A modular photovoltaic device and its control method

Abstract

The present invention relates to the technical field of photovoltaic power generation, and particularly to a modular photovoltaic device and its control method. The method includes the following steps: obtaining photovoltaic system data; extracting the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; performing intensity evaluation on the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; performing intensity clustering on the photovoltaic illumination intensity data to obtain illumination intensity clustering data; extracting the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; and performing photothermal collaborative analysis on the photovoltaic temperature data according to the illumination intensity clustering data to generate photovoltaic photothermal collaborative data. Therefore, through the Internet of Things technology, data analysis technology, adaptive control technology and digital twin technology, the present invention realizes photothermal collaborative analysis of the photovoltaic to realize adaptive adjustment of the photovoltaic array configuration and improve the photovoltaic power output performance.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and particularly to a modular photovoltaic device and a control method thereof. Background Art

[0002] With the development of semiconductor material technology and the improvement of photovoltaic cell efficiency, modular photovoltaic devices have gradually become an industry trend. The modular design makes photovoltaic modules more flexible, enabling rapid deployment and expansion according to different application scenarios, especially showing advantages in distributed energy systems. At the same time, the control technology of photovoltaic systems has also been significantly improved. Early photovoltaic control systems mainly relied on simple inverters and manual adjustment of device output. However, with the development of power electronics technology and intelligent control technology, modern photovoltaic devices have introduced intelligent control systems that can automatically optimize power generation efficiency according to environmental conditions. Combining the Internet of Things and big data analysis, modular photovoltaic devices have achieved remote monitoring, fault diagnosis, and system performance optimization management. These improvements have enhanced the reliability, efficiency, and economy of photovoltaic systems, making modular photovoltaic devices an important part of modern new energy utilization. However, the existing technology lacks the analysis of the synergy between light and heat in photovoltaic systems and is difficult to adaptively adjust the configuration of photovoltaic arrays, resulting in relatively low photovoltaic power output performance. Summary of the Invention

[0003] Based on this, it is necessary to provide a modular photovoltaic device and a control method thereof to solve at least one of the above technical problems. To achieve the above object, a modular photovoltaic control method includes the following steps:

[0004] Step S1: Obtain photovoltaic system data; extract the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; evaluate the intensity of the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; perform intensity clustering on the photovoltaic illumination intensity data to obtain illumination intensity clustering data; extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; perform light-heat synergy analysis on the photovoltaic temperature data according to the illumination intensity clustering data to generate photovoltaic light-heat synergy data;

[0005] Step S2: Predict the photovoltaic power output based on the photovoltaic light-heat synergy data to generate predicted power output data; compare the predicted power output data with a preset power target to generate power output comparison data; perform power loss analysis on the power output comparison data to generate loss analysis data; perform dynamic power compensation adjustment on the photovoltaic light-heat synergy data according to the loss analysis data to generate photovoltaic power compensation data;

[0006] Step S3: Extract the component information of the photovoltaic system data to obtain photovoltaic module data; perform array configuration analysis on the photovoltaic module data to obtain photovoltaic array configuration data; perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array anomaly data; perform adaptive adjustment on the photovoltaic array anomaly data to obtain photovoltaic array adjustment data;

[0007] Step S4: Construct a photovoltaic performance evaluation model by using the photovoltaic power compensation data and the photovoltaic array adjustment data to generate a photovoltaic performance evaluation model; use the photovoltaic performance evaluation model to evaluate the component energy efficiency of the photovoltaic system data to generate photovoltaic component energy efficiency evaluation data; perform real-time monitoring and control on the photovoltaic system data according to the photovoltaic component energy efficiency evaluation data to generate a photovoltaic control optimization report.

[0008] The present invention accurately evaluates the photovoltaic illumination intensity by obtaining the illumination parameter information of the photovoltaic system. Further, illumination intensity clustering is performed to provide an accurate illumination data basis for subsequent photothermal synergy analysis; the photovoltaic temperature data is analyzed in combination with the illumination intensity clustering data to generate photovoltaic photothermal synergy data, which can accurately predict the photovoltaic power output and improve the prediction accuracy; the photovoltaic power output is predicted by using the photovoltaic photothermal synergy data and compared with the preset power target to generate power output comparison data, and power loss analysis is performed, so as to provide a basis for dynamic power compensation; the photovoltaic photothermal synergy data is adjusted according to the loss analysis data to generate photovoltaic power compensation data, which helps to optimize the power output of the photovoltaic system, reduce losses, and improve the photovoltaic utilization efficiency. Extracting the photovoltaic module data and performing array configuration analysis can identify anomalies in the photovoltaic array; and through adaptive adjustment, photovoltaic array adjustment data is generated to further improve the overall performance of the photovoltaic system; the photovoltaic power compensation data and the photovoltaic array adjustment data are integrated to construct a photovoltaic performance evaluation model to ensure accurate evaluation of the energy efficiency of the photovoltaic components and generate photovoltaic component energy efficiency evaluation data; using the photovoltaic performance evaluation model to perform real-time monitoring and control on the photovoltaic system data can generate a photovoltaic control optimization report to guide actual operations and ensure that the photovoltaic system operates in the best state, thereby improving the stability and reliability of the photovoltaic system. Therefore, the present invention realizes photothermal synergy analysis of the photovoltaic through Internet of Things technology, data analysis technology, adaptive control technology and digital twin technology to realize adaptive adjustment of the photovoltaic array configuration; improve the photovoltaic power output performance.

[0009] Preferably, step S1 includes the following steps:

[0010] Step S11: Identify the illumination characteristics of the photovoltaic system data to obtain photovoltaic illumination characteristic data; extract parameter information from the photovoltaic illumination characteristic data to obtain photovoltaic illumination parameter information;

[0011] Step S12: performing light intensity tracking processing on the photovoltaic illumination parameter information in each time period to obtain photovoltaic light intensity tracking data; performing light intensity integral calculation on the photovoltaic light intensity tracking data to obtain photovoltaic illumination intensity data;

[0012] Step S13: performing time series processing on the photovoltaic light intensity data to obtain light intensity time series data; performing nonlinear dimensionality reduction on the light intensity time series data to generate time series dimensionality reduction data; performing hierarchical clustering analysis on the photovoltaic light intensity data based on the time series dimensionality reduction data to obtain light intensity clustering data; extracting temperature data of the photovoltaic system data to obtain photovoltaic temperature data;

[0013] Step S14: Performing photothermal synergy analysis on the photovoltaic temperature data according to the light intensity clustering data to generate photovoltaic photothermal synergy data.

[0014] The present invention can accurately obtain photovoltaic illumination characteristics and parameter information through illumination feature recognition and parameter information extraction, and provide accurate basic data for subsequent light intensity tracking and analysis; the photovoltaic illumination parameter information is subjected to light intensity tracking processing in each time period, so as to obtain photovoltaic light intensity tracking data, which is helpful to understand the illumination changes of the photovoltaic system in different time periods; the photovoltaic light intensity tracking data is subjected to light intensity integral calculation to obtain photovoltaic illumination intensity data, which will provide a quantitative basis for evaluating the energy capture capability of the photovoltaic system; through time series processing and nonlinear dimensionality reduction, light intensity time series dimensionality reduction data is generated, which can simplify the data structure while retaining key information for subsequent data analysis and processing; the photovoltaic illumination intensity data is subjected to hierarchical clustering analysis using the time series dimensionality reduction data to obtain illumination intensity clustering data, which can classify illumination conditions and provide data support for subsequent optimization of the photovoltaic system; the temperature data of the photovoltaic system data is extracted to obtain photovoltaic temperature data; the photovoltaic temperature data is subjected to light-thermal synergistic analysis in combination with the light intensity clustering data to generate photovoltaic light-thermal synergistic data, which comprehensively considers the light and temperature factors and provides a scientific basis for performance optimization and fault diagnosis of the photovoltaic system.

[0015] Preferably, step S14 includes the following steps:

[0016] Step S141: performing time stamp synchronization processing on the light intensity clustering data to obtain light intensity clustering synchronization data; performing thermal response characteristic analysis on the photovoltaic temperature data according to the light intensity clustering synchronization data to obtain photovoltaic temperature thermal response data;

[0017] Step S142: performing temperature change profile recognition on the photovoltaic temperature thermal response data to generate photovoltaic temperature profile data; performing sensitivity temperature fluctuation capture on the photovoltaic temperature profile data to obtain photovoltaic temperature fluctuation data;

[0018] Step S143: Perform light energy feature coupling processing on the photovoltaic temperature fluctuation data and the light intensity clustering data to generate light energy feature coupling data; perform synchronous analysis of the thermo-optical effect on the light energy feature coupling data to obtain photovoltaic thermo-optical effect synchronous data;

[0019] Step S144: Record the photo-thermal response time of the photovoltaic thermo-optical effect synchronous data to obtain photo-thermal response time data; calculate the photo-thermal conversion efficiency of the photovoltaic thermo-optical effect synchronous data based on the photo-thermal response time data to obtain photo-thermal conversion efficiency data; perform photo-thermal collaborative analysis on the photovoltaic temperature data based on the photo-thermal conversion efficiency data to generate photovoltaic photo-thermal collaborative data.

[0020] The present invention performs timestamp synchronization processing on the light intensity clustering data, ensuring the accuracy of the light intensity clustering synchronous data, and providing a reference for the analysis of the thermal response characteristics of the photovoltaic temperature data; performing analysis of the thermal response characteristics of the photovoltaic temperature data based on the light intensity clustering synchronous data enables the clarification of the temperature change characteristics of the photovoltaic system under different lighting conditions, laying a foundation for subsequent temperature change profile recognition and temperature fluctuation capture; performing temperature change profile recognition on the photovoltaic temperature thermal response data helps to identify the performance of the photovoltaic system at different temperatures; capturing the sensitivity temperature fluctuations of the photovoltaic temperature profile data can accurately monitor the real-time temperature changes of the photovoltaic system; performing light energy feature coupling processing on the photovoltaic temperature fluctuation data and the light intensity clustering data provides comprehensive data support for the synchronous analysis of the thermo-optical effect of the photovoltaic system. Performing synchronous analysis of the thermo-optical effect on the light energy feature coupling data enables in-depth analysis of the photo-thermal conversion characteristics of the photovoltaic system, providing a basis for the recording of the photo-thermal response time and the calculation of the photo-thermal conversion efficiency; recording the photo-thermal response time of the photovoltaic thermo-optical effect synchronous data provides a quantitative index for the temperature response speed of the photovoltaic system; calculating the photo-thermal conversion efficiency of the photovoltaic thermo-optical effect synchronous data based on the photo-thermal response time data can directly reflect the energy conversion ability of the photovoltaic system; performing photo-thermal collaborative analysis on the photovoltaic temperature data based on the photo-thermal conversion efficiency data synthesizes the photo-thermal conversion efficiency and the photovoltaic temperature data, providing scientific data support for the performance optimization of the photovoltaic system and capable of improving the overall energy efficiency of the photovoltaic system.

[0021] Preferably, step S2 includes the following steps:

[0022] Step S21: Collect historical data of the photovoltaic photo-thermal collaborative data to obtain historical photovoltaic photo-thermal collaborative data; divide the historical photovoltaic photo-thermal collaborative data set to generate a historical data training set and a historical data test set; perform model training on the historical data training set to generate a power output prediction model; perform model testing on the power output prediction model based on the historical data test set to generate a power output prediction model;

[0023] Step S22: Import the photovoltaic-thermal collaborative data into the power output prediction model to predict the photovoltaic power output and generate predicted power output data;

[0024] Step S23: Perform output accuracy calibration processing on the predicted power output data to obtain power output accuracy calibration data; compare the power output accuracy calibration data with the preset power target to generate power output comparison data; perform efficiency deviation identification on the power output comparison data to obtain power output efficiency deviation data; perform target alignment analysis processing on the power output efficiency deviation data to obtain power output alignment data;

[0025] Step S24: Perform differential quantization analysis on the power output alignment data to obtain power output differential quantization data; perform energy difference analysis on the power output differential quantization data to obtain power energy difference data; perform loss mode identification processing on the power energy difference data to obtain power loss mode data; perform power energy efficiency loss analysis on the power loss mode data to generate loss analysis data;

[0026] Step S25: Dynamically adjust the photovoltaic-thermal collaborative data according to the loss analysis data to generate photovoltaic power compensation data.

[0027] Through historical data collection and dataset division, the present invention establishes a training set and a test set of historical photovoltaic-thermal collaborative data, providing a structured data basis for model training and testing; through model training and testing, a power output prediction model is finally generated, which can accurately predict the photovoltaic power output. Importing the photovoltaic-thermal collaborative data into the power output prediction model to generate predicted power output data will serve as key data for evaluating and optimizing the performance of the photovoltaic system; performing output accuracy calibration processing on the predicted power output data improves the accuracy of power output prediction and ensures the reliability of the power output accuracy calibration data; performing efficiency deviation identification on the power output comparison data clarifies the difference between the actual output of the photovoltaic system and the preset target, providing a basis for further power analysis; performing target alignment analysis processing on the power output efficiency deviation data optimizes the power output to make it closer to the preset target; the analysis of the power output differential quantization data and the power energy difference data provides a quantitative evaluation of the energy output of the photovoltaic system, helping to identify and analyze the deviation of the energy output; performing loss mode identification processing on the power energy difference data enables the identification and analysis of the energy efficiency loss of the photovoltaic system, clarifying the direction for system optimization; dynamically adjusting the photovoltaic-thermal collaborative data according to the loss analysis data to generate photovoltaic power compensation data, which will be used to adjust the photovoltaic system to reduce losses and improve energy efficiency.

[0028] Preferably, step S25 includes the following steps:

[0029] Step S251: Perform power loss location processing on the loss analysis data to obtain power loss location data; monitor the power fluctuation of the photovoltaic-thermal collaborative data according to the power loss location data to obtain power power fluctuation data;

[0030] Step S252: Record the peak load of the power power fluctuation data to obtain power peak load data; identify the power drop characteristics of the power power fluctuation data according to the power peak load data to generate power power drop data; analyze the abnormal conditions of the power power drop data to obtain power abnormal condition data, where the power abnormal condition data includes photovoltaic temperature abnormal data, inverter conversion abnormal data, and current voltage abnormal offset data;

[0031] Step S253: Optimize the photovoltaic module heat conduction path of the photovoltaic-thermal collaborative data according to the photovoltaic temperature abnormal data to generate photovoltaic temperature abnormal adjustment data; adjust the inverter working parameters of the photovoltaic-thermal collaborative data according to the inverter conversion abnormal data to generate inverter conversion abnormal adjustment data; perform dynamic harmonic control on the photovoltaic-thermal collaborative data according to the current voltage abnormal offset data to generate current voltage abnormal offset adjustment data;

[0032] Step S254: Integrate the photovoltaic temperature abnormal adjustment data, the inverter conversion abnormal adjustment data, and the current voltage abnormal offset adjustment data to obtain photovoltaic power compensation data.

[0033] The present invention performs power loss location processing on the loss analysis data to accurately identify the power loss location in the photovoltaic system; monitors the power fluctuation of the photovoltaic-thermal collaborative data using the power loss location data, which helps to monitor and analyze the power change of the photovoltaic system in real time; records the peak load of the power power fluctuation data, providing key reference indicators for the operation of the photovoltaic system; identifies the power drop characteristics of the power power fluctuation data through the power peak load data to further analyze the performance of the photovoltaic system under different load conditions; analyzes the abnormal conditions of the power power drop data, providing a basis for the fault diagnosis and performance optimization of the photovoltaic system; optimizes the photovoltaic module heat conduction path of the photovoltaic-thermal collaborative data according to the photovoltaic temperature abnormal data to improve the heat management efficiency of the photovoltaic module; adjusts the inverter working parameters of the photovoltaic-thermal collaborative data according to the inverter conversion abnormal data, which can optimize the operation efficiency and performance of the inverter; performs dynamic harmonic control on the photovoltaic-thermal collaborative data according to the current voltage abnormal offset data, reducing the harmonic interference in the power system and improving the power quality; integrates the photovoltaic temperature abnormal adjustment data, the inverter conversion abnormal adjustment data, and the current voltage abnormal offset adjustment data, providing a comprehensive power compensation scheme for the photovoltaic system to ensure the stable and efficient operation of the photovoltaic system.

[0034] Preferably, step S3 includes the following steps:

[0035] Step S31: Extract the component information of the photovoltaic system data to obtain photovoltaic component data; identify the arrangement of the photovoltaic component data to obtain photovoltaic component arrangement data; analyze the topological structure of the photovoltaic component arrangement data to generate photovoltaic component topological structure data;

[0036] Step S32: Construct the physical layout of the photovoltaic component topological structure data to generate a 3D layout diagram of the photovoltaic components; identify the connection method of the 3D layout diagram of the photovoltaic components to obtain component connection method data; classify the component connection method data by connection type to obtain component connection type data;

[0037] Step S33: Record the component array spacing of the photovoltaic component topological structure data according to the component connection type data to obtain component array spacing data; analyze the component array direction of the 3D layout diagram of the photovoltaic components according to the component array spacing data to generate component array direction data; measure the tilt angle of the component array direction data to obtain array tilt angle data;

[0038] Step S34: Integrate the component array spacing data, the component array direction data, and the array tilt angle data to obtain photovoltaic array configuration data;

[0039] Step S35: Perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array anomaly data;

[0040] Step S36: Perform adaptive adjustment on the photovoltaic array anomaly data to obtain photovoltaic array adjustment data.

[0041] By extracting the component information of the photovoltaic system data, the present invention can accurately obtain the photovoltaic component data; identify the arrangement of the photovoltaic component data, and generate the photovoltaic component topology structure data through topological structure analysis, which helps to understand the mutual relationship between components and the overall layout of the system; construct the physical layout of the photovoltaic component topology structure data, further classify the connection types, and obtain the component connection type data, which intuitively shows the layout of the photovoltaic system; analyze the component array direction of the three-dimensional layout diagram of the photovoltaic components according to the component array spacing data, and generate the component array direction data; measure the tilt angle of the component array direction data to obtain the array tilt angle data; through the tilt angle measurement, obtaining the array tilt angle data is crucial for optimizing the light reception and system performance of the photovoltaic array; integrate the component array spacing data, the component array direction data, and the array tilt angle data to obtain the photovoltaic array configuration data, providing comprehensive data support for the refined management of the photovoltaic system; perform anomaly detection on the photovoltaic array configuration data to obtain the photovoltaic array anomaly data, which helps to timely discover potential problems in the photovoltaic system; perform adaptive adjustment on the photovoltaic array anomaly data, and improve the overall efficiency and reliability of the photovoltaic system by automatically optimizing the component layout and configuration.

[0042] Preferably, step S35 includes the following steps:

[0043] Step S351: Analyze the occlusion situation between components for the component array spacing data to generate component occlusion situation data; evaluate the light reception rate of the photovoltaic light intensity data according to the component occlusion situation data to obtain the light reception rate evaluation data;

[0044] Step S352: Compare the light reception rate evaluation data with the preset light reception rate data. If the light reception rate evaluation data is less than the preset light reception rate data, generate low light reception rate data; perform anomaly marking on the component array spacing data according to the low light reception rate data to obtain the component array spacing anomaly data;

[0045] Step S353: Measure the light angle for the array tilt angle data to obtain the tilt angle light data; monitor the temperature distribution of the photovoltaic temperature data according to the tilt angle light data to obtain the tilt angle temperature distribution data; analyze the temperature non-uniformity of the tilt angle temperature distribution data to generate the temperature non-uniformity data; record the anomaly of the array tilt angle data according to the temperature non-uniformity data to obtain the array tilt angle anomaly data;

[0046] Step S354: Identify the orientation of the component array direction data to generate array orientation data; calculate the photothermal efficiency of the photovoltaic-thermal collaborative data based on the array orientation data to obtain photothermal efficiency data; extract the low-efficiency data of the photothermal efficiency data to obtain photothermal low-efficiency data; perform anomaly marking on the component array direction data based on the photothermal low-efficiency data to obtain component array direction anomaly data;

[0047] Step S355: Integrate the component array spacing anomaly data, the array tilt angle anomaly data, and the component array direction anomaly data to obtain photovoltaic array anomaly data.

[0048] The present invention analyzes the component array spacing data to generate component occlusion situation data, which helps to identify and evaluate the occlusion problem between components, thereby optimizing the subsequent adjustment of the photovoltaic array; evaluates the light reception rate of the photovoltaic light intensity data based on the component occlusion situation data, enabling an accurate evaluation of the light reception rate of the photovoltaic light intensity data; compares the light reception rate evaluation data with the preset light reception rate data to promptly identify the situation of insufficient light reception rate; and performs anomaly marking on the component array spacing data to obtain component array spacing anomaly data, which will provide a basis for the subsequent adjustment and optimization of the photovoltaic system. Measuring the tilt angle illumination data and analyzing the temperature non-uniformity are of great significance for understanding and improving the temperature performance of photovoltaic components; identifying the orientation of the component array direction data enables the calculation of the photothermal efficiency of the photovoltaic-thermal collaborative data; extracting the low-efficiency data of the photothermal efficiency data provides guidance for improving the photothermal conversion efficiency of the photovoltaic system; integrating the component array spacing anomaly data, the array tilt angle anomaly data, and the component array direction anomaly data helps to comprehensively identify the problems existing in the photovoltaic array and provides comprehensive data support for the performance improvement of the photovoltaic system.

[0049] Preferably, step S36 includes the following steps:

[0050] Step S361: Locate the occlusion area of the component occlusion situation data to obtain occlusion area location data; measure the occlusion shadow area of the occlusion area location data to obtain occlusion shadow area data; automatically adjust the area of the component array spacing anomaly data based on the occlusion area location data and the occlusion shadow area data to obtain spacing anomaly adjustment data;

[0051] Step S362: Measure the tilt angle of the tilt angle illumination data to obtain tilt angle measurement data; record the angle parameters of the tilt angle measurement data based on the temperature non-uniformity data to obtain abnormal tilt angle parameters; adaptively calibrate the array tilt angle anomaly data according to the abnormal tilt angle parameters to obtain tilt angle anomaly adjustment data;

[0052] Step S363: Conduct a lighting path analysis on the array orientation azimuth data to obtain lighting orientation data; perform a radiation azimuth identification on the lighting orientation data to generate lighting radiation azimuth data; perform an adaptive direction repositioning on the component array direction anomaly data based on the lighting radiation azimuth data to obtain array direction anomaly adjustment data;

[0053] Step S364: Integrate the spacing anomaly adjustment data, tilt angle anomaly adjustment data, and array direction anomaly adjustment data to obtain PV array adjustment data.

[0054] The present invention accurately identifies and quantifies the occlusion problem between components through occlusion area positioning and determination of the occlusion shadow area; by using the occlusion area positioning data and occlusion shadow area data, it can automatically adjust the spacing of the component array, which helps to reduce the occlusion effect and improve the overall energy output of the PV array; through the calculation of tilt angle lighting data and analysis of temperature non-uniformity data, abnormal tilt angle parameters are recorded; and through adaptive angle calibration, the lighting reception efficiency of the PV modules is optimized; conduct a lighting path analysis on the array orientation azimuth data to obtain lighting orientation data and clarify the lighting path information of the lighting orientation; perform a radiation azimuth identification on the lighting orientation data to generate lighting radiation azimuth data and clarify the lighting radiation azimuth situation; perform an adaptive direction repositioning on the component array direction anomaly data based on the lighting radiation azimuth data to adaptively reposition the component array direction to enhance the lighting utilization rate of the PV system; integrating the spacing anomaly adjustment data, tilt angle anomaly adjustment data, and array direction anomaly adjustment data helps to comprehensively improve the performance of the PV array and ensure that the PV system can achieve optimal energy capture under different environmental conditions.

[0055] Preferably, step S4 includes the following steps:

[0056] Step S41: Construct a PV performance evaluation model based on the PV power compensation data and PV array adjustment data to obtain a PV performance evaluation pre-model, and use the PV power compensation data and PV array adjustment data to train the PV performance evaluation pre-model to obtain a PV performance evaluation training model;

[0057] Step S42: Conduct a model cross-validation evaluation on the PV performance evaluation training model to obtain PV performance model evaluation data; adjust the model parameters of the PV performance evaluation training model through the PV performance model evaluation data to obtain a PV performance evaluation model;

[0058] Step S43: Conduct an environmental adaptation performance and efficiency analysis on the PV system data based on the PV performance evaluation model to obtain environmental adaptation performance and efficiency data; conduct a PV module energy efficiency evaluation on the PV system data based on the environmental adaptation performance and efficiency data to obtain PV module energy efficiency evaluation data;

[0059] Step S44: Using real-time feedback technology, monitor and feedback the photovoltaic system data in real time to generate photovoltaic monitoring feedback data; perform intelligent optimization control on the photovoltaic system data based on the photovoltaic module energy efficiency evaluation data and the photovoltaic monitoring feedback data to obtain photovoltaic optimization control data;

[0060] Step S45: Integrate the photovoltaic optimization control data and the photovoltaic monitoring feedback data to obtain a photovoltaic control optimization report.

[0061] The present invention combines photovoltaic power compensation data and photovoltaic array adjustment data to construct a pre-model for photovoltaic performance evaluation, and obtains a trained photovoltaic performance evaluation model through training, which provides a scientific method for the performance analysis of photovoltaic systems; through model cross-validation evaluation, the model parameters are further adjusted to ensure the accuracy and reliability of the evaluation results; using the photovoltaic performance evaluation model to perform environmental adaptation performance and efficiency analysis helps to evaluate the performance of photovoltaic systems under different environmental conditions; based on the environmental adaptation performance and efficiency data, perform photovoltaic module energy efficiency evaluation, which provides a data basis for the performance optimization of photovoltaic modules; through real-time feedback technology, generate photovoltaic monitoring feedback data, which can monitor the status of the photovoltaic system in real time and detect and handle problems in a timely manner; combining the photovoltaic module energy efficiency evaluation data and the photovoltaic monitoring feedback data to perform intelligent optimization control helps to improve the overall operation efficiency and stability of the photovoltaic system; integrating the photovoltaic optimization control data and the photovoltaic monitoring feedback data to obtain a photovoltaic control optimization report provides comprehensive reference and guidance for the operation management and decision-making of photovoltaic systems.

[0062] In this specification, a modular photovoltaic device is provided for performing the above-mentioned modular photovoltaic control method. The modular photovoltaic device includes:

[0063] A data acquisition module, configured to acquire photovoltaic system data; extract the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; perform intensity evaluation on the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; perform intensity clustering on the photovoltaic illumination intensity data to obtain illumination intensity clustering data; extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; perform optothermal collaborative analysis on the photovoltaic temperature data according to the illumination intensity clustering data to generate photovoltaic optothermal collaborative data;

[0064] A photovoltaic power analysis module, configured to predict the photovoltaic power output based on the photovoltaic optothermal collaborative data to generate predicted power output data; compare the predicted power output data with a preset power target to generate power output comparison data; perform power loss analysis on the power output comparison data to generate loss analysis data; perform dynamic power compensation adjustment on the photovoltaic optothermal collaborative data according to the loss analysis data to generate photovoltaic power compensation data;

[0065] The photovoltaic array adjustment module is used to extract the component information of the photovoltaic system data to obtain the photovoltaic component data; perform array configuration analysis on the photovoltaic component data to obtain the photovoltaic array configuration data; perform anomaly detection on the photovoltaic array configuration data to obtain the photovoltaic array anomaly data; perform adaptive adjustment on the photovoltaic array anomaly data to obtain the photovoltaic array adjustment data;

[0066] The photovoltaic monitoring and control module is used to construct a photovoltaic performance evaluation model by combining the photovoltaic power compensation data and the photovoltaic array adjustment data, and generate a photovoltaic performance evaluation model; use the photovoltaic performance evaluation model to evaluate the component energy efficiency of the photovoltaic system data to generate the photovoltaic component energy efficiency evaluation data; perform real-time monitoring and control on the photovoltaic system data according to the photovoltaic component energy efficiency evaluation data to generate a photovoltaic control optimization report.

[0067] In the present invention, the data acquisition module obtains the illumination parameter information of the photovoltaic system, accurately evaluates the photovoltaic illumination intensity, and further performs illumination intensity clustering to provide an accurate illumination data basis for subsequent photothermal collaborative analysis; analyzes the photovoltaic temperature data in combination with the illumination intensity clustering data to generate photovoltaic photothermal collaborative data, which can accurately predict the photovoltaic power output and improve the prediction accuracy. The photovoltaic power analysis module predicts the power output by using the photovoltaic photothermal collaborative data, compares it with the preset power target to generate power output comparison data, and performs power loss analysis to provide a basis for dynamic power compensation; adjusts the photovoltaic photothermal collaborative data according to the loss analysis data to generate photovoltaic power compensation data, which helps to optimize the power output of the photovoltaic system, reduce losses, and improve the photovoltaic utilization efficiency. The photovoltaic array adjustment module can identify anomalies in the photovoltaic array by extracting the photovoltaic component data and performing array configuration analysis; and generate the photovoltaic array adjustment data through adaptive adjustment to further improve the overall performance of the photovoltaic system. The photovoltaic monitoring and control module integrates the photovoltaic power compensation data and the photovoltaic array adjustment data to construct a photovoltaic performance evaluation model to ensure accurate evaluation of the energy efficiency of the photovoltaic components and generate the photovoltaic component energy efficiency evaluation data; use the photovoltaic performance evaluation model to perform real-time monitoring and control on the photovoltaic system data, which can generate a photovoltaic control optimization report to guide the actual operation and ensure that the photovoltaic system operates in the best state, thereby improving the stability and reliability of the photovoltaic system. Therefore, the present invention realizes the photothermal collaborative analysis of the photovoltaic through the Internet of Things technology, data analysis technology, adaptive control technology and digital twin technology to realize the adaptive adjustment of the photovoltaic array configuration; improve the photovoltaic power output performance. Description of the Drawings

[0068] Figure 1 It is a schematic diagram of the step flow of a modular photovoltaic control method;

[0069] Figure 2 It isFigure 1 Schematic diagram of the detailed implementation steps of step S3 in

[0070] Figure 3 For Figure 2 Schematic diagram of the detailed implementation steps of step S36 in

[0071] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific implementation manners

[0072] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0073] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus the repeated description thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0074] It should be understood that although the terms "first", "second", etc. may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0075] To achieve the above object, please refer to Figures 1 to 3 , a modular photovoltaic control method, the method includes the following steps:

[0076] Step S1: Obtain photovoltaic system data; extract the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; perform intensity evaluation on the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; perform intensity clustering on the photovoltaic illumination intensity data to obtain illumination intensity clustering data; extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; perform optothermal collaborative analysis on the photovoltaic temperature data according to the illumination intensity clustering data to generate photovoltaic optothermal collaborative data;

[0077] Step S2: Based on the photovoltaic-thermal collaborative data, perform photovoltaic power output prediction to generate predicted power output data; compare the predicted power output data with the preset power target to generate power output comparison data; conduct power loss analysis on the power output comparison data to generate loss analysis data; perform dynamic power compensation adjustment on the photovoltaic-thermal collaborative data according to the loss analysis data to generate photovoltaic power compensation data;

[0078] Step S3: Extract the component information of the photovoltaic system data to obtain photovoltaic component data; conduct array configuration analysis on the photovoltaic component data to obtain photovoltaic array configuration data; perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array anomaly data; perform adaptive adjustment on the photovoltaic array anomaly data to obtain photovoltaic array adjustment data;

[0079] Step S4: Construct a photovoltaic performance evaluation model with the photovoltaic power compensation data and the photovoltaic array adjustment data to generate a photovoltaic performance evaluation model; use the photovoltaic performance evaluation model to conduct component energy efficiency evaluation on the photovoltaic system data to generate photovoltaic component energy efficiency evaluation data; perform real-time monitoring and control on the photovoltaic system data according to the photovoltaic component energy efficiency evaluation data to generate a photovoltaic control optimization report.

[0080] The present invention obtains the illumination parameter information of the photovoltaic system, accurately evaluates the photovoltaic illumination intensity, and further conducts illumination intensity clustering to provide an accurate illumination data basis for subsequent photovoltaic-thermal collaborative analysis; analyzes the photovoltaic temperature data in combination with the illumination intensity clustering data to generate photovoltaic-thermal collaborative data, which can accurately predict the photovoltaic power output and improve the prediction accuracy; uses the photovoltaic-thermal collaborative data to perform power output prediction, compares it with the preset power target to generate power output comparison data, and conducts power loss analysis, providing a basis for dynamic power compensation; adjusts the photovoltaic-thermal collaborative data according to the loss analysis data to generate photovoltaic power compensation data, which helps to optimize the power output of the photovoltaic system, reduce losses, and improve the photovoltaic utilization efficiency. Extracting the photovoltaic component data and conducting array configuration analysis can identify anomalies in the photovoltaic array; and through adaptive adjustment, generate photovoltaic array adjustment data to further improve the overall performance of the photovoltaic system; integrate the photovoltaic power compensation data and the photovoltaic array adjustment data to construct a photovoltaic performance evaluation model to ensure accurate evaluation of the energy efficiency of the photovoltaic components and generate photovoltaic component energy efficiency evaluation data; use the photovoltaic performance evaluation model to perform real-time monitoring and control on the photovoltaic system data, which can generate a photovoltaic control optimization report to guide actual operations and ensure that the photovoltaic system operates in the best state, thereby improving the stability and reliability of the photovoltaic system. Therefore, the present invention realizes photovoltaic-thermal collaborative analysis of the photovoltaic through Internet of Things technology, data analysis technology, adaptive control technology, and digital twin technology to achieve adaptive adjustment of the photovoltaic array configuration; improve the photovoltaic power output performance.

[0081] In an embodiment of the present invention, with reference to Figure 1 as described, it is a schematic flow chart of the steps of a modular photovoltaic control method of the present invention. In this example, the modular photovoltaic control method includes the following steps:

[0082] Step S1: Obtain photovoltaic system data; extract the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; perform intensity evaluation on the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; perform intensity clustering on the photovoltaic illumination intensity data to obtain illumination intensity clustering data; extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; perform optothermal collaborative analysis on the photovoltaic temperature data according to the illumination intensity clustering data to generate photovoltaic optothermal collaborative data;

[0083] In an embodiment of the present invention, sensors are used to obtain photovoltaic system data, where the photovoltaic system data includes illumination parameter information and component information; the obtained photovoltaic system data is preprocessed by using photovoltaic big data analysis technology, such as data cleaning, interpolation to fill in missing data, filtering to remove noise data, and deduplication to delete duplicate data; illumination feature extraction technology is used to extract the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; intensity evaluation is performed on the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; an improved SemiBoost weather clustering method is adopted, and combined with the chaotic cross and particle swarm optimization algorithm (CC-PSO), clustering analysis is performed on the illumination intensity data to obtain illumination intensity clustering data; the temperature data of the photovoltaic system data is extracted to obtain photovoltaic temperature data; temperature perception technology is used to extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; through optothermal technology, and considering the influence of temperature, humidity, and irradiance on the photovoltaic output power, optothermal collaborative analysis is performed on the photovoltaic temperature data to generate photovoltaic optothermal collaborative data.

[0084] Step S2: Perform photovoltaic power output prediction based on the photovoltaic optothermal collaborative data to generate predicted power output data; compare the predicted power output data with a preset power target to generate power output comparison data; perform power loss analysis on the power output comparison data to generate loss analysis data; perform dynamic power compensation adjustment on the photovoltaic optothermal collaborative data according to the loss analysis data to generate photovoltaic power compensation data;

[0085] In the embodiments of the present invention, a photovoltaic power prediction method based on LSSVM (Least Squares Support Vector Machine) is adopted, and multi-variable input conditions are introduced, including solar irradiance, ambient temperature, wind speed, humidity, etc., comprehensively considering various factors affecting photovoltaic power output; then, using multi-step prediction technology, photovoltaic power output prediction is carried out based on photovoltaic-thermal collaborative data to generate predicted power output data; using differential comparison technology, the predicted power output data is compared with a preset power target to generate power output comparison data; adopting a theoretical line loss calculation method, such as the root mean square current method, to analyze the power loss of the power output comparison data. Specifically, the reasons for the electrical energy loss in the line are calculated; according to the loss analysis data, dynamic power compensation adjustment is carried out on the photovoltaic-thermal collaborative data. Specifically, the adjustment can be carried out through dynamic reactive power compensation technology, such as SVC (Static Var Compensator) or STATCOM (Static Synchronous Compensator), to dynamically compensate the reactive power of the power transmission and distribution system to improve the power quality and reduce losses, thereby generating photovoltaic power compensation data.

[0086] Step S3: Extract the component information of the photovoltaic system data to obtain photovoltaic component data; perform array configuration analysis on the photovoltaic component data to obtain photovoltaic array configuration data; perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array anomaly data; perform adaptive adjustment on the photovoltaic array anomaly data to obtain photovoltaic array adjustment data;

[0087] In the embodiments of the present invention, information recognition technology is used to extract the component information of the photovoltaic system data to obtain photovoltaic component data; optimization algorithms such as genetic algorithms and artificial intelligence are used to perform array configuration analysis on the photovoltaic component data. Specifically, the pvlib.pvsystem module in the pvlib-python library is used for array configuration analysis to obtain photovoltaic array configuration data; through an anomaly detection algorithm, anomaly detection is performed on the photovoltaic array configuration data, specifically detecting the anomaly points or anomaly intervals in the photovoltaic array configuration data; through the perturbation observation method and PWM technology, adaptive adjustment is performed on the photovoltaic array anomaly data to obtain photovoltaic array adjustment data.

[0088] Step S4: Construct a photovoltaic performance evaluation model with the photovoltaic power compensation data and the photovoltaic array adjustment data to generate a photovoltaic performance evaluation model; use the photovoltaic performance evaluation model to evaluate the component energy efficiency of the photovoltaic system data to generate photovoltaic component energy efficiency evaluation data; perform real-time monitoring and control on the photovoltaic system data according to the photovoltaic component energy efficiency evaluation data to generate a photovoltaic control optimization report.

[0089] In an embodiment of the present invention, System Advisor Model (SAM) software is used to comprehensively simulate photovoltaic power compensation data and photovoltaic array adjustment data. Specifically, the performance of the photovoltaic array under different working conditions is simulated to determine the energy output of the photovoltaic array; based on the energy output of the photovoltaic array and using a deep learning algorithm, a photovoltaic performance evaluation model is constructed using the photovoltaic power compensation data and the photovoltaic array adjustment data to obtain a photovoltaic performance evaluation model; high-performance IV scanning diagnostic technology is used to evaluate the component energy efficiency of the photovoltaic system data based on the photovoltaic performance evaluation model to generate photovoltaic component energy efficiency evaluation data; and intelligent monitoring and control technology is used to monitor and control the photovoltaic system data in real time according to the photovoltaic component energy efficiency evaluation data to generate a photovoltaic control optimization report.

[0090] Preferably, step S1 comprises the following steps:

[0091] Step S11: performing illumination feature recognition on photovoltaic system data to obtain photovoltaic illumination feature data; performing parameter information extraction on the photovoltaic illumination feature data to obtain photovoltaic illumination parameter information;

[0092] Step S12: performing light intensity tracking processing on the photovoltaic illumination parameter information in each time period to obtain photovoltaic light intensity tracking data; performing light intensity integral calculation on the photovoltaic light intensity tracking data to obtain photovoltaic illumination intensity data;

[0093] Step S13: performing time series processing on the photovoltaic light intensity data to obtain light intensity time series data; performing nonlinear dimensionality reduction on the light intensity time series data to generate time series dimensionality reduction data; performing hierarchical clustering analysis on the photovoltaic light intensity data based on the time series dimensionality reduction data to obtain light intensity clustering data; extracting temperature data of the photovoltaic system data to obtain photovoltaic temperature data;

[0094] Step S14: Performing photothermal synergy analysis on the photovoltaic temperature data according to the light intensity clustering data to generate photovoltaic photothermal synergy data.

[0095] In the embodiments of the present invention, the light characteristic recognition technology is used to recognize the light characteristics of the photovoltaic system data to obtain the photovoltaic light characteristics; the parameter information of the photovoltaic light characteristics is extracted to obtain the photovoltaic light parameter information; the hourly light intensity tracking technology is used to perform hourly light intensity tracking processing on the photovoltaic light parameter information to obtain the photovoltaic light intensity tracking data; the light intensity integration calculation is performed on the photovoltaic light intensity tracking data to obtain the photovoltaic light intensity data; the time series analysis technology is used to perform time series processing on the photovoltaic light intensity data to generate the light intensity time series data; through the non-linear dimensionality reduction technology, such as principal component analysis (PCA) or linear discriminant analysis (LDA), the dimensionality of the time series data is reduced, the key features are extracted, the data structure is simplified, and at the same time the key information of the photovoltaic light is retained to generate the time series dimensionality reduction data; the hierarchical clustering analysis technology is used to cluster the time series dimensionality reduction data to form the light intensity clustering data; the temperature data of the photovoltaic system data is extracted to obtain the photovoltaic temperature data; the photothermal co-analysis is performed on the photovoltaic temperature data according to the light intensity clustering data; by analyzing the performance of the photovoltaic module under different light and temperature conditions, the photovoltaic photothermal co-data is generated.

[0096] Preferably, step S14 includes the following steps:

[0097] Step S141: Perform timestamp synchronization processing on the light intensity clustering data to obtain the light intensity clustering synchronization data; perform thermal response characteristic analysis on the photovoltaic temperature data according to the light intensity clustering synchronization data to obtain the photovoltaic temperature thermal response data;

[0098] Step S142: Identify the temperature change profile of the photovoltaic temperature thermal response data to generate the photovoltaic temperature profile data; capture the sensitivity temperature fluctuation of the photovoltaic temperature profile data to obtain the photovoltaic temperature fluctuation data;

[0099] Step S143: Perform light energy characteristic coupling processing on the photovoltaic temperature fluctuation data and the light intensity clustering data to generate the light energy characteristic coupling data; perform synchronous analysis of the thermo-optical effect on the light energy characteristic coupling data to obtain the photovoltaic thermo-optical effect synchronous data;

[0100] Step S144: Record the photothermal response time of the photovoltaic thermo-optical effect synchronous data to obtain the photothermal response time data; calculate the photothermal conversion efficiency of the photovoltaic thermo-optical effect synchronous data according to the photothermal response time data to obtain the photothermal conversion efficiency data; perform photothermal co-analysis on the photovoltaic temperature data according to the photothermal conversion efficiency data to generate the photovoltaic photothermal co-data.

[0101] In the embodiments of the present invention, data mining technology is adopted to extract light intensity data, and through timestamp synchronization processing, light intensity clustering synchronization data is obtained; then, using a photovoltaic module simulation simulator, combined with ambient temperature and solar irradiance intensity data, thermal response characteristics analysis of photovoltaic temperature data is carried out to obtain photovoltaic temperature thermal response data; temperature change profile recognition of the photovoltaic temperature thermal response data is carried out through trend surface analysis method to identify the influence of panel temperature and radiation amount change on power generation, and photovoltaic temperature profile data is generated; at the same time, high-precision sensors and data collectors are deployed to monitor the temperature and radiation amount of the photovoltaic panel in real time, and photovoltaic temperature fluctuation data is captured. Further, the photovoltaic temperature fluctuation data is combined with the light intensity clustering data for optical energy feature coupling processing to generate optical energy feature coupling data; using the silicon-based thermo-optic phase shifter technology, thermo-optic effect synchronization analysis of the optical energy feature coupling data is carried out to obtain photovoltaic thermo-optic effect synchronization data, and the photothermal response time data is recorded; according to the photothermal response time data, the photothermal conversion efficiency of the photovoltaic thermo-optic effect synchronization data is calculated to obtain photothermal conversion efficiency data; and according to the photothermal conversion efficiency data, photothermal collaborative analysis of the photovoltaic temperature data is carried out to generate photovoltaic photothermal collaborative data.

[0102] Preferably, step S2 includes the following steps:

[0103] Step S21: Collect historical data of the photovoltaic photothermal collaborative data to obtain historical photovoltaic photothermal collaborative data; divide the historical photovoltaic photothermal collaborative data set to generate a historical data training set and a historical data test set; train a model on the historical data training set to generate a power output prediction model; test the power output prediction model according to the historical data test set to generate a power output prediction model;

[0104] Step S22: Import the photovoltaic photothermal collaborative data into the power output prediction model for photovoltaic power output prediction to generate predicted power output data;

[0105] Step S23: Perform output accuracy calibration processing on the predicted power output data to obtain power output accuracy calibration data; compare the power output accuracy calibration data with the preset power target to generate power output comparison data; perform efficiency deviation identification on the power output comparison data to obtain power output efficiency deviation data; perform target alignment analysis processing on the power output efficiency deviation data to obtain power output alignment data;

[0106] Step S24: Perform differential quantization analysis on the power output alignment data to obtain power output differential quantization data; perform energy difference analysis on the power output differential quantization data to obtain power energy difference data; perform loss mode identification processing on the power energy difference data to obtain power loss mode data; perform power energy efficiency loss analysis on the power loss mode data to generate loss analysis data;

[0107] Step S25: Dynamically adjust the photovoltaic and solar thermal collaborative data for power compensation according to the loss analysis data to generate photovoltaic power compensation data.

[0108] In the embodiments of the present invention, the operation data of the photovoltaic-thermal system is collected through a distributed photovoltaic data acquisition system. These data include, but are not limited to, the output power of the photovoltaic panel, ambient temperature, light intensity, etc. The collected data will be preprocessed to ensure the data quality. The preprocessing steps include data cleaning, removing outliers and missing values, and normalization processing. Then, the train_test_split function in the scikit-learn library is used to divide the dataset into a training set and a test set, usually in a ratio of 70% and 30%. A deep learning algorithm is selected, such as a long short-term memory network (LSTM), which is a neural network particularly suitable for processing time series data and can capture the time dependence in the data. The K-fold cross-validation method is used to optimize the model parameters. This is a technique for evaluating the generalization ability of the model. By dividing the training set into K subsets, using one subset as the validation set each time and the rest as the training set, repeating K times and taking the average to evaluate the model performance. After the model training is completed, the test set is used to evaluate the model. The evaluation metrics include mean squared error (MSE), mean absolute error (MAE), etc. According to the evaluation results, the model parameters are further adjusted to improve the prediction accuracy of the model. The preprocessed photovoltaic-thermal collaborative data is input into the trained model to obtain the power output prediction result. The prediction result can be displayed through visualization tools such as Matplotlib to intuitively present the change trend of the predicted power output data. The prediction result is processed by accuracy calibration, introducing an error correction algorithm or using a convolutional neural network (CNN) to improve the prediction accuracy. At the same time, the power output accuracy calibration data is compared with the preset power target. Specifically, the difference between the predicted value and the actual value is calculated to generate the power output comparison data. The efficiency deviation of the power output comparison data is calculated to identify the power output efficiency deviation data. The efficiency deviation data is compared with the preset performance target. Through statistical analysis methods, such as analysis of variance or t-test, it is determined whether the deviation is within the acceptable range to generate the power output alignment data.Perform differential quantization analysis on the power output alignment data to obtain power output differential quantization data; use quantization methods such as regression analysis to perform in-depth quantization analysis on the power output alignment data, thereby quantifying the difference between the power output and the actual power output to obtain power output differential quantization data; perform in-depth energy difference analysis on the power output differential quantization data, and calculate the specific values of energy loss and efficiency reduction to obtain power energy difference data; perform pattern recognition processing on the power energy difference data, using clustering analysis or anomaly detection algorithms in machine learning to identify the patterns and causes of power loss to obtain power loss pattern data; perform power energy efficiency loss analysis on the power loss pattern data to generate loss analysis data; according to the loss analysis data, adopt an adaptive control strategy and introduce an intelligent quantization grading method to perform dynamic power compensation adjustment on the photovoltaic-thermal collaborative data. The adaptive control strategy can adjust the control parameters according to real-time data, while the intelligent quantization grading method can perform grading processing on the data; finally, generate photovoltaic power compensation data.

[0109] Preferably, step S25 includes the following steps:

[0110] Step S251: Perform power loss localization processing to obtain power loss localization data; monitor the power fluctuation of the photovoltaic-thermal collaborative data according to the power loss localization data to obtain power fluctuation data;

[0111] Step S252: Record the peak load of the power fluctuation data to obtain peak load data; identify the power drop characteristics of the power fluctuation data according to the peak load data to generate power drop data; perform anomaly analysis on the power drop data to obtain power anomaly data, where the power anomaly data includes photovoltaic temperature anomaly data, inverter conversion anomaly data, and current-voltage abnormal offset data;

[0112] Step S253: Optimize the photovoltaic module heat conduction path of the photovoltaic-thermal collaborative data according to the photovoltaic temperature anomaly data to generate photovoltaic temperature anomaly adjustment data; adjust the inverter operating parameters of the photovoltaic-thermal collaborative data according to the inverter conversion anomaly data to generate inverter conversion anomaly adjustment data; perform dynamic harmonic control on the photovoltaic-thermal collaborative data according to the current-voltage abnormal offset data to generate current-voltage abnormal offset adjustment data;

[0113] Step S254: Integrate the photovoltaic temperature anomaly adjustment data, the inverter conversion anomaly adjustment data, and the current-voltage abnormal offset adjustment data to obtain photovoltaic power compensation data.

[0114] In the embodiments of the present invention, power fluctuation monitoring technology, such as real-time monitoring and early warning technology in power system stability analysis, is adopted to locate the loss analysis data to obtain power loss location data; and power fluctuation monitoring is performed on the photovoltaic-thermal collaborative data according to the power loss location data to obtain power fluctuation data; through data analysis technology, peak load recording is performed on the power fluctuation data to obtain peak load data; an anomaly analysis method is used to deeply analyze the power drop data to identify anomalies such as abnormal photovoltaic temperature, abnormal inverter conversion, and abnormal current-voltage offset; according to the abnormal photovoltaic temperature data, thermal analysis and design optimization technology of photovoltaic modules are adopted to improve the heat dissipation of photovoltaic modules, optimize the heat conduction path of photovoltaic modules, and generate abnormal photovoltaic temperature adjustment data; according to the abnormal inverter conversion data, the working parameters of the inverter are adjusted to generate abnormal inverter conversion adjustment data; for the abnormal current-voltage offset data, an adaptive notch filter (ANF) technology is applied for dynamic harmonic control to optimize the current-voltage waveform of the power system and generate abnormal current-voltage offset adjustment data; finally, the abnormal photovoltaic temperature adjustment data, abnormal inverter conversion adjustment data, and abnormal current-voltage offset adjustment data are integrated to form photovoltaic power compensation data.

[0115] As an example of the present invention, refer to Figure 2 As shown, in this example, step S3 includes:

[0116] Step S31: Extract the component information of the photovoltaic system data to obtain photovoltaic module data; identify the arrangement of the photovoltaic module data to obtain photovoltaic module arrangement data; perform topological structure analysis on the photovoltaic module arrangement data to generate photovoltaic module topological structure data;

[0117] Step S32: Construct the physical layout of the photovoltaic module topological structure data to generate a three-dimensional layout diagram of the photovoltaic module; identify the connection method of the three-dimensional layout diagram of the photovoltaic module to obtain component connection method data; classify the component connection method data by connection type to obtain component connection type data;

[0118] Step S33: Record the component array spacing of the photovoltaic module topological structure data according to the component connection type data to obtain component array spacing data; analyze the component array direction of the three-dimensional layout diagram of the photovoltaic module according to the component array spacing data to generate component array direction data; measure the tilt angle of the component array direction data to obtain array tilt angle data;

[0119] Step S34: Integrate the component array spacing data, component array direction data, and array tilt angle data to obtain photovoltaic array configuration data;

[0120] Step S35: Perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array anomaly data;

[0121] Step S36: Perform adaptive adjustment on the photovoltaic array anomaly data to obtain photovoltaic array adjustment data.

[0122] In the embodiment of the present invention, the visual AI + detection technology is used to comprehensively extract information of photovoltaic modules to obtain photovoltaic module data; through image processing and machine learning algorithms, the arrangement of photovoltaic modules is recognized to generate photovoltaic module arrangement data; further, the photovoltaic array topology reconstruction method is applied to analyze the topological structure of photovoltaic modules to generate photovoltaic module topological structure data; using 3D design software such as Candela3D, according to the photovoltaic module topological structure data, a 3D layout diagram of photovoltaic modules is constructed; through image recognition, the component connection method is recognized to obtain component connection method data; a classification algorithm is used to analyze the component connection method data to obtain component connection type data; based on the component connection type data, the component array spacing in the photovoltaic module topological structure data is recorded to obtain component array spacing data; combining the component array spacing data, the 3D layout diagram of photovoltaic modules is analyzed to generate component array direction data; through geometric analysis and angle measurement technology, the array tilt angle data is obtained; the component array spacing data, the component array direction data, and the array tilt angle data are integrated to form photovoltaic array configuration data; a photovoltaic array fault diagnosis algorithm, such as the fault diagnosis research based on CNN-LSTM, is used to perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array anomaly data; finally, according to the photovoltaic array anomaly data, adaptive adjustment is performed, such as the maximum power control of the photovoltaic array based on parameter adaptive adjustment, to obtain photovoltaic array adjustment data.

[0123] Preferably, step S35 includes the following steps:

[0124] Step S351: Analyze the inter-component occlusion situation of the component array spacing data to generate component occlusion situation data; evaluate the light reception rate of the photovoltaic light intensity data according to the component occlusion situation data to obtain light reception rate evaluation data;

[0125] Step S352: Compare the light reception rate evaluation data with the preset light reception rate data. If the light reception rate evaluation data is less than the preset light reception rate data, generate low light reception rate data; perform anomaly marking on the component array spacing data according to the low light reception rate data to obtain component array spacing anomaly data;

[0126] Step S353: measuring the illumination angle of the array tilt angle data to obtain tilt angle illumination data; monitoring the temperature distribution of the photovoltaic temperature data according to the tilt angle illumination data to obtain tilt angle temperature distribution data; performing temperature non-uniformity analysis on the tilt angle temperature distribution data to generate temperature non-uniformity data; recording abnormalities of the array tilt angle data according to the temperature non-uniformity data to obtain array tilt angle abnormality data;

[0127] Step S354: performing orientation and orientation identification on the component array direction data to generate array orientation and orientation data; performing photothermal efficiency calculation on the photovoltaic and photothermal synergy data according to the array orientation and orientation data to obtain photothermal efficiency data; extracting low efficiency data of the photothermal efficiency data to obtain photothermal low efficiency data; performing abnormal marking on the component array direction data according to the photothermal low efficiency data to obtain component array direction abnormal data;

[0128] Step S355: Integrate the abnormal data of the component array spacing, the abnormal data of the array tilt angle and the abnormal data of the component array direction to obtain the abnormal data of the photovoltaic array.

[0129] In an embodiment of the present invention, infrared thermal imaging technology is used to scan a photovoltaic module array to identify the obstruction between modules and obtain a module analysis thermal image; the position and size of the obstruction are determined through the component analysis thermal image, and then its impact on light reception is evaluated; an obstruction recognition algorithm based on multi-resolution feature self-selection is used to perform data analysis on the obstruction to generate module obstruction data; the temperature data and obstruction data of the photovoltaic module are combined, and the non-uniform temperature photovoltaic module thermoelectric loss method is used to evaluate the light reception rate to obtain light reception rate evaluation data; the light reception rate evaluation data is compared with the preset light reception rate data. If the light reception rate evaluation data is lower than the preset light reception rate data, an intelligent algorithm, such as an obstruction recognition algorithm based on a convolutional neural network, is used to mark the module array spacing data as abnormal and obtain module array spacing abnormal data. The photovoltaic array fault diagnosis algorithm is used to measure the illumination angle of the array tilt angle data. The temperature non-uniformity analysis technology is used in combination with the temperature sensor data to monitor the temperature distribution of the photovoltaic modules and generate temperature non-uniformity data. The performance evaluation and efficiency improvement method of photovoltaic modules is used to identify the orientation of the module array direction data and generate array orientation data. The photothermal efficiency data is obtained through photothermal efficiency calculation, and the low-efficiency data is extracted to mark the module array direction data as abnormal. Finally, the abnormal data of the module array spacing, the abnormal data of the array tilt angle and the abnormal data of the module array direction are integrated, and the photovoltaic array fault diagnosis algorithm is used to obtain the abnormal data of the photovoltaic array.

[0130] As an example of the present invention, refer to Figure 3As shown, in this example, step S36 includes:

[0131] Step S361: Locate the occluded area for the component occlusion situation data to obtain the occluded area location data; measure the occluded shadow area for the occluded area location data to obtain the occluded shadow area data; automatically adjust the area of the component array spacing anomaly data based on the occluded area location data and the occluded shadow area data to obtain the spacing anomaly adjustment data;

[0132] Step S362: Measure the tilt angle for the tilt angle illumination data to obtain the tilt angle measurement data; record the angle parameters for the tilt angle measurement data according to the temperature non-uniformity data to obtain the abnormal tilt angle parameters; adaptively calibrate the array tilt angle anomaly data according to the abnormal tilt angle parameters to obtain the tilt angle anomaly adjustment data;

[0133] Step S363: Analyze the illumination path for the array orientation azimuth data to obtain the illumination orientation data; identify the radiation azimuth for the illumination orientation data to generate the illumination radiation azimuth data; adaptively reposition the component array direction anomaly data according to the illumination radiation azimuth data to obtain the array direction anomaly adjustment data;

[0134] Step S364: Integrate the spacing anomaly adjustment data, the tilt angle anomaly adjustment data, and the array direction anomaly adjustment data to obtain the photovoltaic array adjustment data.

[0135] In the embodiments of the present invention, the occlusion area positioning technology is adopted to accurately identify the occlusion situation of components. By analyzing the relative position relationship between the occluder and the photovoltaic module, detailed occlusion area positioning data is obtained. Then, the occlusion shadow area measurement technology is used to accurately calculate the shadow area of the identified occlusion area, generating occlusion shadow area data. Combining the occlusion area positioning data and the occlusion shadow area data, the regional area automatic adjustment technology is applied to intelligently adjust the abnormal data of the component array spacing, optimize the spacing between components, and obtain the abnormal spacing adjustment data. The tilt angle measurement technology is used to accurately measure the tilt angle illumination data, obtaining the tilt angle measurement data. Combining the temperature non-uniformity data, the angle parameters of the tilt angle measurement data are recorded to form abnormal tilt angle parameters. Based on the abnormal tilt angle parameters, the adaptive angle calibration technology is adopted to accurately calibrate the abnormal data of the array tilt angle, obtaining the abnormal tilt angle adjustment data. Further, the illumination path analysis technology is used to deeply analyze the array orientation azimuth data, obtaining the illumination orientation data. Through the radiation azimuth identification technology, the illumination orientation data is processed to generate the illumination radiation azimuth data. According to the illumination radiation azimuth data, the adaptive direction repositioning technology is used to intelligently adjust the abnormal data of the component array direction, obtaining the abnormal array direction adjustment data. Finally, through the photovoltaic array adjustment data integration technology, the abnormal spacing adjustment data, the abnormal tilt angle adjustment data, and the abnormal array direction adjustment data are comprehensively analyzed and integrated to form the photovoltaic array adjustment data.

[0136] Preferably, step S4 includes the following steps:

[0137] Step S41: Construct a photovoltaic performance evaluation model based on the photovoltaic power compensation data and the photovoltaic array adjustment data to obtain a preliminary photovoltaic performance evaluation model, and use the photovoltaic power compensation data and the photovoltaic array adjustment data to train the preliminary photovoltaic performance evaluation model to obtain a trained photovoltaic performance evaluation model;

[0138] Step S42: Conduct a model cross-validation evaluation on the trained photovoltaic performance evaluation model to obtain photovoltaic performance model evaluation data; adjust the model parameters of the trained photovoltaic performance evaluation model through the photovoltaic performance model evaluation data to obtain a photovoltaic performance evaluation model;

[0139] Step S43: Conduct an environmental adaptability energy efficiency analysis on the photovoltaic system data based on the photovoltaic performance evaluation model to obtain environmental adaptability energy efficiency data; conduct a photovoltaic module energy efficiency evaluation on the photovoltaic system data based on the environmental adaptability energy efficiency data to obtain photovoltaic module energy efficiency evaluation data;

[0140] Step S44: Using real-time feedback technology, monitor and feedback the photovoltaic system data in real time to generate photovoltaic monitoring feedback data; perform intelligent optimization control on the photovoltaic system data based on the photovoltaic module energy efficiency evaluation data and the photovoltaic monitoring feedback data to obtain photovoltaic optimization control data;

[0141] Step S45: Integrate the photovoltaic optimization control data and the photovoltaic monitoring feedback data to obtain a photovoltaic control optimization report.

[0142] In the embodiment of the present invention, first, using the photovoltaic power compensation data and the photovoltaic array adjustment data, through data preprocessing techniques including data cleaning and normalization, a pre-model for photovoltaic performance evaluation is constructed. Then, machine learning algorithms such as support vector machine (SVM) or random forest (RF) are used to train the pre-model to obtain a trained model for photovoltaic performance evaluation; subsequently, through cross-validation techniques such as k-fold cross-validation, the trained model for photovoltaic performance evaluation is evaluated by model cross-validation to obtain photovoltaic performance model evaluation data; according to the obtained photovoltaic performance model evaluation data, hyperparameter optimization techniques such as grid search or random search are used to adjust the model parameters, thereby obtaining a photovoltaic performance evaluation model. Based on the photovoltaic performance evaluation model, environmental adaptability analysis techniques such as solar position calculation and irradiance model in the pvlib-python library are used to perform environmental adaptability energy efficiency analysis on the photovoltaic system data to obtain environmental adaptability energy efficiency data; further, combined with photovoltaic module energy efficiency evaluation techniques such as photovoltaic module performance testing methods, photovoltaic module energy efficiency evaluation is performed on the photovoltaic system data to obtain photovoltaic module energy efficiency evaluation data. Using real-time feedback technology such as the real-time monitoring function in the HUAWEI 450W intelligent photovoltaic optimizer, the photovoltaic system data is monitored and feedback in real time to generate photovoltaic monitoring feedback data; according to the photovoltaic module energy efficiency evaluation data and the photovoltaic monitoring feedback data, through intelligent optimization control algorithms such as genetic algorithm (GA) or particle swarm optimization (PSO), intelligent optimization control is performed on the photovoltaic system data to obtain photovoltaic optimization control data; finally, through data integration technology, the photovoltaic optimization control data and the photovoltaic monitoring feedback data are integrated to form a photovoltaic control optimization report, providing decision support for the operation and maintenance of the photovoltaic system.

[0143] In this specification, a modular photovoltaic device is provided for performing the above modular photovoltaic control method. The modular photovoltaic device includes:

[0144] The data acquisition module is used to acquire photovoltaic system data; extract the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; perform intensity evaluation on the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; perform intensity clustering on the photovoltaic illumination intensity data to obtain illumination intensity clustering data; extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; perform photothermal synergy analysis on the photovoltaic temperature data according to the light intensity clustering data to generate photovoltaic photothermal synergy data;

[0145] The photovoltaic power analysis module is used to predict photovoltaic power output based on photovoltaic-thermal synergy data and generate predicted power output data; compare the predicted power output data with the preset power target to generate power output comparison data; perform power loss analysis on the power output comparison data to generate loss analysis data; perform dynamic power compensation adjustment on the photovoltaic-thermal synergy data according to the loss analysis data to generate photovoltaic power compensation data;

[0146] The photovoltaic array adjustment module is used to extract the component information of the photovoltaic system data to obtain the photovoltaic component data; perform array configuration analysis on the photovoltaic component data to obtain the photovoltaic array configuration data; perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array abnormal data; perform adaptive adjustment on the photovoltaic array abnormal data to obtain photovoltaic array adjustment data;

[0147] The photovoltaic monitoring and control module is used to construct a photovoltaic performance evaluation model based on photovoltaic power compensation data and photovoltaic array adjustment data to generate a photovoltaic performance evaluation model; use the photovoltaic performance evaluation model to evaluate the component energy efficiency of the photovoltaic system data to generate photovoltaic component energy efficiency evaluation data; monitor and control the photovoltaic system data in real time based on the photovoltaic component energy efficiency evaluation data to generate a photovoltaic control optimization report.

[0148] The present invention obtains the illumination parameter information of the photovoltaic system through the data acquisition module, accurately evaluates the photovoltaic illumination intensity, and further performs illumination intensity clustering to provide an accurate illumination data basis for subsequent photothermal collaborative analysis. By combining the illumination intensity clustering data, the photovoltaic temperature data is analyzed to generate photovoltaic-thermal collaborative data, which can accurately predict the photovoltaic power output and improve the accuracy of prediction. The photovoltaic power analysis module predicts the power output by using the photovoltaic-thermal collaborative data, compares it with the preset power target to generate power output comparison data, and performs power loss analysis to provide a basis for dynamic power compensation. According to the loss analysis data, the photovoltaic-thermal collaborative data is adjusted to generate photovoltaic power compensation data, which helps to optimize the power output of the photovoltaic system, reduce losses, and improve the photovoltaic utilization efficiency. The photovoltaic array adjustment module can identify abnormal conditions in the photovoltaic array by extracting photovoltaic component data and performing array configuration analysis, and generate photovoltaic array adjustment data through adaptive adjustment to further improve the overall performance of the photovoltaic system. The photovoltaic monitoring and control module integrates the photovoltaic power compensation data and the photovoltaic array adjustment data to construct a photovoltaic performance evaluation model, ensuring accurate evaluation of the energy efficiency of photovoltaic components and generating photovoltaic component energy efficiency evaluation data. By using the photovoltaic performance evaluation model to monitor and control the photovoltaic system data in real time, a photovoltaic control optimization report can be generated to guide actual operations and ensure that the photovoltaic system operates in the best state, thereby improving the stability and reliability of the photovoltaic system. Therefore, through the Internet of Things technology, data analysis technology, adaptive control technology, and digital twin technology, the present invention realizes photothermal collaborative analysis of the photovoltaic system to achieve adaptive adjustment of the photovoltaic array configuration and improve the photovoltaic power output performance.

[0149] Therefore, in any aspect, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application document are intended to be included in the present invention.

[0150] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A modular photovoltaic control method, characterized in that, It includes the following steps: Step S1: Obtain photovoltaic system data; extract the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; perform intensity evaluation on the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; perform intensity clustering on the photovoltaic illumination intensity data to obtain illumination intensity clustering data; extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; perform optothermal collaborative analysis on the photovoltaic temperature data according to the illumination intensity clustering data to generate photovoltaic optothermal collaborative data; Step S2: Based on the photovoltaic optothermal collaborative data, perform photovoltaic power output prediction to generate predicted power output data; Compare the predicted power output data with the preset power target to generate power output comparison data; perform power loss analysis on the power output comparison data to generate loss analysis data; According to the loss analysis data, perform dynamic power compensation adjustment on the photovoltaic optothermal collaborative data to generate photovoltaic power compensation data; Step S3: Extract the component information of the photovoltaic system data to obtain photovoltaic component data; perform array configuration analysis on the photovoltaic component data to obtain photovoltaic array configuration data; perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array anomaly data; perform adaptive adjustment on the photovoltaic array anomaly data to obtain photovoltaic array adjustment data; Step S4: Construct a photovoltaic performance evaluation model with the photovoltaic power compensation data and the photovoltaic array adjustment data to generate a photovoltaic performance evaluation model; use the photovoltaic performance evaluation model to perform component energy efficiency evaluation on the photovoltaic system data to generate photovoltaic component energy efficiency evaluation data; perform real-time monitoring and control on the photovoltaic system data according to the photovoltaic component energy efficiency evaluation data to generate a photovoltaic control optimization report.

2. The modular photovoltaic control method according to claim 1, wherein Step S1 includes the following steps: Step S11: Perform illumination feature recognition on the photovoltaic system data to obtain photovoltaic illumination feature data; extract parameter information from the photovoltaic illumination feature data to obtain photovoltaic illumination parameter information; Step S12: Perform hour-by-hour light intensity tracking processing on the photovoltaic illumination parameter information to obtain photovoltaic light intensity tracking data; perform light intensity integration calculation on the photovoltaic light intensity tracking data to obtain photovoltaic illumination intensity data; Step S13: Perform time series processing on the photovoltaic illumination intensity data to obtain light intensity time series data; perform non-linear dimensionality reduction on the light intensity time series data to generate time series dimensionality reduction data; perform hierarchical clustering analysis on the photovoltaic illumination intensity data according to the time series dimensionality reduction data to obtain illumination intensity clustering data; extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; Step S14: Perform optothermal collaborative analysis on the photovoltaic temperature data according to the illumination intensity clustering data to generate photovoltaic optothermal collaborative data.

3. The modular photovoltaic control method according to claim 2, wherein Step S14 includes the following steps: Step S141: Perform timestamp synchronization processing on the illumination intensity clustering data to obtain light intensity clustering synchronization data; perform thermal response characteristic analysis on the photovoltaic temperature data according to the light intensity clustering synchronization data to obtain photovoltaic temperature thermal response data; Step S142: Perform temperature change profile recognition on the photovoltaic temperature thermal response data to generate photovoltaic temperature profile data; perform sensitivity temperature fluctuation capture on the photovoltaic temperature profile data to obtain photovoltaic temperature fluctuation data; Step S143: performing light energy characteristic coupling processing on the photovoltaic temperature fluctuation data and the light intensity clustering data to generate light energy characteristic coupling data; performing thermal-optical effect synchronization analysis on the light energy characteristic coupling data to obtain photovoltaic thermal-optical effect synchronization data; Step S144: record the photothermal response time of the photovoltaic thermal-optical effect synchronization data to obtain photothermal response time data; calculate the photothermal conversion efficiency of the photovoltaic thermal-optical effect synchronization data based on the photothermal response time data to obtain photothermal conversion efficiency data; perform photothermal synergy analysis on the photovoltaic temperature data based on the photothermal conversion efficiency data to generate photovoltaic-photothermal synergy data.

4. The modular photovoltaic control method according to claim 1, wherein Step S2 includes the following steps: Step S21: historical data collection is performed on photovoltaic-thermal synergy data to obtain historical photovoltaic-thermal synergy data; historical photovoltaic-thermal synergy data is divided into data sets to generate historical data training sets and historical data test sets; model training is performed on the historical data training sets to generate a power output pre-model; model testing is performed on the power output pre-model according to the historical data test set to generate a power output prediction model; Step S22: importing the photovoltaic-thermal synergy data into the power output prediction model to perform photovoltaic power output prediction and generate predicted power output data; Step S23: performing output accuracy calibration processing on the predicted power output data to obtain power output accuracy calibration data; comparing the power output accuracy calibration data with the preset power target to generate power output comparison data; performing performance deviation identification on the power output comparison data to obtain power output performance deviation data; performing target alignment analysis processing on the power output performance deviation data to obtain power output alignment data; Step S24: performing difference quantification analysis on the power output alignment data to obtain power output difference quantification data; performing energy difference analysis on the power output difference quantification data to obtain power energy difference data; performing loss pattern recognition processing on the power energy difference data to obtain power loss pattern data; performing power energy efficiency loss analysis on the power loss pattern data to generate loss analysis data; Step S25: Dynamically adjust the photovoltaic-thermal synergy data for power compensation according to the loss analysis data to generate photovoltaic power compensation data.

5. The modular photovoltaic control method according to claim 4, wherein Step S25 includes the following steps: Step S251: performing power loss location processing on the loss analysis data to obtain power loss location data; performing power fluctuation monitoring on the photovoltaic and thermal synergy data according to the power loss location data to obtain power power fluctuation data; Step S252: recording the peak load of the electric power fluctuation data to obtain the power peak load data; identifying the power drop characteristics of the electric power fluctuation data according to the power peak load data to generate the electric power drop data; analyzing the abnormal situation of the electric power drop data to obtain the power abnormal situation data, wherein the power abnormal situation data includes the photovoltaic temperature abnormality data, the inverter conversion abnormality data and the current and voltage abnormal offset data; Step S253: Optimize the photovoltaic component heat conduction path for the photovoltaic-thermal collaborative data based on the photovoltaic temperature anomaly data to generate photovoltaic temperature anomaly adjustment data; adjust the inverter operating parameters for the photovoltaic-thermal collaborative data based on the inverter conversion anomaly data to generate inverter conversion anomaly adjustment data; perform dynamic harmonic control on the photovoltaic-thermal collaborative data based on the current-voltage anomaly offset data to generate current-voltage anomaly offset adjustment data; Step S254: Integrate the photovoltaic temperature anomaly adjustment data, the inverter conversion anomaly adjustment data, and the current-voltage anomaly offset adjustment data to obtain photovoltaic power compensation data.

6. The modular photovoltaic control method according to claim 1, wherein Step S3 includes the following steps: Step S31: Extract the component information of the photovoltaic system data to obtain photovoltaic component data; identify the arrangement situation of the photovoltaic component data to obtain photovoltaic component arrangement data; perform topological structure analysis on the photovoltaic component arrangement data to generate photovoltaic component topological structure data; Step S32: Construct the physical layout for the photovoltaic component topological structure data to generate a three-dimensional layout diagram of the photovoltaic components; identify the connection method of the three-dimensional layout diagram of the photovoltaic components to obtain component connection method data; classify the connection types of the component connection method data to obtain component connection type data; Step S33: Record the component array spacing for the photovoltaic component topological structure data based on the component connection type data to obtain component array spacing data; analyze the component array direction for the three-dimensional layout diagram of the photovoltaic components based on the component array spacing data to generate component array direction data; measure the tilt angle of the component array direction data to obtain array tilt angle data; Step S34: Integrate the component array spacing data, the component array direction data, and the array tilt angle data to obtain photovoltaic array configuration data; Step S35: Perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array anomaly data; Step S36: Perform adaptive adjustment on the photovoltaic array anomaly data to obtain photovoltaic array adjustment data.

7. The modular photovoltaic control method according to claim 6, characterized in that, Step S35 includes the following steps: Step S351: Analyze the shading situation between components for the component array spacing data to generate component shading situation data; evaluate the light reception rate of the photovoltaic light intensity data based on the component shading situation data to obtain light reception rate evaluation data; Step S352: Compare the light reception rate evaluation data with the preset light reception rate data. If the light reception rate evaluation data is less than the preset light reception rate data, generate low light reception rate data; mark the component array spacing data as abnormal based on the low light reception rate data to obtain component array spacing anomaly data; Step S353: Measure the light angle for the array tilt angle data to obtain tilt angle light data; monitor the temperature distribution of the photovoltaic temperature data based on the tilt angle light data to obtain tilt angle temperature distribution data; analyze the temperature non-uniformity of the tilt angle temperature distribution data to generate temperature non-uniformity data; record the anomaly of the array tilt angle data based on the temperature non-uniformity data to obtain array tilt angle anomaly data; Step S354: Identify the orientation of the component array direction data to generate array orientation data; calculate the photothermal efficiency of the photovoltaic-thermal collaborative data based on the array orientation data to obtain photothermal efficiency data; extract the low-efficiency data of the photothermal efficiency data to obtain photothermal low-efficiency data; perform anomaly marking on the component array direction data according to the photothermal low-efficiency data to obtain component array direction anomaly data; Step S355: Integrate the component array spacing anomaly data, array tilt angle anomaly data, and component array direction anomaly data to obtain photovoltaic array anomaly data.

8. The modular photovoltaic control method according to claim 6, wherein Step S36 includes the following steps: Step S361: Locate the occlusion area of the component occlusion situation data to obtain occlusion area location data; measure the occlusion shadow area of the occlusion area location data to obtain occlusion shadow area data; automatically adjust the area of the component array spacing anomaly data based on the occlusion area location data and the occlusion shadow area data to obtain spacing anomaly adjustment data; Step S362: Measure the tilt angle of the tilt angle illumination data to obtain tilt angle measurement data; record the angle parameters of the tilt angle measurement data according to the temperature non-uniformity data to obtain abnormal tilt angle parameters; perform adaptive angle calibration on the array tilt angle anomaly data according to the abnormal tilt angle parameters to obtain tilt angle anomaly adjustment data; Step S363: Analyze the illumination path of the array orientation data to obtain illumination orientation data; identify the radiation orientation of the illumination orientation data to generate illumination radiation orientation data; perform adaptive direction repositioning on the component array direction anomaly data according to the illumination radiation orientation data to obtain array direction anomaly adjustment data; Step S364: Integrate the spacing anomaly adjustment data, tilt angle anomaly adjustment data, and array direction anomaly adjustment data to obtain photovoltaic array adjustment data.

9. The modular photovoltaic control method according to claim 1, characterized in that Step S4 includes the following steps: Step S41: Construct a photovoltaic performance evaluation model based on the photovoltaic power compensation data and the photovoltaic array adjustment data to obtain a preliminary photovoltaic performance evaluation model, and use the photovoltaic power compensation data and the photovoltaic array adjustment data to train the preliminary photovoltaic performance evaluation model to obtain a trained photovoltaic performance evaluation model; Step S42: Perform model cross-validation evaluation on the trained photovoltaic performance evaluation model to obtain photovoltaic performance model evaluation data; adjust the model parameters of the trained photovoltaic performance evaluation model through the photovoltaic performance model evaluation data to obtain a photovoltaic performance evaluation model; Step S43: Analyze the environmental adaptation performance efficiency of the photovoltaic system data based on the photovoltaic performance evaluation model to obtain environmental adaptation performance efficiency data; evaluate the energy efficiency of the photovoltaic components of the photovoltaic system data based on the environmental adaptation performance efficiency data to obtain photovoltaic component energy efficiency evaluation data; Step S44: Use real-time feedback technology to perform real-time monitoring and feedback on the photovoltaic system data to generate photovoltaic monitoring feedback data; perform intelligent optimization control on the photovoltaic system data according to the photovoltaic component energy efficiency evaluation data and the photovoltaic monitoring feedback data to obtain photovoltaic optimization control data; Step S45: Integrate the photovoltaic optimization control data and the photovoltaic monitoring feedback data to obtain a photovoltaic control optimization report.

10. A modular photovoltaic device, characterized in that, For executing the modular photovoltaic control method according to claim 1, the modular photovoltaic device comprises: The data acquisition module is used to acquire photovoltaic system data; extract the illumination parameter information of the photovoltaic system data to obtain photovoltaic illumination parameter information; perform intensity evaluation on the photovoltaic illumination parameter information to obtain photovoltaic illumination intensity data; perform intensity clustering on the photovoltaic illumination intensity data to obtain illumination intensity clustering data; extract the temperature data of the photovoltaic system data to obtain photovoltaic temperature data; perform photothermal synergy analysis on the photovoltaic temperature data according to the light intensity clustering data to generate photovoltaic photothermal synergy data; The photovoltaic power analysis module is used to predict photovoltaic power output based on photovoltaic-thermal synergy data and generate predicted power output data; compare the predicted power output data with the preset power target to generate power output comparison data; perform power loss analysis on the power output comparison data to generate loss analysis data; perform dynamic power compensation adjustment on the photovoltaic-thermal synergy data according to the loss analysis data to generate photovoltaic power compensation data; The photovoltaic array adjustment module is used to extract the component information of the photovoltaic system data to obtain the photovoltaic component data; perform array configuration analysis on the photovoltaic component data to obtain the photovoltaic array configuration data; perform anomaly detection on the photovoltaic array configuration data to obtain photovoltaic array abnormal data; perform adaptive adjustment on the photovoltaic array abnormal data to obtain photovoltaic array adjustment data; The photovoltaic monitoring and control module is used to construct a photovoltaic performance evaluation model based on photovoltaic power compensation data and photovoltaic array adjustment data to generate a photovoltaic performance evaluation model; use the photovoltaic performance evaluation model to evaluate the component energy efficiency of the photovoltaic system data to generate photovoltaic component energy efficiency evaluation data; monitor and control the photovoltaic system data in real time based on the photovoltaic component energy efficiency evaluation data to generate a photovoltaic control optimization report.

Images