponding nominal output prediction value, correct the nominal output prediction value, and obtain the corrected output prediction value of each photovoltaic module;

[0032] The photovoltaic output aggregation module is used to aggregate the corrected output prediction values ​​of each photovoltaic module to obtain the photovoltaic output prediction value of the distributed photovoltaic system.

[0033] The third aspect disclosed in the present application provides an electronic device, which includes: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute the distributed photovoltaic output characteristic prediction method combined with health factors provided in the present application.

[0034] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0035] Since a distributed photovoltaic system is adopted, the distributed photovoltaic system includes multiple distributed photovoltaic clusters, where each distributed photovoltaic cluster includes multiple photovoltaic modules, which lays the foundation for the subsequent modeling and analysis of a single photovoltaic module; for each photovoltaic module, the health factor of each photovoltaic module is calculated respectively, and the health factor represents the health degree of the actual working state of the photovoltaic module relative to its factory nominal state, and quantitatively evaluates the difference between the actual working state of the photovoltaic module and its factory nominal state, which provides a basis for considering the performance attenuation of the photovoltaic module in the output prediction; the target environmental data of each photovoltaic module within the target prediction period is obtained, the nominal power generation power of each photovoltaic module is predicted, and the nominal output prediction value of each photovoltaic module is obtained, and the ideal state is obtained. The expected output of the photovoltaic components is calculated to prepare for the subsequent correction of the predicted value; the health factor of each photovoltaic component is matched with the corresponding nominal output prediction value, the nominal output prediction value is corrected, and the corrected output prediction value of each photovoltaic component is obtained, and the output prediction result of the photovoltaic components taking into account the actual health status is obtained; the corrected output prediction value of each photovoltaic component is summarized to obtain the photovoltaic output prediction value of the distributed photovoltaic system. The technical solution solves the technical problem that the existing technology lacks accurate assessment of the actual health status of photovoltaic components, resulting in low output prediction accuracy of the distributed photovoltaic system. By introducing the health factor to characterize the actual health status of the photovoltaic components and combining it with the nominal output prediction value, the technical effect of improving the output prediction accuracy of the distributed photovoltaic system is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1A flow chart of a method for predicting distributed photovoltaic output characteristics combined with health factors is provided for an embodiment of the present application;

[0037] Figure 2 A structural schematic diagram of a distributed photovoltaic output characteristic prediction system combined with health factors is provided for the embodiment of the present application;

[0038] Figure 3 A structural schematic diagram of a distributed photovoltaic output characteristic prediction device combined with a health factor is provided for an embodiment of the present application.

[0039] Explanation of the reference numerals: system determination module 11 , health factor calculation module 12 , environmental data acquisition module 13 , nominal output prediction module 14 , photovoltaic output aggregation module 15 , processor 21 , memory 22 , input device 23 , output device 24 . DETAILED DESCRIPTION

[0040] The overall idea of ​​the technical solution provided by this application is as follows:

[0041] The embodiments of the present application provide a method and device for predicting distributed photovoltaic output characteristics in combination with a health factor. First, for a distributed photovoltaic system composed of multiple photovoltaic modules, a health factor is introduced to quantitatively evaluate the degree of attenuation of the actual working state of a single photovoltaic module relative to its factory nominal state. Secondly, the nominal power generation power of each photovoltaic module is predicted using environmental data within the target prediction period, such as irradiance, temperature, etc., to obtain the expected output under ideal conditions, that is, the nominal output prediction value. Thirdly, the health factor is matched with the nominal output prediction value, and the nominal output prediction value is corrected to obtain the output prediction result of the photovoltaic module that takes into account the actual health status, that is, the corrected output prediction value. Afterwards, the corrected output prediction values ​​of all photovoltaic modules are summarized to obtain the photovoltaic output prediction value of the entire distributed photovoltaic system.

[0042] By integrating the health factors that reflect the actual working conditions of photovoltaic modules and the nominal output prediction values ​​based on environmental data, the shortcomings of existing methods that only consider nominal parameters but ignore actual performance degradation are overcome, and the accuracy and reliability of distributed photovoltaic output prediction are improved.

[0043] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0044] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a method for predicting distributed photovoltaic output characteristics combined with health factors, the method comprising:

[0045] S1: Determine a distributed photovoltaic system, where the distributed photovoltaic system includes a plurality of distributed photovoltaic clusters, wherein each distributed photovoltaic cluster includes a plurality of photovoltaic modules.

[0046] Specifically, the hierarchical structure of the distributed photovoltaic system is clarified, that is, the entire system is composed of multiple distributed photovoltaic clusters, and each distributed photovoltaic cluster contains multiple photovoltaic modules. Among them, the distributed photovoltaic system is distributed in different geographical locations, such as residential roofs, factory buildings or open areas, etc., each location is installed with one or more distributed photovoltaic clusters, and each distributed photovoltaic cluster is composed of several photovoltaic modules, so that the distributed photovoltaic system can adapt to different installation environments and power generation needs.

[0047] First, the overall topological structure information of the distributed photovoltaic system is collected, including the geographical distribution, installation angle, orientation, etc. of each distributed photovoltaic cluster. Secondly, the photovoltaic components in each distributed photovoltaic cluster are registered in detail, and their model, rated power, production date and other parameters are recorded. After that, this information is organized into structured data and stored in the system database of the distributed photovoltaic system, laying the foundation for subsequent analysis and prediction work. By clarifying the structure of the distributed photovoltaic system, conditions are created for subsequent health factor calculation and output prediction, so that the characteristics and working status of each photovoltaic component can be considered more finely, and the accuracy of the overall prediction can be improved.

[0048] S2: for each photovoltaic module, respectively calculating the health factor of each photovoltaic module, where the health factor indicates the health level of the actual working state of the photovoltaic module relative to its factory nominal state.

[0049] Specifically, in actual operation, photovoltaic modules are affected by factors such as dust shielding, local hot spots, and material aging, and their performance is often significantly different from the factory state. The health factor can quantify this difference, thereby more accurately reflecting the actual working state of photovoltaic modules in subsequent output forecasts.

[0050] In order to calculate the health factor, first, obtain the historical operating data of the photovoltaic module, including but not limited to parameters such as output voltage, current, and power. Secondly, collect environmental data for the corresponding period, such as light intensity, temperature, humidity, etc. Then, compare and analyze these actual operating data with the factory nominal parameters of the photovoltaic module to quantify the performance of the photovoltaic module in each working link. For example, evaluate indicators such as the photoelectric conversion efficiency, carrier collection efficiency, and circuit conversion efficiency of each photovoltaic module, and compare these indicators with the photovoltaic performance indicators under ideal conditions to obtain a health factor that reflects the overall health of the photovoltaic module. Among them, the value range of the health factor is between 0 and 1, where 1 indicates that the component is in an ideal health state and fully meets the factory nominal performance, while a value close to 0 indicates that the performance of the component is severely degraded and requires maintenance or replacement.

[0051] By calculating the health factor of each PV module, an important correction basis is provided for subsequent output forecasts, which can effectively capture the performance changes of PV modules during long-term operation, thereby improving the accuracy and reliability of the overall output forecast of the distributed PV system.

[0052] S3: Obtain target environmental data of each photovoltaic module within a target prediction period, predict the nominal power generation of each photovoltaic module, and obtain a predicted nominal output value of each photovoltaic module.

[0053] Specifically, first, the target prediction period is clarified. The target prediction period refers to a period of time in the future, such as the next 24 hours or the next week. For the target prediction period, the predicted data of the environment in which each photovoltaic module is located, that is, the target environment data, is collected, including but not limited to the predicted meteorological parameters such as light intensity, temperature, humidity, and wind speed. These target environment data can be obtained from the meteorological department or generated by a professional meteorological forecast model. Next, based on these target environment data, combined with the factory nominal parameters of the photovoltaic module, the power generation power of each photovoltaic module under ideal conditions is predicted to obtain the nominal output prediction value of each photovoltaic module. For example, using a statistical model constructed based on the principle of photovoltaic power generation, considering factors such as solar radiation intensity, inclination and orientation of the photovoltaic module, the theoretical power generation is calculated. Among them, the statistical model uses historical data to establish the correlation between environmental parameters and power generation, and improves the accuracy of the prediction through methods such as machine learning. Among them, the predicted nominal output prediction value is the output of the photovoltaic module under ideal conditions, that is, assuming that the photovoltaic module maintains the performance level at the time of leaving the factory, reflecting the best power generation performance that the photovoltaic module can theoretically achieve under given environmental conditions.

[0054] By obtaining the predicted nominal output value of each PV module within the target prediction period, the foundation is laid for subsequent accurate prediction, but the possible performance degradation of PV modules in actual operation is not considered.

[0055] S4: Matching the health factor of each photovoltaic module with the corresponding nominal output prediction value, correcting the nominal output prediction value, and obtaining a corrected output prediction value of each photovoltaic module.

[0056] Specifically, the nominal output prediction value is calculated based on the performance of the PV module under ideal conditions, while the health factor reflects the degree of performance degradation of the PV module in actual operation. By combining these two parameters, a corrected output prediction value that is closer to the actual situation is obtained. Specifically, the nominal output prediction value of each PV module is multiplied by its corresponding health factor, which is between 0 and 1. The nominal output prediction value under ideal conditions can be appropriately reduced according to the actual health status of the PV module. For example, for a PV module with a health factor of 0.9, its actual output is expected to be 90% of that under ideal conditions. The nominal output prediction value corresponding to each PV module is corrected by the health factor of each PV module, so as to achieve personalized prediction adjustment for each individual PV module, instead of using a unified correction factor for the entire distributed PV system. This refined processing method of adjusting each PV module individually helps to improve the accuracy of the overall prediction, especially in large-scale distributed PV systems, where different PV modules may be in different health states. Among them, the correction process should be dynamic. As time goes by, the health status of the PV module changes, so the health factor should be updated regularly to ensure the accuracy of the correction. At the same time, this correction method also provides important information for the operation and maintenance of distributed photovoltaic systems, which can help identify photovoltaic modules with significantly degraded performance and perform maintenance or replacement in a timely manner.

[0057] By obtaining the corrected output prediction value that takes the actual operating conditions into consideration, the foundation is laid for the final overall output prediction of the distributed photovoltaic system, which not only improves the prediction accuracy but also provides important support for the refined management of the distributed photovoltaic system.

[0058] S5: Summarize the corrected output prediction values ​​of each photovoltaic module to obtain the photovoltaic output prediction value of the distributed photovoltaic system.

[0059] Specifically, after completing the calculation of the corrected output prediction value of each photovoltaic component, the corrected output prediction values ​​of each photovoltaic component are summarized to obtain the photovoltaic output prediction value of the distributed photovoltaic system, thereby integrating the prediction results at the level of a single photovoltaic component to obtain the overall output prediction of the entire distributed photovoltaic system. The aggregation process is based on the structure of the distributed photovoltaic system. First, the corrected output prediction values ​​of the photovoltaic components belonging to the same distributed photovoltaic cluster are added and loss correction is performed to obtain the predicted output of the distributed photovoltaic cluster. Then, the predicted outputs of all distributed photovoltaic clusters are added and loss correction is performed to obtain the overall output prediction value of the entire distributed photovoltaic system.

[0060] Through the bottom-up, step-by-step forecasting method, the overall output forecast value of the distributed photovoltaic system is obtained taking into account various practical factors, taking into account the individual characteristics and health status of each photovoltaic component in the distributed photovoltaic system, so it is more accurate and reliable. At the same time, this method also has good scalability and adaptability, and can be adjusted accordingly as the scale of the distributed photovoltaic system expands or the structure changes, providing important data support for the precise management and optimized operation of the distributed photovoltaic system.

[0061] Furthermore, the embodiment of the present application also includes:

[0062] For the multi-stage energy conversion process of photovoltaic power generation, a photoelectric conversion efficiency model, a carrier collection efficiency model and a circuit conversion efficiency model are established, wherein the multi-stage energy conversion process includes multiple energy conversion stages, namely, a photoelectric conversion stage, a carrier collection stage and a circuit conversion stage;

[0063] Set a preset time period and read the historical operation data and corresponding historical environmental data of each photovoltaic module within the preset time period;

[0064] Based on the historical operation data and historical environmental data of each photovoltaic module, combined with the photoelectric conversion efficiency model, the carrier collection efficiency model and the circuit conversion efficiency model, the health of each photovoltaic module in multiple energy conversion stages is obtained;

[0065] The health of each photovoltaic module in multiple energy conversion stages is comprehensively evaluated to obtain the health factor of each photovoltaic module.

[0066] In a feasible implementation, the photovoltaic power generation process can be divided into multiple energy conversion stages, including a photoelectric conversion stage, a carrier collection stage, and a circuit conversion stage. First, for these three stages, a photoelectric conversion efficiency model, a carrier collection efficiency model, and a circuit conversion efficiency model are established respectively to quantitatively describe the energy conversion efficiency of photovoltaic modules in each energy conversion stage under the standard factory state, providing a theoretical basis for subsequent health assessments. Secondly, a preset time period is set, and the historical operating data and corresponding historical environmental data of each photovoltaic module within the time period are read. Among them, the preset time period can be selected as a recent month or a quarter; the historical operating data includes but is not limited to the output voltage, current, power and other parameters of the photovoltaic module, and the historical environmental data includes meteorological factors such as light intensity, temperature, humidity, etc., which provide a basis for the actual operating conditions for subsequent health assessments.

[0067] Next, based on the collected historical environmental data, combined with the established photoelectric conversion efficiency model, carrier collection efficiency model and circuit conversion efficiency model, the health of each photovoltaic module in multiple energy conversion stages is calculated. Specifically, based on the historical operation data and historical environmental data of each photovoltaic module, the actual efficiency of the photovoltaic module in each energy conversion stage is obtained, and the nominal efficiencies in the photoelectric conversion efficiency model, carrier collection efficiency model and circuit conversion efficiency model are compared to evaluate the health of the photovoltaic module in each energy conversion stage. Afterwards, a comprehensive evaluation is conducted on the health of each photovoltaic module in multiple energy conversion stages to obtain the overall health factor of each photovoltaic module, which fully reflects the overall working status and performance level of the photovoltaic module.

[0068] By deeply analyzing the working process of PV modules and evaluating their health status from multiple energy conversion stages, a comprehensive and accurate health factor is obtained, which provides a reliable correction basis for subsequent output predictions and helps to improve the accuracy of output predictions for the entire distributed PV system.

[0069] Furthermore, the embodiment of the present application also includes:

[0070] Obtain factory inspection data of standard photovoltaic modules of the same model as each photovoltaic module as nominal sample data;

[0071] The nominal sample data are grouped and labeled to obtain samples of the photoelectric conversion stage, samples of the carrier collection stage, and samples of the circuit conversion stage;

[0072] The photoelectric conversion efficiency model is constructed by taking the irradiance and temperature of the sample in the photoelectric conversion stage as input and the photogenerated carrier concentration as output;

[0073] The carrier collection efficiency model is constructed by taking the photogenerated carrier concentration in the sample during the carrier collection stage as input and the photovoltaic current and photovoltaic voltage as output;

[0074] The photovoltaic current and photovoltaic voltage in the samples of the circuit conversion stage are taken as input, and the photovoltaic power is taken as output to construct a circuit conversion efficiency model.

[0075] In a feasible implementation, first, the factory inspection data of the standard photovoltaic modules of the same model as each photovoltaic module is obtained as the nominal sample data. These nominal sample data represent the performance parameters of the photovoltaic modules under ideal conditions and provide a benchmark for the establishment of subsequent models. The standard photovoltaic module is a product of the same model that has been strictly screened and tested, and its performance parameters are the standard level of the photovoltaic module of this model. Secondly, the obtained nominal sample data are grouped and labeled. According to the multi-stage energy conversion process of photovoltaic power generation, the sample data are divided into samples of the photoelectric conversion stage, samples of the carrier collection stage, and samples of the circuit conversion stage, which is helpful for the subsequent establishment of corresponding efficiency models for different stages. Among them, the labeling process requires professionals to carry out according to the physical meaning and purpose of the data to ensure that each group of sample data can accurately reflect the characteristics of the corresponding stage. Then, a photoelectric conversion efficiency model is constructed. The model uses the irradiance and temperature in the samples of the photoelectric conversion stage as input variables and the photogenerated carrier concentration as the output variable. It aims to describe the process efficiency of the photovoltaic module converting solar energy into photogenerated carriers, and quantifies the efficiency of the photoelectric conversion stage by analyzing the influence of irradiance and temperature on the photogenerated carrier concentration. Then, a carrier collection efficiency model is constructed. This model uses the photogenerated carrier concentration in the sample during the carrier collection phase as the input variable, and the photovoltaic current and photovoltaic voltage as the output variables. It describes the movement and collection process of the carriers inside the photovoltaic module, and reflects how the photogenerated carriers are effectively converted into usable current and voltage. After that, a circuit conversion efficiency model is constructed. This model uses the photovoltaic current and photovoltaic voltage in the sample during the circuit conversion phase as the input variables, and the photovoltaic power as the output variable. It describes how the photovoltaic module converts the internally generated current and voltage into the final output power, reflecting the circuit characteristics and power conversion efficiency of the photovoltaic module.

[0076] Based on the physical principles of photovoltaic power generation and actual nominal sample data, an efficiency model system is established to comprehensively describe the photovoltaic power generation process, accurately reflect the ideal performance of photovoltaic modules at each stage, and provide a reliable theoretical basis and comparison standard for subsequent evaluation of the actual health status of photovoltaic modules.

[0077] Furthermore, the embodiment of the present application also includes:

[0078] According to the historical operation data of each photovoltaic module and the corresponding historical environmental data, the actual photoelectric conversion efficiency, the actual carrier collection efficiency and the actual circuit conversion efficiency of each photovoltaic module are calculated;

[0079] Compare the actual photoelectric conversion efficiency, actual carrier collection efficiency and actual circuit conversion efficiency of each photovoltaic module with the standard efficiency values ​​of the photoelectric conversion efficiency model, the carrier collection efficiency model and the circuit conversion efficiency model, respectively, and calculate the difference between the two;

[0080] The difference is converted into health degree representation to obtain the health degree of each photovoltaic module in the photoelectric conversion stage, carrier collection stage and circuit conversion stage.

[0081] In a feasible implementation, first, the actual efficiency value of each photovoltaic module is calculated based on the historical operation data of each photovoltaic module and the corresponding historical environmental data. Specifically, the photoelectric conversion efficiency, carrier collection efficiency and circuit conversion efficiency of each photovoltaic module under actual operating conditions are calculated respectively. For example, the photoelectric conversion efficiency is calculated by the ratio of the incident light energy to the generated electron-hole pair energy; the carrier collection efficiency is calculated by the ratio of the number of carriers actually collected to the number of carriers theoretically generated; and the circuit conversion efficiency is calculated by the ratio of the actual output power to the theoretical maximum power. Secondly, the calculated actual efficiency value is compared with the standard efficiency values ​​of the aforementioned established photoelectric conversion efficiency model, carrier collection efficiency model and circuit conversion efficiency model, and the difference between the two is calculated. Among them, the standard efficiency value refers to the efficiency level that the photovoltaic module in the ideal state should achieve under the same environmental conditions, which is obtained from the aforementioned established efficiency model. By comparing the actual efficiency value and the standard efficiency value, the performance deviation of the photovoltaic module in each energy conversion stage is quantified, and the difference between the actual situation of each photovoltaic module and the standard situation is obtained. Afterwards, the calculated difference is converted into a health degree representation. For example, a case where the difference is zero is defined as 100% healthy, and as the difference increases, the health decreases accordingly. Through this conversion, the health of each photovoltaic module in the photoelectric conversion stage, the carrier collection stage, and the circuit conversion stage is obtained.

[0082] By calculating the actual efficiency of each PV module and then comparing it with the ideal model, the performance deviation of the PV module in actual operation can be accurately reflected, providing reliable data support for subsequent output prediction and system optimization, and helping to improve the overall efficiency and reliability of distributed PV systems.

[0083] Furthermore, the embodiment of the present application also includes:

[0084] Obtain weight coefficients of multiple transduction stages;

[0085] The health of each photovoltaic module in the photoelectric conversion stage, carrier collection stage and circuit conversion stage is multiplied by the corresponding weight coefficient to obtain the weighted health;

[0086] The weighted health of each photovoltaic module in multiple energy conversion stages is multiplied to obtain the health factor of each photovoltaic module.

[0087] In a feasible implementation, first, the weight coefficients of multiple energy conversion stages are obtained. These weight coefficients reflect the relative importance of the photoelectric conversion stage, the carrier collection stage, and the circuit conversion stage in the photovoltaic power generation process. The weight coefficients are determined based on expert experience so as to reasonably weight the health of different stages in the subsequent comprehensive evaluation. Secondly, the health of each photovoltaic component in the photoelectric conversion stage, the carrier collection stage, and the circuit conversion stage is multiplied by the corresponding weight coefficient to obtain the weighted health, so that the health is adjusted according to the importance of each stage, so that the final health factor can more accurately reflect the overall health of the photovoltaic component. Afterwards, the weighted health of each photovoltaic component in multiple energy conversion stages is multiplied to obtain the health factor of each photovoltaic component.

[0088] Through a comprehensive and detailed assessment of the health status of PV modules, the health status of multiple conversion stages is integrated into a single health factor. This health factor not only takes into account the various conversion stages of photovoltaic power generation, but also reflects the relative importance of these stages. It can accurately characterize the overall health status of PV modules and provide a reliable correction basis for subsequent output forecasts, thereby improving the accuracy and reliability of the overall output forecast of distributed photovoltaic systems.

[0089] Furthermore, the embodiment of the present application also includes:

[0090] Establishing a mapping relationship between the difference threshold interval and healthiness;

[0091] Based on the mapping relationship, the health of each photovoltaic component in the corresponding energy conversion stage is determined according to the differences of each photovoltaic component in the photoelectric conversion stage, the carrier collection stage and the circuit conversion stage, wherein the smaller the difference, the greater the corresponding health, and the greater the difference, the smaller the corresponding health.

[0092] In a feasible implementation, first, a mapping relationship between the difference threshold interval and the health degree is established, so as to create a standardized evaluation system and convert the continuous difference value into a discrete health level. Specifically, the value range of the difference is divided into multiple difference threshold intervals, each difference threshold interval corresponds to a specific health degree, so that the difference is converted into a health index. Secondly, based on the established mapping relationship, the health degree of each photovoltaic component in the corresponding energy conversion stage is determined according to the difference of each photovoltaic component in the photoelectric conversion stage, the carrier collection stage and the circuit conversion stage. In this process, the principle that the smaller the difference, the greater the corresponding health degree, and the greater the difference, the smaller the corresponding health degree is followed. In specific operations, the difference value calculated for each photovoltaic component in each energy conversion stage is substituted into the mapping relationship to obtain the corresponding health degree.

[0093] By converting from quantitative difference to qualitative health, a health index is provided for the performance evaluation of photovoltaic modules, which provides reliable basic data for subsequent health factor calculation and output prediction, helping to improve the accuracy of overall performance evaluation and prediction of distributed photovoltaic systems.

[0094] Furthermore, the embodiment of the present application also includes:

[0095] Dividing the value range of the difference degree into multiple difference degree threshold intervals;

[0096] Determine the upper limit and lower limit of each difference threshold interval;

[0097] For each difference threshold interval, a unique corresponding health degree is set to form a one-to-one mapping relationship between the difference threshold interval and the health degree, wherein the smaller the upper limit value of the difference threshold interval, the greater the corresponding health degree, and the larger the upper limit value of the difference threshold interval, the smaller the corresponding health degree.

[0098] In a feasible implementation, first, the range of the difference is divided into multiple difference threshold intervals, aiming to discretize the continuous difference to facilitate the subsequent health assessment. Specifically, according to the performance characteristics and actual operating experience of the photovoltaic module, the entire range of the difference (such as 0% to 100%) is divided into several intervals. For example, the difference is divided into multiple intervals such as 0-5%, 5-10%, 10-20%, 20-50% and 50-100%. This division method can be adjusted according to actual needs to adapt to different types of photovoltaic modules or different application scenarios. Secondly, the upper and lower limits of each difference threshold interval are determined. For example, for the interval of 0-5%, the lower limit is 0% and the upper limit is 5%. By clearly defining the boundaries of each interval, a clear reference standard is provided for the subsequent health mapping. The setting of these upper and lower limits should take into account the actual performance change law of the photovoltaic module to ensure the rationality and practicality of the division. Afterwards, for each difference threshold interval, a unique corresponding health is set to form a one-to-one mapping relationship between the difference threshold interval and the health. In this process, the principle of "the smaller the upper limit of the difference threshold interval, the greater the corresponding health, and the larger the upper limit of the difference threshold interval, the smaller the corresponding health" is followed. For example, the following mapping relationship is set: 0-5% difference corresponds to 95-100% health, 5-10% difference corresponds to 90-95% health, and so on. The establishment of this mapping relationship reflects the characteristics of photovoltaic module performance degradation, that is, as the difference increases, the health shows an accelerated decline trend.

[0099] The conversion from difference to health provides a reliable basis for subsequent health factor calculation and output prediction, which helps to improve the accuracy and practicality of the overall performance evaluation and prediction of distributed photovoltaic systems.

[0100] Furthermore, the embodiments of the present application include:

[0101] The calculation formula for photovoltaic output prediction is as follows:

[0102]

[0103] Among them, Ptotal is the total photovoltaic output forecast value of the distributed photovoltaic system, Pij is the corrected output forecast value of the jth photovoltaic module in the i-th distributed photovoltaic cluster, Lij is the transmission loss rate from the jth photovoltaic module in the i-th distributed photovoltaic cluster to the cluster collection point, Ti is the transmission loss rate from the i-th distributed photovoltaic cluster to the grid connection point, n is the total number of distributed photovoltaic clusters, and m is the number of photovoltaic modules in each distributed photovoltaic cluster;

[0104] The photovoltaic output prediction value of the distributed photovoltaic system is obtained by combining the photovoltaic output prediction calculation formula with the corrected output prediction value of each photovoltaic module.

[0105] In a preferred embodiment, in order to obtain the photovoltaic output prediction value of the distributed photovoltaic system, the photovoltaic output prediction calculation formula is extracted. The formula takes into account the contribution of each photovoltaic component in the distributed photovoltaic system and its loss during the transmission process through a double summation operation. First, for the distributed photovoltaic cluster, the actual contribution of each photovoltaic component is calculated, that is, its corrected output prediction value Pij is multiplied by (1-Lij), where (1-Lij) represents the transmission efficiency from the photovoltaic component to the cluster collection point. Then, all photovoltaic components in the same distributed photovoltaic cluster are summed to obtain the total output of the distributed photovoltaic cluster. Next, the total cluster output is multiplied by (1-Ti), where (1-Ti) represents the transmission efficiency from the distributed photovoltaic cluster to the grid connection point, thereby obtaining the actual contribution of each distributed photovoltaic cluster to the total output. After that, the contributions of all distributed photovoltaic clusters are summed to obtain the total photovoltaic output prediction value of the entire distributed photovoltaic system.

[0106] By applying this photovoltaic output prediction calculation formula and combining the corrected output prediction values ​​of each photovoltaic module, the overall photovoltaic output prediction value of the distributed photovoltaic system is effectively calculated, thereby providing a comprehensive and accurate photovoltaic output prediction value. In summary, the distributed photovoltaic output characteristic prediction method combined with health factors provided in the embodiment of the present application has the following technical effects:

[0107] Determine the distributed photovoltaic system, which includes multiple distributed photovoltaic clusters, each of which includes multiple photovoltaic modules. Clarify the object to which the method is applicable, that is, the distributed photovoltaic system composed of multiple photovoltaic clusters, each of which is composed of multiple photovoltaic modules, to lay the foundation for the subsequent modeling and analysis of individual photovoltaic modules. For each photovoltaic module, calculate the health factor of each photovoltaic module respectively. The health factor indicates the health degree of the actual working state of the photovoltaic module relative to its factory nominal state. The health factor is introduced to quantitatively evaluate the difference between the actual working state of the photovoltaic module and its factory nominal state, providing a basis for considering the performance attenuation of the photovoltaic module in the output prediction. Obtain the target environmental data of each photovoltaic module within the target prediction period, predict the nominal power generation of each photovoltaic module, obtain the nominal output prediction value of each photovoltaic module, and obtain the expected output of the photovoltaic module under ideal conditions, in preparation for the subsequent correction of the prediction value. Match the health factor of each photovoltaic module with the corresponding nominal output prediction value, correct the nominal output prediction value, obtain the corrected output prediction value of each photovoltaic module, and obtain the output prediction result of the photovoltaic module taking into account the actual health status, so as to improve the prediction accuracy. The corrected output prediction values ​​of each photovoltaic module are summarized to obtain the photovoltaic output prediction value of the distributed photovoltaic system, which realizes the output characteristic prediction at the system level and improves the output prediction precision and accuracy of the distributed photovoltaic system.

[0108] Embodiment 2, as Figure 2 As shown, based on the same inventive concept as the distributed photovoltaic output characteristic prediction method combined with health factors in the aforementioned embodiment, the embodiment of the present application provides a distributed photovoltaic output characteristic prediction system combined with health factors, the system comprising:

[0109] The system determination module 11 is used to determine a distributed photovoltaic system, wherein the distributed photovoltaic system includes a plurality of distributed photovoltaic clusters, wherein each distributed photovoltaic cluster includes a plurality of photovoltaic modules;

[0110] A health factor calculation module 12 is used to calculate the health factor of each photovoltaic module for each photovoltaic module, wherein the health factor indicates the health degree of the actual working state of the photovoltaic module relative to its factory nominal state;

[0111] The environmental data acquisition module 13 is used to acquire the target environmental data of each photovoltaic module within the target prediction period, predict the nominal power generation of each photovoltaic module, and obtain the nominal output prediction value of each photovoltaic module;

[0112] The nominal output prediction module 14 is used to match the health factor of each photovoltaic module with the corresponding nominal output prediction value, correct the nominal output prediction value, and obtain the corrected output prediction value of each photovoltaic module;

[0113] The photovoltaic output aggregation module 15 is used to aggregate the corrected output prediction values ​​of each photovoltaic module to obtain the photovoltaic output prediction value of the distributed photovoltaic system.

[0114] Furthermore, the health factor calculation module 12 includes the following execution steps:

[0115] For the multi-stage energy conversion process of photovoltaic power generation, a photoelectric conversion efficiency model, a carrier collection efficiency model and a circuit conversion efficiency model are established, wherein the multi-stage energy conversion process includes multiple energy conversion stages, namely, a photoelectric conversion stage, a carrier collection stage and a circuit conversion stage;

[0116] Set a preset time period and read the historical operation data and corresponding historical environmental data of each photovoltaic module within the preset time period;

[0117] Based on the historical operation data and historical environmental data of each photovoltaic module, combined with the photoelectric conversion efficiency model, the carrier collection efficiency model and the circuit conversion efficiency model, the health of each photovoltaic module in multiple energy conversion stages is obtained;

[0118] The health of each photovoltaic module in multiple energy conversion stages is comprehensively evaluated to obtain the health factor of each photovoltaic module.

[0119] Furthermore, the health factor calculation module 12 also includes the following execution steps:

[0120] Obtain factory inspection data of standard photovoltaic modules of the same model as each photovoltaic module as nominal sample data;

[0121] The nominal sample data are grouped and labeled to obtain samples of the photoelectric conversion stage, samples of the carrier collection stage, and samples of the circuit conversion stage;

[0122] The photoelectric conversion efficiency model is constructed by taking the irradiance and temperature of the sample in the photoelectric conversion stage as input and the photogenerated carrier concentration as output;

[0123] The carrier collection efficiency model is constructed by taking the photogenerated carrier concentration in the sample during the carrier collection stage as input and the photovoltaic current and photovoltaic voltage as output;

[0124] The photovoltaic current and photovoltaic voltage in the samples of the circuit conversion stage are taken as input, and the photovoltaic power is taken as output to construct a circuit conversion efficiency model.

[0125] Furthermore, the health factor calculation module 12 also includes the following execution steps:

[0126] According to the historical operation data of each photovoltaic module and the corresponding historical environmental data, the actual photoelectric conversion efficiency, the actual carrier collection efficiency and the actual circuit conversion efficiency of each photovoltaic module are calculated;

[0127] Compare the actual photoelectric conversion efficiency, actual carrier collection efficiency and actual circuit conversion efficiency of each photovoltaic module with the standard efficiency values ​​of the photoelectric conversion efficiency model, the carrier collection efficiency model and the circuit conversion efficiency model, respectively, and calculate the difference between the two;

[0128] The difference is converted into health degree representation to obtain the health degree of each photovoltaic module in the photoelectric conversion stage, carrier collection stage and circuit conversion stage.

[0129] Furthermore, the health factor calculation module 12 also includes the following execution steps:

[0130] Obtain weight coefficients of multiple transduction stages;

[0131] The health of each photovoltaic module in the photoelectric conversion stage, carrier collection stage and circuit conversion stage is multiplied by the corresponding weight coefficient to obtain the weighted health;

[0132] The weighted health of each photovoltaic module in multiple energy conversion stages is multiplied to obtain the health factor of each photovoltaic module.

[0133] Furthermore, the health factor calculation module 12 also includes the following execution steps:

[0134] Establishing a mapping relationship between the difference threshold interval and healthiness;

[0135] Based on the mapping relationship, the health of each photovoltaic component in the corresponding energy conversion stage is determined according to the differences of each photovoltaic component in the photoelectric conversion stage, the carrier collection stage and the circuit conversion stage, wherein the smaller the difference, the greater the corresponding health, and the greater the difference, the smaller the corresponding health.

[0136] Furthermore, the health factor calculation module 12 also includes the following execution steps:

[0137] Dividing the value range of the difference degree into multiple difference degree threshold intervals;

[0138] Determine the upper limit and lower limit of each difference threshold interval;

[0139] For each difference threshold interval, a unique corresponding health degree is set to form a one-to-one mapping relationship between the difference threshold interval and the health degree, wherein the smaller the upper limit value of the difference threshold interval, the greater the corresponding health degree, and the larger the upper limit value of the difference threshold interval, the smaller the corresponding health degree.

[0140] Furthermore, the photovoltaic output aggregation module 15 includes the following execution steps:

[0141] The calculation formula for photovoltaic output prediction is as follows:

[0142]

[0143] Among them, Ptotal is the total photovoltaic output forecast value of the distributed photovoltaic system, Pij is the corrected output forecast value of the jth photovoltaic module in the i-th distributed photovoltaic cluster, Lij is the transmission loss rate from the jth photovoltaic module in the i-th distributed photovoltaic cluster to the cluster collection point, Ti is the transmission loss rate from the i-th distributed photovoltaic cluster to the grid connection point, n is the total number of distributed photovoltaic clusters, and m is the number of photovoltaic modules in each distributed photovoltaic cluster;

[0144] The photovoltaic output prediction calculation formula is combined with the corrected output prediction value of each photovoltaic module to obtain the photovoltaic output prediction value of the distributed photovoltaic system. Figure 3 The structure diagram of the electronic device provided is a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. The electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 3 Taking a processor 21 as an example, the processor 21, memory 22, input device 23 and output device 24 in the electronic device can be connected through a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0145] The memory 22, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the distributed photovoltaic output characteristic prediction method combined with health factors in the embodiment of the present application. The processor 21 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 22, that is, realizing the above-mentioned distributed photovoltaic output characteristic prediction method combined with health factors.

[0146] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0147] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to the selection of multiple elements individually or in whole. Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these changes and variations.

Claims

1. A method for predicting distributed photovoltaic output characteristics combined with health factors, characterized in that: Here are the steps: S1: Determine a distributed photovoltaic system, where the distributed photovoltaic system includes a plurality of distributed photovoltaic clusters, wherein each distributed photovoltaic cluster includes a plurality of photovoltaic modules; S2: for each photovoltaic module, respectively calculating the health factor of each photovoltaic module, wherein the health factor indicates the health degree of the actual working state of the photovoltaic module relative to its factory nominal state; S3: Obtain target environmental data of each photovoltaic module within the target prediction period, predict the nominal power generation of each photovoltaic module, and obtain the predicted nominal output value of each photovoltaic module; S4: matching the health factor of each photovoltaic module with the corresponding nominal output prediction value, correcting the nominal output prediction value, and obtaining a corrected output prediction value of each photovoltaic module; S5: Summarize the corrected output prediction values ​​of each photovoltaic module to obtain the photovoltaic output prediction value of the distributed photovoltaic system.

2. The method for predicting distributed photovoltaic output characteristics combined with health factors according to claim 1, characterized in that: The method for calculating the health factor of each photovoltaic module described in S2 is: first, obtain the historical operation data of the photovoltaic module, including but not limited to the output voltage, current, and power parameters; second, collect the environmental data of the corresponding time period, such as light intensity, temperature, and humidity; then, compare and analyze these actual operation data with the factory nominal parameters of the photovoltaic module to quantify the performance of the photovoltaic module in each working link; wherein, the value range of the health factor is between 0 and 1, where 1 indicates that the module is in an ideal healthy state and fully meets the factory nominal performance, while a value close to 0 indicates that the performance of the module is severely degraded and requires maintenance or replacement.

3. The method for predicting distributed photovoltaic output characteristics combined with health factors according to claim 2, characterized in that: The method for matching the health factor of each photovoltaic module with the corresponding nominal output prediction value in S4 is: multiplying the nominal output prediction value of each photovoltaic module by its corresponding health factor.

4. The method for predicting distributed photovoltaic output characteristics combined with health factors according to claim 1, characterized in that: The aggregation process in S5 is performed based on the structure of the distributed photovoltaic system. First, the corrected output prediction values ​​of the photovoltaic modules belonging to the same distributed photovoltaic cluster are added together and loss correction is performed to obtain the predicted output of the distributed photovoltaic cluster. Then, the predicted outputs of all distributed photovoltaic clusters are added together and loss correction is performed to obtain the overall output prediction value of the entire distributed photovoltaic system.

5. The method for predicting distributed photovoltaic output characteristics combined with health factors according to claim 1, characterized in that: For the multi-stage energy conversion process of photovoltaic power generation, a photoelectric conversion efficiency model, a carrier collection efficiency model and a circuit conversion efficiency model are established, wherein the multi-stage energy conversion process includes multiple energy conversion stages, namely, a photoelectric conversion stage, a carrier collection stage and a circuit conversion stage; Set a preset time period and read the historical operation data and corresponding historical environmental data of each photovoltaic module within the preset time period; Based on the historical operation data and historical environmental data of each photovoltaic module, combined with the photoelectric conversion efficiency model, the carrier collection efficiency model and the circuit conversion efficiency model, the health of each photovoltaic module in multiple energy conversion stages is obtained; The health of each photovoltaic module in multiple energy conversion stages is comprehensively evaluated to obtain the health factor of each photovoltaic module.

6. The method for predicting distributed photovoltaic output characteristics combined with health factors according to claim 5, characterized in that: Obtain factory inspection data of standard photovoltaic modules of the same model as each photovoltaic module as nominal sample data; The nominal sample data are grouped and labeled to obtain samples of the photoelectric conversion stage, samples of the carrier collection stage, and samples of the circuit conversion stage; The photoelectric conversion efficiency model is constructed by taking the irradiance and temperature of the sample in the photoelectric conversion stage as input and the photogenerated carrier concentration as output; The carrier collection efficiency model is constructed by taking the photogenerated carrier concentration in the sample during the carrier collection stage as input and the photovoltaic current and photovoltaic voltage as output; The photovoltaic current and photovoltaic voltage in the samples of the circuit conversion stage are taken as input, and the photovoltaic power is taken as output to construct a circuit conversion efficiency model.

7. The method for predicting distributed photovoltaic output characteristics combined with health factors according to claim 6, characterized in that: According to the historical operation data of each photovoltaic module and the corresponding historical environmental data, the actual photoelectric conversion efficiency, the actual carrier collection efficiency and the actual circuit conversion efficiency of each photovoltaic module are calculated; Compare the actual photoelectric conversion efficiency, actual carrier collection efficiency and actual circuit conversion efficiency of each photovoltaic module with the standard efficiency values ​​of the photoelectric conversion efficiency model, the carrier collection efficiency model and the circuit conversion efficiency model, respectively, and calculate the difference between the two; The difference is converted into health degree representation to obtain the health degree of each photovoltaic module in the photoelectric conversion stage, carrier collection stage and circuit conversion stage.

8. The method for predicting distributed photovoltaic output characteristics combined with health factors according to claim 7, characterized in that: Obtain weight coefficients of multiple transduction stages; The health of each photovoltaic module in the photoelectric conversion stage, carrier collection stage and circuit conversion stage is multiplied by the corresponding weight coefficient to obtain the weighted health; The weighted health of each photovoltaic module in multiple energy conversion stages is multiplied to obtain the health factor of each photovoltaic module.

9. A prediction system for the distributed photovoltaic output characteristic prediction method combined with health factors according to claim 1, characterized in that: include: A system determination module is used to determine a distributed photovoltaic system, wherein the distributed photovoltaic system includes a plurality of distributed photovoltaic clusters, wherein each distributed photovoltaic cluster includes a plurality of photovoltaic modules; A health factor calculation module is used to calculate the health factor of each photovoltaic module for each photovoltaic module, wherein the health factor indicates the health degree of the actual working state of the photovoltaic module relative to its factory nominal state; The environmental data acquisition module is used to acquire the target environmental data of each photovoltaic module within the target prediction period, predict the nominal power generation of each photovoltaic module, and obtain the nominal output prediction value of each photovoltaic module; The nominal output prediction module is used to match the health factor of each photovoltaic module with the corresponding nominal output prediction value, correct the nominal output prediction value, and obtain the corrected output prediction value of each photovoltaic module; The photovoltaic output aggregation module is used to aggregate the corrected output prediction values ​​of each photovoltaic module to obtain the photovoltaic output prediction value of the distributed photovoltaic system.

10. An electronic device, comprising: processor; A memory for storing instructions executable by the processor; wherein the processor is used to execute the method for predicting distributed photovoltaic output characteristics combined with health factors as described in claim 1.

Images