An AI-based integrated solar power generation management system, device, and method

Abstract

The present invention discloses an AI-based integrated solar power generation management system, equipment, and method, specifically relating to the field of photovoltaic power generation technology; by analyzing the light-induced attenuation data of photovoltaic modules, a convolutional neural network is used to determine whether the light-induced attenuation of photovoltaic modules is reversible; based on the light intensity change data of the light intensity mutation area at the edge of the cloud layer, the degree of influence of the nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array is evaluated; based on the judgment result of whether the light-induced attenuation is reversible and the evaluation result of the nonlinear shading and reflection gain effects, the working state of the photovoltaic module is determined. When the module is in an abnormal working state, the degree of influence of the nonlinear attenuation of the aerosol retention layer on the transmittance is evaluated by analyzing the transmittance change. Based on the comprehensive evaluation results, it is determined whether the operation and maintenance plan is to be activated, thereby realizing intelligent diagnosis and refined management of the operating state of the photovoltaic module, and improving the operating efficiency and reliability of solar power generation.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic power generation technology, and more specifically, to an AI-based intelligent solar power generation integrated management system, equipment, and method. Background Art

[0002] Traditional photovoltaic systems typically rely solely on monitoring power generation and meteorological data, making it difficult to accurately identify the impact of light-induced attenuation and cloud cover on power fluctuations. This makes it difficult to ensure timely and scientific operation and maintenance decisions. Furthermore, the aerosol retention layer, which reduces light transmittance and exacerbates power generation efficiency, is often overlooked. Existing management models often lack multi-dimensional data mining capabilities, making it difficult to conduct in-depth and comprehensive analysis of the factors affecting module performance degradation, making it difficult to address faults in a timely manner.

[0003] In order to solve the above problems, an AI-based integrated solar power generation management system, equipment and method are provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an AI-based intelligent solar power generation integrated management system, device and method to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An AI-based integrated solar power generation management method includes the following steps:

[0007] By analyzing the light-induced degradation data of photovoltaic modules, the convolutional neural network is used to determine whether the light-induced degradation of photovoltaic modules is reversible.

[0008] Based on the light intensity variation data in the cloud edge light intensity mutation area, the impact of the nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array is evaluated;

[0009] The working state of the photovoltaic module is determined based on the judgment result of whether the light-induced degradation of the photovoltaic module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array. The working state of the photovoltaic module includes normal working state and abnormal working state.

[0010] When the PV module is in an abnormal working state, the nonlinear attenuation effect of the aerosol retention layer on the PV module transmittance is evaluated by analyzing the changes in the PV module surface transmittance.

[0011] A comprehensive analysis is conducted on the impact of the nonlinear shading and reflection gain effects of the cloud edge on the power fluctuations of the photovoltaic array and the nonlinear attenuation of the aerosol retention layer on the transmittance of the photovoltaic module to determine whether to activate the operation and maintenance plan.

[0012] In a preferred embodiment, by analyzing the light-induced degradation data of the photovoltaic module, a convolutional neural network is used to determine whether the light-induced degradation of the photovoltaic module is reversible, specifically:

[0013] Regularly collect light-induced degradation data of photovoltaic modules through high-precision sensors;

[0014] Standardize the collected light-induced attenuation data;

[0015] A convolutional neural network is used to extract key features from light-induced degradation data and identify spatiotemporal patterns in the degradation process of photovoltaic modules.

[0016] Train a convolutional neural network using a labeled light-induced attenuation dataset;

[0017] Use the trained convolutional neural network model to determine whether the light-induced degradation of photovoltaic modules is reversible.

[0018] In a preferred embodiment, determining whether the light-induced degradation of a photovoltaic module is reversible is specifically as follows:

[0019] A reversible threshold is preset, and the probability value of photoinduced decay being reversible is compared with the reversible threshold:

[0020] When the probability value of the reversible light-induced degradation is greater than the reversible threshold, the light-induced degradation of the photovoltaic module is determined to be reversible;

[0021] When the probability value of the reversible light-induced degradation is less than or equal to the reversible threshold, it is determined that the light-induced degradation of the photovoltaic module is irreversible.

[0022] In a preferred embodiment, based on the light intensity variation data of the cloud edge light intensity mutation area, the impact of the nonlinear shading and reflection gain effect of the cloud edge on the photovoltaic array power fluctuation is evaluated, specifically:

[0023] Use high-precision sensors to collect data on light intensity changes in cloud edge areas;

[0024] Analyze light intensity data, identify areas with sudden changes in light intensity, and determine the distribution characteristics of cloud edges;

[0025] A mathematical model is proposed to describe the impact of nonlinear shading caused by cloud edges on light intensity;

[0026] Using the principle of optical reflection, a reflection gain model is constructed to simulate the reflection gain effect of light intensity;

[0027] Combined with the light intensity variation model, a mathematical model of photovoltaic array power fluctuation is established;

[0028] Based on the modeling results, the influence of nonlinear shading and reflection gain effects on power fluctuations is quantified.

[0029] In a preferred embodiment, the working state of the photovoltaic module is determined based on the judgment result of whether the light-induced degradation of the photovoltaic module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array. The working state of the photovoltaic module includes a normal working state and an abnormal working state, specifically:

[0030] Preset the volatility coefficient threshold and compare the volatility coefficient with the volatility coefficient threshold:

[0031] When the volatility coefficient is greater than the volatility coefficient threshold, it means that the nonlinear shading and reflection gain effect of the cloud edge has a high degree of influence on the power fluctuation of the photovoltaic array;

[0032] When the volatility coefficient is less than or equal to the volatility coefficient threshold, it means that the nonlinear shading and reflection gain effect of the cloud edge has a low impact on the power fluctuation of the photovoltaic array.

[0033] When the probability value of the reversible light-induced degradation is greater than the reversible threshold and the volatility coefficient is less than or equal to the volatility coefficient threshold, the working state of the photovoltaic module is determined to be a normal working state; otherwise, the working state of the photovoltaic module is determined to be an abnormal working state.

[0034] In a preferred embodiment, the nonlinear attenuation effect of the aerosol retention layer on the transmittance of the photovoltaic module is evaluated by analyzing the transmittance change on the surface of the photovoltaic module, specifically:

[0035] Collect transmittance data and aerosol accumulation on the surface of photovoltaic modules;

[0036] Monitor the aerosol retention layer through meteorological sensors and image recognition technology;

[0037] Based on the collected transmittance data and aerosol retention layer data, a nonlinear regression model between transmittance and aerosol accumulation was established using regression analysis.

[0038] A transmittance attenuation model was established to evaluate the nonlinear attenuation of the aerosol retention layer on the transmittance of photovoltaic modules: the attenuation coefficient was calculated as follows: ;in, is the attenuation coefficient; For the The transmittance attenuation value of each transmittance sampling point; For the The weight coefficient of each transmittance sampling point; is the number of transmittance sampling points.

[0039] In a preferred embodiment, a comprehensive analysis is performed on the impact of the nonlinear shading and reflection gain effects of the cloud edge on the power fluctuation of the photovoltaic array and the impact of the aerosol retention layer on the nonlinear attenuation of the transmittance of the photovoltaic module to determine whether to activate the operation and maintenance plan, specifically:

[0040] The normalized volatility coefficient and attenuation coefficient are calculated to obtain the health score of the photovoltaic module. The calculation formula is: ;in, Provide health scores for PV panels; is the attenuation coefficient; is the volatility coefficient; is the weight factor of the volatility coefficient; is the weight factor of the attenuation coefficient; is the smoothing factor;

[0041] Preset health score threshold and compare the health score with the health score threshold:

[0042] When the health score is greater than or equal to the health score threshold, there is no need to enable the operation and maintenance plan;

[0043] When the health score is lower than the health score threshold, the operation and maintenance solution needs to be activated.

[0044] On the other hand, the present invention provides an AI-based intelligent integrated solar power generation management system, which includes a decay reversibility judgment module, a power fluctuation assessment module, a working state determination module, a transmittance analysis module, and a comprehensive analysis module;

[0045] The attenuation reversibility judgment module analyzes the light-induced attenuation data of photovoltaic modules and determines whether the light-induced attenuation of photovoltaic modules is reversible based on the convolutional neural network;

[0046] The power fluctuation assessment module evaluates the impact of nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array based on the light intensity change data in the area with sudden changes in light intensity at the cloud edge.

[0047] The working status determination module determines the working status of the photovoltaic module based on the judgment result of whether the light-induced degradation of the photovoltaic module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array. The working status of the photovoltaic module includes normal working status and abnormal working status.

[0048] When the working state of the photovoltaic module is abnormal, the transmittance analysis module analyzes the transmittance change of the photovoltaic module surface to evaluate the nonlinear attenuation effect of the aerosol retention layer on the transmittance of the photovoltaic module;

[0049] The comprehensive analysis module comprehensively analyzes the impact of the nonlinear shading and reflection gain effects of the cloud edge on the power fluctuation of the photovoltaic array and the nonlinear attenuation of the aerosol retention layer on the transmittance of the photovoltaic module to determine whether to activate the operation and maintenance plan.

[0050] On the other hand, the present invention provides an AI-based integrated solar power generation management device, comprising: a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, an AI-based integrated solar power generation management method is implemented.

[0051] The technical effects and advantages of the AI-based solar power generation integrated management system, equipment and method of the present invention are as follows:

[0052] By analyzing the light-induced attenuation data of photovoltaic modules using a convolutional neural network, it is possible to quickly determine whether the attenuation of photovoltaic modules is reversible, providing a scientific basis for their maintenance. Secondly, by evaluating the impact of nonlinear shading and reflection gain effects at the cloud edge on power fluctuations, the output fluctuation characteristics of photovoltaic modules can be predicted in advance, helping to ensure power generation stability. In addition, when photovoltaic modules are in abnormal operating conditions, the nonlinear attenuation effect of the aerosol retention layer is further evaluated through transmittance change analysis, revealing the long-term impact of environmental pollution on photovoltaic module performance. Finally, through comprehensive analysis, it is determined whether to activate the operation and maintenance plan, and efficient and intelligent operation and maintenance of photovoltaic modules is achieved, significantly improving power generation efficiency and stability, while reducing maintenance costs, extending the service life of photovoltaic modules, and improving overall economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a schematic diagram of a solar power generation integrated management method based on AI intelligence of the present invention;

[0054] Figure 2 This is a structural diagram of an AI-based intelligent solar power generation integrated management system of the present invention. DETAILED DESCRIPTION

[0055] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention. Example

[0056] Figure 1The present invention provides an AI-based integrated management method for solar power generation, which includes the following steps:

[0057] By analyzing the light-induced degradation data of photovoltaic modules, the convolutional neural network is used to determine whether the light-induced degradation of photovoltaic modules is reversible.

[0058] Based on the light intensity variation data in the cloud edge light intensity mutation area, the impact of the nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array is evaluated;

[0059] The working state of the photovoltaic module is determined based on the judgment result of whether the light-induced degradation of the photovoltaic module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array. The working state of the photovoltaic module includes normal working state and abnormal working state.

[0060] When the PV module is in an abnormal working state, the nonlinear attenuation effect of the aerosol retention layer on the PV module transmittance is evaluated by analyzing the changes in the PV module surface transmittance.

[0061] A comprehensive analysis is conducted on the impact of the nonlinear shading and reflection gain effects of the cloud edge on the power fluctuations of the photovoltaic array and the nonlinear attenuation of the aerosol retention layer on the transmittance of the photovoltaic module to determine whether to activate the operation and maintenance plan.

[0062] Specifically, by analyzing the light-induced degradation data of photovoltaic modules, a convolutional neural network is used to determine whether the light-induced degradation of photovoltaic modules is reversible, including:

[0063] High-precision sensors are used to regularly collect data on the light-induced degradation of photovoltaic modules. Light-induced degradation is the phenomenon in which the performance of photovoltaic modules degrades over time under prolonged sunlight. To obtain high-quality data, sensors should have high temporal resolution and be able to collect PV module degradation data at an appropriate frequency under different environments. Collected data should include, but is not limited to, information such as the operating temperature and irradiance of the PV modules. Sensors should be deployed at various locations in the PV array to monitor the degradation of each PV module and ensure comprehensive data on light-induced degradation is captured. The frequency and scope of data collection should be adjusted according to actual needs, typically requiring multiple data collection sessions over multiple time periods to reflect changing trends in light-induced degradation.

[0064] Standardize the collected light-induced attenuation data: The collected light-induced attenuation data needs to be standardized to eliminate the interference of dimensional differences and environmental factors. The standardization process includes:

[0065] Remove outliers: Eliminate or correct abnormal data caused by sensor failure or external interference;

[0066] Data normalization: mapping data to a uniform scale;

[0067] Time series smoothing: using moving average or Gaussian smoothing methods to reduce short-term noise and highlight long-term trends;

[0068] The standardized data provides reliable input for feature extraction.

[0069] Convolutional neural networks are used to extract key features from light-induced degradation data and identify spatiotemporal patterns in the degradation of photovoltaic modules. Convolutional neural networks can learn local and global characteristic patterns from raw data, revealing the changing patterns in the degradation of photovoltaic modules. The input data is standardized light-induced degradation data, typically represented as a time series.

[0070] First convolution layer: In the convolution operation, the convolution kernel extracts local features from the input data, such as the local trend of power drop. The formula for the convolution operation is: ;in, is the feature map output by the convolution layer, at time The characteristic value of is the convolution kernel Weight coefficients; Represents input data In time The value of Indicates the size of the convolution kernel.

[0071] In the convolution operation, the input data is multiplied by the convolution kernel point by point and accumulated to obtain the time The convolution layer extracts multiple different feature patterns from the data by operating multiple convolution kernels in parallel.

[0072] Pooling layer: This layer reduces the dimensionality of features obtained by the convolution operation, reducing the amount of computation and enhancing the generalization ability of the model. A commonly used pooling method is max pooling.

[0073] Fully connected layers: These layers pass features extracted from convolution and pooling to fully connected layers for further feature fusion and decision making. By adjusting weights and biases between layers, the network can learn global patterns in the data.

[0074] After processing by the convolutional neural network, a set of key features representing the light-induced degradation process are obtained, which can provide a decision basis for subsequent degradation evaluation.

[0075] Training a convolutional neural network using a labeled light-induced decay dataset: A convolutional neural network is trained using a labeled light-induced decay dataset. Each sample in the labeled dataset contains known decay information, including decay rate, reversibility, and decay amplitude.

[0076] Loss function: Use mean square error as the loss function to optimize the parameters of the convolutional neural network. The loss function formula is as follows: ;in, Represents the value of the loss function; is the number of samples in the dataset; The convolutional neural network model predicts The attenuation value of each sample; is the decay value of the true label.

[0077] During the training process, the back-propagation algorithm is used to adjust the network weights by optimizing the loss function, so that the model can accurately predict the attenuation characteristics of photovoltaic modules.

[0078] Use the trained convolutional neural network model to determine whether the light-induced degradation of photovoltaic modules is reversible: The output of the convolutional neural network model is used to determine whether the light-induced degradation of photovoltaic modules is reversible. The output of the convolutional neural network model is normalized to the [0,1] interval using the Sigmoid function to indicate whether the light-induced degradation is reversible: ;in, is the output of the Sigmoid function, indicating the probability that the photodegradation is reversible; It is the original output of the convolutional neural network model, usually the output of the last layer of the neural network, representing the unprocessed value of the prediction of the reversibility of photodegradation; is the base of natural logarithms.

[0079] A reversible threshold is preset, and the probability value of photoinduced decay being reversible is compared with the reversible threshold:

[0080] When the probability value of reversible light-induced degradation is greater than the reversible threshold, the light-induced degradation of the photovoltaic module is determined to be reversible, indicating that the damage to the photovoltaic module is relatively minor and can be restored through repair or specific maintenance measures. Generally, it will not have a significant impact on long-term operating performance and the difficulty of restoration is relatively low. After these photovoltaic modules are marked as reversibly degraded, resource allocation can be optimized, and limited maintenance resources can be prioritized for photovoltaic modules with irreversible degradation.

[0081] When the probability of reversible light-induced degradation is less than or equal to the reversibility threshold, the light-induced degradation of a PV module is considered irreversible, meaning that the degradation process is irreversible. Degradation is typically caused by irreversible factors such as prolonged high-temperature exposure, material aging, the growth of microcracks, or other severe damage to the PV module. These damages not only affect the module's photoelectric conversion efficiency but can also lead to further performance degradation. Modules with irreversible degradation often require replacement or more complex repairs. For these PV modules with irreversible degradation, appropriate emergency measures are necessary, such as reducing the overall load or considering replacing them with newer, higher-performing modules.

[0082] Specifically, based on the light intensity variation data in the cloud edge light intensity mutation area, the impact of the nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array is evaluated, including:

[0083] Use high-precision sensors to collect data on light intensity changes at cloud edges: Sensors need to be deployed near photovoltaic arrays to monitor light intensity changes at cloud edges in real time. These sensors should have high sensitivity, a wide dynamic range, and low noise to ensure they can capture sufficiently accurate data in rapidly changing lighting environments.

[0084] During data collection, the light intensity variation data recorded by the sensor will include information about light intensity fluctuations caused by cloud obstruction and reflection. The data collected by the sensor should include light intensity values ​​over multiple time periods. In particular, the sensor should be set up at different vertical and horizontal positions to accurately capture light intensity variations and avoid data loss due to obstruction.

[0085] Analyze light intensity data to identify areas of sudden changes in light intensity and determine the distribution characteristics of cloud edges. These sudden changes in light intensity are often associated with cloud edges or changes in cloud thickness. Data analysis methods should be combined with time series analysis techniques, such as fast Fourier transforms and wavelet transforms in signal processing, to accurately detect the locations of these sudden changes in light intensity.

[0086] After identifying the point of sudden change in light intensity, we further analyze the distribution characteristics of the area of ​​sudden change in light intensity to determine the specific location of the cloud edge. By combining multi-dimensional data interpolation and machine learning techniques with multi-point light intensity data, we can infer the shape of the cloud edge and its relationship with light intensity fluctuations.

[0087] A mathematical model is proposed to describe the impact of nonlinear cloud-edge-induced shading on light intensity: After obtaining light intensity data and determining cloud edge characteristics, a mathematical model is developed to describe the impact of nonlinear cloud-edge-induced shading on light intensity. Nonlinear shading refers to the fact that cloud shading does not vary linearly with cloud thickness but is influenced by multiple factors, such as cloud type, thickness, angle, and solar radiation direction.

[0088] The established mathematical model should be based on the optical transmission model. Specifically, the following formula can be used to describe the cloud cover effect on light intensity: ;in, For the time point Light intensity after being blocked by clouds; is the initial incident light intensity before the cloud covers it; is the transmission coefficient of the cloud layer; is the incident angle of sunlight; is the thickness of the cloud layer; is the base of natural logarithms.

[0089] The transmission coefficient describes the degree of attenuation of light when passing through clouds. It depends on the thickness and composition of the clouds and the angle of incidence of sunlight, and needs to be calibrated using experimental data.

[0090] Using the principles of optical reflection, a reflection gain model was constructed to simulate the reflection gain effect of light intensity. In addition to the occlusion effect, the reflection gain effect is also a significant factor influencing light intensity fluctuations at cloud edges. This effect is caused by the reflective properties of clouds. In particular, at specific angles and cloud surface conditions, the reflected light intensity at cloud edges is enhanced. A reflection gain model was established to simulate the contribution of cloud reflection to light intensity.

[0091] The reflection gain can be described by the following formula: ;in, It's at the time The reflected light intensity; is the reflectivity of the cloud layer; is the initial incident light intensity before the cloud covers it; is the incident angle of sunlight.

[0092] The reflectivity describes the ability of a cloud surface to reflect light, and depends on the surface properties of the cloud (such as smoothness, cloud moisture, etc.) and the angle of incidence of sunlight.

[0093] The reflection gain effect can cause a sudden change in light intensity within a short period of time, which in turn affects the output power of the photovoltaic array. Therefore, the optical transmission model needs to comprehensively consider the dual effects of cloud cover and reflection on light intensity changes.

[0094] Combined with the light intensity variation model, a mathematical model of photovoltaic array power fluctuation is established: the output power of the photovoltaic array is proportional to the incident light intensity, so the light intensity variation model can directly affect the power output. The output power of the photovoltaic array is defined as , which can be expressed as: ;in, For the time point Output power; The energy conversion efficiency of the photovoltaic array indicates the ability of the photovoltaic array to convert light energy into electrical energy, which is usually a constant. The effective area of ​​the photovoltaic array represents the total area of ​​the photovoltaic array, usually measured in square meters, and determines the amount of light energy that the photovoltaic array can capture; For the time point The total light intensity, including the sum of cloud cover and reflection gain, is expressed as: .

[0095] Based on the mathematical model of photovoltaic array power fluctuation, the impact of cloud edge shading and reflection gain effect on photovoltaic array power can be analyzed, thereby predicting the amplitude and frequency of power fluctuation.

[0096] Based on the modeling results, the influence of nonlinear shading and reflection gain effects on power fluctuations is quantified: Since the shading and reflection effects of clouds are usually nonlinear, the amplitude of power fluctuations will be quantified by the fluctuation of light intensity. The amplitude of power fluctuation is defined as ;in, is the average output power of the photovoltaic array; is the power fluctuation amplitude.

[0097] Rapid changes in light intensity will cause the frequency of power fluctuations to also fluctuate. Spectral analysis (such as Fourier transform) is used to quantify the frequency characteristics of power fluctuations, and the expression is:

[0098] ;in, Represents the distribution of power fluctuations in the frequency domain; is an imaginary unit; is the frequency variable, which represents the frequency component of power fluctuation in the frequency domain; is the base of natural logarithms.

[0099] According to the results of Fourier transform, the contribution of different frequency components to power fluctuation can be quantified by calculating the spectral density of power fluctuation. It can be obtained by the following points: ;in, is the energy of power fluctuation.

[0100] Since the obstruction and reflection effects of clouds are time-varying, they not only affect the light intensity in a short period of time, but may also cause long-term light intensity fluctuations over time. Therefore, it is necessary to consider the time correlation, that is, whether the power fluctuation has autocorrelation characteristics, which is defined as:

[0101] ;in, is the autocorrelation function of the power fluctuation; Indicates time delay; It represents the time averaging operation, i.e., the time averaging of the product of power fluctuations, which is usually used to eliminate randomness and reveal the systematic changes of power fluctuations.

[0102] The volatility coefficient is defined to quantify the impact of the nonlinear shading and reflection gain effects of the cloud edge on the power fluctuation of the photovoltaic array. The calculation formula is: ;in, is the volatility coefficient; is the average value of the autocorrelation function of the power fluctuation; is the energy of power fluctuation; is the average output power of the photovoltaic array.

[0103] The larger the volatility coefficient, the more significant the impact of the nonlinear shading and reflection gain effects caused by cloud edges on the power fluctuations of the photovoltaic array. A larger volatility coefficient indicates that the changes in light intensity caused by cloud shading and reflection effects are more dramatic and frequent, directly causing significant fluctuations in the output power of the photovoltaic array. This volatility may manifest as strong power fluctuations in a short period of time, resulting in a decrease in the stability of the photovoltaic array, which may increase the complexity of load regulation and reduce the predictability of energy output. Larger volatility coefficients are generally associated with highly nonlinear effects of clouds, such as the complex morphology of cloud edges and the reflection enhancement effect of light. Especially in the short-term response of photovoltaic arrays, these nonlinear effects may have superimposed effects at different scales. Therefore, the increase in the volatility coefficient indicates the impact of more complex meteorological conditions on photovoltaic performance, and more sophisticated scheduling and prediction mechanisms are needed to reduce the instability and power loss caused by these fluctuations.

[0104] Specifically, the working state of the photovoltaic module is determined based on the judgment result of whether the light-induced degradation of the photovoltaic module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array. The working state of the photovoltaic module includes normal working state and abnormal working state, including:

[0105] Preset the volatility coefficient threshold and compare the volatility coefficient with the volatility coefficient threshold:

[0106] When the volatility coefficient is greater than the volatility coefficient threshold, it means that the power fluctuation of the PV array is not within the controllable range. The nonlinear shading and reflection gain effects of the cloud edge have a high degree of influence on the power fluctuation of the PV array. In this case, the dynamic changes of the cloud edge will cause drastic fluctuations in light intensity in a short period of time, directly leading to large fluctuations in the power generation of the PV array. A large volatility coefficient usually means that the output power of the PV module is interfered with by unstable factors, such as sudden shadow changes or a sharp increase in light intensity. This causes the power output to show large fluctuations, which may affect the overall stability and power generation efficiency.

[0107] When the volatility coefficient is less than or equal to the volatility coefficient threshold, the PV array's power fluctuations are within controllable limits, and the nonlinear shading and reflection gain effects of cloud edges have a low impact on the PV array's power fluctuations. At this point, the cloud layer's impact on light intensity is relatively mild, and the PV module's power generation remains relatively stable, with minimal fluctuations. Due to the weak cloud edge effect, variations in light intensity will not significantly affect the PV array's power output, helping to improve overall power generation efficiency and reduce the risks associated with frequent fluctuations.

[0108] The volatility coefficient threshold is set based on a comprehensive analysis of historical PV array power fluctuation data, cloud distribution characteristics, and regional climate conditions. By analyzing extensive historical data, the statistical characteristics of PV array power fluctuations under different weather conditions can be calculated, allowing a threshold to be determined that effectively reflects the impact of volatility. The threshold is typically set based on the sensitivity of the PV array and its ability to withstand power fluctuations in specific environments. For example, if cloud edge effects are frequent and intense in a region, the volatility coefficient threshold may be set lower to identify potential high volatility risks earlier. Conversely, in regions with more gradual cloud changes, the volatility coefficient threshold may be set higher.

[0109] When the probability value of the reversible light-induced degradation is greater than the reversible threshold and the volatility coefficient is less than or equal to the volatility coefficient threshold, the working state of the photovoltaic module is determined to be a normal working state; otherwise, the working state of the photovoltaic module is determined to be an abnormal working state.

[0110] Specifically, by analyzing the changes in light transmittance on the surface of the photovoltaic module, the nonlinear attenuation effect of the aerosol retention layer on the light transmittance of the photovoltaic module is evaluated, including:

[0111] Collecting transmittance data and aerosol accumulation on the surface of photovoltaic modules: Data on the transmittance of photovoltaic modules is collected. A high-precision spectrometer is used to measure the transmittance of photovoltaic modules in real time. The high-precision spectrometer provides full-spectrum data from ultraviolet to infrared, accurately capturing subtle changes in the transmittance of photovoltaic module surfaces.

[0112] Meteorological sensors and image recognition technology are used to monitor the aerosol stagnation layer. Meteorological sensors measure factors such as humidity and wind speed, dynamically acquiring data on environmental changes that influence aerosol deposition. Image recognition technology, meanwhile, uses high-definition cameras to capture real-time images of the photovoltaic module surface and computer vision algorithms to quantitatively analyze the aerosol accumulation on the module surface. Combined with meteorological conditions, this technology analyzes the distribution and adhesion characteristics of aerosols.

[0113] Based on the collected transmittance data and aerosol retention layer data, a regression analysis method was used to establish a nonlinear regression model between transmittance and aerosol accumulation: Based on the transmittance data and aerosol retention layer data, a nonlinear regression model was established using regression analysis to analyze the relationship between the aerosol retention layer thickness and transmittance. The regression model takes into account the accumulation characteristics of aerosols, the uniformity of aerosol distribution on the surface of photovoltaic modules, and the influence of environmental factors. The regression model expression is:

[0114] ;in, is the light transmittance of the photovoltaic module; is the thickness of the aerosol retention layer; is the uniformity of aerosol distribution on the surface; is the ambient humidity; is the adhesion coefficient of aerosol on the surface of photovoltaic modules.

[0115] Through regression analysis of each variable, a nonlinear function describing the relationship between transmittance change and aerosol accumulation was obtained. .

[0116] A transmittance attenuation model was established to evaluate the nonlinear attenuation of the aerosol stagnation layer on the transmittance of photovoltaic modules: Based on the results of the regression analysis, a transmittance attenuation model was established. The degree of transmittance attenuation is a nonlinear process. The transmittance attenuation model includes the following expression to calculate the impact of aerosols on the transmittance of photovoltaic modules: ;in, is the attenuation value of light transmittance; are regression coefficients, which respectively represent the influence of the thickness of the aerosol retention layer, the uniformity of aerosol distribution on the surface and the degree of influence of ambient humidity on the transmittance attenuation.

[0117] According to the attenuation value of the transmittance, the attenuation coefficient is calculated to evaluate the nonlinear attenuation degree of the aerosol retention layer on the transmittance of the photovoltaic module. The calculation formula is: ;in, is the attenuation coefficient; For the The transmittance attenuation value of each transmittance sampling point; For the The weight coefficient of each transmittance sampling point; is the number of transmittance sampling points.

[0118] A larger attenuation coefficient indicates a greater degree of nonlinear attenuation of the PV module's light transmittance due to the aerosol retention layer. A larger attenuation coefficient indicates a thicker and more unevenly distributed aerosol deposit layer on the PV module surface, reducing the light intensity entering the module. A larger attenuation coefficient also reflects the PV module's dependence on environmental conditions for power generation. Factors such as high humidity, severe pollution, or low wind speeds can exacerbate aerosol accumulation and adhesion. A larger attenuation coefficient suggests the need for timely maintenance measures, such as regular cleaning of the PV module surface, to remove accumulated aerosols and restore light transmittance. By accurately assessing the attenuation coefficient, PV power plant managers can more effectively schedule cleaning and maintenance cycles to ensure maximum energy output.

[0119] Specifically, a comprehensive analysis is conducted on the impact of the nonlinear shading and reflection gain effects of cloud edges on the power fluctuations of the photovoltaic array, and the impact of the aerosol retention layer on the nonlinear attenuation of the transmittance of photovoltaic modules, to determine whether to activate the operation and maintenance plan, including:

[0120] The volatility coefficient corresponding to the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array and the attenuation coefficient corresponding to the degree of nonlinear attenuation of the aerosol retention layer on the transmittance of the photovoltaic module are normalized respectively. The normalized volatility coefficient and attenuation coefficient are calculated to obtain the health score of the photovoltaic module. The calculation formula is: ;in, Provide health scores for PV panels; is the attenuation coefficient; is the volatility coefficient; is the weight factor of the volatility coefficient; is the weight factor of the attenuation coefficient; is the smoothing factor.

[0121] Preset health score threshold and compare the health score with the health score threshold:

[0122] When the health score is greater than or equal to the health score threshold, it indicates that the PV module is currently in good operating condition and does not need to activate the operation and maintenance plan. The existing operating status can be maintained.

[0123] When the health score is below the health score threshold, it indicates that the PV module is in poor operating condition and requires the implementation of an operation and maintenance plan. This includes initiating a surface cleaning procedure for the PV modules, such as using automated cleaning equipment or manual cleaning to remove surface aerosol layers, dust, and other contaminants to restore the cleanliness of the PV modules. The power output characteristics of the PV modules are tested to identify any abnormal electrical characteristics, such as localized hot spots or series mismatches. The inverter's operating parameters are then adjusted to optimize power output. Furthermore, the operation and maintenance plan may include manual inspections, focusing on identifying physical damage or aging on the surface of the PV modules and promptly replacing damaged modules. Example

[0124] The difference between Example 2 of the present invention and Example 1 is that this example introduces an AI-based intelligent integrated solar power generation management system.

[0125] Figure 2 The present invention provides a schematic structural diagram of an AI-based integrated solar power generation management system, which includes an attenuation reversibility judgment module, a power fluctuation assessment module, a working status determination module, a transmittance analysis module, and a comprehensive analysis module.

[0126] The attenuation reversibility judgment module analyzes the light-induced attenuation data of photovoltaic modules and determines whether the light-induced attenuation of photovoltaic modules is reversible based on the convolutional neural network;

[0127] The power fluctuation assessment module evaluates the impact of nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array based on the light intensity change data in the area with sudden changes in light intensity at the cloud edge.

[0128] The working status determination module determines the working status of the photovoltaic module based on the judgment result of whether the light-induced degradation of the photovoltaic module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array. The working status of the photovoltaic module includes normal working status and abnormal working status.

[0129] When the working state of the photovoltaic module is abnormal, the transmittance analysis module analyzes the transmittance change of the photovoltaic module surface to evaluate the nonlinear attenuation effect of the aerosol retention layer on the transmittance of the photovoltaic module;

[0130] The comprehensive analysis module comprehensively analyzes the impact of the nonlinear shading and reflection gain effects of the cloud edge on the power fluctuation of the photovoltaic array and the nonlinear attenuation of the aerosol retention layer on the transmittance of the photovoltaic module to determine whether to activate the operation and maintenance plan. Example

[0131] A solar power generation integrated management device based on AI intelligence includes: a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, an AI intelligence-based solar power generation integrated management method is implemented.

[0132] The above formulas are dimensionless and numerical calculations. They are based on the most recent real-world conditions obtained through software simulation using a large amount of data. The preset parameters and thresholds in the formulas are set by those skilled in the art based on actual conditions. Any matters not described in this invention apply to the prior art.

Claims

1. A solar power generation integrated management method based on AI intelligence, characterized in that: The steps include: By analyzing the light-induced degradation data of photovoltaic modules, the convolutional neural network is used to determine whether the light-induced degradation of photovoltaic modules is reversible. Based on the light intensity variation data in the cloud edge light intensity mutation area, the impact of the nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array is evaluated; The working state of the photovoltaic module is determined based on the judgment result of whether the light-induced degradation of the photovoltaic module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array. The working state of the photovoltaic module includes normal working state and abnormal working state. When the PV module is in an abnormal working state, the nonlinear attenuation effect of the aerosol retention layer on the PV module transmittance is evaluated by analyzing the changes in the PV module surface transmittance. Collect transmittance data and aerosol accumulation on the surface of photovoltaic modules; Monitor the aerosol retention layer through meteorological sensors and image recognition technology; Based on the collected transmittance data and aerosol retention layer data, a nonlinear regression model between transmittance and aerosol accumulation was established using regression analysis. A transmittance attenuation model was established to evaluate the nonlinear attenuation of the aerosol retention layer on the transmittance of photovoltaic modules: the attenuation coefficient was calculated as follows: ;in, is the attenuation coefficient; For the The transmittance attenuation value of each transmittance sampling point; For the The weight coefficient of each transmittance sampling point; is the number of transmittance sampling points; Comprehensively analyze the impact of nonlinear cloud edge shading and reflection gain effects on PV array power fluctuations, and the impact of the aerosol retention layer on the nonlinear attenuation of PV module transmittance, to determine whether to activate the operation and maintenance plan; The normalized volatility coefficient and attenuation coefficient are calculated to obtain the health score of the photovoltaic module. The calculation formula is: ;in, Provide health scores for PV panels; is the attenuation coefficient; is the volatility coefficient; is the weight factor of the volatility coefficient; is the weight factor of the attenuation coefficient; is the smoothing factor; Preset health score threshold and compare the health score with the health score threshold: When the health score is greater than or equal to the health score threshold, there is no need to enable the operation and maintenance plan; When the health score is lower than the health score threshold, the operation and maintenance solution needs to be activated.

2. The AI-based integrated management method for solar power generation according to claim 1, characterized in that: By analyzing the light-induced degradation data of photovoltaic modules, the convolutional neural network is used to determine whether the light-induced degradation of photovoltaic modules is reversible. Specifically: Regularly collect light-induced degradation data of photovoltaic modules through high-precision sensors; Standardize the collected light-induced attenuation data; A convolutional neural network is used to extract key features from light-induced degradation data and identify spatiotemporal patterns in the degradation process of photovoltaic modules. Train a convolutional neural network using a labeled light-induced attenuation dataset; Use the trained convolutional neural network model to determine whether the light-induced degradation of photovoltaic modules is reversible.

3. The AI-based integrated management method for solar power generation according to claim 2, characterized in that: Determine whether the light-induced degradation of photovoltaic modules is reversible, specifically: A reversible threshold is preset, and the probability value of photoinduced decay being reversible is compared with the reversible threshold: When the probability value of the reversible light-induced degradation is greater than the reversible threshold, the light-induced degradation of the photovoltaic module is determined to be reversible; When the probability value of the reversible light-induced degradation is less than or equal to the reversible threshold, it is determined that the light-induced degradation of the photovoltaic module is irreversible.

4. The AI-based integrated management method for solar power generation according to claim 3, characterized in that: Based on the light intensity variation data in the cloud edge light intensity mutation area, the impact of the nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array is evaluated. Specifically: Use high-precision sensors to collect data on light intensity changes in cloud edge areas; Analyze light intensity data, identify areas with sudden changes in light intensity, and determine the distribution characteristics of cloud edges; A mathematical model is proposed to describe the impact of nonlinear shading caused by cloud edges on light intensity; Using the principle of optical reflection, a reflection gain model is constructed to simulate the reflection gain effect of light intensity; Combined with the light intensity variation model, a mathematical model of photovoltaic array power fluctuation is established; Based on the modeling results, the influence of nonlinear shading and reflection gain effects on power fluctuations is quantified.

5. The AI-based integrated management method for solar power generation according to claim 4, characterized in that: The working state of the PV module is determined based on the judgment result of whether the light-induced degradation of the PV module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the PV array. The working state of the PV module includes normal working state and abnormal working state, specifically: Preset the volatility coefficient threshold and compare the volatility coefficient with the volatility coefficient threshold: When the volatility coefficient is greater than the volatility coefficient threshold, it means that the nonlinear shading and reflection gain effect of the cloud edge has a high degree of influence on the power fluctuation of the photovoltaic array; When the volatility coefficient is less than or equal to the volatility coefficient threshold, it means that the nonlinear shading and reflection gain effect of the cloud edge has a low impact on the power fluctuation of the photovoltaic array. When the probability value of the reversible light-induced degradation is greater than the reversible threshold and the volatility coefficient is less than or equal to the volatility coefficient threshold, the working state of the photovoltaic module is determined to be a normal working state; otherwise, the working state of the photovoltaic module is determined to be an abnormal working state.

6. An AI-based integrated solar power generation management system, used to implement the AI-based integrated solar power generation management method according to any one of claims 1 to 5, characterized in that: It includes attenuation reversibility judgment module, power fluctuation assessment module, working status determination module, transmittance analysis module and comprehensive analysis module; The attenuation reversibility judgment module analyzes the light-induced attenuation data of photovoltaic modules and determines whether the light-induced attenuation of photovoltaic modules is reversible based on the convolutional neural network; The power fluctuation assessment module evaluates the impact of nonlinear shading and reflection gain effects at the cloud edge on the power fluctuation of the photovoltaic array based on the light intensity change data in the area with sudden changes in light intensity at the cloud edge. The working status determination module determines the working status of the photovoltaic module based on the judgment result of whether the light-induced degradation of the photovoltaic module is reversible and the degree of influence of the nonlinear shading and reflection gain effect of the cloud edge on the power fluctuation of the photovoltaic array. The working status of the photovoltaic module includes normal working status and abnormal working status. When the working state of the photovoltaic module is abnormal, the transmittance analysis module analyzes the transmittance change of the photovoltaic module surface to evaluate the nonlinear attenuation effect of the aerosol retention layer on the transmittance of the photovoltaic module; The comprehensive analysis module comprehensively analyzes the impact of the nonlinear shading and reflection gain effects of the cloud edge on the power fluctuation of the photovoltaic array and the nonlinear attenuation of the aerosol retention layer on the transmittance of the photovoltaic module to determine whether to activate the operation and maintenance plan.

7. An AI-based integrated solar power generation management device, characterized in that: include: A processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein when the program or instruction is executed by the processor, an AI-based integrated management method for solar power generation is implemented as described in any one of claims 1 to 5.

Images