Photovoltaic module cooling method, system and equipment and storage medium

Abstract

The invention relates to the technical field of photovoltaic power generation. The invention provides a photovoltaic module cooling method, system and device and a storage medium, and the method comprises the steps: collecting the working condition parameter data of a photovoltaic module and the environment parameter data in a corresponding range of the photovoltaic module in real time, and obtaining a basic data set; based on the basic data set, a relation model between the working condition parameters and the environmental parameters of the photovoltaic module is established, the relation model is utilized to predict the temperature change trend and the output power change condition of the photovoltaic module under different environmental conditions, and a prediction result is obtained; and starting a liquid cooling, air cooling and phase change material collaborative cooling mechanism according to the prediction result, continuously monitoring the working condition parameters of the photovoltaic module in the cooling process, and dynamically adjusting and optimizing the cooling mode and the corresponding parameters according to the monitoring result. The problems that an existing photovoltaic module lacks an effective temperature adjusting means, the output power is obviously reduced when the working temperature rises, and the overall efficiency and economic benefits of a photovoltaic power generation system are reduced are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to a photovoltaic module cooling method, system, device and storage medium. Background Art

[0002] In the field of photovoltaic power generation, photovoltaic modules, as core components for converting solar energy into electricity, have a performance and stability that directly determines the overall efficiency and economic benefits of photovoltaic power generation systems. The output power of photovoltaic modules is closely related to the operating temperature, with an optimal operating temperature range of 15-25 degrees Celsius. Within this temperature range, photovoltaic modules can efficiently convert solar energy into electricity, achieving relatively ideal power generation results.

[0003] However, when the operating temperature of a photovoltaic module increases, its output power decreases significantly. Research shows that for every 1°C increase in temperature, the output power of a photovoltaic module decreases by approximately 0.35%. This phenomenon stems from the fact that rising temperature causes the open-circuit voltage of the photovoltaic module to decrease. This decrease in open-circuit voltage further negatively impacts the performance of the photovoltaic module, reducing its efficiency in converting solar energy into electricity.

[0004] Currently, photovoltaic modules lack effective temperature regulation during actual operation, especially in high-temperature environments. As temperature rises, the voltage drop across the modules increases, significantly reducing output power and leading to a significant decrease in the overall efficiency of photovoltaic power generation systems. This not only impacts the efficiency of photovoltaic power generation systems in utilizing solar energy, reducing power generation, but also directly reduces the economic benefits of photovoltaic power generation projects, hindering the further development of the photovoltaic power generation industry. Summary of the Invention

[0005] The purpose of the present invention is to provide a photovoltaic module cooling method, system, equipment and storage medium, aiming to solve the problem that existing photovoltaic modules lack effective temperature regulation means in high-temperature environments, resulting in a significant decrease in output power when the operating temperature rises, thereby reducing the overall efficiency and economic benefits of the photovoltaic power generation system, and restricting the development of the photovoltaic power generation industry.

[0006] The present invention is achieved through the following technical solutions:

[0007] A photovoltaic module cooling method comprises the following steps:

[0008] Real-time collection of operating parameter data of photovoltaic modules and environmental parameter data within the corresponding range of photovoltaic modules to obtain basic data sets;

[0009] Based on the basic data set, historical data is analyzed and learned through machine learning algorithms to establish a relationship model between the operating parameters and environmental parameters of photovoltaic modules. The relationship model is then used to predict the temperature change trend and output power change of photovoltaic modules under different environmental conditions, and the prediction results are obtained.

[0010] According to the prediction results, the coordinated cooling mechanism of liquid cooling, air cooling and phase change materials is activated. During the cooling process, the operating parameters of the photovoltaic modules are continuously monitored. According to the monitoring results, the cooling method and corresponding parameters are dynamically adjusted and optimized.

[0011] Optionally, the specific process of collecting the operating parameter data of the photovoltaic module and the environmental parameter data within the corresponding range of the photovoltaic module in real time to obtain the basic data set is:

[0012] Use temperature sensors to collect real-time temperature data on the surface and inside of photovoltaic modules;

[0013] The output current and output voltage data of the photovoltaic modules are collected in real time through current sensors and voltage sensors;

[0014] Use wind speed sensors to monitor the wind speed within the corresponding range of the photovoltaic modules in real time;

[0015] Use humidity sensors to detect the air humidity within the corresponding range of photovoltaic modules in real time;

[0016] Use the light intensity sensor to obtain the light intensity data within the corresponding range of the photovoltaic module in real time;

[0017] All the above-collected working condition parameter data and environmental parameter data are integrated to form a basic data set.

[0018] Optionally, the specific process of analyzing and learning historical data through a machine learning algorithm based on the basic data set to establish a relationship model between the operating parameters of the photovoltaic module and the environmental parameters is:

[0019] Assume that in the basic data set, the operating parameter vector of the photovoltaic module is Among them, T s,i represents the surface temperature of the photovoltaic module in the i-th sample, T i,i Indicates the internal temperature of the photovoltaic module in the i-th sample, I i represents the output current of the photovoltaic module in the i-th sample, V i represents the output voltage of the photovoltaic module in the i-th sample;

[0020] The environmental parameter vector is Among them, v i Indicates the wind speed within the range of the photovoltaic module in the i-th sample, h iIndicates the air humidity within the range corresponding to the photovoltaic module in the i-th sample, L i represents the light intensity within the corresponding range of the photovoltaic module in the i-th sample;

[0021] Combine the operating parameter vector and the environmental parameter vector to obtain the input vector The corresponding target value is the temperature or output power of the photovoltaic module;

[0022] The model is built using support vector machines, and the objective function is shown in the following formula (1):

[0023]

[0024] Among them, w represents the weight vector; w T represents the transpose of w; b represents the bias term; ξ i and Both represent slack variables, which are used to deal with samples that do not meet the error range; C represents the penalty parameter, which is used to balance the complexity and error of the model; n represents the number of samples;

[0025] The constraints are shown in formula (2):

[0026]

[0027] Among them, y i Indicates the target value corresponding to the i-th sample, w T x i +v represents the predicted value, and ∈ represents the error range.

[0028] Optionally, by introducing Lagrange multipliers, equation (1) is transformed into the following equation (3):

[0029]

[0030] Among them, α and α * Both represent Lagrange multiplier vectors; α i and Denotes the corresponding Lagrange multiplier vectors α and α * The i-th element in; K represents the kernel function;

[0031] The constraint condition is transformed into the following formula (4):

[0032]

[0033] Solve to get the optimal Lagrange multiplier μ i and The optimal weight vector w * As shown in the following formula (5):

[0034]

[0035] The relational model is shown in the following formula (6):

[0036]

[0037] Where x represents the input vector; x i represents the i-th sample vector; b * represents the optimal bias term.

[0038] Optionally, the specific process of starting the collaborative cooling mechanism of liquid cooling, air cooling and phase change material according to the prediction result is:

[0039] When the forecast results show that the temperature of the photovoltaic module will exceed the upper limit of the optimal operating temperature range in the future, and the output power is expected to drop by more than the preset threshold, the air cooling system is activated to control the fan speed so that air flows through the surface of the photovoltaic module at a preset flow rate to cool the photovoltaic module;

[0040] Based on the predicted temperature rise amplitude and rate, determine whether the liquid cooling system needs to be activated. If necessary, start the liquid cooling circulation pump to circulate the coolant in the cooling channels inside the photovoltaic module, absorb the heat generated inside the photovoltaic module, and bring the heat to the radiator for dissipation;

[0041] Phase change materials are arranged at designated locations on photovoltaic modules. When the temperature of the photovoltaic modules rises to the phase change temperature of the phase change materials, the phase change materials undergo phase change and absorb heat, helping to lower the temperature of the photovoltaic modules.

[0042] Optionally, during the cooling process, the operating parameters of the photovoltaic modules are continuously monitored, and the cooling method and corresponding parameters are dynamically adjusted and optimized according to the monitoring results. The specific process is as follows:

[0043] Continuously use temperature sensors to collect real-time temperature data on the surface and inside of photovoltaic modules, and use current sensors and voltage sensors to collect real-time output current and output voltage data of photovoltaic modules;

[0044] The real-time collected working condition parameter data is matched with the input vector structure in the previously established relational model to form a real-time working condition parameter vector;

[0045] Substitute the real-time input vector into the established relationship model to obtain the current predicted temperature and output power;

[0046] The temperature adjustment target value is set to the median value of the optimal operating temperature range, and the output power adjustment target value is set to k% of the maximum output power predicted by the relationship model under the current environmental parameters, where k is a preset proportional coefficient;

[0047] Calculate the temperature deviation and output power deviation, and dynamically adjust and optimize the cooling method and corresponding parameters according to the temperature deviation and output power deviation through preset rules.

[0048] Optionally, the preset rule is:

[0049] When the temperature deviation is greater than a preset temperature deviation threshold and the output power deviation is greater than a preset output power deviation threshold, simultaneously increasing the fan speed of the air cooling system and the coolant flow rate of the liquid cooling system;

[0050] When the temperature deviation is greater than the preset temperature deviation threshold and the output power deviation is less than or equal to the preset output power deviation threshold, only the fan speed of the air cooling system is increased;

[0051] When the temperature deviation is less than or equal to the preset temperature deviation threshold and the output power deviation is greater than the preset output power deviation threshold, only the coolant flow rate of the liquid cooling system is increased;

[0052] When the temperature deviation and the output power deviation are both less than or equal to the corresponding preset thresholds, the current cooling mode and parameters are kept unchanged.

[0053] Based on the same inventive concept, the present invention also provides a photovoltaic module cooling system for implementing the photovoltaic module cooling method, comprising a data acquisition module, a model building module, a prediction module, a cooling execution module and a dynamic adjustment module connected in sequence;

[0054] The data acquisition module is used to collect the working parameter data of the photovoltaic modules and the environmental parameter data within the corresponding range in real time using various sensors, and integrate them to form a basic data set;

[0055] The model building module is used to analyze and learn historical data based on the basic data set through a machine learning algorithm to establish a relationship model between the operating parameters of the photovoltaic module and the environmental parameters;

[0056] The prediction module is used to use the established relationship model to predict the temperature change trend and output power change of the photovoltaic module under different environmental conditions and obtain the prediction results;

[0057] The cooling execution module is used to start the coordinated cooling mechanism of liquid cooling, air cooling and phase change material according to the prediction results;

[0058] The dynamic adjustment module is used to continuously monitor the operating parameters of the photovoltaic components during the cooling process, and dynamically adjust and optimize the cooling method and corresponding parameters through a machine learning algorithm based on the monitoring results.

[0059] Based on the same inventive concept, the present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above-mentioned photovoltaic component cooling method.

[0060] Based on the same inventive concept, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned photovoltaic module cooling method when the computer program is executed by a processor.

[0061] The technical solution of the present invention has at least the following advantages and beneficial effects:

[0062] Accurate prediction and early regulation: By collecting the operating parameter data of photovoltaic modules and the environmental parameter data within the corresponding range in real time to form a basic data set, and using machine learning algorithms to conduct in-depth analysis and learning of historical data, an accurate relationship model between the operating parameters and environmental parameters is established. This can predict the temperature change trend and output power change of photovoltaic modules under different environmental conditions in advance; before the temperature rises significantly and has a serious impact on the performance of photovoltaic modules, the corresponding cooling mechanism can be started in advance based on the prediction results to avoid the output power drop caused by the temperature rise, greatly improving the stability and reliability of the photovoltaic power generation system.

[0063] Efficient collaborative cooling: The collaborative cooling mechanism of liquid cooling, air cooling and phase change materials is activated to give full play to the advantages of multiple cooling methods. Different cooling methods have their own optimal effects in different temperature ranges and environmental conditions. Working together, they can cool photovoltaic modules in an all-round and multi-level manner. Compared with a single cooling method, it can more quickly and effectively control the temperature of photovoltaic modules within the optimal operating temperature range (15-25 degrees Celsius), thereby significantly improving the efficiency of photovoltaic modules in converting solar energy into electrical energy and increasing power generation.

[0064] Dynamic optimization and adjustment: During the cooling process, the operating parameters of the photovoltaic modules are continuously monitored, and the cooling method and corresponding parameters are dynamically adjusted and optimized based on the monitoring results, so that the cooling system can adapt to the changing working conditions of the photovoltaic modules and the dynamic changes of the external environment in real time; for example, when the ambient temperature suddenly rises or the workload of the photovoltaic modules changes, the system can promptly adjust the parameters such as the liquid cooling flow rate, the air cooling speed and the intensity of the phase change material to always maintain the best cooling effect, further ensuring the stable and efficient operation of the photovoltaic modules, improving the overall efficiency of the photovoltaic power generation system, and effectively promoting the development of the photovoltaic power generation industry.

[0065] Improve economic benefits: It can effectively control the temperature of photovoltaic modules and reduce the output power drop caused by temperature increase. The power generation of photovoltaic power generation systems will increase significantly. More power generation means higher economic benefits, which has a positive effect on the return on investment of photovoltaic power generation projects. At the same time, the stable performance of photovoltaic modules also reduces the maintenance cost and failure rate of equipment, improving the overall economic benefits of photovoltaic power generation projects from multiple aspects and laying a solid foundation for the sustainable development of the photovoltaic power generation industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 Schematic diagram of a photovoltaic module cooling method according to an embodiment of the present invention;

[0067] Figure 2 Schematic diagram of the structure of a photovoltaic module cooling system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The following is a specific implementation method with reference to the accompanying drawings.

[0069] Reference Figure 1 A photovoltaic module cooling method comprises the following steps:

[0070] Step 1: Collect the operating parameter data of the photovoltaic modules and the environmental parameter data within the corresponding range of the photovoltaic modules in real time to obtain a basic data set.

[0071] In some embodiments, the specific process of collecting the operating parameter data of the photovoltaic module and the environmental parameter data within the corresponding range of the photovoltaic module in real time to obtain the basic data set is as follows:

[0072] Temperature sensors are used to collect real-time temperature data on the surface and interior of PV modules. Surface temperature sensors can be installed at multiple locations evenly spaced across the module surface (e.g., at the four corners and the center) to ensure accurate reflection of the module's average surface temperature. Internal temperature sensors are also installed at key heat-generating locations within the module (e.g., near the solar cells). After installation, the temperature sensors are calibrated and debugged to ensure accurate, real-time temperature data collection. The data collection frequency is set to once per second.

[0073] Current and voltage sensors are used to collect real-time output current and voltage data from PV modules. These sensors can be connected in series and in parallel to the PV module's output circuit, ensuring a secure connection without affecting normal circuit operation. The current and voltage sensors are calibrated to accurately collect real-time output current and voltage data from the PV module. The data collection frequency is the same as for the temperature sensor, once per second.

[0074] Use a wind speed sensor to monitor the wind speed within the PV array's range in real time. Install the wind speed sensor within the PV array's range (e.g., a 5-meter radius centered on the PV array) to ensure it accurately measures the wind speed around the PV array. Debug the wind speed sensor to collect wind speed data in real time, with a data collection frequency set to every 5 seconds.

[0075] Use a humidity sensor to monitor the air humidity within the range of the PV panels in real time. Install the humidity sensor within the range of the PV panels, choosing a suitable installation location (e.g., away from direct sunlight and water sources) to ensure accurate measurement of the air humidity within that range. Calibrate and debug the humidity sensor to enable it to collect real-time air humidity data at a frequency of once every 10 seconds.

[0076] Use a light intensity sensor to obtain real-time light intensity data within the range of the PV module. Install the light intensity sensor within the range of the PV module, in a location that receives sufficient light to ensure it accurately measures the light intensity within that range. Debug the light intensity sensor to enable it to collect light intensity data in real time, with a data collection frequency of once every 5 seconds.

[0077] All the operating parameter data and environmental parameter data collected above are integrated to form a basic data set. The data recording device integrates all the collected operating parameter data (PV module surface temperature, internal temperature, output current, output voltage) and environmental parameter data (wind speed, air humidity, light intensity). In chronological order, all parameter data at the same time are combined into a data sample. Each data sample contains the operating parameters of the PV module at that moment and the environmental parameters within the corresponding range. All data samples are stored in a data storage device (such as a hard disk) in a certain format (such as CSV format) to form a basic data set for subsequent analysis and modeling.

[0078] Step 2: Based on the basic data set, historical data is analyzed and learned through machine learning algorithms to establish a relationship model between the operating parameters and environmental parameters of photovoltaic modules. The relationship model is then used to predict the temperature change trend and output power change of photovoltaic modules under different environmental conditions to obtain prediction results.

[0079] In some embodiments, based on the basic data set, the historical data is analyzed and learned by a machine learning algorithm to establish a relationship model between the operating parameters of the photovoltaic module and the environmental parameters. The specific process is:

[0080] Assume that in the basic data set, the operating parameter vector of the photovoltaic module is Among them, T s,irepresents the surface temperature of the photovoltaic module in the i-th sample, T i,i Indicates the internal temperature of the photovoltaic module in the i-th sample, I i represents the output current of the photovoltaic module in the i-th sample, V i represents the output voltage of the photovoltaic module in the i-th sample;

[0081] The environmental parameter vector is Among them, v i Indicates the wind speed within the range of the photovoltaic module in the i-th sample, h i Indicates the air humidity within the range corresponding to the photovoltaic module in the i-th sample, L i represents the light intensity within the corresponding range of the photovoltaic module in the i-th sample;

[0082] Combine the operating parameter vector and the environmental parameter vector to obtain the input vector The corresponding target value is the temperature or output power of the photovoltaic module;

[0083] The model is built using support vector machines, and the objective function is shown in the following formula (1):

[0084]

[0085] Among them, w represents the weight vector; w T represents the transpose of w; b represents the bias term; ξ i and Both represent slack variables, which are used to deal with samples that do not meet the error range; C represents the penalty parameter, which is used to balance the complexity and error of the model; n represents the number of samples;

[0086] The constraints are shown in formula (2):

[0087]

[0088] Among them, y i Indicates the target value corresponding to the i-th sample, w T x i +b represents the predicted value, and ∈ represents the error range.

[0089] In some embodiments, by introducing Lagrange multipliers, equation (1) is transformed into the following equation (3):

[0090]

[0091] Among them, α and α * Both represent Lagrange multiplier vectors; α i and Denotes the corresponding Lagrange multiplier vectors α and α * The i-th element in; K represents the kernel function;

[0092] The constraint condition is transformed into the following formula (4):

[0093]

[0094] Solve to get the optimal Lagrange multiplier μ i and The optimal weight vector w * As shown in the following formula (5):

[0095]

[0096] The relational model is shown in the following formula (6):

[0097]

[0098] Where x represents the input vector; x i represents the i-th sample vector; b * Denotes the optimal bias term. Substituting the corresponding input vectors under different environmental conditions into the established relationship model, the predicted results of the temperature change trend and output power change of the photovoltaic module are obtained.

[0099] Step 3: Based on the prediction results, start the collaborative cooling mechanism of liquid cooling, air cooling and phase change materials. During the cooling process, continuously monitor the operating parameters of the photovoltaic modules. Based on the monitoring results, dynamically adjust and optimize the cooling method and corresponding parameters.

[0100] In some embodiments, based on the prediction results, the specific process of starting the coordinated cooling mechanism of liquid cooling, air cooling, and phase change material is as follows:

[0101] When the forecast results show that the temperature of the photovoltaic module will exceed the upper limit of the optimal operating temperature range in the future, and the output power is expected to drop by more than the preset threshold, the air cooling system is activated to control the fan speed so that air flows through the surface of the photovoltaic module at a preset flow rate to cool the photovoltaic module;

[0102] Based on the predicted temperature rise amplitude and rate, determine whether the liquid cooling system needs to be activated. If necessary, start the liquid cooling circulation pump to circulate the coolant in the cooling channels inside the photovoltaic module, absorb the heat generated inside the photovoltaic module, and bring the heat to the radiator for dissipation;

[0103] Phase change materials are arranged at designated locations on photovoltaic modules. When the temperature of the photovoltaic modules rises to the phase change temperature of the phase change materials, the phase change materials undergo phase change and absorb heat, helping to lower the temperature of the photovoltaic modules.

[0104] In some embodiments, during the cooling process, the operating parameters of the photovoltaic modules are continuously monitored. Based on the monitoring results, the cooling method and corresponding parameters are dynamically adjusted and optimized as follows:

[0105] Continuously use temperature sensors to collect real-time temperature data on the surface and inside of photovoltaic modules, and use current sensors and voltage sensors to collect real-time output current and output voltage data of photovoltaic modules;

[0106] The real-time collected working condition parameter data is matched with the input vector structure in the previously established relational model to form a real-time working condition parameter vector;

[0107] Substitute the real-time input vector into the established relationship model to obtain the current predicted temperature and output power;

[0108] The temperature adjustment target value is set to the median value of the optimal operating temperature range, and the output power adjustment target value is set to k% of the maximum output power predicted by the relationship model under the current environmental parameters, where k is a preset proportional coefficient;

[0109] Calculate the temperature deviation and output power deviation, and dynamically adjust and optimize the cooling method and corresponding parameters according to the temperature deviation and output power deviation through preset rules.

[0110] In some embodiments, the preset rules are:

[0111] When the temperature deviation is greater than a preset temperature deviation threshold and the output power deviation is greater than a preset output power deviation threshold, simultaneously increasing the fan speed of the air cooling system and the coolant flow rate of the liquid cooling system;

[0112] When the temperature deviation is greater than the preset temperature deviation threshold and the output power deviation is less than or equal to the preset output power deviation threshold, only the fan speed of the air cooling system is increased;

[0113] When the temperature deviation is less than or equal to the preset temperature deviation threshold and the output power deviation is greater than the preset output power deviation threshold, only the coolant flow rate of the liquid cooling system is increased;

[0114] When the temperature deviation and the output power deviation are both less than or equal to the corresponding preset thresholds, the current cooling mode and parameters are kept unchanged.

[0115] Based on the same inventive concept, corresponding to any of the above embodiments, refer to Figure 2 , the present invention provides a photovoltaic module cooling system for implementing the aforementioned photovoltaic module cooling method, comprising a data acquisition module, a model building module, a prediction module, a cooling execution module and a dynamic adjustment module connected in sequence;

[0116] The data acquisition module is used to use various sensors to collect the working parameter data of photovoltaic modules and the environmental parameter data within the corresponding range in real time, and integrate them to form a basic data set;

[0117] The model building module is used to analyze and learn historical data based on the basic data set through machine learning algorithms to establish a relationship model between the operating parameters of photovoltaic modules and environmental parameters;

[0118] The prediction module is used to use the established relationship model to predict the temperature change trend and output power change of photovoltaic modules under different environmental conditions and obtain the prediction results;

[0119] The cooling execution module is used to start the coordinated cooling mechanism of liquid cooling, air cooling and phase change materials according to the prediction results;

[0120] The dynamic adjustment module is used to continuously monitor the operating parameters of photovoltaic modules during the cooling process. Based on the monitoring results, the cooling method and corresponding parameters are dynamically adjusted and optimized through machine learning algorithms.

[0121] Based on the same inventive concept, corresponding to any of the above embodiments, the present invention provides an electronic device, including a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the photovoltaic component cooling method of Example 1.

[0122] Optionally, the above-mentioned electronic device may be a server.

[0123] In addition, this embodiment further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the photovoltaic module cooling method of the embodiment is implemented.

[0124] It is understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0125] The method steps in the embodiments of the present invention can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC.

[0126] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a storage medium or transmitted via a storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

Claims

1. A photovoltaic module cooling method, characterized in that: The following steps are involved: Real-time collection of operating parameter data of photovoltaic modules and environmental parameter data within the corresponding range of photovoltaic modules to obtain basic data sets; Based on the basic data set, historical data is analyzed and learned through machine learning algorithms to establish a relationship model between the operating parameters and environmental parameters of photovoltaic modules. The relationship model is then used to predict the temperature change trend and output power change of photovoltaic modules under different environmental conditions, and the prediction results are obtained. According to the prediction results, the coordinated cooling mechanism of liquid cooling, air cooling and phase change materials is activated. During the cooling process, the operating parameters of the photovoltaic modules are continuously monitored. According to the monitoring results, the cooling method and corresponding parameters are dynamically adjusted and optimized.

2. The photovoltaic module cooling method according to claim 1, wherein: The specific process of real-time acquisition of the working parameter data of the photovoltaic module and the environmental parameter data within the corresponding range of the photovoltaic module to obtain the basic data set is as follows: Use temperature sensors to collect real-time temperature data on the surface and inside of photovoltaic modules; The output current and output voltage data of the photovoltaic modules are collected in real time through current sensors and voltage sensors; Use wind speed sensors to monitor the wind speed within the corresponding range of the photovoltaic modules in real time; Use humidity sensors to detect the air humidity within the corresponding range of photovoltaic modules in real time; Use the light intensity sensor to obtain the light intensity data within the corresponding range of the photovoltaic module in real time; All the above-collected working condition parameter data and environmental parameter data are integrated to form a basic data set.

3. The photovoltaic module cooling method according to claim 1, wherein: The specific process of analyzing and learning historical data based on the basic data set through a machine learning algorithm to establish a relationship model between the operating parameters of the photovoltaic module and the environmental parameters is as follows: Assume that in the basic data set, the operating parameter vector of the photovoltaic module is Among them, T s,i represents the surface temperature of the photovoltaic module in the i-th sample, T i,i Indicates the internal temperature of the photovoltaic module in the i-th sample, I i represents the output current of the photovoltaic module in the i-th sample, V i represents the output voltage of the photovoltaic module in the i-th sample; The environmental parameter vector is Among them, v i Indicates the wind speed within the range of the photovoltaic module in the i-th sample, h i Indicates the air humidity within the range corresponding to the photovoltaic module in the i-th sample, L i represents the light intensity within the corresponding range of the photovoltaic module in the i-th sample; Combine the operating parameter vector and the environmental parameter vector to obtain the input vector The corresponding target value is the temperature or output power of the photovoltaic module; The model is built using support vector machines, and the objective function is shown in the following formula (1): Among them, w represents the weight vector; w T represents the transpose of w; b represents the bias term; ξ i and Both represent slack variables, which are used to deal with samples that do not meet the error range; C represents the penalty parameter, which is used to balance the complexity and error of the model; n represents the number of samples; The constraints are shown in formula (2): Among them, y i Indicates the target value corresponding to the i-th sample, w T x i +b represents the predicted value, and ∈ represents the error range.

4. The photovoltaic module cooling method according to claim 3, wherein: By introducing the Lagrange multiplier, equation (1) is transformed into the following equation (3): Among them, α and α * Both represent Lagrange multiplier vectors; α i and Denotes the corresponding Lagrange multiplier vectors α and α * The i-th element in; K represents the kernel function; The constraint condition is transformed into the following formula (4): Solve to get the optimal Lagrange multiplier μ i and The optimal weight vector w * As shown in the following formula (5): The relational model is shown in the following formula (6): Where x represents the input vector; x i represents the i-th sample vector; b * represents the optimal bias term.

5. The photovoltaic module cooling method according to claim 1, wherein: According to the prediction results, the specific process of starting the coordinated cooling mechanism of liquid cooling, air cooling and phase change materials is as follows: When the forecast results show that the temperature of the photovoltaic module will exceed the upper limit of the optimal operating temperature range in the future, and the output power is expected to drop by more than the preset threshold, the air cooling system is activated to control the fan speed so that air flows through the surface of the photovoltaic module at a preset flow rate to cool the photovoltaic module; Based on the predicted temperature rise amplitude and rate, determine whether the liquid cooling system needs to be activated. If necessary, start the liquid cooling circulation pump to circulate the coolant in the cooling channels inside the photovoltaic module, absorb the heat generated inside the photovoltaic module, and bring the heat to the radiator for dissipation; Phase change materials are arranged at designated locations on photovoltaic modules. When the temperature of the photovoltaic modules rises to the phase change temperature of the phase change materials, the phase change materials undergo phase change and absorb heat, helping to lower the temperature of the photovoltaic modules.

6. The photovoltaic module cooling method according to claim 1, wherein: During the cooling process, the operating parameters of the photovoltaic modules are continuously monitored, and the cooling method and corresponding parameters are dynamically adjusted and optimized according to the monitoring results. The specific process is as follows: Continuously use temperature sensors to collect real-time temperature data on the surface and inside of photovoltaic modules, and use current sensors and voltage sensors to collect real-time output current and output voltage data of photovoltaic modules; The real-time collected working condition parameter data is matched with the input vector structure in the previously established relational model to form a real-time working condition parameter vector; Substitute the real-time input vector into the established relationship model to obtain the current predicted temperature and output power; The temperature adjustment target value is set to the median value of the optimal operating temperature range, and the output power adjustment target value is set to k% of the maximum output power predicted by the relationship model under the current environmental parameters, where k is a preset proportional coefficient; Calculate the temperature deviation and output power deviation, and dynamically adjust and optimize the cooling method and corresponding parameters according to the temperature deviation and output power deviation through preset rules.

7. The photovoltaic module cooling method according to claim 6, wherein: The preset rules are: When the temperature deviation is greater than a preset temperature deviation threshold and the output power deviation is greater than a preset output power deviation threshold, simultaneously increasing the fan speed of the air cooling system and the coolant flow rate of the liquid cooling system; When the temperature deviation is greater than the preset temperature deviation threshold and the output power deviation is less than or equal to the preset output power deviation threshold, only the fan speed of the air cooling system is increased; When the temperature deviation is less than or equal to the preset temperature deviation threshold and the output power deviation is greater than the preset output power deviation threshold, only the coolant flow rate of the liquid cooling system is increased; When the temperature deviation and the output power deviation are both less than or equal to the corresponding preset thresholds, the current cooling mode and parameters are kept unchanged.

8. A photovoltaic module cooling system, used to implement the photovoltaic module cooling method according to any one of claims 1 to 7, characterized in that: It includes a data acquisition module, a model building module, a prediction module, a cooling execution module and a dynamic adjustment module connected in sequence; The data acquisition module is used to collect the working parameter data of the photovoltaic modules and the environmental parameter data within the corresponding range in real time using various sensors, and integrate them to form a basic data set; The model building module is used to analyze and learn historical data based on the basic data set through a machine learning algorithm to establish a relationship model between the operating parameters of the photovoltaic module and the environmental parameters; The prediction module is used to use the established relationship model to predict the temperature change trend and output power change of the photovoltaic module under different environmental conditions and obtain the prediction results; The cooling execution module is used to start the coordinated cooling mechanism of liquid cooling, air cooling and phase change material according to the prediction results; The dynamic adjustment module is used to continuously monitor the operating parameters of the photovoltaic components during the cooling process, and dynamically adjust and optimize the cooling method and corresponding parameters through a machine learning algorithm based on the monitoring results.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the photovoltaic component cooling method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the photovoltaic module cooling method according to any one of claims 1 to 7 is implemented.

Images