Photovoltaic module performance evaluation method and device, storage medium and computer equipment

Abstract

This invention discloses a photovoltaic module performance evaluation method, apparatus, storage medium, and computer equipment, applied to an outdoor photovoltaic module testing system. The system includes a test channel, a multi-channel switching array, and a central processing unit. The method comprises: acquiring evaluation requirement information and real-time environmental data of the photovoltaic module to be evaluated; determining whether the operating mode of the test channel conforms to the I-V scan measurement mode based on the evaluation requirement information and real-time environmental data; if so, switching the test channel to the I-V scan measurement mode to acquire the electrical performance parameters of the photovoltaic module operating in the I-V scan measurement mode; switching the test channel to the MPPT operating mode to acquire the electrical energy output parameters of the photovoltaic module operating in the MPPT operating mode; and acquiring second environmental monitoring data at the time of electrical energy output parameter acquisition; and performing performance evaluation of the photovoltaic module to be evaluated based on the electrical performance parameters, electrical energy output parameters, first environmental monitoring data, and second environmental monitoring data.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic module performance testing technology, and in particular to a photovoltaic module performance evaluation method, apparatus, storage medium, and computer equipment. Background Technology

[0002] The actual outdoor performance of photovoltaic modules differs from that under standard laboratory testing conditions, and their power generation efficiency and degradation characteristics are affected by a combination of outdoor factors. Therefore, outdoor empirical testing is crucial for evaluating module performance.

[0003] Currently, dedicated current scanners are typically used to perform transient current tests on photovoltaic (PV) modules, and the performance of PV modules is determined based on the transient current. However, evaluating PV module performance solely based on transient current provides limited information and cannot accurately assess the module's performance. Summary of the Invention

[0004] This invention provides a method, apparatus, storage medium, and computer equipment for evaluating the performance of photovoltaic modules, which mainly improves the accuracy of performance evaluation of photovoltaic modules.

[0005] According to a first aspect of the present invention, a method for evaluating the performance of photovoltaic modules is provided, applied to an outdoor testing system for photovoltaic modules. The outdoor testing system for photovoltaic modules includes a test channel, a multi-channel switching array, and a central processing unit, comprising: The test channel is connected to the photovoltaic module to be evaluated, and the evaluation requirements information and real-time environmental data of the photovoltaic module to be evaluated are obtained. Based on the evaluation requirements and the real-time environmental data, it is determined whether the working mode of the test channel conforms to the IV scan measurement mode. If so, the central processing unit uses the multiplexer array to switch the test channel to the IV scan measurement mode, obtains the electrical performance parameters of the photovoltaic module to be evaluated when it is running in the IV scan measurement mode, and obtains the first environmental monitoring data at the time of the electrical performance parameter acquisition. Based on the first environmental monitoring data, it is determined whether the test channel meets the preset conditions for mode switching. If so, the central processing unit uses the multi-channel switching array to switch the test channel from the IV scan measurement mode to the MPPT (Maximum Power Point Tracking) operation mode, and obtains the electrical energy output parameters of the photovoltaic module to be evaluated when it is running in the MPPT operation mode, and obtains the second environmental monitoring data at the time of the electrical energy output parameter acquisition. The performance of the photovoltaic module to be evaluated is assessed based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data.

[0006] Optionally, the photovoltaic module outdoor testing system further includes an integrated MPPT power processing module and a data acquisition module; Using the central processing unit to switch the test channel to the IV scan measurement mode via the multiplexer array, the following is included: The input terminal of the test channel is connected to the photovoltaic module to be evaluated, and the output terminal of the test channel is connected in parallel to the common DC bus via a bus. The central processing unit uses the multiplexer array to control the input terminal of the data acquisition module to be connected to the common DC bus, so as to switch the test channel to the IV scan measurement mode. Using the central processing unit to switch the test channel from the IV scan measurement mode to the MPPT operation mode via the multiplexer array, the following steps are included: The central processing unit controls the input terminal of the integrated MPPT power processing module to be connected to the common DC bus via the multi-channel switching array, and the output terminal of the integrated MPPT power processing module to be connected to the load, so as to switch the test channel from the IV scan measurement mode to the MPPT operation mode.

[0007] Optionally, after the central processing unit switches the test channel from the IV scan measurement mode to the MPPT (Maximum Power Point Tracking) operation mode via the multiplexer array, the method further includes: The system acquires the output power generated by the photovoltaic module under evaluation in the MPPT operation mode in real time, acquires the device attribute data of the power output parameter acquisition device in the MPPT operation mode in real time, and acquires the dynamic environmental parameters of the location of the photovoltaic module under evaluation in the MPPT operation mode in real time. Based on the output power, the dynamic power fluctuation entropy of the photovoltaic module to be evaluated is determined in real time; based on the device attribute data, the MPPT tracking efficiency in the MPPT operation mode is determined in real time; and based on the dynamic environmental parameters, the runtime correction coefficient is determined. Based on the dynamic power fluctuation entropy and the MPPT tracking efficiency, the initial operating time of the photovoltaic module to be evaluated in the MPPT operating mode is determined, and the initial operating time is corrected based on the operating time correction coefficient. The corrected initial operating time is taken as the final operating time, and the photovoltaic module to be evaluated is controlled to operate in the MPPT operating mode based on the final operating time.

[0008] Optionally, the performance evaluation of the photovoltaic module to be evaluated based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data includes: Determine the electrical performance feature vector corresponding to the electrical performance parameter, the electrical energy feature vector corresponding to the electrical energy output parameter, the first environmental monitoring feature vector corresponding to the first environmental monitoring data, and the second environmental monitoring feature vector corresponding to the second environmental monitoring data, respectively. The electrical performance feature vector, the electrical energy feature vector, the first environmental monitoring feature vector, and the second environmental monitoring feature vector are fused to obtain a performance fusion feature vector. The performance fusion feature vector is input into a preset performance evaluation model for performance evaluation, and the performance evaluation result of the photovoltaic module to be evaluated is obtained.

[0009] Optionally, the step of fusing the electrical performance feature vector, the electrical energy feature vector, the first environmental monitoring feature vector, and the second environmental monitoring feature vector to obtain a performance fusion feature vector includes: The electrical performance vector complexity of the electrical performance feature vector, the electrical energy vector complexity of the electrical energy feature vector, the first environmental vector complexity corresponding to the first environmental monitoring feature vector, and the second environmental vector complexity of the second environmental monitoring feature vector are determined respectively. Based on the electrical performance vector complexity, the electrical energy vector complexity, the first environment vector complexity, and the second environment vector complexity, the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environment linear transformation coefficient, and the second environment linear transformation coefficient are determined respectively. Based on the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental linear transformation coefficient, the electrical performance fusion weight, the electrical energy fusion weight, the first environmental fusion weight, and the second environmental fusion weight are determined. Based on the electrical performance linear transformation coefficient, the electrical performance feature vector is linearly transformed; based on the electrical energy linear transformation coefficient, the electrical energy feature vector is linearly transformed; based on the first environmental linear transformation coefficient, the first environmental monitoring feature vector is linearly transformed; and based on the second environmental linear transformation coefficient, the second environmental monitoring feature vector is linearly transformed. Based on the electrical performance fusion weight, the electrical energy fusion weight, the first environmental fusion weight, and the second environmental fusion weight, the linearly transformed electrical performance feature vector, the linearly transformed electrical energy feature vector, the linearly transformed first environmental monitoring feature vector, and the linearly transformed second environmental monitoring feature vector are weighted and fused to obtain the performance fusion feature vector.

[0010] Optionally, determining whether the operating mode of the test channel conforms to the IV scan measurement mode based on the evaluation requirement information and the real-time environmental data includes: Obtain the component feature data of the photovoltaic module to be evaluated, and determine the demand feature vector corresponding to the evaluation demand information, the environmental feature vector corresponding to the real-time environmental data, and the component feature vector corresponding to the component feature data, respectively. The number of dimensions, dynamics, and uncertainties of the evaluation requirement information, the real-time environmental data, and the component feature data are determined respectively. Based on the number of dimensions, the dynamics, and the uncertainties, the requirement complexity of the requirement feature vector, the environmental complexity of the environmental feature vector, and the component complexity of the component feature vector are determined accordingly. Based on the requirement complexity, the environment complexity, and the component complexity, the weight coefficients of the requirement feature vector, the environment feature vector, and the component feature vector are determined respectively. Based on the weight coefficients, the requirement feature vector, the environment feature vector, and the component feature vector are weighted and summed to obtain the pattern fusion feature vector. The mode fusion feature vector is input into a preset evaluation parameter prediction model to predict evaluation parameters, and the evaluation parameters are obtained. Based on the evaluation parameters, it is determined whether the working mode of the test channel conforms to the IV scan measurement mode.

[0011] Optionally, before performing a performance evaluation of the photovoltaic module to be evaluated based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data, the method further includes: Each of the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data is taken as a target type of data, and each of the target type of data is taken as a target data to be detected. A preset sliding time window is determined, and the mean value of the target type data within the preset sliding time window is determined; The data matrix corresponding to the target type data is determined, and the covariance matrix corresponding to the data matrix is ​​determined. The covariance matrix is ​​then decomposed to obtain eigenvalues ​​and eigenvectors corresponding to the eigenvalues. Based on the magnitude of the eigenvalues, principal component eigenvectors are selected from the eigenvectors. Based on the principal component eigenvectors, the direction of data feature change is determined. Based on the mean and the direction of change of the data features, it is determined whether the target data to be detected is abnormal data. If so, the abnormal data in the target category data is removed. The method for determining whether the target data to be detected is abnormal data includes: Determine whether the difference between the target data to be detected and the mean is greater than a preset threshold, and / or determine whether the direction of change of the target data to be detected conflicts with the direction of change of the data feature. If the difference is greater than the preset threshold and the direction of change of the target data to be detected conflicts with the direction of change of the data feature, then the target data to be detected is determined to be abnormal data; otherwise, the target data to be detected is determined to be normal data.

[0012] According to a second aspect of the present invention, a photovoltaic module performance evaluation device is provided, applied to a photovoltaic module outdoor testing system. The photovoltaic module outdoor testing system includes a test channel, a multi-channel switching array, and a central processing unit, comprising: The acquisition unit is used to control the test channel to connect with the photovoltaic module to be evaluated, and to acquire the evaluation requirement information and real-time environmental data of the photovoltaic module to be evaluated; The first mode switching unit is used to determine whether the working mode of the test channel conforms to the IV scan measurement mode based on the evaluation requirement information and the real-time environmental data. If so, the central processing unit uses the multiplexer array to switch the test channel to the IV scan measurement mode, obtains the electrical performance parameters of the photovoltaic module to be evaluated when it is running in the IV scan measurement mode, and obtains the first environmental monitoring data at the time of the electrical performance parameter acquisition. The second mode switching unit is used to determine whether the test channel meets the preset conditions for mode switching based on the first environmental monitoring data. If so, the central processing unit uses the multi-channel switching array to switch the test channel from the IV scan measurement mode to the MPPT (Maximum Power Point Tracking) operation mode, and obtains the electrical energy output parameters of the photovoltaic module to be evaluated when it is running in the MPPT operation mode, and obtains the second environmental monitoring data at the time of the electrical energy output parameter acquisition. The performance evaluation unit is used to evaluate the performance of the photovoltaic module to be evaluated based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data.

[0013] According to a third aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described photovoltaic module performance evaluation method.

[0014] According to a fourth aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described photovoltaic module performance evaluation method.

[0015] The photovoltaic module performance evaluation method, apparatus, storage medium, and computer equipment provided by this invention, compared with the current method of using a dedicated current scanner to perform transient current testing on photovoltaic modules and determining the performance of photovoltaic modules based on transient current, this invention acquires the electrical performance parameters and electrical energy output parameters of the photovoltaic module in both IV scanning measurement mode and MPPT operation mode, and acquires environmental monitoring data. Then, it comprehensively analyzes the multiple factors, including electrical performance parameters, electrical energy output parameters, and environmental monitoring data, to evaluate the performance of the photovoltaic module. This provides sufficient information, thereby improving the accuracy of photovoltaic module performance evaluation. By evaluating demand information and real-time environmental data, the switching mode is determined, avoiding errors caused by manual determination of the switching mode. Therefore, this invention improves the accuracy of switching mode determination and ensures the effectiveness of photovoltaic module performance evaluation. When evaluating the performance of photovoltaic modules, by collecting data in MPPT operation mode, continuous and long-term data can be collected. Evaluating photovoltaic module performance based on continuous and long-term data improves the accuracy of photovoltaic module performance evaluation. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 A flowchart of a photovoltaic module performance evaluation method provided by an embodiment of the present invention is shown; Figure 2 A flowchart of another photovoltaic module performance evaluation method provided by an embodiment of the present invention is shown; Figure 3 This diagram illustrates the structure of a photovoltaic module performance evaluation device provided in an embodiment of the present invention. Figure 4 This invention provides a schematic diagram of the structure of another photovoltaic module performance evaluation device according to an embodiment of the invention. Figure 5 A schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention is shown. Detailed Implementation

[0017] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present application can be combined with each other.

[0018] Currently, dedicated current scanners are commonly used to perform transient current tests on photovoltaic modules. However, determining the performance of photovoltaic modules based on transient current relies on limited information and cannot accurately assess their performance.

[0019] To address the aforementioned problems, embodiments of the present invention provide a method for evaluating the performance of photovoltaic modules, such as... Figure 1 As shown, the method includes: The photovoltaic module performance evaluation method of this invention is applied to an outdoor photovoltaic module testing system, which includes a test channel, a multi-channel switching array, and a central processing unit.

[0020] 101. The control test channel is connected to the photovoltaic module to be evaluated and obtains the evaluation requirements information and real-time environmental data of the photovoltaic module to be evaluated.

[0021] The assessment requirements information may include assessment accuracy requirements, assessment purpose, etc.; real-time environmental data includes, but is not limited to, the total solar irradiance at the location of the photovoltaic module, the backsheet temperature of the photovoltaic module, the ambient temperature, wind speed, and wind direction parameters.

[0022] In this embodiment of the invention, an outdoor photovoltaic module testing system is used to perform performance tests on photovoltaic modules. This system includes multiple independent test channels connected to the photovoltaic module under test, a high-precision data acquisition module for measuring electrical performance parameters such as the IV characteristic curve of the photovoltaic module, an integrated MPPT power processing module for providing maximum power point tracking load, and a high-speed multiplexer array controlled by a central processing unit. The high-speed multiplexer array can be composed of relays or solid-state power switches. The central processing unit is configured to control the high-speed multiplexer array to switch any test channel in a time-division manner to the high-precision data acquisition module for measuring electrical performance parameters, or to the integrated MPPT power processing module for continuous maximum power point operation testing. Specifically, when performance evaluation of the photovoltaic module is required, real-time environmental data of the test location of the photovoltaic module is first acquired using sensors and other measuring devices, and the evaluation requirements of the photovoltaic module are determined.

[0023] 102. Based on the assessment requirements and real-time environmental data, determine whether the working mode of the test channel conforms to the IV scan measurement mode. If so, use the central processing unit to switch the test channel to the IV scan measurement mode through a multi-channel switching array, obtain the electrical performance parameters of the photovoltaic module to be evaluated when it is running in the IV scan measurement mode, and obtain the first environmental monitoring data at the time of electrical performance parameter acquisition.

[0024] 103. Based on the first environmental monitoring data, determine whether the test channel meets the preset conditions for mode switching. If so, use the central processing unit to switch the test channel from the IV scan measurement mode to the MPPT operation mode through the multi-channel switching array, and obtain the power output parameters of the photovoltaic module to be evaluated when it is running in the MPPT operation mode, and obtain the second environmental monitoring data at the time of power output parameter acquisition.

[0025] In this embodiment of the invention, to evaluate the performance of photovoltaic modules, performance tests are required. These tests include performance tests in IV scan measurement mode and performance tests in MPPT operation mode. To achieve performance tests in multiple modes, switching between modes is necessary. Therefore, step 102 specifically includes: connecting the input of the test channel to the photovoltaic module to be evaluated, and connecting the output of the test channel to a common DC bus via a bus; using the central processing unit to control the input of the data acquisition module to be connected to the common DC bus via the multiplexer array, thereby switching the test channel to the IV scan measurement mode; using the central processing unit to control the input of the integrated MPPT power processing module to be connected to the common DC bus via the multiplexer array, and connecting the output of the integrated MPPT power processing module to the load, thereby switching the test channel from the IV scan measurement mode to the MPPT operation mode.

[0026] Specifically, if there are multiple photovoltaic modules, there will also be multiple test channels. Each channel's input is connected to one photovoltaic module under test, and its output is connected in parallel to a common DC bus and / or a simulated power grid via a bus. If analysis of evaluation requirements and real-time environmental data determines that the test channel needs to be switched to IV (current-voltage) scanning measurement mode, the test channel needs to be switched to a data acquisition module. This can be achieved by using a central processing unit to control the input of the data acquisition module to connect to the common DC bus via a multiplexer array, thus switching the test channel to IV scanning measurement mode. The data acquisition module applies a scanning signal, and after application, measures and records the photovoltaic module's IV (current-voltage) curve, PV (power-voltage) curve, short-circuit current, open-circuit voltage, maximum power, maximum power point current, maximum power point voltage, conversion efficiency, and other electrical performance parameters. The data acquisition module includes a programmable DC power supply and a measurement unit, enabling fast, low-disturbance IV curve scanning. It should be noted that if there are multiple independent test channels, an independent IV scanning time window can be allocated to each channel at fixed time intervals.

[0027] Furthermore, if analysis of environmental monitoring data during the performance testing of photovoltaic modules in IV scan measurement mode determines that the test channel needs to be switched to MPPT operation mode, the photovoltaic modules need to be connected to the MPPT power processing module. For example, the central processing unit controls the input of the integrated MPPT power processing module to be connected to the common DC bus via a multi-channel switching array, and the output of the integrated MPPT power processing module to be connected to the load, thereby achieving the switching of MPPT operation mode. By connecting the modules to the integrated MPPT power processing module, a loop is formed between the modules and the MPPT power processing module, allowing for long-term maximum power point (MPPT) power generation testing of the photovoltaic modules, and real-time recording of the photovoltaic modules' output power, power generation data, and other electrical energy output parameters during the power generation test. The integrated MPPT power processing module integrates a DC-DC conversion circuit and an MPPT algorithm controller. In continuous operation mode, the MPPT power processing module provides a unified, automatically tracking MPPT load for all photovoltaic modules switched to this mode. Its MPPT algorithm can simultaneously perform global or independent MPPT tracking on multiple modules connected in parallel. This invention determines the switching mode by evaluating demand information and real-time environmental data, avoiding errors caused by manual determination. This improves the accuracy of switching mode determination and ensures effective performance evaluation of photovoltaic modules. When evaluating photovoltaic module performance, collecting data under MPPT operating mode enables the acquisition of continuous and long-term data. Evaluating photovoltaic module performance based on this continuous and long-term data improves the accuracy of performance evaluation. It should be noted that if multiple test channels are simultaneously connected to the integrated MPPT power processing module, the photovoltaic modules corresponding to these channels operate in parallel, with the MPPT power processing module performing unified maximum power point tracking.

[0028] In another embodiment of the invention, different modes can be switched by setting a schedule. For example, several fixed test time windows for IV scan measurement mode are allocated to each channel each day, such as 5-10 minutes each time, with the remaining time in MPPT operation mode. The method of switching modes according to the schedule is as follows: the central processing unit controls the multi-channel switching array according to the preset cyclic test plan, switching each channel to IV scan measurement mode in a time-sharing and cyclical manner to perform high-precision IV curve scanning and obtain transient electrical performance parameters; during the time period when IV scan measurement mode testing is not performed, each channel is switched to MPPT operation mode, and through the shared integrated MPPT power processing module, each photovoltaic module operates at its own maximum power point for a long time to perform continuous power generation and aging assessment, and records its long-term electrical energy output parameters. The system runs continuously, periodically executing multiple modes and synchronously recording data under all modes.

[0029] 104. Based on electrical performance parameters, electrical energy output parameters, first environmental monitoring data, and second environmental monitoring data, the performance of the photovoltaic module to be evaluated is carried out.

[0030] The first environmental monitoring data includes, but is not limited to, the total solar irradiance, photovoltaic module backsheet temperature, ambient temperature, wind speed, and wind direction parameters during the performance test of the photovoltaic module in IV scan measurement mode; the second environmental monitoring parameters include, but are not limited to, the total solar irradiance, photovoltaic module backsheet temperature, ambient temperature, wind speed, and wind direction parameters during the performance test of the photovoltaic module in MPPT operation mode.

[0031] In this embodiment of the invention, the first environmental monitoring data is timestamped with the electrical performance parameters, and the second environmental monitoring data is timestamped with the electrical energy output parameters. Then, the electrical performance parameters, electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data are comprehensively analyzed. Based on the comprehensive analysis results, the performance evaluation result of the photovoltaic module is determined. For example, the central processing unit analyzes and processes the collected data to evaluate the performance of each module under different environmental conditions, its long-term degradation trend, and compares the performance differences of different modules under the same outdoor operating conditions.

[0032] This invention acquires the electrical performance parameters and power output parameters of photovoltaic modules in both IV scanning measurement mode and MPPT operation mode, and also acquires environmental monitoring data. Then, it comprehensively analyzes the electrical performance parameters, power output parameters, and environmental monitoring data to evaluate the performance of photovoltaic modules. Based on sufficient information, it can improve the accuracy of photovoltaic module performance evaluation.

[0033] The photovoltaic module performance evaluation method provided by this invention differs from current methods that use dedicated current scanners to perform transient current tests on photovoltaic modules and determine module performance based on transient current. This invention acquires electrical performance parameters and energy output parameters of the photovoltaic module in both IV scanning measurement mode and MPPT operation mode, along with environmental monitoring data. Then, it comprehensively analyzes this multi-factor data (electrical performance parameters, energy output parameters, and environmental monitoring data) to evaluate the photovoltaic module performance. This comprehensive analysis provides more information and improves the accuracy of photovoltaic module performance evaluation. Furthermore, by evaluating demand information and real-time environmental data, the switching mode is determined, avoiding errors caused by manual selection. This improves the accuracy of switching mode determination and ensures effective photovoltaic module performance evaluation. Finally, by collecting data in MPPT operation mode, continuous and long-term data can be acquired, further enhancing the accuracy of photovoltaic module performance evaluation.

[0034] Furthermore, to better illustrate the above process of evaluating the performance of photovoltaic modules, as a refinement and extension of the above embodiments, this invention provides another method for evaluating the performance of photovoltaic modules, such as... Figure 2 As shown, the method includes: 201. The control test channel is connected to the photovoltaic module to be evaluated and obtains the evaluation requirements information and real-time environmental data of the photovoltaic module to be evaluated.

[0035] Specifically, upon receiving a performance evaluation signal for the photovoltaic module, the environmental data at the current test location of the photovoltaic module is first measured using sensors and other measuring devices. The test channel is connected to the photovoltaic module. By switching the test channel to IV scan measurement mode, IV scan performance testing of the photovoltaic module is performed. By switching the test channel to MPPT operation mode, performance testing of the module in a long-term continuous maximum power point power generation operation state is performed.

[0036] 202. Based on the assessment requirements and real-time environmental data, determine whether the working mode of the test channel conforms to the IV scan measurement mode. If so, use the central processing unit to switch the test channel to the IV scan measurement mode through a multi-channel switching array, obtain the electrical performance parameters of the photovoltaic module to be evaluated when it is running in the IV scan measurement mode, and obtain the first environmental monitoring data at the time of electrical performance parameter acquisition.

[0037] In this embodiment of the invention, in order to conduct reasonable performance tests on photovoltaic modules, it is first necessary to determine the test mode of the photovoltaic modules at the current moment. Based on this, step 202 specifically includes: obtaining the module feature data of the photovoltaic modules to be evaluated; determining the demand feature vector corresponding to the evaluation demand information, the environmental feature vector corresponding to the real-time environmental data, and the module feature vector corresponding to the module feature data; determining the number of dimensions, dynamics, and uncertainties of the evaluation demand information, the real-time environmental data, and the module feature data; and determining the demand complexity of the demand feature vector based on the number of dimensions, the dynamics, and the uncertainties. The environmental complexity of the environmental feature vector and the component complexity of the component feature vector are determined. Based on the requirement complexity, the environmental complexity, and the component complexity, weight coefficients are determined for the requirement feature vector, the environmental feature vector, and the component feature vector, respectively. Based on the weight coefficients, the requirement feature vector, the environmental feature vector, and the component feature vector are weighted and summed to obtain a mode fusion feature vector. The mode fusion feature vector is input into a preset evaluation parameter prediction model to predict evaluation parameters and obtain evaluation parameters. Based on the evaluation parameters, it is determined whether the working mode of the test channel conforms to the IV scan measurement mode.

[0038] Among them, component characteristic data includes, but is not limited to, photovoltaic module model, years of use, and degree of aging; the number of dimensions refers to the number of independent attributes in the assessment demand information, real-time environmental data, and component characteristic data; dynamics are determined by whether the assessment demand information, real-time environmental data, and component characteristic data change over time and the strength of the trend of change over time, such as the greater the strength of the trend of change over time, the greater the dynamics; uncertainty is determined by the proportion of fuzzy data in the assessment demand information, real-time environmental data, and component characteristic data, such as the greater the proportion of fuzzy data, the greater the corresponding uncertainty.

[0039] Specifically, taking the determination of requirement complexity as an example, the number of dimensions, dynamism, and uncertainty of the evaluation requirement information are scored separately, and weight coefficients are determined for each of these factors. Based on these weight coefficients, the scores for the number of dimensions, dynamism, and uncertainty are weighted and summed to obtain a comprehensive score. The higher the comprehensive score, the greater the requirement complexity of the requirement feature vector. Similarly, environmental complexity and component complexity can be determined in the same way. Then, based on the requirement complexity, environmental complexity, and component complexity, weight coefficients are assigned to the requirement feature vector, environmental feature vector, and component feature vector. In the process of assigning weight coefficients, the higher the complexity, the higher the weight coefficient should be assigned. Finally, based on the weight coefficients, the requirement feature vector, environmental feature vector, and component feature vector are weighted and summed to obtain the pattern fusion feature vector. Next, a preset evaluation parameter prediction model needs to be used to analyze the pattern fusion feature vector. In this process, in order to improve the prediction accuracy of the preset evaluation parameter prediction model, it is first necessary to train and construct the preset evaluation parameter prediction model. Based on this, the method includes: constructing a preset initial evaluation parameter prediction model; obtaining a sample dataset, wherein the sample dataset includes component feature data, evaluation requirement information, and real-time environmental data of sample photovoltaic modules with pattern evaluation parameter labels; dividing the sample dataset into a training set and a test set, using the training set to train the preset initial evaluation parameter prediction model, and using the test set to test the trained preset initial evaluation parameter prediction model, and finally using the trained preset initial evaluation parameter prediction model that meets the test conditions as the preset evaluation parameter prediction model.

[0040] Specifically, during model training, the process begins by constructing a prediction model with pre-defined initial evaluation parameters, followed by acquiring a sample dataset. This dataset ensures it contains all necessary files, including component diagnostic data such as model number and years of use for multiple sample photovoltaic modules, evaluation requirement information such as accuracy requirements, and real-time environmental data such as temperature, humidity, illuminance, and photovoltaic module backsheet temperature. The data is then converted to a format understandable by the prediction model with pre-defined initial evaluation parameters. Finally, the model is trained and tested. Specifically, the dataset can be divided first: using randomness or a specific strategy (such as stratified sampling), the sample dataset is divided into training and testing sets. The training set is then used to train the model, and the testing set is used to test the trained model and evaluate its performance on unseen data. Precision, recall, and other metrics on the test set are calculated and recorded. If the model performance does not meet the requirements, the training phase can be returned for further iterations or adjustments. This process yields a prediction model with pre-defined evaluation parameters that meets the requirements.

[0041] Finally, the mode fusion feature vector is directly input into the preset evaluation parameter prediction model. The preset evaluation parameter prediction model can directly output the mode evaluation parameters. If the mode evaluation parameters are greater than the preset threshold set according to actual needs, it is determined that the working mode of the test channel conforms to the IV scan measurement mode. If the mode evaluation parameters are less than or equal to the preset threshold, it is determined that the working mode of the test channel does not conform to the IV scan measurement mode. At this time, the performance test of the photovoltaic module can be stopped first, and the working mode judgment and performance test can be carried out after a preset time. Alternatively, the working mode of the test channel can be switched to MPPT operation mode for performance testing.

[0042] Furthermore, once it is determined that the operating mode of the test channel conforms to the IV scan measurement mode, the test channel is switched to connect to the data acquisition module to achieve the switching of the IV scan measurement mode. In the IV scan measurement mode, an IV scan is performed to obtain the transient electrical performance parameters of the photovoltaic module. At the same time, it is also necessary to collect first environmental monitoring data such as total solar irradiance, module backsheet temperature, ambient temperature, wind speed, and wind direction parameters at the same acquisition time as the transient electrical performance parameters through sensors and other measuring devices.

[0043] 203. Based on the first environmental monitoring data, determine whether the test channel meets the preset conditions for mode switching. If so, use the central processing unit to switch the test channel from the IV scan measurement mode to the MPPT operation mode through the multi-channel switching array, and obtain the power output parameters of the photovoltaic module to be evaluated when it is running in the MPPT operation mode, and obtain the second environmental monitoring data at the time of power output parameter acquisition.

[0044] Specifically, real-time analysis of primary environmental monitoring data is used to determine whether mode switching is necessary. For example, if the total solar irradiance changes significantly, the maximum power point (MPPT) of the photovoltaic module will also change, requiring the MPPT operating mode to track the MPPT in real time. In this case, the test channel needs to be switched to MPPT operating mode. Increased temperature leads to a decrease in module output power and open-circuit voltage. When temperature changes are significant, the module's current-voltage characteristic curve will change, and the position of the maximum power point will shift, requiring adjustment using the MPPT operating mode. After switching the test channel to MPPT operation mode, it is also necessary to determine the duration of MPPT operation mode, i.e., the test duration (running time) of the photovoltaic module in MPPT operation mode. Based on this, the method includes: acquiring the output power generated by the photovoltaic module to be evaluated in MPPT operation mode in real time; acquiring the device attribute data of the power output parameter acquisition device in MPPT operation mode in real time; acquiring the dynamic environmental parameters of the location of the photovoltaic module to be evaluated in MPPT operation mode in real time; determining the dynamic power fluctuation entropy of the photovoltaic module to be evaluated in real time based on the output power; determining the MPPT tracking efficiency in MPPT operation mode in real time based on the device attribute data; determining the running time correction coefficient based on the dynamic environmental parameters; determining the initial running time of the photovoltaic module to be evaluated in MPPT operation mode based on the dynamic power fluctuation entropy and the MPPT tracking efficiency; correcting the initial running time based on the running time correction coefficient; taking the corrected initial running time as the final running time; and controlling the photovoltaic module to be evaluated to operate in MPPT operation mode based on the final running time.

[0045] The device attribute data includes, but is not limited to, the measurement accuracy, sampling frequency, and response speed of the electrical energy output parameter acquisition device; the dynamic environmental data includes, but is not limited to, total solar irradiance and ambient temperature.

[0046] Specifically, after switching the test channel to MPPT operation mode, the photovoltaic modules undergo performance testing in MPPT mode. The output power of the photovoltaic modules is acquired in real time during the performance test, and the dynamic power fluctuation entropy (PFE) is calculated according to the following formula:

[0047] in, Let N be the probability distribution of output power within power interval i, and N be the total number of probability intervals. Furthermore, the MPPT tracking efficiency is determined based on data such as measurement accuracy, sampling frequency, and response speed; for example, higher measurement accuracy, higher sampling frequency, and faster response speed result in higher MPPT tracking efficiency. Further, the final runtime is determined according to the following formula. :

[0048] in, The base duration is set according to actual needs. For MPPT tracking efficiency, Here, T is the environmental compensation function, and G is the ambient temperature and G is the total solar irradiance. The result is the runtime correction factor. , These are the weighting coefficients for MPPT tracking efficiency and dynamic power fluctuation entropy, respectively.

[0049] The final runtime The duration of the current MPPT operation mode, i.e., the duration during which the photovoltaic module under evaluation operates in the MPPT operation mode, is the final operating duration. This invention, through comprehensive analysis of the photovoltaic module's operating status, the attribute data of the acquisition device, and environmental data, determines the duration of the MPPT operating mode. This improves the rationality of the duration determination and thus enhances the accuracy of photovoltaic module performance evaluation. Within the final operating duration, the electrical energy output parameters of the photovoltaic module under evaluation are continuously collected during its MPPT operation, and second environmental monitoring data are collected sequentially within this duration.

[0050] 204. Determine the electrical performance feature vector corresponding to the electrical performance parameters, the electrical energy feature vector corresponding to the electrical energy output parameters, the first environmental monitoring feature vector corresponding to the first environmental monitoring data, and the second environmental monitoring feature vector corresponding to the second environmental monitoring data, respectively.

[0051] In this embodiment of the invention, to improve the data quality of electrical performance parameters, electrical energy output parameters, first environmental monitoring data, and second environmental monitoring data, the data needs to be cleaned and processed to remove outliers before using this data to evaluate the performance of photovoltaic modules. Therefore, the method includes: taking any one of the electrical performance parameters, electrical energy output parameters, first environmental monitoring data, and second environmental monitoring data as a target data type, and taking any one of the target data types as a target data to be detected; determining a preset sliding time window, and determining the mean of the target data type within the preset sliding time window; determining the data matrix corresponding to the target data type, and determining the covariance matrix corresponding to the data matrix, and performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and their corresponding values. Based on the feature vectors, principal component feature vectors are selected from the feature vectors according to the magnitude of the feature values, and the direction of data feature change is determined based on the principal component feature vectors. Based on the mean and the direction of data feature change, it is determined whether the target data to be detected is abnormal data. If so, the abnormal data in the target data is removed. The method for determining whether the target data to be detected is abnormal data includes: determining whether the difference between the target data to be detected and the mean is greater than a preset threshold, and / or determining whether the direction of change of the target data to be detected conflicts with the direction of data feature change. If the difference is greater than the preset threshold and the direction of change of the target data to be detected conflicts with the direction of data feature change, the target data to be detected is determined to be abnormal data; otherwise, the target data to be detected is determined to be normal data.

[0052] The preset sliding time window is set according to actual needs, such as a sliding time window of 10:00-10:20.

[0053] Specifically, taking any data from any of the following categories of data—electrical performance parameters, electrical energy output parameters, first environmental monitoring data, and second environmental monitoring data—as an example, for instance, taking the current collected at a certain moment in the electrical performance parameters as the target data to be detected. The mean current value of each current between 10:00 and 10:20 is determined, along with the data matrix of the electrical performance parameters. The covariance between each data point in this data matrix is ​​then determined, and a covariance matrix is ​​constructed from these covariances. The covariance matrix is ​​then subjected to eigenvalue decomposition to obtain eigenvalues ​​and their corresponding eigenvectors. The eigenvalues ​​are then sorted in descending order. A predetermined number of eigenvalues ​​are determined, and their corresponding eigenvectors are used as principal component eigenvectors. The direction of these principal component eigenvectors is taken as the direction of data feature change. If the difference between the target data to be detected and the mean is greater than a predetermined threshold, and the direction of change of the target data to be detected is conflicting (i.e., different), then the target data to be detected is determined to be abnormal data, and the abnormal data in the electrical performance parameters is removed. Therefore, by following the above method, abnormal data can be detected and removed from electrical performance parameters, electrical energy output parameters, first environmental monitoring data, and second environmental monitoring data, thereby enhancing data quality, avoiding the impact of abnormal data on the performance evaluation results of photovoltaic modules, and also avoiding the time and resources spent on analyzing abnormal data.

[0054] Furthermore, feature extraction models, such as CNN models, are used to extract the electrical performance feature vector of the electrical performance parameters after anomaly processing, the electrical energy output parameter's electrical energy feature vector, the first environmental monitoring feature vector of the first environmental monitoring data, and the second environmental monitoring feature vector of the second environmental monitoring data.

[0055] 205. The electrical performance feature vector, electrical energy feature vector, first environmental monitoring feature vector, and second environmental monitoring feature vector are fused to obtain the performance fusion feature vector.

[0056] In this embodiment of the invention, to extract more implicit information, it is first necessary to fuse the electrical performance feature vector, the electrical energy feature vector, the first environmental monitoring feature vector, and the second environmental monitoring feature vector. Based on this, step 205 specifically includes: determining the electrical performance vector complexity of the electrical performance feature vector, the electrical energy vector complexity of the electrical energy feature vector, the first environmental vector complexity corresponding to the first environmental monitoring feature vector, and the second environmental vector complexity of the second environmental monitoring feature vector; based on the electrical performance vector complexity, the electrical energy vector complexity, the first environmental vector complexity, and the second environmental vector complexity, determining the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental linear transformation coefficient; based on the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental vector complexity, determining the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental linear transformation coefficient; and based on the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental vector complexity, determining the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental vector complexity, determining the electrical energy ... Two environmental linear transformation coefficients are used to determine the electrical performance fusion weight, electrical energy fusion weight, first environmental fusion weight, and second environmental fusion weight. Based on the electrical performance linear transformation coefficient, the electrical performance feature vector is linearly transformed; based on the electrical energy linear transformation coefficient, the electrical energy feature vector is linearly transformed; based on the first environmental linear transformation coefficient, the first environmental monitoring feature vector is linearly transformed; based on the second environmental linear transformation coefficient, the second environmental monitoring feature vector is linearly transformed. Based on the electrical performance fusion weight, the electrical energy fusion weight, the first environmental fusion weight, and the second environmental fusion weight, the linearly transformed electrical performance feature vector, the linearly transformed electrical energy feature vector, the linearly transformed first environmental monitoring feature vector, and the linearly transformed second environmental monitoring feature vector are weighted and fused to obtain the performance fusion feature vector.

[0057] Specifically, in the vector fusion process, firstly, the square root of the sum of squares of each vector element in the electrical performance feature vector, electrical energy feature vector, first environmental monitoring feature vector, and second environmental monitoring feature vector is determined. The square root of the sum of squares of each vector element is used as the electrical performance vector complexity, electrical energy vector complexity, first environmental vector complexity, and second environmental vector complexity of the corresponding vector. Then, the sum of squares of the electrical performance vector complexity, electrical energy vector complexity, first environmental vector complexity, and second environmental vector complexity is determined. The ratio of the square of the electrical performance vector complexity, electrical energy vector complexity, first environmental vector complexity, and second environmental vector complexity to the sum of squares is used as the corresponding electrical performance linear transformation coefficient, electrical energy linear transformation coefficient, first environmental linear transformation coefficient, and second environmental linear transformation coefficient. Furthermore, the sum of the linear transformation coefficients for electrical performance, electrical energy, the first environment, and the second environment is determined as the total transformation coefficient. The ratios of these coefficients to the total transformation coefficient are then used as the corresponding electrical performance fusion weight, electrical energy fusion weight, first environment fusion weight, and second environment fusion weight, respectively. Further, the linear transformation coefficients for electrical performance are multiplied by the electrical performance feature vector to obtain the linearly transformed electrical performance feature vector; the linear transformation coefficients for electrical energy are multiplied by the electrical energy feature vector to obtain the linearly transformed electrical energy feature vector; the linear transformation coefficients for the first environment are multiplied by the first environment monitoring feature vector to obtain the linearly transformed first environment monitoring feature vector; and the linear transformation coefficients for the second environment are multiplied by the second environment monitoring feature vector to obtain the linearly transformed second environment monitoring feature vector. Finally, based on the electrical performance fusion weight, the electrical energy fusion weight, the first environmental fusion weight, and the second environmental fusion weight, the linearly transformed electrical performance feature vector, the linearly transformed electrical energy feature vector, the linearly transformed first environmental monitoring feature vector, and the linearly transformed second environmental monitoring feature vector are weighted and summed to obtain the performance fusion feature vector. This embodiment of the invention, by fusing various vectors, can automatically or explicitly combine different features to generate new feature combinations. These combined features may contain complex nonlinear relationships between the original features, enabling the model to capture more refined and richer information in the data. That is, it can fully utilize the relationships between various data, extract more latent features, make more efficient use of the data, and obtain more accurate performance evaluation results.

[0058] 206. Input the performance fusion feature vector into the preset performance evaluation model for performance evaluation to obtain the performance evaluation results of the photovoltaic module to be evaluated.

[0059] In this embodiment of the invention, to improve the performance evaluation accuracy of the preset performance evaluation model, it is first necessary to train and construct the preset performance evaluation model. Based on this, the method includes: constructing a preset initial performance evaluation model; obtaining a sample dataset, wherein the sample dataset includes electrical performance parameters, electrical energy output parameters, environmental monitoring data simultaneously with the electrical performance parameters, and environmental monitoring data simultaneously with the electrical energy output parameters of sample photovoltaic modules with performance labels during actual operation; dividing the sample dataset into a training set and a test set; training the preset initial performance evaluation model using the training set; and testing the trained preset initial performance evaluation model using the test set; finally, the trained preset initial performance evaluation model that meets the test conditions is used as the preset performance evaluation model. Specifically, in the model training process, the preset initial performance evaluation model is first constructed, and then the sample dataset is obtained. It is ensured that the dataset contains all necessary files. The data is converted to a format that the preset initial performance evaluation model can understand, and finally, the model is trained and tested. Specifically, the dataset can be divided first: the sample dataset can be divided into a training set and a test set using random or specific strategies (such as stratified sampling). The model is then trained using the training set and tested on the test set to evaluate its performance on unseen data. Precision, recall, and other metrics on the test set are calculated and recorded. If the model performance does not meet requirements, it can be returned to the training phase for further iterations or adjustments. This process yields a pre-defined performance evaluation model that meets the requirements. Finally, the performance fusion feature vector is directly input into the pre-defined performance evaluation model to evaluate the performance of the photovoltaic module. Based on the performance evaluation results, the performance score and performance level of the photovoltaic module can be determined.

[0060] According to another photovoltaic module performance evaluation method provided by this invention, compared with the current method of using a dedicated current scanner to perform transient current testing on photovoltaic modules and determining the performance of photovoltaic modules based on transient current, this invention acquires the electrical performance parameters and power output parameters of photovoltaic modules in both IV scanning measurement mode and MPPT operation mode, and also acquires environmental monitoring data. Then, it comprehensively analyzes the multiple factors, including electrical performance parameters, power output parameters, and environmental monitoring data, to evaluate the performance of photovoltaic modules. This provides sufficient information, thereby improving the accuracy of photovoltaic module performance evaluation. By evaluating demand information and real-time environmental data to determine the switching mode, this invention avoids errors caused by manual determination of the switching mode, thus improving the accuracy of switching mode determination and ensuring the effectiveness of photovoltaic module performance evaluation. When evaluating the performance of photovoltaic modules, by collecting data in MPPT operation mode, continuous and long-term data can be collected. Evaluating photovoltaic module performance based on continuous and long-term data improves the accuracy of photovoltaic module performance evaluation.

[0061] Furthermore, as Figure 1 In specific implementation, embodiments of the present invention provide a photovoltaic module performance evaluation device, such as... Figure 3 As shown, the device is applied to an outdoor testing system for photovoltaic modules. The outdoor testing system for photovoltaic modules includes a test channel, a multi-channel switching array, and a central processing unit. The device includes: an acquisition unit 31, a first mode switching unit 32, a second mode switching unit 33, and a performance evaluation unit 34.

[0062] The acquisition unit 31 can be used to control the test channel to connect with the photovoltaic module to be evaluated, and to acquire the evaluation requirements information and real-time environmental data of the photovoltaic module to be evaluated.

[0063] The first mode switching unit 32 can be used to determine whether the working mode of the test channel conforms to the IV scan measurement mode based on the evaluation requirement information and the real-time environmental data. If so, the central processing unit can switch the test channel to the IV scan measurement mode through the multiplexer array to obtain the electrical performance parameters of the photovoltaic module to be evaluated when it is running in the IV scan measurement mode, and obtain the first environmental monitoring data at the time of the electrical performance parameter acquisition.

[0064] The second mode switching unit 33 can be used to determine whether the test channel meets the preset conditions for mode switching based on the first environmental monitoring data. If so, the central processing unit uses the multi-channel switching array to switch the test channel from the IV scan measurement mode to the MPPT (Maximum Power Point Tracking) operation mode, and obtains the electrical energy output parameters of the photovoltaic module to be evaluated when it is running in the MPPT operation mode, and obtains the second environmental monitoring data at the time of the electrical energy output parameter acquisition.

[0065] The performance evaluation unit 34 can be used to evaluate the performance of the photovoltaic module to be evaluated based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data.

[0066] In specific application scenarios, the photovoltaic module outdoor testing system also includes an integrated MPPT power processing module and a data acquisition module. To allow the central processing unit to switch the test channel to the IV scan measurement mode via a multi-channel switching array, the first mode switching unit 32 can be used to connect the input of the test channel to the photovoltaic module under evaluation, and the output of the test channel to a common DC bus via a bus. The central processing unit controls the input of the data acquisition module to connect to the common DC bus via the multi-channel switching array, thereby switching the test channel to the IV scan measurement mode. The central processing unit also controls the input of the integrated MPPT power processing module to connect to the common DC bus via the multi-channel switching array, and the output of the integrated MPPT power processing module to the load, thereby switching the test channel from the IV scan measurement mode to the MPPT operation mode.

[0067] In specific application scenarios, in order to determine the operating time of photovoltaic modules in MPPT mode, such as Figure 4 As shown, the device also includes a duration determination unit 35.

[0068] The duration determination unit 35 can be used to acquire in real time the output power generated by the photovoltaic module to be evaluated in the MPPT operation mode, acquire in real time the device attribute data of the power output parameter acquisition device in the MPPT operation mode, and acquire in real time the dynamic environmental parameters of the location of the photovoltaic module to be evaluated in the MPPT operation mode; based on the output power, determine in real time the dynamic power fluctuation entropy of the photovoltaic module to be evaluated, determine in real time the MPPT tracking efficiency in the MPPT operation mode based on the device attribute data, determine the running time correction coefficient based on the dynamic environmental parameters; determine the initial running time of the photovoltaic module to be evaluated in the MPPT operation mode based on the dynamic power fluctuation entropy and the MPPT tracking efficiency, correct the initial running time based on the running time correction coefficient, take the corrected initial running time as the final running time, and control the photovoltaic module to be evaluated to operate in the MPPT operation mode based on the final running time.

[0069] In specific application scenarios, in order to evaluate the performance of the photovoltaic module to be evaluated, the performance evaluation unit 34 includes a first determination module 341, a first fusion module 342, and a performance evaluation module 343.

[0070] The first determining module 341 can be used to determine the electrical performance feature vector corresponding to the electrical performance parameter, the electrical energy feature vector corresponding to the electrical energy output parameter, the first environmental monitoring feature vector corresponding to the first environmental monitoring data, and the second environmental monitoring feature vector corresponding to the second environmental monitoring data.

[0071] The first fusion module 342 can be used to fuse the electrical performance feature vector, the electrical energy feature vector, the first environmental monitoring feature vector, and the second environmental monitoring feature vector to obtain a performance fusion feature vector.

[0072] The performance evaluation module 343 can be used to input the performance fusion feature vector into a preset performance evaluation model for performance evaluation, and obtain the performance evaluation result of the photovoltaic module to be evaluated.

[0073] In specific application scenarios, in order to fuse various feature vectors, the first fusion module 342 can be used to determine the electrical performance vector complexity of the electrical performance feature vector, the electrical energy vector complexity of the electrical energy feature vector, the first environmental vector complexity corresponding to the first environmental monitoring feature vector, and the second environmental vector complexity of the second environmental monitoring feature vector; based on the electrical performance vector complexity, the electrical energy vector complexity, the first environmental vector complexity, and the second environmental vector complexity, determine the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental linear transformation coefficient, respectively; and based on the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental linear transformation coefficient, determine the electrical performance fusion weight. The system comprises three weighted systems: an electrical energy fusion weight, a first environmental fusion weight, and a second environmental fusion weight. Based on the electrical performance linear transformation coefficient, the electrical performance feature vector is linearly transformed; based on the electrical energy linear transformation coefficient, the electrical energy feature vector is linearly transformed; based on the first environmental linear transformation coefficient, the first environmental monitoring feature vector is linearly transformed; based on the second environmental linear transformation coefficient, the second environmental monitoring feature vector is linearly transformed; and based on the electrical performance fusion weight, the electrical energy fusion weight, the first environmental fusion weight, and the second environmental fusion weight, the linearly transformed electrical performance feature vector, the linearly transformed electrical energy feature vector, the linearly transformed first environmental monitoring feature vector, and the linearly transformed second environmental monitoring feature vector are weighted and fused to obtain a performance fusion feature vector.

[0074] In specific application scenarios, in order to determine whether the working mode of the test channel conforms to the IV scan measurement mode, the first mode switching unit 32 includes a second determination module 321, a second fusion module 322, and a parameter prediction module 323.

[0075] The second determining module 321 can be used to obtain the component feature data of the photovoltaic module to be evaluated, and respectively determine the demand feature vector corresponding to the evaluation demand information, the environmental feature vector corresponding to the real-time environmental data, and the component feature vector corresponding to the component feature data.

[0076] The second determining module 321 can also be used to determine the number of dimensions, dynamics, and uncertainty of the evaluation requirement information, the real-time environmental data, and the component feature data, respectively. Based on the number of dimensions, the dynamics, and the uncertainty, the requirement complexity of the requirement feature vector, the environmental complexity of the environmental feature vector, and the component complexity of the component feature vector are determined accordingly.

[0077] The second fusion module 322 can be used to determine the weight coefficients of the requirement feature vector, the environment feature vector, and the component feature vector based on the requirement complexity, the environment complexity, and the component complexity, respectively, and to perform a weighted summation of the requirement feature vector, the environment feature vector, and the component feature vector based on the weight coefficients to obtain the pattern fusion feature vector.

[0078] The parameter prediction module 323 can be used to input the mode fusion feature vector into a preset evaluation parameter prediction model to predict evaluation parameters, obtain evaluation parameters, and determine whether the working mode of the test channel conforms to the IV scan measurement mode based on the evaluation parameters.

[0079] In specific application scenarios, in order to detect anomalies in data such as electrical performance parameters, electrical energy output parameters, first environmental monitoring data, and second environmental monitoring data, the device also includes an anomaly detection unit 36.

[0080] The anomaly detection unit 36 ​​can be used to take any one of the electrical performance parameters, electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data as a target type of data, and take any one of the target type of data as a target data to be detected; determine a preset sliding time window, and determine the mean of the target type of data within the preset sliding time window; determine the data matrix corresponding to the target type of data, and determine the covariance matrix corresponding to the data matrix, and perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors corresponding to the eigenvalues; select principal component eigenvectors from the eigenvectors based on the magnitude of the eigenvalues, and based on the principal components... The feature vector determines the direction of data feature change. Based on the mean and the direction of data feature change, it is determined whether the target data to be detected is abnormal data. If so, the abnormal data in the target category data is removed. The method for determining whether the target data to be detected is abnormal data includes: determining whether the difference between the target data to be detected and the mean is greater than a preset threshold, and / or determining whether the direction of change of the target data to be detected conflicts with the direction of change of the data feature. If the difference is greater than the preset threshold and the direction of change of the target data to be detected conflicts with the direction of change of the data feature, the target data to be detected is determined to be abnormal data; otherwise, the target data to be detected is determined to be normal data.

[0081] It should be noted that other corresponding descriptions of the functional modules involved in the photovoltaic module performance evaluation device provided in this embodiment of the invention can be found in [reference]. Figure 1 The corresponding description of the method shown will not be repeated here.

[0082] Based on the above, Figure 1Correspondingly, this embodiment of the invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the following steps: controlling the test channel to connect to the photovoltaic module to be evaluated, and acquiring the evaluation requirement information and real-time environmental data of the photovoltaic module to be evaluated; based on the evaluation requirement information and the real-time environmental data, determining whether the operating mode of the test channel conforms to the IV scan measurement mode; if so, using the central processing unit to switch the test channel to the IV scan measurement mode through the multiplexer array, acquiring the electrical performance parameters of the photovoltaic module to be evaluated during operation in the IV scan measurement mode, and acquiring the first environmental monitoring data at the time of acquisition of the electrical performance parameters; based on the first environmental monitoring data, determining whether the test channel meets the preset conditions for mode switching; if so, using the central processing unit to switch the test channel from the IV scan measurement mode to MPPT (Maximum Power Point) through the multiplexer array. The system operates in a Maximum Power Point Tracking (MPPT) mode and acquires the electrical energy output parameters of the photovoltaic module under evaluation during operation in the MPPT mode. It also acquires the second environmental monitoring data at the time of acquisition of the electrical energy output parameters. Based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data, the system performs a performance evaluation on the photovoltaic module under evaluation.

[0083] Based on the above, Figure 1 The method shown and as Figure 3 The embodiment of the device shown in the invention also provides a physical structure diagram of a computer device, such as... Figure 5As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor. Both the memory 42 and the processor 41 are mounted on a bus 43. When the processor 41 executes the program, it performs the following steps: controlling the test channel to connect to the photovoltaic module to be evaluated, and acquiring the evaluation requirement information and real-time environmental data of the photovoltaic module to be evaluated; based on the evaluation requirement information and the real-time environmental data, determining whether the operating mode of the test channel conforms to the IV scan measurement mode; if so, using the central processing unit to switch the test channel to the IV scan measurement mode via the multiplexer array, acquiring the electrical performance parameters of the photovoltaic module to be evaluated during operation in the IV scan measurement mode, and acquiring the first environmental monitoring data at the time of acquisition of the electrical performance parameters; based on the first environmental monitoring data, determining whether the test channel meets the preset conditions for mode switching; if so, using the central processing unit to switch the test channel from the IV scan measurement mode to MPPT (Maximum Power Transmission Test) via the multiplexer array. The system operates in Maximum Power Point Tracking (MPPT) mode and acquires the electrical energy output parameters of the photovoltaic module under evaluation during operation in MPPT mode. It also acquires the second environmental monitoring data at the time of acquisition of the electrical energy output parameters. Based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data, the system performs a performance evaluation on the photovoltaic module under evaluation.

[0084] Through the technical solution of this invention, the electrical performance parameters and power output parameters of photovoltaic modules are acquired in both IV scanning measurement mode and MPPT operation mode, along with environmental monitoring data. Then, a comprehensive analysis of these multiple factors—including electrical performance parameters, power output parameters, and environmental monitoring data—is performed to evaluate the performance of the photovoltaic modules. This comprehensive analysis improves the accuracy of photovoltaic module performance evaluation. By determining the switching mode based on evaluation demand information and real-time environmental data, the invention avoids errors caused by manual determination of the switching mode, thus improving the accuracy of switching mode determination and ensuring the effectiveness of photovoltaic module performance evaluation. Furthermore, by collecting data in MPPT operation mode, continuous and long-term data can be collected during photovoltaic module performance evaluation, further improving the accuracy of photovoltaic module performance evaluation.

[0085] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0086] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating the performance of photovoltaic modules, characterized in that, This system is used in outdoor testing systems for photovoltaic modules. The outdoor testing system includes test channels, a multi-channel switching array, and a central processing unit, comprising: The test channel is connected to the photovoltaic module to be evaluated, and the evaluation requirements information and real-time environmental data of the photovoltaic module to be evaluated are obtained. Based on the evaluation requirements and the real-time environmental data, it is determined whether the working mode of the test channel conforms to the IV scan measurement mode. If so, the central processing unit uses the multiplexer array to switch the test channel to the IV scan measurement mode, obtains the electrical performance parameters of the photovoltaic module to be evaluated when it is running in the IV scan measurement mode, and obtains the first environmental monitoring data at the time of the electrical performance parameter acquisition. Based on the first environmental monitoring data, it is determined whether the test channel meets the preset conditions for mode switching. If so, the central processing unit uses the multi-channel switching array to switch the test channel from the IV scan measurement mode to the MPPT (Maximum Power Point Tracking) operation mode, and obtains the electrical energy output parameters of the photovoltaic module to be evaluated when it is running in the MPPT operation mode, and obtains the second environmental monitoring data at the time of the electrical energy output parameter acquisition. The performance of the photovoltaic module to be evaluated is assessed based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data.

2. The method according to claim 1, characterized in that, The photovoltaic module outdoor testing system also includes an integrated MPPT power processing module and a data acquisition module; Using the central processing unit to switch the test channel to the IV scan measurement mode via the multiplexer array, the following is included: The input terminal of the test channel is connected to the photovoltaic module to be evaluated, and the output terminal of the test channel is connected in parallel to the common DC bus via a bus. The central processing unit uses the multiplexer array to control the input terminal of the data acquisition module to be connected to the common DC bus, so as to switch the test channel to the IV scan measurement mode. Using the central processing unit to switch the test channel from the IV scan measurement mode to the MPPT operation mode via the multiplexer array, the following steps are included: The central processing unit controls the input terminal of the integrated MPPT power processing module to be connected to the common DC bus via the multi-channel switching array, and the output terminal of the integrated MPPT power processing module to be connected to the load, so as to switch the test channel from the IV scan measurement mode to the MPPT operation mode.

3. The method according to claim 1, characterized in that, After the central processing unit switches the test channel from the IV scan measurement mode to the MPPT (Maximum Power Point Tracking) operating mode via the multiplexer array, the method further includes: The system acquires the output power generated by the photovoltaic module under evaluation in the MPPT operation mode in real time, acquires the device attribute data of the power output parameter acquisition device in the MPPT operation mode in real time, and acquires the dynamic environmental parameters of the location of the photovoltaic module under evaluation in the MPPT operation mode in real time. Based on the output power, the dynamic power fluctuation entropy of the photovoltaic module to be evaluated is determined in real time; based on the device attribute data, the MPPT tracking efficiency in the MPPT operation mode is determined in real time; and based on the dynamic environmental parameters, the runtime correction coefficient is determined. Based on the dynamic power fluctuation entropy and the MPPT tracking efficiency, the initial operating time of the photovoltaic module to be evaluated in the MPPT operating mode is determined, and the initial operating time is corrected based on the operating time correction coefficient. The corrected initial operating time is taken as the final operating time, and the photovoltaic module to be evaluated is controlled to operate in the MPPT operating mode based on the final operating time.

4. The method according to claim 1, characterized in that, The performance evaluation of the photovoltaic module to be evaluated based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data includes: Determine the electrical performance feature vector corresponding to the electrical performance parameter, the electrical energy feature vector corresponding to the electrical energy output parameter, the first environmental monitoring feature vector corresponding to the first environmental monitoring data, and the second environmental monitoring feature vector corresponding to the second environmental monitoring data, respectively. The electrical performance feature vector, the electrical energy feature vector, the first environmental monitoring feature vector, and the second environmental monitoring feature vector are fused to obtain a performance fusion feature vector. The performance fusion feature vector is input into a preset performance evaluation model for performance evaluation, and the performance evaluation result of the photovoltaic module to be evaluated is obtained.

5. The method according to claim 4, characterized in that, The process of fusing the electrical performance feature vector, the electrical energy feature vector, the first environmental monitoring feature vector, and the second environmental monitoring feature vector to obtain a performance fusion feature vector includes: The electrical performance vector complexity of the electrical performance feature vector, the electrical energy vector complexity of the electrical energy feature vector, the first environmental vector complexity corresponding to the first environmental monitoring feature vector, and the second environmental vector complexity of the second environmental monitoring feature vector are determined respectively. Based on the electrical performance vector complexity, the electrical energy vector complexity, the first environment vector complexity, and the second environment vector complexity, the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environment linear transformation coefficient, and the second environment linear transformation coefficient are determined respectively. Based on the electrical performance linear transformation coefficient, the electrical energy linear transformation coefficient, the first environmental linear transformation coefficient, and the second environmental linear transformation coefficient, the electrical performance fusion weight, the electrical energy fusion weight, the first environmental fusion weight, and the second environmental fusion weight are determined. Based on the electrical performance linear transformation coefficient, the electrical performance feature vector is linearly transformed; based on the electrical energy linear transformation coefficient, the electrical energy feature vector is linearly transformed; based on the first environmental linear transformation coefficient, the first environmental monitoring feature vector is linearly transformed; and based on the second environmental linear transformation coefficient, the second environmental monitoring feature vector is linearly transformed. Based on the electrical performance fusion weight, the electrical energy fusion weight, the first environmental fusion weight, and the second environmental fusion weight, the linearly transformed electrical performance feature vector, the linearly transformed electrical energy feature vector, the linearly transformed first environmental monitoring feature vector, and the linearly transformed second environmental monitoring feature vector are weighted and fused to obtain the performance fusion feature vector.

6. The method according to claim 1, characterized in that, The step of determining whether the operating mode of the test channel conforms to the IV scan measurement mode based on the evaluation requirement information and the real-time environmental data includes: Obtain the component feature data of the photovoltaic module to be evaluated, and determine the demand feature vector corresponding to the evaluation demand information, the environmental feature vector corresponding to the real-time environmental data, and the component feature vector corresponding to the component feature data, respectively. The number of dimensions, dynamics, and uncertainties of the evaluation requirement information, the real-time environmental data, and the component feature data are determined respectively. Based on the number of dimensions, the dynamics, and the uncertainties, the requirement complexity of the requirement feature vector, the environmental complexity of the environmental feature vector, and the component complexity of the component feature vector are determined accordingly. Based on the requirement complexity, the environment complexity, and the component complexity, the weight coefficients of the requirement feature vector, the environment feature vector, and the component feature vector are determined respectively. Based on the weight coefficients, the requirement feature vector, the environment feature vector, and the component feature vector are weighted and summed to obtain the pattern fusion feature vector. The mode fusion feature vector is input into a preset evaluation parameter prediction model to predict evaluation parameters, and the evaluation parameters are obtained. Based on the evaluation parameters, it is determined whether the working mode of the test channel conforms to the IV scan measurement mode.

7. The method according to claim 1, characterized in that, Before performing a performance evaluation of the photovoltaic module to be evaluated based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data, the method further includes: Each of the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data is taken as a target type of data, and each of the target type of data is taken as a target data to be detected. A preset sliding time window is determined, and the mean value of the target type data within the preset sliding time window is determined; The data matrix corresponding to the target type data is determined, and the covariance matrix corresponding to the data matrix is ​​determined. The covariance matrix is ​​then decomposed to obtain eigenvalues ​​and eigenvectors corresponding to the eigenvalues. Based on the magnitude of the eigenvalues, principal component eigenvectors are selected from the eigenvectors. Based on the principal component eigenvectors, the direction of data feature change is determined. Based on the mean and the direction of change of the data features, it is determined whether the target data to be detected is abnormal data. If so, the abnormal data in the target category data is removed. The method for determining whether the target data to be detected is abnormal data includes: Determine whether the difference between the target data to be detected and the mean is greater than a preset threshold, and / or determine whether the direction of change of the target data to be detected conflicts with the direction of change of the data feature. If the difference is greater than the preset threshold and the direction of change of the target data to be detected conflicts with the direction of change of the data feature, then the target data to be detected is determined to be abnormal data; otherwise, the target data to be detected is determined to be normal data.

8. A photovoltaic module performance evaluation device, characterized in that, This system is used in outdoor testing systems for photovoltaic modules. The outdoor testing system includes test channels, a multi-channel switching array, and a central processing unit, comprising: The acquisition unit is used to control the test channel to connect with the photovoltaic module to be evaluated, and to acquire the evaluation requirement information and real-time environmental data of the photovoltaic module to be evaluated; The first mode switching unit is used to determine whether the working mode of the test channel conforms to the IV scan measurement mode based on the evaluation requirement information and the real-time environmental data. If so, the central processing unit uses the multiplexer array to switch the test channel to the IV scan measurement mode, obtains the electrical performance parameters of the photovoltaic module to be evaluated when it is running in the IV scan measurement mode, and obtains the first environmental monitoring data at the time of the electrical performance parameter acquisition. The second mode switching unit is used to determine whether the test channel meets the preset conditions for mode switching based on the first environmental monitoring data. If so, the central processing unit uses the multi-channel switching array to switch the test channel from the IV scan measurement mode to the MPPT (Maximum Power Point Tracking) operation mode, and obtains the electrical energy output parameters of the photovoltaic module to be evaluated when it is running in the MPPT operation mode, and obtains the second environmental monitoring data at the time of the electrical energy output parameter acquisition. The performance evaluation unit is used to evaluate the performance of the photovoltaic module to be evaluated based on the electrical performance parameters, the electrical energy output parameters, the first environmental monitoring data, and the second environmental monitoring data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images