Power generation layout optimization method, device and equipment of photovoltaic power generation system and storage medium
By extracting and analyzing the voltage, current, and temperature data of photovoltaic modules, health degradation data and power mismatch were constructed, and the layout of photovoltaic modules was optimized. This solved the system mismatch loss caused by site-adaptive layout and achieved the optimal electrical performance of the system.
Patent Information
- Application Number
- CN202511678099.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-17
- Publication Date
- 2026-03-17
AI Technical Summary
Existing photovoltaic power generation systems suffer from system mismatch losses due to site-adaptive layout, which affects the system's electrical performance and reliability.
By acquiring voltage, current, and temperature data of photovoltaic modules, feature extraction and derivative analysis are performed to construct health degradation data and power mismatch. A multi-objective optimization algorithm is then used to generate photovoltaic module reconfiguration schemes and optimize the module topology connections.
This eliminates power mismatch losses caused by site layout, ensuring optimal electrical performance and reliability of the system.
Smart Images
Figure CN121683121A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of photovoltaic power generation layout optimization technology, and in particular to a method, apparatus, equipment and storage medium for optimizing the power generation layout of a photovoltaic power generation system. Background Technology
[0002] A photovoltaic power generation system typically consists of an array of photovoltaic modules connected in series and in parallel. It outputs electrical energy to the power grid through current collection, inversion, and grid connection. The layout of the photovoltaic power generation system directly determines the output characteristics, power generation efficiency, and reliability of the electrical energy.
[0003] In existing technologies, photovoltaic power generation systems generally adopt a string layout structure, which involves connecting a certain number of photovoltaic modules in series to form a string, and then connecting multiple strings with similar operating characteristics in parallel to a string inverter. This layout is mostly determined based on the available site. However, in order to adapt to the site, it is often necessary to sacrifice the optimal electrical performance of the system, which makes the overall output characteristics of the power station more unpredictable and less smooth.
[0004] Therefore, how to solve the system mismatch loss caused by site adaptability layout and ensure the optimal electrical performance of the system has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention
[0005] This invention provides a method, apparatus, equipment, and storage medium for optimizing the power generation layout of a photovoltaic power generation system, in order to solve the technical problem of system mismatch loss caused by site adaptability layout, and to ensure the optimal electrical performance of the system.
[0006] To address the aforementioned technical problems, this invention provides a method for optimizing the power generation layout of a photovoltaic power generation system, the method comprising: Acquire photovoltaic data from several photovoltaic modules in a target photovoltaic power generation system, wherein the photovoltaic data includes voltage data, current data, and temperature data; The voltage and current data of each photovoltaic module are processed by feature extraction to obtain the voltage and current response curves of several photovoltaic modules; the voltage and current response curves of each photovoltaic module are processed by derivative analysis technology to obtain the degradation characteristic quantity of each photovoltaic module. Based on the degradation characteristics and the temperature data, the health degradation data of the photovoltaic module is obtained; The voltage and current data of each photovoltaic module are processed, and a photovoltaic module traction matrix is constructed based on the obtained power mismatch. The health decline data and the photovoltaic module traction matrix are input into the constructed photovoltaic module reorganization model for processing to obtain a photovoltaic module reorganization scheme, wherein the photovoltaic module reorganization model takes maximizing the expected value of total power generation as the objective function; Based on the photovoltaic module recombination scheme, a topology connection command signal is generated, and the power generation layout of the target photovoltaic power generation system is optimized based on the topology connection command signal.
[0007] As one preferred embodiment, the step of performing feature extraction processing on the voltage and current data of each photovoltaic module to obtain voltage and current response curves for several photovoltaic modules includes: The voltage and current data of each photovoltaic module are curve-fitted using the least squares technique to obtain the initial response curve; The initial response curve is subjected to parameter feature extraction processing to obtain the voltage and current response curves of several photovoltaic modules.
[0008] As one preferred embodiment, the step of processing each voltage-current response curve using derivative analysis to obtain the degradation characteristic quantity of each photovoltaic module includes: Based on the voltage and current response curves, the short-circuit point, open-circuit point, and maximum power point of each photovoltaic module are determined. The short-circuit point of each photovoltaic module is processed using derivative analysis technology to obtain the change in series resistance; the open-circuit point of each photovoltaic module is processed using derivative analysis technology to obtain the parallel resistance attenuation rate; and the maximum power point of each photovoltaic module is processed using derivative analysis technology to obtain the power point derivative coefficient. The degradation characteristic quantity is determined based on the change in series resistance, the attenuation rate of parallel resistance, and the power point derivative coefficient.
[0009] As one preferred embodiment, obtaining the health degradation data of the photovoltaic module based on the degradation characteristic quantity and the temperature data includes: The degradation feature quantity and the temperature data are subjected to feature fusion processing to obtain a health fusion feature vector; The health fusion feature vector is processed using machine learning techniques to obtain the health degradation data of the photovoltaic module.
[0010] As one preferred embodiment, the processing of voltage and current data for each photovoltaic module, and the construction of a photovoltaic module traction matrix based on the obtained power mismatch, includes: The power mismatch degree is obtained by performing power parameter analysis on the voltage and current data of each photovoltaic module. The power mismatch is quantified using matrix modeling techniques to obtain the photovoltaic module traction matrix.
[0011] As one preferred embodiment, the step of inputting the health decline data and the photovoltaic module traction matrix into a pre-constructed photovoltaic module restructuring model for processing to obtain a photovoltaic module restructuring scheme includes: The health decline data and the photovoltaic module traction matrix are subjected to feature fusion processing to obtain the input feature set; The input feature set is input into the photovoltaic module reconfiguration model constructed by the multi-objective optimization algorithm for multi-objective optimization solution and constraint verification processing to obtain the photovoltaic module reconfiguration scheme.
[0012] As one preferred embodiment, the generation of topology connection command signals based on the photovoltaic module recombination scheme includes: Extract the component connection information of each photovoltaic module and the electrical connection relationship between several photovoltaic modules from the photovoltaic module recombination scheme; The component connection information and the electrical link relationship are encoded to obtain connection control parameters; Based on the hardware adaptation protocol and instruction frame construction rules, the connection control parameters are analyzed to obtain the topology connection instruction signal.
[0013] The present invention also provides a power generation layout optimization device for a photovoltaic power generation system, comprising: An acquisition module is used to acquire photovoltaic data of several photovoltaic modules in a target photovoltaic power generation system. The photovoltaic data includes voltage data, current data, and temperature data. An extraction module is used to perform feature extraction processing on the voltage and current data of each photovoltaic module to obtain voltage and current response curves of several photovoltaic modules; and to process each voltage and current response curve using derivative analysis technology to obtain degradation characteristic quantities of each photovoltaic module. The degradation analysis module is used to obtain the health degradation data of the photovoltaic module based on the degradation characteristic quantity and the temperature data; A construction module is used to process the voltage and current data of each photovoltaic module and construct a photovoltaic module traction matrix based on the obtained power mismatch. The processing module is used to input the health decline data and the photovoltaic module traction matrix into the constructed photovoltaic module reorganization model for processing to obtain a photovoltaic module reorganization scheme, wherein the photovoltaic module reorganization model takes the maximization of the expected value of total power generation as the objective function; An optimization module is used to generate a topology connection command signal based on the photovoltaic module recombination scheme, and to optimize the power generation layout of the target photovoltaic power generation system based on the topology connection command signal.
[0014] The present invention also provides a photovoltaic power generation layout optimization device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the photovoltaic power generation layout optimization method as described above.
[0015] The present invention further provides a computer-readable storage medium storing a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the photovoltaic power generation layout optimization method of the photovoltaic power generation system as described above.
[0016] Compared with the prior art, the beneficial effects of the present invention are at least one of the following: This invention acquires photovoltaic data from several photovoltaic modules in a target photovoltaic power generation system, including voltage, current, and temperature data. Feature extraction processing is performed on the voltage and current data of each photovoltaic module to obtain voltage and current response curves. Derivative analysis is used to process each voltage and current response curve to obtain degradation characteristic quantities for each photovoltaic module. Based on the degradation characteristic quantities and the temperature data, health degradation data of the photovoltaic modules is obtained. The voltage and current data of each photovoltaic module are processed to construct a photovoltaic module traction matrix based on the obtained power mismatch. The health degradation data and the photovoltaic module traction matrix are input into a pre-constructed photovoltaic module reconfiguration model for processing to obtain a photovoltaic module reconfiguration scheme. A topology connection command signal is generated based on the photovoltaic module reconfiguration scheme, and the power generation layout of the target photovoltaic power generation system is optimized based on the topology connection command signal.
[0017] Compared with existing technologies, this invention collects voltage, current, and temperature data of photovoltaic modules, extracts voltage and current response curves through feature extraction, and obtains degradation characteristic quantities by combining derivative analysis, thereby obtaining module health degradation data. At the same time, a photovoltaic module traction matrix is constructed based on power mismatch. The health degradation data and traction matrix are input into the recombination model to obtain the optimal recombination scheme. Finally, the series and parallel layout of the system is adjusted through topology connection instructions, which breaks through the limitations of site adaptability layout on module combination. By optimizing the combination of modules with high performance matching, the power mismatch loss caused by site layout is eliminated, ensuring the optimal electrical performance of the system. Attached Figure Description
[0018] Figure 1This is a flowchart illustrating a photovoltaic power generation layout optimization method in one embodiment of the present invention. Figure 2 This is a schematic diagram of the power generation layout optimization device of a photovoltaic power generation system in one embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the photovoltaic power generation layout optimization device in one embodiment of the present invention; Figure label: Among them, 11. Acquisition module; 12. Extraction module; 13. Decline analysis module; 14. Construction module; 15. Processing module; 16. Optimization module; 21. Processor; 22. Memory. Detailed Implementation
[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.
[0020] In the description of this invention, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.
[0021] One embodiment of the present invention provides a method for optimizing the power generation layout of a photovoltaic power generation system. For details, please refer to [link to relevant documentation]. Figure 1 , Figure 1 The diagram shown is a flowchart illustrating a photovoltaic power generation layout optimization method according to one embodiment of the present invention. The method includes: S1: Obtain photovoltaic data of several photovoltaic modules in the target photovoltaic power generation system, wherein the photovoltaic data includes voltage data, current data and temperature data; S2: Perform feature extraction processing on the voltage and current data of each photovoltaic module to obtain the voltage and current response curves of several photovoltaic modules; use derivative analysis technology to process each voltage and current response curve to obtain the degradation characteristic quantity of each photovoltaic module. S3: Based on the degradation characteristic quantity and the temperature data, obtain the health degradation data of the photovoltaic module; S4: Process the voltage and current data of each photovoltaic module and construct a photovoltaic module traction matrix based on the obtained power mismatch. S5: Input the health decline data and the photovoltaic module traction matrix into the constructed photovoltaic module reorganization model for processing to obtain a photovoltaic module reorganization scheme, wherein the photovoltaic module reorganization model takes maximizing the expected value of total power generation as the objective function; S6: Generate a topology connection command signal based on the photovoltaic module recombination scheme, and optimize the power generation layout of the target photovoltaic power generation system based on the topology connection command signal.
[0022] Specifically, high-precision current and voltage sensors are installed at the output end or string branch of each module to directly collect the real-time output voltage and current signals when the module is working. Temperature sensors are also attached to the back panel of the module or near the cells to collect the actual operating temperature of the module, ensuring that the data matches the module's operating conditions.
[0023] At the same time, voltage, current and temperature data are synchronized by timestamps to ensure that the three types of data correspond one-to-one at the same time, avoiding data misalignment during analysis.
[0024] The voltage and current data of each photovoltaic module are processed for feature extraction to obtain voltage and current response curves of several photovoltaic modules. Specifically, this includes: using least squares technique to perform curve fitting on the voltage and current data of each photovoltaic module to obtain an initial response curve; and performing parameter feature extraction on the initial response curve to obtain voltage and current response curves of several photovoltaic modules.
[0025] In this process, the voltage and current data of individual photovoltaic modules are first preprocessed to remove outliers caused by sensor interference and sudden environmental changes. Then, data noise is reduced through smoothing to ensure the stability and reliability of the original data.
[0026] Next, based on the characteristics of the voltage-current relationship of the photovoltaic module, a suitable fitting model is selected. Commonly used models include polynomial models or single diode equivalent circuit models. The model selection needs to be adapted to the actual electrical output law of the module.
[0027] Then, the preprocessed voltage data is used as the independent variable and the current data as the dependent variable, and substituted into the selected model. The optimal parameters of the model are calculated by the least squares technique. The core of the calculation process is to minimize the sum of squared errors between the actual measured values of voltage and current and the predicted values of the model for each set. The model parameters that minimize the sum of squared errors are determined through iterative calculation. The final initial response curve is a continuous representation of the original discrete data.
[0028] In this process, random interference in the original data is eliminated, and the scattered voltage and current data are transformed into smooth and continuous curves, clearly showing the relationship between the voltage and current of the component.
[0029] Based on the obtained initial response curve, key parameters that reflect the electrical performance of the component are identified and extracted point by point, including the short-circuit current corresponding to the short-circuit point, the open-circuit voltage corresponding to the open-circuit point, and the voltage, current and power value corresponding to the maximum power point. At the same time, the slope change characteristics of the curve in different voltage ranges are recorded. The extracted key parameters are then verified to ensure that the parameter values are consistent with the actual trend of the initial response curve and that there are no abnormal parameters that deviate from the curve pattern.
[0030] These verified key parameters are combined with the overall trend of the initial response curve to form the final voltage and current response curve.
[0031] The degradation characteristic quantities of each photovoltaic module are obtained by processing the voltage and current response curves using derivative analysis techniques. Specifically, this includes: determining the short-circuit point, open-circuit point, and maximum power point of each photovoltaic module based on the voltage and current response curves; processing the short-circuit point of each photovoltaic module using derivative analysis techniques to obtain the series resistance change; processing the open-circuit point of each photovoltaic module using derivative analysis techniques to obtain the parallel resistance attenuation rate; processing the maximum power point of each photovoltaic module using derivative analysis techniques to obtain the power point derivative coefficient; and determining the degradation characteristic quantities based on the series resistance change, the parallel resistance attenuation rate, and the power point derivative coefficient.
[0032] By iterating through all the data points of the voltage and current response curves, the current value corresponding to the minimum voltage value and the point that tends to be stable is selected, which is the short circuit point; the voltage value corresponding to the minimum current value and the point that tends to be stable is the open circuit point; the power value is obtained by multiplying each set of voltage and current data on the curve, and the point with the maximum power value is found. The corresponding voltage and current data pair is the maximum power point. These three points are the core locations that reflect the electrical performance of the photovoltaic module.
[0033] In obtaining the change in series resistance, a curve segment within a certain voltage range near the short-circuit point is first extracted to ensure that the segment accurately reflects the slope change of the curve around the short-circuit point. The first derivative is calculated point by point for this curve segment to obtain the derivative sequence within the range. The average value of the derivative sequence is taken as the characteristic derivative at the short-circuit point. Then, the standard characteristic derivative of the short-circuit point under the initial state of the photovoltaic module is retrieved. Combining the inverse relationship between the series resistance and the derivative at the short-circuit point, the change in series resistance is obtained by calculating the difference between the current characteristic derivative and the standard characteristic derivative and the corresponding ratio.
[0034] The parallel resistance attenuation rate follows the same process: A curve segment within a certain current range near the open-circuit point is selected, ensuring this segment reflects the slope characteristics of the curve around the open-circuit point. The first derivative is calculated point-by-point for this curve segment, and the corresponding derivative sequence is averaged as the characteristic derivative at the open-circuit point. The standard characteristic derivative at the open-circuit point under the initial state of the module is retrieved. Based on the correlation between the parallel resistance and the open-circuit point derivative, the deviation ratio between the current characteristic derivative and the standard characteristic derivative is calculated to obtain the parallel resistance attenuation rate. Parallel resistance attenuation leads to increased module leakage and decreased output efficiency, directly reflecting degradation problems such as module encapsulation aging and microcracks in the cells.
[0035] The power point derivative coefficient is obtained by accurately calculating the first derivative at the maximum power point of the voltage-current response curve and obtaining the absolute value of the derivative at that point. Simultaneously, the power value corresponding to the maximum power point is extracted, and the ratio of the absolute value of the derivative to the power value is calculated to obtain the power point derivative coefficient.
[0036] The obtained series resistance change, parallel resistance attenuation rate and power point derivative coefficient are first standardized, and then the three standardized parameters are integrated according to the reasonable weights set by the component degradation mechanism to obtain the degradation characteristic quantity.
[0037] In step S3, based on the degradation feature quantity and the temperature data, the health degradation data of the photovoltaic module is obtained, specifically including: performing feature fusion processing on the degradation feature quantity and the temperature data to obtain a health fusion feature vector; and using machine learning technology to process the health fusion feature vector to obtain the health degradation data of the photovoltaic module.
[0038] Specifically, for degraded features, outliers caused by sensor errors or sudden interference are removed, and data noise is reduced through smoothing. For temperature data, statistical features within a specified period are calculated, and high-frequency temperature data is transformed into features with the same time scale as the degraded features.
[0039] Next, the two types of preprocessed data are standardized, such as Z-score normalization, to eliminate the magnitude difference between different features. Then, the standardized degenerate features and temperature statistics are combined in a preset order using feature concatenation to form a one-dimensional health fusion feature vector.
[0040] Selecting a suitable machine learning model is crucial. Commonly used models include gradient boosting trees, random forests, or long short-term memory networks. These models can effectively capture the nonlinear relationships and temporal changes between features.
[0041] The model is trained using historical data. The training process is as follows: a large number of component health fusion feature vectors are collected as input samples, and the corresponding actual health status data are used as labels. The model parameters are adjusted through the backpropagation algorithm to minimize the error between the model's predicted output and the actual label.
[0042] After training is complete, the newly generated health fusion feature vector is input into the trained model. The model outputs health decline data by learning the mapping relationship between the features and the health status.
[0043] The voltage and current data of each photovoltaic module are processed, and a photovoltaic module traction matrix is constructed based on the obtained power mismatch. This includes: performing power parameter analysis on the voltage and current data of each photovoltaic module to obtain the power mismatch; and using matrix modeling technology to quantify the matching relationship of the power mismatch to obtain the photovoltaic module traction matrix.
[0044] Specifically, the voltage and current data of individual photovoltaic modules are preprocessed to remove outliers caused by sensor malfunctions and environmental interference. Smoothing techniques such as moving averages are used to reduce data noise and ensure the accuracy of the original data. Then, based on the processed voltage and current data, the real-time output power of the module is calculated point by point. After traversing all power values, the actual maximum power of the module is determined. Next, the actual maximum power of all modules to be analyzed in the target photovoltaic power generation system is statistically analyzed, and the average of these power values is calculated as a power reference benchmark, or the standard maximum power of modules in the same batch is selected as a reference benchmark. Finally, the power mismatch of the module is obtained by calculating the difference between the actual maximum power of the individual module and the reference benchmark, and then dividing by the reference benchmark. If the difference is positive, it means that the module power is higher than the benchmark, and if the difference is negative, it is lower than the benchmark. The larger the absolute value of the mismatch, the more significant the difference from the benchmark.
[0045] The matrix dimension is determined based on the total number of photovoltaic modules to be analyzed. If there are N modules, an N-row N-column square matrix is constructed, with each row and column corresponding to a photovoltaic module. The row index and column index identify different module numbers.
[0046] The power mismatch obtained in the first step is converted into a matching index between components. Specifically, the absolute value of the difference between the power mismatches of any two components is calculated. The smaller the absolute value, the closer the power characteristics of the two components are and the higher the matching degree. Then, the matching degree is mapped to a value in the range of 0-1 according to a preset rule. The closer the value is to 1, the higher the matching degree, and the closer it is to 0, the lower the matching degree.
[0047] Then, the mapped matching degree values are filled into the corresponding positions in the matrix, that is, the element value in the i-th row and j-th column represents the matching degree between the i-th component and the j-th component.
[0048] The process involves inputting the health degradation data and the photovoltaic module traction matrix into a pre-constructed photovoltaic module reorganization model for processing to obtain a photovoltaic module reorganization scheme. This includes: performing feature fusion processing on the health degradation data and the photovoltaic module traction matrix to obtain an input feature set; and inputting the input feature set into a photovoltaic module reorganization model constructed by a multi-objective optimization algorithm for multi-objective optimization solution and constraint verification processing to obtain the photovoltaic module reorganization scheme.
[0049] First, the health degradation data is quantified and standardized by converting scattered health indices, power attenuation rates, and other indicators into standardized values within a certain range to ensure consistent data volume and intuitive reflection of the module's health status. Next, the photovoltaic module traction matrix is dimensionally adapted by flattening the N×N matrix structure into a one-dimensional vector using row-first or column-first methods, preserving the matching degree information between all modules without losing key correlations. Then, a feature splicing strategy is adopted to combine the standardized health degradation data with the flattened traction matrix vector in a preset order to form a dimensionally unified and information-complete input feature set. Each feature element in this feature set corresponds to a health attribute of the module or a set of matching relationships between modules.
[0050] With the dual objectives of minimizing system power mismatch and maximizing overall system power generation efficiency, constraints are set, including that the total string voltage must be within the inverter MPPT operating range, the physical installation location of the components must remain unchanged, and the total number of components after reorganization must be consistent with the original system.
[0051] The solution is obtained iteratively through a multi-objective optimization algorithm: several sets of random component series-parallel combination schemes are initialized as the initial population, the fitness of each scheme is calculated using the input feature set, the population is updated through selection, crossover, mutation and other operations of the algorithm, schemes with low fitness are eliminated, and schemes with high fitness are retained and optimized, until the number of iterations reaches the threshold or the fitness score tends to stabilize, and the candidate optimal scheme is obtained.
[0052] Finally, the candidate schemes are constrained and verified. The string voltage is checked one by one to see if it meets the inverter requirements and the module connection meets the physical installation restrictions. If the verification passes, the scheme is output. If it fails, the iteration stage is returned to fine-tune the combination method until a photovoltaic module recombination scheme that meets all constraints is generated.
[0053] Finally, a topology connection command signal is generated based on the photovoltaic module reconfiguration scheme, including: extracting the module connection information of each photovoltaic module and the electrical link relationship between several photovoltaic modules from the photovoltaic module reconfiguration scheme; encoding the module connection information and the electrical link relationship to obtain connection control parameters; and analyzing the connection control parameters based on the hardware adaptation protocol and command frame construction rules to obtain the topology connection command signal.
[0054] From the photovoltaic module reconfiguration plan, the specific connection information of each module is located one by one, including the string number to which each module belongs, its series position within the string, and the specific port connected to the combiner box or inverter. At the same time, the electrical connection relationships between modules are sorted out, such as the series sequence of modules within a string and the parallel connection method between strings, to ensure that all connection relationships are completely consistent with the series and parallel logic in the plan.
[0055] The extracted component connection information is quantified using a unified encoding rule. A unique digital code is assigned to discrete information such as string number, component position, and port number. Electrical connection relationships are identified using specific symbols or binary codes, such as 01 for series connection and 10 for parallel connection.
[0056] The encoded information is organized into a fixed format of component ID-string encoding-position encoding-connection relationship encoding-port encoding to form a structured set of connection control parameters, ensuring that each parameter can uniquely correspond to a specific connection action or relationship.
[0057] According to the determined communication protocol and instruction frame structure, the connection control parameters are filled into the corresponding fields, and the fields are combined in sequence to form a complete topology connection instruction signal, which is sent to the target hardware through the communication bus. Then, the power generation layout of the target photovoltaic power generation system is optimized based on the topology connection instruction signal.
[0058] Another embodiment of the present invention provides a power generation layout optimization device for a photovoltaic power generation system. For details, please refer to [link to relevant documentation]. Figure 2 , Figure 2 The diagram shown is a structural schematic of a photovoltaic power generation layout optimization device according to one embodiment of the present invention. The device includes: The acquisition module 11 is used to acquire photovoltaic data of several photovoltaic modules in the target photovoltaic power generation system, wherein the photovoltaic data includes voltage data, current data and temperature data; The extraction module 12 is used to perform feature extraction processing on the voltage and current data of each photovoltaic module to obtain the voltage and current response curves of several photovoltaic modules; and to process each voltage and current response curve using derivative analysis technology to obtain the degradation characteristic quantity of each photovoltaic module. The degradation analysis module 13 is used to obtain the health degradation data of the photovoltaic module based on the degradation characteristic quantity and the temperature data; Module 14 is used to process the voltage and current data of each photovoltaic module and construct a photovoltaic module traction matrix based on the obtained power mismatch. Processing module 15 is used to input the health decline data and the photovoltaic module traction matrix into the constructed photovoltaic module reorganization model for processing to obtain a photovoltaic module reorganization scheme, wherein the photovoltaic module reorganization model takes maximizing the expected value of total power generation as the objective function; The optimization module 16 is used to generate a topology connection command signal based on the photovoltaic module recombination scheme, and to optimize the power generation layout of the target photovoltaic power generation system based on the topology connection command signal.
[0059] See Figure 3 This is a schematic diagram of the structure of a photovoltaic power generation layout optimization device provided in an embodiment of the present invention. The photovoltaic power generation layout optimization device includes a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, it implements the steps described in the above-described photovoltaic power generation layout optimization method embodiment, for example... Figure 1 The steps S1 to S6 described above; or, when the processor 21 executes the computer program, it implements the functions of each module in the above-described device embodiments, such as the acquisition module 11.
[0060] For example, the computer program can be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the power generation layout optimization device of the photovoltaic power generation system. For example, the computer program can be divided into an acquisition module 11, an extraction module 12, a degradation analysis module 13, etc., with the specific functions of each module as follows: The acquisition module 11 is used to acquire photovoltaic data of several photovoltaic modules in the target photovoltaic power generation system, wherein the photovoltaic data includes voltage data, current data and temperature data; The extraction module 12 is used to perform feature extraction processing on the voltage and current data of each photovoltaic module to obtain the voltage and current response curves of several photovoltaic modules; and to process each voltage and current response curve using derivative analysis technology to obtain the degradation characteristic quantity of each photovoltaic module. The degradation analysis module 13 is used to obtain the health degradation data of the photovoltaic module based on the degradation characteristic quantity and the temperature data; Module 14 is used to process the voltage and current data of each photovoltaic module and construct a photovoltaic module traction matrix based on the obtained power mismatch. Processing module 15 is used to input the health decline data and the photovoltaic module traction matrix into the constructed photovoltaic module reorganization model for processing to obtain a photovoltaic module reorganization scheme, wherein the photovoltaic module reorganization model takes maximizing the expected value of total power generation as the objective function; The optimization module 16 is used to generate a topology connection command signal based on the photovoltaic module recombination scheme, and to optimize the power generation layout of the target photovoltaic power generation system based on the topology connection command signal.
[0061] The power generation layout optimization device for the photovoltaic power generation system may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of the power generation layout optimization device for the photovoltaic power generation system and does not constitute a limitation on the device. It may include more or fewer components than shown in the diagram, or combine certain components, or use different components. For example, the power generation layout optimization device for the photovoltaic power generation system may also include input / output devices, network access devices, buses, etc.
[0062] The processor 21 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 21 is the control center of the photovoltaic power generation system's power generation layout optimization equipment, connecting various parts of the equipment through various interfaces and lines.
[0063] The memory 22 can be used to store the computer programs and / or modules. The processor 21 realizes various functions of the photovoltaic power generation system's power generation layout optimization equipment by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0064] If the modules integrated into the photovoltaic power generation layout optimization equipment are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.
[0065] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.
[0066] Accordingly, embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform steps in the photovoltaic power generation layout optimization method of the above embodiments, for example... Figure 1 Steps S1 to S6 as described above.
[0067] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.
Claims
1. A method for optimizing power generation layout of a photovoltaic power generation system, characterized in that, The method comprises the following steps: acquiring photovoltaic data of a plurality of photovoltaic components in a target photovoltaic power generation system, the photovoltaic data comprising voltage data, current data and temperature data; performing feature extraction processing on the voltage data and the current data of each photovoltaic component to obtain voltage-current response curves of the plurality of photovoltaic components; and processing each voltage-current response curve by using a derivative analysis technique to obtain a degradation characteristic quantity of each photovoltaic component; obtaining health degradation data of the photovoltaic components based on the degradation characteristic quantity and the temperature data; processing the voltage data and the current data of each photovoltaic component, and constructing a photovoltaic component traction matrix based on a power mismatch degree obtained; inputting the health degradation data and the photovoltaic component traction matrix into a constructed photovoltaic component reorganization model to obtain a photovoltaic component reorganization scheme, wherein the photovoltaic component reorganization model takes maximization of a total power generation amount expectation value as an objective function; generating a topological connection instruction signal based on the photovoltaic component reorganization scheme, and optimizing a power generation layout of the target photovoltaic power generation system based on the topological connection instruction signal.
2. The method of claim 1, wherein the method is characterized by: The feature extraction processing on the voltage data and the current data of each photovoltaic component to obtain the voltage-current response curves of the plurality of photovoltaic components comprises the following steps: performing curve fitting on the voltage data and the current data of each photovoltaic component by using a least square technique to obtain an initial response curve; performing parameter feature extraction processing on the initial response curve to obtain the voltage-current response curves of the plurality of photovoltaic components.
3. The method of claim 1, wherein the method is characterized by: The processing of each voltage-current response curve by using a derivative analysis technique to obtain a degradation characteristic quantity of each photovoltaic component comprises the following steps: determining a short-circuit point, an open-circuit point and a maximum power point of each photovoltaic component based on the voltage-current response curve; processing the short-circuit point of each photovoltaic component by using a derivative analysis technique to obtain a series resistance change quantity; processing the open-circuit point of each photovoltaic component by using a derivative analysis technique to obtain a parallel resistance attenuation rate; and processing the maximum power point of each photovoltaic component by using a derivative analysis technique to obtain a power point derivative coefficient; determining the degradation characteristic quantity based on the series resistance change quantity, the parallel resistance attenuation rate and the power point derivative coefficient.
4. The method of claim 1, wherein the photovoltaic power generation system is a solar power generation system. The obtaining of health degradation data of the photovoltaic components based on the degradation characteristic quantity and the temperature data comprises the following steps: performing feature fusion processing on the degradation characteristic quantity and the temperature data to obtain a health fusion feature vector; processing the health fusion feature vector by using a machine learning technique to obtain the health degradation data of the photovoltaic components.
5. The method of claim 1, wherein the method is characterized by: The processing of the voltage data and the current data of each photovoltaic component, and the construction of a photovoltaic component traction matrix based on a power mismatch degree obtained comprises the following steps: performing power parameter analysis processing on the voltage data and the current data of each photovoltaic component to obtain the power mismatch degree; quantifying a matching relationship of the power mismatch degree by using a matrix modeling technique to obtain the photovoltaic component traction matrix.
6. The method of claim 1, wherein the photovoltaic power system is a solar power system. The process of inputting the health decline data and the photovoltaic module traction matrix into the constructed photovoltaic module restructuring model for processing to obtain a photovoltaic module restructuring scheme includes: The health decline data and the photovoltaic module traction matrix are subjected to feature fusion processing to obtain the input feature set; The input feature set is input into the photovoltaic module reconfiguration model constructed by the multi-objective optimization algorithm for multi-objective optimization solution and constraint verification processing to obtain the photovoltaic module reconfiguration scheme.
7. The method of claim 1, wherein the method is performed by a computer system. The generation of topology connection command signals based on the photovoltaic module recombination scheme includes: Extract the component connection information of each photovoltaic module and the electrical connection relationship between several photovoltaic modules from the photovoltaic module recombination scheme; The component connection information and the electrical link relationship are encoded to obtain connection control parameters; Based on the hardware adaptation protocol and instruction frame construction rules, the connection control parameters are analyzed to obtain the topology connection instruction signal.
8. An apparatus for optimizing a power generation layout of a photovoltaic power generation system, characterized by comprising: include: The acquisition module is used to acquire photovoltaic data of several photovoltaic modules in the target photovoltaic power generation system, including voltage data, current data and temperature data. An extraction module is used to perform feature extraction processing on the voltage and current data of each photovoltaic module to obtain voltage and current response curves of several photovoltaic modules; and to process each voltage and current response curve using derivative analysis technology to obtain degradation characteristic quantities of each photovoltaic module. The degradation analysis module is used to obtain the health degradation data of the photovoltaic module based on the degradation characteristic quantity and the temperature data; A construction module is used to process the voltage and current data of each photovoltaic module and construct a photovoltaic module traction matrix based on the obtained power mismatch. The processing module is used to input the health decline data and the photovoltaic module traction matrix into the constructed photovoltaic module reorganization model for processing to obtain a photovoltaic module reorganization scheme, wherein the photovoltaic module reorganization model takes the maximization of the expected value of total power generation as the objective function; An optimization module is used to generate a topology connection command signal based on the photovoltaic module recombination scheme, and to optimize the power generation layout of the target photovoltaic power generation system based on the topology connection command signal.
9. A power generation layout optimization device for a photovoltaic power generation system, characterized by, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the power generation layout optimization method for a photovoltaic power generation system as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the photovoltaic power generation layout optimization method of any one of claims 1 to 7.