Cooperative power management system for multi-source distributed photovoltaic power generation system

Abstract

The invention discloses a collaborative power management system for a multi-source distributed photovoltaic power generation system, belongs to the field of power grid control, and particularly relates to a collaborative power management and power grid control technology of a power distribution network, and the system comprises a data processing module which is used for determining first and second state parameters of photovoltaic modules of different materials; the power attenuation module is used for determining a first power attenuation amount and a second power attenuation amount based on the equivalent power generation efficiency attenuation coefficient and the state parameters, and accurately predicting the total output power of the photovoltaic power generation system based on the first attenuation power and the second attenuation power; and the control module is used for comparing the total output power with an output power target value and generating a power regulation instruction to control the output power of the energy storage system and realize collaborative power management, so that smooth processing of photovoltaic power generation fluctuation and balance control of the power grid output power can be realized by implementing the photovoltaic power generation system, and the power generation efficiency is improved. Therefore, the power balance and stable operation of the power distribution network after the multi-source distributed photovoltaic access to the power grid are realized.

Description

Technical Field

[0001] This invention relates to the field of power grid control, and more particularly to a collaborative power management system for multi-source distributed photovoltaic power generation systems. Background Technology

[0002] In the field of AC distribution network operation and control, the integration of high proportions of multi-source distributed photovoltaic (PV) power has brought significant challenges to power flow management, voltage stability, and dispatch planning. The collaborative power management system of the distribution network relies on accurate prediction of the output power of distributed PV power generation systems to formulate charging and discharging strategies for energy storage systems, schedule the switching of reactive power compensation equipment, and optimize the power flow distribution of the grid.

[0003] In existing technologies, the collaborative power management system for photovoltaic (PV) power generation systems, energy storage systems, and other power grid systems in distribution networks is mainly based on macroscopic predictions of the overall output power of PV power generation systems to formulate energy storage charging and discharging strategies. However, current power predictions neglect the differentiated performance of PV modules made of different materials in multi-source distributed PV power generation systems under specific environments. Especially in dry environments, the accumulation of dust on the surface of PV modules due to static electricity causes the management system to be unable to adjust its judgment on the output power of PV power generation systems in a timely manner when faced with sudden environmental changes. As a result, the energy storage charging and discharging plan formulated based on PV predictions does not match the actual demand during the power system management process. This fails to effectively smooth the power fluctuations injected into the distribution network, causing the line power flow to deviate from expectations, increasing the risk of line overload or voltage exceeding limits, and leading to unstable grid operation. Summary of the Invention

[0004] This invention provides a collaborative power management system for multi-source distributed photovoltaic power generation systems, which can solve the problem of how to overcome the power prediction deviation caused by the difference in the state of materials and components of distributed photovoltaic power generation systems, thereby improving the accuracy of power management of photovoltaic and energy storage collaboration in the distribution network, so as to maintain the power flow stability and voltage quality of the distribution network.

[0005] This invention provides a collaborative power management system for multi-source distributed photovoltaic power generation systems, comprising: The data processing module is used to acquire the first state data of the glass photovoltaic module and the second state data of the plastic photovoltaic module; A power attenuation module, connected to the data processing module, is used to determine a first equivalent power generation efficiency attenuation coefficient of the glass photovoltaic module based on the first state data, and to determine a first power attenuation amount based on the first equivalent power generation efficiency attenuation coefficient; to determine a second equivalent power generation efficiency attenuation coefficient of the plastic photovoltaic module based on the second state data, and to determine a second power attenuation amount based on the second equivalent power generation efficiency attenuation coefficient; and to determine the predicted output power value of the photovoltaic power generation system based on the first power attenuation amount, the second power attenuation amount, the first state data, and the second state data. The control module, connected to the power attenuation module, is used to generate a charge / discharge control command for the energy storage control system based on the difference between the predicted output power value and the target output power value of the distribution network, if the difference is greater than a preset deviation threshold, and to control the output power of the energy storage control system based on the charge / discharge control command, so as to realize the coordinated power management of the photovoltaic power generation system and the energy storage control system by the distribution network.

[0006] This invention achieves differentiated and precise perception of the dust accumulation characteristics of photovoltaic modules made of glass and plastic materials by acquiring state parameters (such as electrostatic parameters and dust density), providing a data foundation for accurate evaluation. By determining the power attenuation of modules made of different materials separately based on their state parameters, it overcomes the error of evaluating photovoltaic arrays as a homogeneous whole, improving the accuracy of power prediction for photovoltaic power generation systems in specific environments (such as dry environments). Furthermore, by integrating the equivalent power generation efficiency attenuation coefficient, power attenuation, and electrostatic parameters for system-level prediction, it achieves forward-looking prediction from the microscopic state of the modules to the macroscopic output of the system. By comparing the difference between the predicted output power of the photovoltaic power generation system and the target output power corresponding to the power demand of the distribution network, the energy storage system is controlled, improving the accuracy of the distribution network's coordinated power management of photovoltaic and energy storage, thereby maintaining the power flow stability and voltage quality of the distribution network.

[0007] Furthermore, the step of generating charge / discharge control commands for the energy storage control system based on the difference, and controlling the output power of the energy storage control system according to the charge / discharge control commands, specifically involves: The current state of charge and maximum charge / discharge power of the energy storage control system are obtained. If the current state of charge is greater than or equal to a preset safety threshold and the maximum charge / discharge power is greater than the power adjustment amount corresponding to the difference, a charge / discharge control command corresponding to the power adjustment amount is generated. If the current state of charge is less than the preset safety threshold, or the maximum charging / discharging power is less than or equal to the power adjustment amount, the maximum power adjustment amount of the energy storage control system is determined, and a charging / discharging control command corresponding to the maximum power adjustment amount is generated. Furthermore, a collaborative scheduling command is generated based on the second difference between the power adjustment amount and the maximum power adjustment amount, and the microgrid or distributed power source within a preset distance range is controlled according to the collaborative scheduling command.

[0008] By generating charge and discharge control commands corresponding to the power adjustment, precise power commands can be executed within the energy storage system's capacity, achieving optimal power support. Generating coordinated dispatch commands activates a system-level redundancy backup mechanism when the energy storage system's output power is insufficient. Through collaboration with microgrids or nearby distributed power sources, the system's resilience and reliability in extreme situations are greatly enhanced, ensuring the power supply security of critical loads.

[0009] Furthermore, the acquisition of first state data for glass photovoltaic modules and second state data for plastic photovoltaic modules, wherein the first state data includes a first electrostatic parameter and a first dust density, and the second state data includes a second electrostatic parameter and a second dust density, wherein both the first and second electrostatic parameters are used to characterize changes in electrostatic adsorption performance, specifically: When the ambient humidity data is lower than the preset humidity threshold, a dry environment monitoring command is generated and responded to, and the electrostatic field strength of the glass photovoltaic module and the plastic photovoltaic module is measured respectively to obtain the first electrostatic field strength distribution and the second electrostatic field strength distribution. By analyzing the first electrostatic field strength distribution, the electrostatic uniform region of the glass photovoltaic module is determined, and the ratio of the electric field strength of the electrostatic uniform region to the preset electric field strength is calculated to obtain the first electrostatic parameter. The electrostatic uniform region refers to the region where the field strength value changes continuously and the deviation between the field strength at any point and the average field strength of the region does not exceed a first preset threshold. By analyzing the second electrostatic field strength distribution, the electrostatic non-uniform region of the plastic photovoltaic module is determined, and the second electrostatic parameter is determined based on the average electric field strength of the electrostatic non-uniform region. The electrostatic non-uniform region refers to a region where there is a sudden change in field strength and a local point field strength deviates from the regional average field strength by more than a second preset threshold. The first dust accumulation thickness per unit area of ​​the glass photovoltaic module is obtained by detecting the dust using a laser dust detection sensor, and the first dust density is calculated by combining the first electrostatic parameter. The dust coverage rate is obtained by processing the photovoltaic surface image of the plastic photovoltaic module using image recognition technology, and the second dust accumulation thickness and the second electrostatic parameter of the plastic photovoltaic module are measured by laser triangulation method, and the second dust density is calculated.

[0010] This approach, by triggering a dry environment monitoring command when the ambient humidity falls below a threshold, achieves triggered intelligent monitoring, optimizing resource utilization and ensuring data validity. By analyzing the electrostatic field intensity distribution and distinguishing between uniform and non-uniform regions to extract electrostatic parameters, precise quantification of the spatial distribution characteristics of electrostatics is achieved, making the parameters more closely aligned with the material's physical properties. For glass components, laser dust detection combined with electrostatic parameters to calculate dust density, and for plastic components, image recognition and laser triangulation are combined to achieve precise and customized measurements through multi-sensor information fusion.

[0011] Furthermore, the determination of the first equivalent power generation efficiency attenuation coefficient of the glass photovoltaic module based on the first state data specifically involves: Based on the first dust density, the concentration of environmental particulate matter is obtained by inversion using a sedimentation model. A correlation analysis was performed between the environmental particulate matter concentration and the first electrostatic parameter to determine the dust adsorption growth rate. Based on the dust adsorption growth rate and the first dust density, the first equivalent power generation efficiency attenuation coefficient is calculated using the transmittance attenuation function.

[0012] This approach, by inverting environmental particulate matter concentration based on dust density, allows for the inference of environmental causes from the "result" on the component surface, providing input for predicting future dust accumulation trends. By correlating environmental particulate matter concentration with electrostatic parameters to determine the dust adsorption rate, a quantitative prediction of future dust accumulation speed is achieved. Furthermore, by combining the dust adsorption rate and current dust density to calculate the first equivalent power generation efficiency decay coefficient, a dynamic and nonlinear assessment of the first equivalent power generation efficiency decay coefficient is realized, making the assessment results closer to the actual physical process.

[0013] Furthermore, the step of determining the second equivalent power generation efficiency attenuation coefficient of the plastic photovoltaic module based on the second state data, and determining the second power attenuation amount based on the second equivalent power generation efficiency attenuation coefficient, specifically involves: The surface image of the plastic photovoltaic module is binarized to obtain dust areas and clean areas. The dust coverage rate is obtained based on the ratio of the area of ​​the dust area to the total area. Based on the dust coverage rate, a preset mapping relationship table between the dust coverage rate and the average light transmittance is queried to determine the second equivalent power generation efficiency attenuation coefficient. The actual output power is determined based on the second equivalent power generation efficiency attenuation coefficient and the preset output power of the plastic photovoltaic module under the current irradiance. The second power attenuation is obtained by calculating the actual output power and the preset output power.

[0014] By binarizing the surface image to obtain the dust coverage rate, a rapid and intuitive assessment of the dust distribution area on the surface of plastic components is achieved. By querying a preset mapping table, the dust coverage rate is converted into a second equivalent power generation efficiency attenuation coefficient, enabling a rapid and efficient conversion from spatial coverage to optical blocking effects. The actual output power is determined based on the second equivalent power generation efficiency attenuation coefficient, achieving direct calculation of power attenuation based on optical principles, with clear and accurate logic.

[0015] Furthermore, determining the predicted output power of the photovoltaic power generation system based on the first power attenuation, the second power attenuation, the first state data, and the second state data specifically involves: The first capacity proportion of the glass photovoltaic module in the photovoltaic power generation system and the second capacity proportion of the plastic photovoltaic module are determined respectively. The first electrostatic parameter is weighted according to the first capacity ratio to obtain a first electrostatic weighted result, and the second electrostatic parameter is weighted according to the second capacity ratio to obtain a second electrostatic weighted result. The comprehensive electrostatic parameters of the photovoltaic power generation system are obtained by combining the first electrostatic weighted result and the second electrostatic weighted result. The first power attenuation is weighted according to the first capacity ratio to obtain a first power weighted result, and the second power attenuation is weighted according to the second capacity ratio to obtain a second power weighted result. The current power attenuation is obtained by combining the first power weighted result and the second power weighted result. The environmental humidity prediction data is obtained by inputting the current power attenuation, the comprehensive electrostatic parameters, the environmental humidity prediction data, and the initial output power prediction value of the photovoltaic power generation system into a time series prediction model to obtain the output power prediction value.

[0016] By introducing weighting factors through the first and second capacity proportions, it becomes clear that different component types contribute differently to the system. Weighting electrostatic parameters and power attenuation based on capacity proportions yields comprehensive electrostatic parameters and current power attenuation, enabling system state integration from micro to macro levels. Through weighted averaging, multiple parameters characterizing different component materials are synthesized into a single macroscopic parameter representing the current state and future trends of the entire photovoltaic power generation system, providing accurate input for system-level power prediction. Acquiring environmental humidity prediction data and inputting it into the time series prediction model enhances the model's responsiveness to key environmental drivers, making the prediction results more forward-looking.

[0017] Furthermore, the time series prediction model is trained based on a historical dataset, which includes historical environmental humidity data, historical comprehensive electrostatic parameters, historical power attenuation, and corresponding historical power training data, specifically: The historical dataset is divided into a training set and a validation set according to the time series. An initial time series prediction model is constructed based on an LSTM neural network. The root mean square error between the model's predicted value and the historical power training data is used as the loss function. The initial time series prediction model is trained using the training set, and the model hyperparameters are adjusted using the validation set to obtain the time series prediction model.

[0018] This time series forecasting model, built upon an LSTM neural network, leverages the LSTM model's strength in handling long-term dependencies in time series data. It effectively learns the complex nonlinear relationships between power decay, environmental changes, and power generation, capturing their dynamic evolution and significantly improving prediction accuracy. Using the root mean square error as the loss function ensures that the training objective directly optimizes the deviation between predicted and true values, guiding the model towards its most practical convergence. Adjusting the model's hyperparameters using a validation set effectively avoids overfitting, ensuring the model maintains good generalization ability when facing unknown new data and improving the system's robustness.

[0019] Further, determining the first power attenuation amount based on the first equivalent power generation efficiency attenuation coefficient specifically involves: Based on the first equivalent power generation efficiency attenuation coefficient, the first initial power attenuation is determined through the first mapping relationship. At the same time, the mass density difference is calculated based on the first dust density. The first theoretical power attenuation is obtained by calculating the mass density difference, the first electrostatic parameter, and the power attenuation linear coefficient. Calculate the third difference between the first theoretical power attenuation and the first initial power attenuation. If the third difference is greater than or exceeds the second preset threshold, adjust the power attenuation linearity coefficient according to the first initial power attenuation to obtain the target power attenuation linearity coefficient. The first power attenuation amount is calculated based on the target power attenuation linearity coefficient.

[0020] This dual verification mechanism establishes a system where the initial power attenuation is determined based on the first equivalent power generation efficiency attenuation coefficient, and the first theoretical power attenuation is obtained based on the mass density difference. The measurement of the first equivalent power generation efficiency attenuation coefficient serves as a direct and reliable "benchmark truth," while the mass density model acts as a "theoretical prediction" with adjustable parameters. Calculating the third difference to determine whether to adjust the power attenuation linearity coefficient enables online self-calibration of the model. When a significant deviation occurs between the theoretical prediction and the benchmark truth, the system automatically adjusts the model parameters, continuously approximating the actual physical process. This allows the system to adapt to environmental characteristics in different locations and seasons, possesses continuous learning and optimization capabilities, and maintains high accuracy over the long term.

[0021] Furthermore, the power attenuation linear coefficient is obtained through linear regression analysis of historical datasets, wherein the historical datasets include multiple sets of dust density sequence data, environmental humidity sequence data, and corresponding actual power attenuation sequence data, specifically: The environmental humidity sequence data is divided into multiple environmental humidity intervals, and the dust density sequence data and the actual power attenuation sequence data are divided according to each environmental humidity interval. Multiple linear regression analysis is performed on the divided data, with dust density and electrostatic parameters as independent variables and actual power attenuation value as dependent variable, to obtain the preset power attenuation linear coefficient corresponding to each environmental humidity interval.

[0022] By dividing the environmental humidity sequence data into multiple intervals, it can be recognized that humidity is a key factor affecting the "dust-power attenuation" relationship, allowing for a "divide and conquer" strategy. Multiple linear regression analysis is performed on the data within each humidity interval, yielding corresponding linear coefficients that enable customized assessment models for different humidity environments. For example, coefficients in dry environments (low humidity) amplify the effect of electrostatic adsorption, while coefficients in humid environments (high humidity) better reflect the effect of gravitational settling. A pre-defined power attenuation linear coefficient lookup table allows the system to quickly query and retrieve the most suitable parameters based on real-time humidity during operation, ensuring high accuracy in power attenuation assessment under various weather conditions and significantly enhancing the system's environmental adaptability.

[0023] Furthermore, the collaborative power management system for multi-source distributed photovoltaic power generation systems also includes: The cleaning module is used to calculate the cleaning benefit based on the first power attenuation and the second power attenuation. When the fourth difference between the cleaning benefit and the cleaning cost is greater than a third preset threshold, and the predicted output power value is expected to be lower than the target output power value for a period of time greater than a preset time threshold, a cleaning scheduling instruction is generated. The cleaning scheduling instruction is used to start the cleaning device to clean the surface of the photovoltaic module and to determine the cleaning sequence based on the magnitude of the first power attenuation and the second power attenuation.

[0024] This method calculates cleaning revenue based on power attenuation. When the fourth difference between the cleaning revenue and cleaning cost exceeds a threshold, a cleaning dispatch instruction is generated. This transforms cleaning decisions from time- or experience-driven to data-driven, economically sound decisions. Cleaning is only initiated when the power generation revenue from cleaning significantly exceeds the cost, maximizing the return on investment for O&M activities. Determining the cleaning sequence based on the magnitude of the first and second power attenuation allows for optimal allocation of cleaning resources. Prioritizing the cleaning of component types with more severe power attenuation enables the fastest restoration of system power generation capacity with minimal cleaning costs, improving O&M efficiency. Attached Figure Description

[0025] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the structure of a collaborative power management system for a multi-source distributed photovoltaic power generation system provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of another collaborative power management system for a multi-source distributed photovoltaic power generation system provided in an embodiment of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0029] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0030] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0031] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0032] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0033] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0034] See Figure 1To address the issue of power prediction deviations caused by differences in the material and component conditions of distributed photovoltaic (PV) power generation systems in existing technologies, thereby improving the accuracy of power management of PV and energy storage in the distribution network to maintain power flow stability and voltage quality, an embodiment of the present invention provides a collaborative power management system 100 for multi-source distributed PV power generation systems, comprising: The data processing module 102 is used to acquire the first electrostatic parameter and the first dust density of the glass photovoltaic module, and the second electrostatic parameter and the second dust density of the plastic photovoltaic module, wherein the first electrostatic parameter and the second electrostatic parameter are used to characterize the change in electrostatic adsorption performance.

[0035] As an example of an embodiment of the present invention, the acquisition of first state data of a glass photovoltaic module and second state data of a plastic photovoltaic module, wherein the first state data includes a first electrostatic parameter and a first dust density, and the second state data includes a second electrostatic parameter and a second dust density, both the first and second electrostatic parameters being used to characterize changes in electrostatic adsorption performance, specifically: when the ambient humidity data is lower than a preset humidity threshold, a dry environment monitoring command is generated and responded to, and the electrostatic field strength of the glass photovoltaic module and the plastic photovoltaic module are measured respectively to obtain a first electrostatic field strength distribution and a second electrostatic field strength distribution; by analyzing the first electrostatic field strength distribution, the electrostatic uniform region of the glass photovoltaic module is determined, and the ratio of the electric field strength of the electrostatic uniform region to the preset electric field strength is calculated to obtain the first electrostatic parameter, wherein the electrostatic uniform region refers to the electric field strength... The region is defined as follows: The electrostatic field strength distribution is analyzed to determine the electrostatic non-uniform region of the plastic photovoltaic module. Based on the average electric field strength of the electrostatic non-uniform region, the second electrostatic parameter is determined. The electrostatic non-uniform region refers to a region where there are sudden changes in field strength and where the deviation between the field strength at a local point and the average field strength of the region exceeds the second preset threshold. A laser dust detection sensor is used to detect the first dust accumulation thickness per unit area of ​​the glass photovoltaic module. Combined with the first electrostatic parameter, the first dust density is calculated. Image recognition technology is used to process the photovoltaic surface image of the plastic photovoltaic module to obtain the dust coverage rate. A laser triangulation method is used to measure the second dust accumulation thickness and the second electrostatic parameter of the plastic photovoltaic module, and the second dust density is calculated.

[0036] In this embodiment, when the ambient humidity sensor detects that the ambient humidity data is lower than a preset threshold, the system determines that the photovoltaic module is in a dry environment and automatically generates a dry environment monitoring command. In response to this command, the system initiates electrostatic field strength measurement of the photovoltaic module. For glass photovoltaic modules, a non-contact electrometer is used to scan and measure along a predetermined grid path on the module surface, obtaining a set of discrete field strength values. A continuous first electrostatic field strength distribution is generated using a spatial interpolation algorithm. When analyzing this distribution, the sliding window method is used to calculate the average field strength and standard deviation of the local area. Areas where the field strength value changes continuously, and the deviation of the field strength at any measurement point within the window from the average field strength of the window does not exceed a first preset threshold (e.g., ±5%), are identified as electrostatically uniform regions. Subsequently, the average electric field strength of this electrostatically uniform region is calculated and compared with an ideal electric field strength value preset based on material properties. The ratio of the two is calculated, and this ratio is determined as the first electrostatic parameter, used to quantify the degree of deviation of the current electrostatic adsorption performance from the ideal state.

[0037] For photovoltaic modules made of plastic, the second electrostatic field intensity distribution is also obtained by scanning with a non-contact electrometer. When analyzing this distribution, the focus is on identifying regions where the field intensity value changes abruptly; that is, regions where the field intensity at a local point deviates from the average field intensity of the surrounding larger area by more than a second preset threshold (e.g., ±15%). These regions are defined as electrostatically non-uniform regions. The average electric field intensity of these electrostatically non-uniform regions is calculated, and this average field intensity value is directly used as the basis for calculating the second electrostatic parameter. This parameter reflects the electrostatic adsorption characteristics of the plastic surface caused by material inhomogeneity or localized charge accumulation.

[0038] While acquiring electrostatic parameters, dust density is measured. For glass photovoltaic modules, a laser dust detection sensor is used. This sensor emits a laser beam and detects the intensity of light scattered by dust on the module surface. Combining this with a known optical model, the initial dust accumulation thickness per unit area is calculated. Subsequently, the obtained initial dust accumulation thickness is multiplied by the previously calculated initial electrostatic parameters to comprehensively reflect the enhanced dust adhesion due to electrostatic adsorption, ultimately yielding the initial dust density.

[0039] For plastic photovoltaic modules, determining dust density combines two technologies. First, high-definition cameras capture images of the photovoltaic surface. Image recognition technology is used to perform grayscale analysis and contour recognition, calculating the percentage of dust-covered area to the total area, thus obtaining the dust coverage rate. Simultaneously, laser triangulation is employed. By emitting a laser onto the module surface and detecting the positional shift of the reflected light spot on the sensor, the second accumulated dust thickness is precisely measured. Finally, the second accumulated dust thickness, the calculated dust coverage rate, and the second electrostatic parameter are fused (e.g., by weighted averaging or a combination based on empirical formulas) to obtain a more comprehensive and accurate second dust density. This density value considers the physical coverage thickness, the coverage area ratio, and the influence of electrostatic adsorption on the dust adhesion state.

[0040] The power attenuation module 104, connected to the data processing module 102, is used to determine the first equivalent power generation efficiency attenuation coefficient of the glass photovoltaic module based on the first state data, and determine the first power attenuation amount based on the first equivalent power generation efficiency attenuation coefficient; determine the second equivalent power generation efficiency attenuation coefficient of the plastic photovoltaic module based on the second state data, and determine the second power attenuation amount based on the second equivalent power generation efficiency attenuation coefficient; and determine the predicted output power value of the photovoltaic power generation system based on the first power attenuation amount, the second power attenuation amount, the first state data, and the second state data.

[0041] In this embodiment, the glass material has a smooth surface and uniform electrostatic distribution. Dust adsorption forms a uniform covering layer that affects the overall incident light flux. Therefore, the first equivalent power generation efficiency attenuation coefficient is characterized by transmittance as an index to represent the attenuation of light transmission efficiency. In contrast, the surface characteristics of plastic materials easily lead to uneven electrostatic distribution and localized dust accumulation. Their impact on power generation is mainly manifested as obstruction of the effective light-receiving area. Therefore, dust coverage and average light transmission blocking rate are used to reflect area loss. Specifically, for glass photovoltaic modules, a mapping relationship between the first dust density and the concentration of environmental particulate matter is first established. This mapping relationship is used to derive the current environmental particulate matter concentration level. Subsequently, a correlation analysis is performed between the first electrostatic parameter and the environmental particulate matter concentration to quantify the enhancing effect of electrostatic adsorption on dust accumulation. Then, the comprehensive first equivalent power generation efficiency attenuation coefficient of the module surface is calculated using an optical attenuation model. Finally, based on the linear relationship between the first equivalent power generation efficiency attenuation coefficient and power output in photovoltaic power generation characteristics, the first power attenuation amount is determined using the value of the first equivalent power generation efficiency attenuation coefficient. For photovoltaic modules made of plastic materials, the proportion of the dust-covered area to the total area of ​​the module, i.e., the dust coverage rate, is identified and calculated by analyzing the coverage characteristic information contained in the second dust density. Then, according to the area loss model, the dust coverage rate is directly mapped to the degree of reduction in power generation efficiency, thereby determining the second power attenuation.

[0042] Meteorological forecasts, including irradiance and ambient temperature, for a specific future period are obtained, and based on this, the initial predicted output power of the photovoltaic power generation system under ideal cleanliness conditions for the module surfaces are calculated. Subsequently, based on the capacity ratio of glass and plastic photovoltaic modules in the system, the first electrostatic parameter, the second electrostatic parameter, and the first and second power attenuation amounts calculated using the first equivalent power generation efficiency attenuation coefficient are fused to obtain a comprehensive electrostatic parameter characterizing the overall dust adsorption characteristics of the system and the current total power attenuation. Finally, combined with predicted data on future ambient humidity trends, the initial predicted output power, total power attenuation, and comprehensive electrostatic parameter are input into a time series prediction model. This model dynamically adjusts the predicted power attenuation value by quantifying the impact of comprehensive electrostatic parameters and humidity changes on future dust accumulation rates or dissipation potential, and then subtracts this attenuation from the initial predicted output power value to calculate the final predicted output power of the photovoltaic power generation system.

[0043] The control module 106, connected to the power attenuation module 104, is used to generate a charge and discharge control command for the energy storage control system based on the difference between the predicted output power value and the target output power value of the distribution network, if the difference is greater than a preset deviation threshold, and to control the output power of the energy storage control system based on the charge and discharge control command, so as to realize the coordinated power management of the photovoltaic power generation system and the energy storage control system by the distribution network.

[0044] As an example of an embodiment of the present invention, the step of generating a charge / discharge control command for the energy storage control system based on the difference, and controlling the output power of the energy storage control system based on the charge / discharge control command, specifically involves: obtaining the current state of charge and maximum charge / discharge power of the energy storage control system; if the current state of charge is greater than or equal to a preset safety threshold, and the maximum charge / discharge power is greater than the power adjustment amount corresponding to the difference, then generating a charge / discharge control command corresponding to the power adjustment amount; if the current state of charge is less than the preset safety threshold, or the maximum charge / discharge power is less than or equal to the power adjustment amount, determining the maximum power adjustment amount of the energy storage control system, and generating a charge / discharge control command corresponding to the maximum power adjustment amount; furthermore, generating a collaborative scheduling command based on a second difference between the power adjustment amount and the maximum power adjustment amount, and controlling the microgrid or distributed power source within a preset distance range based on the collaborative scheduling command.

[0045] In this embodiment, when the difference between the predicted output power and the target power exceeds a preset threshold, a power compensation decision mechanism is activated. This mechanism first assesses the real-time operating status and capacity limits of the energy storage control system itself, and generates preliminary charging and discharging control commands based on this. Its core principle is to ensure that the commands are within the safe and feasible operating range of the energy storage system. If the assessment finds that the energy storage system alone cannot fully compensate for the power difference, a system coordination mechanism is further activated to calculate the remaining difference between the maximum compensation power that the energy storage system can provide and the total demand power, and generates coordinated dispatch commands for other distributed power sources or microgrids accordingly. Finally, by executing this series of commands, coordinated control of the output power of the energy storage system and other controllable units is achieved, thereby ensuring the stability and reliability of the total output power of the photovoltaic power generation system and completing coordinated power management.

[0046] As an example of an embodiment of the present invention, such as Figure 2 As shown, another collaborative power management system 200 for multi-source distributed photovoltaic power generation systems is provided, which further includes: a cleaning module 108, used to calculate cleaning revenue based on the first power attenuation and the second power attenuation, and to generate a cleaning scheduling instruction when the fourth difference between the cleaning revenue and the cleaning cost is greater than a third preset threshold, and the predicted output power value is expected to be lower than the output power target value for a period of time greater than a preset time threshold. The cleaning scheduling instruction is used to start the cleaning device to clean the surface of the photovoltaic module, and to determine the cleaning sequence based on the magnitude of the first power attenuation and the second power attenuation.

[0047] In this embodiment, the module receives a first power attenuation amount and a second power attenuation amount from the power attenuation module. The calculation of cleaning benefits is based on the power loss represented by these attenuation amounts, converting it into economic value. Specifically, the module multiplies the power attenuation amount (in kilowatts) by the local real-time electricity price (yuan / kWh) and estimates the total energy loss caused by the continued attenuation in the next planned cleaning cycle (e.g., 24 hours), thereby calculating the economic benefits that could be recovered if cleaning is carried out. Simultaneously, the module obtains cleaning cost parameters from the system database, including water consumption, labor costs, and equipment wear and tear. The difference between the cleaning benefits and the cleaning costs is the net benefit. When this net benefit is greater than a third preset threshold (determined according to a preset rate of return on investment), and the output of the power prediction module indicates that the state of the power prediction value being lower than the target value is expected to continue for more than a preset time threshold (e.g., for 3 consecutive hours), the cleaning module determines to trigger a cleaning operation. When generating a cleaning scheduling instruction, the module determines the cleaning sequence based on the relationship between the first and second power attenuation amounts. The logic is to prioritize cleaning the component areas with more severe power attenuation to restore maximum power generation capacity as quickly as possible. For example, if the first power degradation of the glass module is significantly higher than the second power degradation of the plastic module, the cleaning sequence will instruct the cleaning device to prioritize cleaning the area of ​​the glass module. This scheduling instruction is sent to the cleaning device (such as an automated cleaning robot or a spray system) to initiate its cleaning operation on the surface of the photovoltaic module. Through this intelligent decision-making based on economic efficiency and the urgency of power recovery, the optimal allocation of cleaning resources is achieved.

[0048] As an example of an embodiment of the present invention, the step of determining the first equivalent power generation efficiency attenuation coefficient of the glass photovoltaic module based on the first state data specifically involves: obtaining the environmental particulate matter concentration by inverting the sedimentation model based on the first dust density; performing a correlation analysis between the environmental particulate matter concentration and the first electrostatic parameter to determine the dust adsorption growth rate; and calculating the first equivalent power generation efficiency attenuation coefficient based on the dust adsorption growth rate and the first dust density using a transmittance attenuation function.

[0049] In this embodiment, the environmental particulate matter concentration is first obtained by inverting the first dust density using a sedimentation model. This process is achieved by establishing a physical model based on sedimentation theory. This model uses the cumulative mass of dust collected per unit area on the surface of the photovoltaic module (i.e., the first dust density) as the core input parameter, and integrates real-time meteorological monitoring data, including wind speed, wind direction, and air turbulence intensity. The model performs inversion calculations by solving the balance equation between dust sedimentation flux and atmospheric particulate matter concentration, where the sedimentation velocity is determined based on the particle size distribution and aerodynamic characteristics of typical dust particles. In specific implementation, an iterative optimization algorithm is used to continuously adjust the assumed value of environmental particulate matter concentration in the model until the error between the theoretical sedimentation amount calculated by the model and the measured first dust density is minimized. The corresponding concentration value at this point is the current environmental particulate matter concentration obtained by inversion.

[0050] Next, a correlation analysis was performed between the environmental particulate matter concentration and the first electrostatic parameter to determine the dust adsorption growth rate. This step was accomplished using a pre-calibrated adsorption kinetic model. This model uses the environmental particulate matter concentration and the first electrostatic parameter (characterizing the enhancement factor of electrostatic adsorption capacity) as independent variables. The functional relationship typically shows that the dust adsorption growth rate is positively correlated with the environmental particulate matter concentration and proportional to a certain power of the electrostatic parameter (determined through fitting experimental data). By substituting the real-time particulate matter concentration value and the first electrostatic parameter into this model, the rate of increase in dust mass per unit area per unit time under the current conditions can be calculated, i.e., the dust adsorption growth rate.

[0051] Finally, based on the calculated dust adsorption growth rate and the measured first dust density, the first equivalent power generation efficiency attenuation coefficient of the glass photovoltaic module is calculated using the transmittance attenuation coefficient. This transmittance attenuation coefficient is constructed based on the radiative transmission theory of light through a turbid medium (dust layer), the core of which is to treat the dust layer as a homogeneous medium that absorbs and scatters light. The input parameters of the function include the total mass of the current dust layer (characterized by the first dust density), the dust adsorption growth rate (to reflect the dynamic trend of dust accumulation and its potential impact on particle packing morphology), and the optical characteristic parameters of the dust particles (such as extinction coefficient) determined by laboratory measurements. The function directly outputs the real-time first equivalent power generation efficiency attenuation coefficient of the module by calculating the attenuation ratio of the incident light intensity after passing through the dust layer. Through this series of continuous calculations based on physical models and experimental calibration, a precise and reproducible conversion from dust density and electrostatic parameters to the first equivalent power generation efficiency attenuation coefficient is achieved.

[0052] As an example of an embodiment of the present invention, determining the first power attenuation amount based on the first equivalent power generation efficiency attenuation coefficient specifically involves: determining the first initial power attenuation amount based on the first equivalent power generation efficiency attenuation coefficient through a first mapping relationship; simultaneously, calculating the mass density difference based on the first dust density; calculating the mass density difference, the first electrostatic parameter, and the power attenuation linear coefficient to obtain the first theoretical power attenuation amount; calculating the third difference between the first theoretical power attenuation amount and the first initial power attenuation amount; if the third difference is greater than or exceeds a second preset threshold, adjusting the power attenuation linear coefficient based on the first initial power attenuation amount to obtain a target power attenuation linear coefficient; and calculating the first power attenuation amount based on the target power attenuation linear coefficient.

[0053] In this embodiment, based on the calculated first equivalent power generation efficiency attenuation coefficient, a pre-generated transmittance-power attenuation mapping table is consulted. This mapping relationship is established based on the photoelectric conversion principle of photovoltaic modules and reflects the linear positive correlation between the first equivalent power generation efficiency attenuation coefficient and the output power. Through this mapping relationship, a preliminary power attenuation estimate, i.e., the first initial power attenuation, is directly obtained. Simultaneously, the mass density difference is calculated based on the first dust density. This calculation process involves subtracting the currently measured first dust density value from a baseline dust density value of the module surface calibrated experimentally under standard cleaning conditions. The resulting difference is the mass density difference, which directly reflects the degree of deviation of the current dust adhesion from the clean state. Subsequently, the mass density difference, the first electrostatic parameter, and a preset power attenuation linear coefficient are multiplied to obtain the first theoretical power attenuation. The power attenuation linear coefficient is a proportionality constant derived from regression analysis of a large amount of historical data; its physical meaning is the power attenuation caused by a unit mass density difference under a unit electrostatic adsorption capacity. Next, the third difference between the first theoretical power attenuation and the first initial power attenuation is calculated. If the absolute value of the third difference is greater than a preset second threshold, it indicates a significant deviation between the theoretical calculation based on the physical model and the initial estimate based on direct photoelectric mapping. In this case, the system initiates a coefficient adjustment process: using the first initial power attenuation as a reference benchmark closer to actual operating conditions, the power attenuation linear coefficient is adjusted in reverse according to the magnitude and direction of the third difference, so that the calculated theoretical value converges to the initial estimate. After this adjustment, a new, more accurate target power attenuation linear coefficient is obtained. Finally, using the target power attenuation linear coefficient, the previous calculation process is re-executed, that is, multiplied by the mass density difference and the first electrostatic parameter, to calculate the finally confirmed first power attenuation. This method of cross-checking the initial estimate with the theoretical calculation and dynamically correcting key coefficients effectively improves the accuracy and reliability of the power attenuation assessment results.

[0054] As an example of an embodiment of the present invention, the power attenuation linear coefficient is obtained by performing linear regression analysis on a historical dataset. The historical dataset includes multiple sets of dust density sequence data, environmental humidity sequence data, and corresponding actual power attenuation sequence data. Specifically, the environmental humidity sequence data is divided into multiple environmental humidity intervals, and the dust density sequence data and the actual power attenuation sequence data are divided according to each environmental humidity interval. A multiple linear regression analysis is performed on the divided data, with dust density and electrostatic parameters as independent variables and actual power attenuation value as dependent variables, to obtain the preset power attenuation linear coefficient corresponding to each environmental humidity interval.

[0055] In this embodiment, the system first extracts a historical dataset from a long-running database. This dataset contains multiple sets of sequence data aligned by timestamps, including a dust density sequence periodically collected by a dust sensor, an ambient humidity sequence collected by an environmental sensor, and an actual power attenuation sequence within the corresponding time period recorded by a power monitoring unit.

[0056] Subsequently, the numerical range of the entire environmental humidity series data was divided into several continuous intervals, such as a dry interval with humidity below 30%, a moderate humidity interval from 30% to 60%, and a high humidity interval above 60%. The basis for this division is that humidity has a phased impact on the physical properties of static electricity generation and dissipation.

[0057] Then, based on this humidity range division, the original dust density sequence data and actual power attenuation sequence data are also divided accordingly, thus forming multiple data subsets associated with specific humidity ranges. For example, all dust density data and actual power attenuation data collected under humidity conditions below 30% are classified into the dry range subset.

[0058] Next, multiple linear regression analysis was performed on the data subset corresponding to each humidity range. In the regression model, the dust density value and the electrostatic parameter value at the same moment were used as two independent variables, and the corresponding actual power attenuation value was used as the dependent variable. The goal of the regression analysis was to fit a linear equation of the form: actual power attenuation = k1 * dust density + k2 * electrostatic parameter + b.

[0059] By using regression algorithms such as least squares, the regression coefficients k1 and k2 corresponding to each humidity interval subset can be calculated. Here, k1 is the basic influence coefficient of dust density on power attenuation within that specific humidity interval, while k2 reflects the additional influence of electrostatic parameters. This invention defines the combination of these two coefficients, or a comprehensive coefficient integrated based on the system model, as the preset power attenuation linear coefficient corresponding to that humidity interval.

[0060] Finally, the system stores this series of preset power attenuation linear coefficients determined according to different humidity ranges in the coefficient database. In practical applications, the system automatically selects the preset power attenuation linear coefficient corresponding to the humidity range based on the real-time monitored ambient humidity value for calculation, thereby ensuring the environmental adaptability and accuracy of the power attenuation assessment model.

[0061] As an example of an embodiment of the present invention, the step of determining the second equivalent power generation efficiency attenuation coefficient of the plastic photovoltaic module based on the second state data, and determining the second power attenuation amount based on the second equivalent power generation efficiency attenuation coefficient, specifically involves: performing binarization processing on the surface image of the plastic photovoltaic module to obtain a dust area and a clean area; obtaining the dust coverage rate based on the ratio of the area of ​​the dust area to the total area; determining the current second equivalent power generation efficiency attenuation coefficient of the plastic photovoltaic module based on the dust coverage rate and the preset mapping relationship table between the dust coverage rate and the average light transmittance blocking rate; determining the actual output power based on the current second equivalent power generation efficiency attenuation coefficient and the preset output power of the plastic photovoltaic module under the current irradiance; and calculating the second power attenuation amount by comparing the actual output power with the preset output power.

[0062] In this embodiment, a high-resolution industrial camera mounted above the photovoltaic array first acquires surface images of the plastic photovoltaic modules. An adaptive thresholding algorithm is then used to binarize the images. This algorithm dynamically determines a segmentation threshold based on the grayscale distribution characteristics of local image regions, classifying pixels with grayscale values ​​higher than the threshold as dust-covered areas and those lower as clean areas. The dust coverage rate is accurately calculated by statistically analyzing the ratio of the total number of pixels in dust-covered areas to the total number of pixels on the module surface.

[0063] Subsequently, based on the calculated dust coverage rate, a pre-established mapping table is consulted. This mapping table was constructed by measuring the first equivalent power generation efficiency attenuation coefficient of plastic components under different dust coverage rates in a laboratory setting, and calculating their light obstruction relative to a clean state. The system then uses linear interpolation to find the second equivalent power generation efficiency attenuation coefficient value corresponding to the current dust coverage rate in the mapping table.

[0064] Then, by combining real-time solar irradiance monitoring data, the preset output power value of the plastic photovoltaic module under standard clean conditions is obtained. Using the current second equivalent power generation efficiency attenuation coefficient as the power attenuation factor, the actual output power of the module is calculated through a photoelectric conversion model. This model considers the attenuation effect of light transmission obstruction on incident light intensity, as well as the changes in the current-voltage characteristics of the photovoltaic cell itself.

[0065] Finally, the calculated actual output power is compared with the preset output power under clean conditions, and the difference is the second power attenuation. This calculation process fully considers the uneven distribution of dust on the surface of plastic components, and achieves accurate quantification of power loss caused by local occlusion by combining image recognition technology with optical property mapping.

[0066] As an example of an embodiment of the present invention, determining the predicted output power of the photovoltaic power generation system based on the first power attenuation, the second power attenuation, the first state data, and the second state data specifically involves: determining the first capacity proportion of the glass photovoltaic module and the second capacity proportion of the plastic photovoltaic module in the photovoltaic power generation system; weighting the first electrostatic parameter according to the first capacity proportion to obtain a first electrostatic weighted result, and weighting the second electrostatic parameter according to the second capacity proportion to obtain a second electrostatic weighted result; combining the first electrostatic weighted result and the second electrostatic weighted result to obtain the comprehensive electrostatic parameter of the photovoltaic power generation system; weighting the first power attenuation according to the first capacity proportion to obtain a first power weighted result, and weighting the second power attenuation according to the second capacity proportion to obtain a second power weighted result; combining the first power weighted result and the second power weighted result to obtain the current power attenuation; acquiring environmental humidity prediction data, and inputting the current power attenuation, the comprehensive electrostatic parameter, the environmental humidity prediction data, and the initial predicted output power of the photovoltaic power generation system into a time series prediction model to obtain the predicted output power value.

[0067] In this embodiment, firstly, the installation capacities of glass photovoltaic modules and plastic photovoltaic modules are obtained from the configuration database of the photovoltaic power generation system, and their proportions in the total system capacity are calculated, denoted as the first capacity proportion and the second capacity proportion, respectively. Next, a weighted fusion method is used to process the parameters of photovoltaic modules of different materials: the first electrostatic parameter is multiplied by the first capacity proportion to obtain the first electrostatic weighted result, and the second electrostatic parameter is multiplied by the second capacity proportion to obtain the second electrostatic weighted result. These two weighted results are then added to obtain the comprehensive electrostatic parameter reflecting the overall electrostatic adsorption characteristics of the system. Simultaneously, the first power attenuation is multiplied by the first capacity proportion to obtain the first power weighted result, and the second power attenuation is multiplied by the second capacity proportion to obtain the second power weighted result. These two weighted results are then added to obtain the current overall power attenuation of the system.

[0068] Then, the system obtains the environmental humidity prediction data sequence for a specific future period from the meteorological forecast system, and the initial output power prediction value under ideal clean conditions and predicted irradiance and temperature conditions from the photovoltaic power generation performance model. Finally, the current power attenuation, comprehensive electrostatic parameters, environmental humidity prediction data sequence, and initial output power prediction value are used as input features and fed into a pre-trained time series prediction model. This model captures the temporal dependency between feature parameters and power changes through a long short-term memory network architecture, comprehensively analyzes historical power attenuation trends, electrostatic adsorption potential, and the impact of humidity changes on dust accumulation, and finally outputs the power prediction value sequence of the photovoltaic power generation system for the specified future period. This process achieves a comprehensive consideration of the characteristics of different material components, environmental factors, and system configuration, ensuring the accuracy and practicality of power prediction.

[0069] As an example of an embodiment of the present invention, the time series prediction model is trained based on a historical dataset, wherein the historical dataset includes historical environmental humidity data, historical comprehensive electrostatic parameters, historical power attenuation, and corresponding historical power training data. Specifically, the historical dataset is divided into a training set and a validation set according to time series; an initial time series prediction model is constructed based on an LSTM neural network, using the root mean square error between the model's predicted value and the historical power training data as the loss function; the initial time series prediction model is trained using the training set; and the model hyperparameters of the initial time series prediction model are adjusted using the validation set to obtain the time series prediction model.

[0070] In this embodiment, firstly, historical operational data is collected and organized to construct a historical dataset. This dataset includes historical environmental humidity data aligned to timestamps, historical comprehensive electrostatic parameters calculated using the weighting method, historical power attenuation, and corresponding historical power training data obtained from actual measurements. This data covers different seasons, weather conditions, and component contamination states to ensure the model's generalization ability.

[0071] Subsequently, the entire historical dataset is divided chronologically, typically retaining the last 20% of the data as the validation set and the first 80% as the training set to ensure the continuity of the time series is not disrupted. An initial time series prediction model is constructed based on a long short-term memory neural network. The input layer of this model is designed to receive a feature window containing multiple time steps. The features of each time step include historical ambient humidity, historical comprehensive electrostatic parameters, historical power decay, and the historical power value of the previous time step.

[0072] The model is trained using the root mean square error between predicted values ​​and historical power training data as the loss function, and employs backpropagation and an adaptive moment estimation optimizer for parameter updates. During training, the model's performance is continuously monitored using a validation set. An early stopping mechanism is triggered to prevent overfitting when the validation set loss stops decreasing for several consecutive training epochs. Simultaneously, a grid search method is used to optimize key hyperparameters, including the number of neurons in the LSTM hidden layer, the learning rate, the dropout rate, and the length of the input time window. Through this systematic training and tuning process, a time series prediction model that accurately captures the dynamic characteristics of the system and has good prediction accuracy is finally obtained. This model can effectively integrate the combined effects of environmental humidity changes, the overall electrostatic state of the system, and existing power decay on future power generation, achieving high-precision power prediction.

[0073] It should be noted that the system embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0074] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A collaborative power management system for multi-source distributed photovoltaic power generation systems, characterized in that, include: The data processing module is used to acquire the first state data of the glass photovoltaic module and the second state data of the plastic photovoltaic module; A power attenuation module, connected to the data processing module, is used to determine a first equivalent power generation efficiency attenuation coefficient of the glass photovoltaic module based on the first state data, and to determine a first power attenuation amount based on the first equivalent power generation efficiency attenuation coefficient; to determine a second equivalent power generation efficiency attenuation coefficient of the plastic photovoltaic module based on the second state data, and to determine a second power attenuation amount based on the second equivalent power generation efficiency attenuation coefficient; and to determine the predicted output power value of the photovoltaic power generation system based on the first power attenuation amount, the second power attenuation amount, the first state data, and the second state data. The control module, connected to the power attenuation module, is used to generate a charge / discharge control command for the energy storage control system based on the difference between the predicted output power value and the target output power value of the distribution network, if the difference is greater than a preset deviation threshold, and to control the output power of the energy storage control system based on the charge / discharge control command, so as to realize the coordinated power management of the photovoltaic power generation system and the energy storage control system by the distribution network.

2. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claim 1, characterized in that, The step of generating charge and discharge control commands for the energy storage control system based on the difference, and controlling the output power of the energy storage control system based on the charge and discharge control commands, specifically involves: The current state of charge and maximum charge / discharge power of the energy storage control system are obtained. If the current state of charge is greater than or equal to a preset safety threshold and the maximum charge / discharge power is greater than the power adjustment amount corresponding to the difference, a charge / discharge control command corresponding to the power adjustment amount is generated. If the current state of charge is less than the preset safety threshold, or the maximum charging / discharging power is less than or equal to the power adjustment amount, the maximum power adjustment amount of the energy storage control system is determined, and a charging / discharging control command corresponding to the maximum power adjustment amount is generated. Furthermore, a collaborative scheduling command is generated based on the second difference between the power adjustment amount and the maximum power adjustment amount, and the microgrid or distributed power source within a preset distance range is controlled according to the collaborative scheduling command.

3. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claim 1, characterized in that, The acquisition of first-state data for glass photovoltaic modules and second-state data for plastic photovoltaic modules, wherein the first-state data includes a first electrostatic parameter and a first dust density, and the second-state data includes a second electrostatic parameter and a second dust density, wherein both the first and second electrostatic parameters are used to characterize changes in electrostatic adsorption performance, specifically: When the ambient humidity data is lower than the preset humidity threshold, a dry environment monitoring command is generated and responded to, and the electrostatic field strength of the glass photovoltaic module and the plastic photovoltaic module is measured respectively to obtain the first electrostatic field strength distribution and the second electrostatic field strength distribution. By analyzing the first electrostatic field strength distribution, the electrostatic uniform region of the glass photovoltaic module is determined, and the ratio of the electric field strength of the electrostatic uniform region to the preset electric field strength is calculated to obtain the first electrostatic parameter. The electrostatic uniform region refers to the region where the field strength value changes continuously and the deviation between the field strength at any point and the average field strength of the region does not exceed a first preset threshold. By analyzing the second electrostatic field strength distribution, the electrostatic non-uniform region of the plastic photovoltaic module is determined, and the second electrostatic parameter is determined based on the average electric field strength of the electrostatic non-uniform region. The electrostatic non-uniform region refers to a region where there is a sudden change in field strength and a local point field strength deviates from the regional average field strength by more than a second preset threshold. The first dust accumulation thickness per unit area of ​​the glass photovoltaic module is obtained by detecting the dust using a laser dust detection sensor, and the first dust density is calculated by combining the first electrostatic parameter. The dust coverage rate is obtained by processing the photovoltaic surface image of the plastic photovoltaic module using image recognition technology, and the second dust accumulation thickness and the second electrostatic parameter of the plastic photovoltaic module are measured by laser triangulation method, and the second dust density is calculated.

4. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claim 3, characterized in that, The determination of the first equivalent power generation efficiency attenuation coefficient of the glass photovoltaic module based on the first state data is specifically as follows: Based on the first dust density, the concentration of environmental particulate matter is obtained by inversion using a sedimentation model. A correlation analysis was performed between the environmental particulate matter concentration and the first electrostatic parameter to determine the dust adsorption growth rate. Based on the dust adsorption growth rate and the first dust density, the first equivalent power generation efficiency attenuation coefficient is calculated using the transmittance attenuation function.

5. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claim 3, characterized in that, The process of determining the second equivalent power generation efficiency attenuation coefficient of the plastic photovoltaic module based on the second state data, and determining the second power attenuation amount based on the second equivalent power generation efficiency attenuation coefficient, specifically involves: The surface image of the plastic photovoltaic module is binarized to obtain dust areas and clean areas. The dust coverage rate is obtained based on the ratio of the area of ​​the dust area to the total area. Based on the dust coverage rate, a preset mapping relationship table between the dust coverage rate and the average light transmittance is queried to determine the second equivalent power generation efficiency attenuation coefficient. The actual output power is determined based on the second equivalent power generation efficiency attenuation coefficient and the preset output power of the plastic photovoltaic module under the current irradiance. The second power attenuation is obtained by calculating the actual output power and the preset output power.

6. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claims 2-5, characterized in that, The step of determining the predicted output power of the photovoltaic power generation system based on the first power attenuation, the second power attenuation, the first state data, and the second state data specifically involves: The first capacity proportion of the glass photovoltaic module in the photovoltaic power generation system and the second capacity proportion of the plastic photovoltaic module are determined respectively. The first electrostatic parameter is weighted according to the first capacity ratio to obtain a first electrostatic weighted result, and the second electrostatic parameter is weighted according to the second capacity ratio to obtain a second electrostatic weighted result. The comprehensive electrostatic parameters of the photovoltaic power generation system are obtained by combining the first electrostatic weighted result and the second electrostatic weighted result. The first power attenuation is weighted according to the first capacity ratio to obtain a first power weighted result, and the second power attenuation is weighted according to the second capacity ratio to obtain a second power weighted result. The current power attenuation is obtained by combining the first power weighted result and the second power weighted result. The environmental humidity prediction data is obtained by inputting the current power attenuation, the comprehensive electrostatic parameters, the environmental humidity prediction data, and the initial output power prediction value of the photovoltaic power generation system into a time series prediction model to obtain the output power prediction value.

7. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claim 6, characterized in that, The time series prediction model is trained based on a historical dataset, which includes historical environmental humidity data, historical comprehensive electrostatic parameters, historical power attenuation, and corresponding historical power training data, specifically: The historical dataset is divided into a training set and a validation set according to the time series. An initial time series prediction model is constructed based on an LSTM neural network. The root mean square error between the model's predicted value and the historical power training data is used as the loss function. The initial time series prediction model is trained using the training set, and the model hyperparameters are adjusted using the validation set to obtain the time series prediction model.

8. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claims 2-5, characterized in that, The determination of the first power attenuation amount based on the first equivalent power generation efficiency attenuation coefficient specifically involves: Based on the first equivalent power generation efficiency attenuation coefficient, the first initial power attenuation is determined through the first mapping relationship. At the same time, the mass density difference is calculated based on the first dust density. The first theoretical power attenuation is obtained by calculating the mass density difference, the first electrostatic parameter, and the power attenuation linear coefficient. Calculate the third difference between the first theoretical power attenuation and the first initial power attenuation. If the third difference is greater than or exceeds the second preset threshold, adjust the power attenuation linearity coefficient according to the first initial power attenuation to obtain the target power attenuation linearity coefficient. The first power attenuation amount is calculated based on the target power attenuation linearity coefficient.

9. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claim 8, characterized in that, The power attenuation linear coefficient is obtained through linear regression analysis of historical datasets. These historical datasets include multiple sets of dust density sequence data, environmental humidity sequence data, and corresponding actual power attenuation sequence data, specifically: The environmental humidity sequence data is divided into multiple environmental humidity intervals, and the dust density sequence data and the actual power attenuation sequence data are divided according to each environmental humidity interval. Multiple linear regression analysis is performed on the divided data, with dust density and electrostatic parameters as independent variables and actual power attenuation value as dependent variable, to obtain the preset power attenuation linear coefficient corresponding to each environmental humidity interval.

10. The collaborative power management system for multi-source distributed photovoltaic power generation systems as described in claim 1, characterized in that, Also includes: The cleaning module is used to calculate the cleaning benefit based on the first power attenuation and the second power attenuation. When the fourth difference between the cleaning benefit and the cleaning cost is greater than a third preset threshold, and the predicted output power value is expected to be lower than the target output power value for a period of time greater than a preset time threshold, a cleaning scheduling instruction is generated. The cleaning scheduling instruction is used to start the cleaning device to clean the surface of the photovoltaic module and to determine the cleaning sequence based on the magnitude of the first power attenuation and the second power attenuation.

Images