A distributed photovoltaic module power generation management method and system based on the Internet of Things

Abstract

The present application discloses a method and system for distributed photovoltaic module power generation management based on the Internet of Things. The method is applied to the control module of the distributed photovoltaic module power generation management system; it includes: obtaining the operation data of multiple photovoltaic modules collected by a multi-modal sensor array; obtaining the fused satellite cloud map and UAV aerial photography data corresponding to the multiple photovoltaic modules; inputting the fused satellite cloud map and UAV aerial photography data into a preset spatio-temporal attention prediction network to output a future shadow distribution heat map; obtaining the node contribution degree corresponding to each photovoltaic module, and constructing a hybrid topology structure corresponding to the multiple photovoltaic modules according to each node contribution degree; generating management information corresponding to each photovoltaic module according to the operation data, future shadow distribution heat map and hybrid topology structure corresponding to the multiple photovoltaic modules; the management information at least includes the inclination angle adjustment information of the photovoltaic module; and completing the distributed management of the multiple photovoltaic modules.

Description

Technical Field

[0001] The present application relates to the technical field of power network systems, and particularly to a distributed photovoltaic module power generation management method and system based on the Internet of Things. Background Art

[0002] With the continuous growth of global energy demand and the increasingly severe environmental problems, photovoltaic power generation, as a clean and renewable energy form, has received extensive attention. Distributed photovoltaic power generation systems are widely used in scenarios such as rooftops and building facades due to their flexibility and adaptability. However, there are still many deficiencies in the existing distributed photovoltaic management methods in terms of operation efficiency, data collection and analysis, system optimization, etc., and there is an urgent need to propose an innovative management method to improve system performance.

[0003] Traditional photovoltaic management methods mainly rely on a single data source (such as meteorological data or local sensor data) for power generation prediction and system management, and it is difficult to comprehensively reflect the operating status of photovoltaic modules in a complex environment, resulting in the difficulty of further improving the operation efficiency and reliability of photovoltaic power generation systems.

[0004] Therefore, there is an urgent need for a method to improve the operation efficiency and reliability of photovoltaic power generation systems. Summary of the Invention

[0005] The present application provides a distributed photovoltaic module power generation management method and system based on the Internet of Things, aiming to solve the problem that traditional photovoltaic management methods mainly rely on a single data source (such as meteorological data or local sensor data) for power generation prediction and system management, and it is difficult to comprehensively reflect the operating status of photovoltaic modules in a complex environment, resulting in the difficulty of further improving the operation efficiency and reliability of photovoltaic power generation systems.

[0006] In a first aspect, the present application provides a distributed photovoltaic module power generation management method, which is applied to the control module of a distributed photovoltaic module power generation management system; the method includes:

[0007] Obtain the operation data of multiple photovoltaic modules collected by a multi-modal sensor array; the multi-modal sensor array includes a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager;

[0008] Obtain the fused satellite cloud map and UAV aerial photography data corresponding to multiple photovoltaic modules;

[0009] Input the fused satellite cloud map and UAV aerial photography data into a preset spatio-temporal attention prediction network, and output a future shadow distribution heat map;

[0010] Obtain the node contribution degree corresponding to each photovoltaic module, and construct a hybrid topology structure corresponding to multiple photovoltaic modules according to each node contribution degree;

[0011] Generate management information corresponding to each of the photovoltaic modules based on the operating data corresponding to multiple photovoltaic modules, the future shadow distribution heat map, and the hybrid topology;

[0012] The management information at least includes the tilt angle adjustment information of the photovoltaic module; complete the distributed management of multiple photovoltaic modules.

[0013] In some embodiments, the inputting the fused satellite cloud map and the UAV aerial photography data into a preset spatio-temporal attention prediction network includes: respectively obtaining the geographic coordinate systems corresponding to the fused satellite cloud map and the UAV aerial photography data; aligning the fused satellite cloud map and the UAV aerial photography data spatially and temporally according to the geographic coordinate systems; adjusting the resolutions of the fused satellite cloud map and the UAV aerial photography data based on interpolation or downsampling techniques; respectively extracting satellite feature information and aerial photography feature information from the adjusted fused satellite cloud map and UAV aerial photography data; the satellite feature information at least includes cloud distribution and cloud thickness; the aerial photography feature information at least includes terrain features and occlusion features; inputting the satellite feature information and the aerial photography feature information into the spatio-temporal attention prediction network to output the future shadow distribution heat map.

[0014] Exemplarily, the spatio-temporal attention prediction network includes a convolutional layer, a long short-term memory layer, and an attention module; the inputting the satellite feature information and the aerial photography feature information into the spatio-temporal attention prediction network to output the future shadow distribution heat map includes: respectively inputting the satellite feature information and the aerial photography feature information into the convolutional layer and the long short-term memory layer, the convolutional layer outputs the spatial features corresponding to the satellite feature information and the aerial photography feature information, and the long short-term memory layer outputs the time feature sequence corresponding to the satellite feature information and the aerial photography feature information; respectively inputting the spatial features and the time feature sequence into the attention module, the attention module respectively outputs time attention information and spatial attention information; the time attention information is used to determine the key change moments in the time feature sequence; the spatial attention information is used to determine the occlusion region features corresponding to the spatial features; output the future shadow distribution heat map according to the occlusion region features and the key change moments.

[0015] It should be noted that, in some embodiments, the outputting the future shadow distribution heat map according to the occlusion region features and the key change moments includes: obtaining the shadow distribution influence weight corresponding to the occlusion region features; obtaining the environmental change information corresponding to the key change moments; the environmental change information at least includes cloud movement and solar incident angle change; adjusting the shadow distribution influence weight according to the environmental change information; generating the future shadow distribution heat map according to the adjusted shadow distribution influence weight.

[0016] In some embodiments, obtaining the node contribution degree corresponding to each photovoltaic module includes: obtaining the operation data corresponding to each photovoltaic module; the operation data only includes power output information, current information, and voltage information; obtaining the topology structure information corresponding to each photovoltaic module; the topology structure information is used to determine the connection relationship between each photovoltaic module and the remaining photovoltaic modules; obtaining the environmental data corresponding to each photovoltaic module; the environmental data at least includes light intensity, temperature, and wind speed; calculating the node contribution degree corresponding to each photovoltaic module according to the operation data, topology structure information, and environmental data.

[0017] Exemplarily, calculating the node contribution degree corresponding to each photovoltaic module according to the operation data, topology structure information, and environmental data includes: calculating the energy contribution degree corresponding to each photovoltaic module according to the operation data; calculating the reliability information corresponding to each photovoltaic module according to the operation data and environmental data; the reliability information is used to determine the stability of each photovoltaic module under abnormal conditions; calculating the network influence coefficient corresponding to each photovoltaic module according to the topology structure information and operation data; the network influence coefficient is used to determine the influence of the position of each photovoltaic module on the communication and energy transmission of multiple photovoltaic modules.

[0018] In some embodiments, constructing the hybrid topology structure corresponding to multiple photovoltaic modules according to each node contribution degree includes: respectively dividing multiple photovoltaic modules into any one of a sensing layer, a transmission layer, and a management layer according to the node contribution degree; wherein, each photovoltaic module in the sensing layer adopts a mesh topology, each photovoltaic module in the transmission layer adopts a tree topology, and the photovoltaic modules in the management layer adopt a star topology; constructing the hybrid topology structure according to the sensing layer, transmission layer, and management layer.

[0019] Exemplarily, constructing the hybrid topology structure according to the sensing layer, transmission layer, and management layer includes: obtaining a preset topology optimization target; the topology optimization target at least includes a target energy transmission efficiency, a target communication delay, and a target reliability; adjusting the connection relationship between the sensing layer, transmission layer, and management layer according to the topology optimization target to complete the construction of the topology structure.

[0020] In some embodiments, generating management information corresponding to each of the photovoltaic modules based on the operation data corresponding to a plurality of photovoltaic modules, the future shadow distribution heat map, and the hybrid topology structure includes: parsing the operation data, obtaining the efficiency impact information of each photovoltaic module according to the light intensity information and the temperature information, and obtaining the component health information of each photovoltaic module according to the IV curve information and the hot spot information; parsing the future shadow distribution heat map, obtaining the occlusion area and the occlusion time corresponding to the occlusion area, and calculating the shadow impact information corresponding to each photovoltaic module according to the occlusion area and the corresponding occlusion time; obtaining the importance information corresponding to each photovoltaic module according to the hybrid topology structure; and outputting the management information corresponding to each photovoltaic module based on a preset optimization algorithm according to the efficiency impact information, the component health information, the shadow impact information, and the importance information corresponding to each photovoltaic module, so as to maximize the power generation amount corresponding to the plurality of photovoltaic modules.

[0021] In a second aspect, the present application provides an Internet of Things-based distributed photovoltaic module power generation management system, including:

[0022] A plurality of photovoltaic modules;

[0023] A multimodal sensor array; the multimodal sensor array includes at least a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager;

[0024] A control module, the control module includes a memory and a processor; the memory is used for storing a computer program; the processor is used for executing the computer program and implementing the method provided in any embodiment of the present application when executing the computer program.

[0025] In a third aspect, the present application provides a distributed photovoltaic module power generation management device, including:

[0026] A data acquisition unit, configured to acquire the operation data of a plurality of photovoltaic modules collected by a multimodal sensor array; the multimodal sensor array includes a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager;

[0027] A cloud map acquisition unit, configured to acquire the fused satellite cloud map and the UAV aerial photography data corresponding to a plurality of photovoltaic modules;

[0028] A data fusion unit, configured to input the fused satellite cloud map and the UAV aerial photography data into a preset spatio-temporal attention prediction network, and output a future shadow distribution heat map;

[0029] A contribution acquisition unit, configured to acquire the node contribution degree corresponding to each photovoltaic module, and construct a hybrid topology structure corresponding to the plurality of photovoltaic modules according to each node contribution degree;

[0030] A management completion unit is used to generate management information corresponding to each of the plurality of photovoltaic modules according to the operation data, future shadow distribution heat map, and hybrid topology structure corresponding to the plurality of photovoltaic modules; the management information at least includes tilt angle adjustment information of the photovoltaic module; and distributed management of the plurality of photovoltaic modules is completed.

[0031] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and when the computer-readable instructions are executed by a processor, one or more processors are caused to execute the method provided in any embodiment of the present application.

[0032] The present application provides a method and system for distributed photovoltaic module power generation management based on the Internet of Things, and the specific technical content is as follows:

[0033] Multi-modal sensor data acquisition: Use a multi-modal sensor array (including a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager) to collect the operation data of a plurality of photovoltaic modules. These data can comprehensively reflect the operation status of the photovoltaic modules under different environmental conditions;

[0034] Fusion of satellite cloud images and UAV aerial photography data: Obtain the fusion satellite cloud images and UAV aerial photography data corresponding to a plurality of photovoltaic modules. These data provide a larger range of environmental information, which helps to more accurately predict the future operation status of the photovoltaic modules;

[0035] Spatio-temporal attention prediction network: Input the fusion satellite cloud images and UAV aerial photography data into a preset spatio-temporal attention prediction network to output a future shadow distribution heat map. This network can capture changes in time and space, predict future shadow distribution, and thus provide a basis for the management of photovoltaic modules;

[0036] Node contribution degree and hybrid topology structure: Obtain the node contribution degree corresponding to each photovoltaic module, and construct a hybrid topology structure corresponding to the plurality of photovoltaic modules according to each node contribution degree. This helps to optimize the layout and connection mode of the photovoltaic modules, and improve the efficiency and reliability of the overall system;

[0037] Management information generation: Generate management information corresponding to each photovoltaic module according to the operation data, future shadow distribution heat map, and hybrid topology structure corresponding to the plurality of photovoltaic modules. The management information at least includes tilt angle adjustment information of the photovoltaic module, so as to realize distributed management of the plurality of photovoltaic modules.

[0038] The method provided at least has the following beneficial effects:

[0039] Comprehensive data collection and analysis: Through a multi-modal sensor array and by integrating satellite cloud images and UAV aerial photography data, it is possible to comprehensively collect and analyze the operating data of photovoltaic modules, overcoming the limitation of traditional methods that rely on a single data source;

[0040] Precise prediction and optimization: By using a spatio-temporal attention prediction network, it is possible to accurately predict future shadow distributions, providing a scientific basis for the management of photovoltaic modules. Combining node contribution degrees and a hybrid topology structure can optimize the layout and connection methods of photovoltaic modules, improving the overall efficiency and reliability of the system;

[0041] Distributed management: By generating management information corresponding to each photovoltaic module, distributed management of multiple photovoltaic modules is achieved. This management method can perform personalized adjustments according to the specific conditions of each photovoltaic module, further improving the operating efficiency and reliability of the system;

[0042] Improve the operating efficiency and reliability of the photovoltaic power generation system: Through the above technical means, it is possible to comprehensively reflect the operating status of photovoltaic modules in a complex environment, optimize the management of photovoltaic modules, thereby improving the operating efficiency and reliability of the photovoltaic power generation system;

[0043] In summary, the method and system provided in this application effectively solve the limitations of traditional photovoltaic management methods and significantly improve the operating efficiency and reliability of the photovoltaic power generation system through comprehensive data collection, precise prediction and optimization, distributed management and other technical means.

[0044] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. Description of the Drawings

[0045] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0046] Figure 1 is a schematic block diagram of the structure of a distributed photovoltaic module power generation management system provided by an embodiment of this application;

[0047] Figure 2 is a schematic flow chart of the steps of a distributed photovoltaic module power generation management method based on the Internet of Things provided by an embodiment of this application;

[0048] Figure 3 is a schematic block diagram of the structure of a control module provided by an embodiment of this application.

[0049] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit this application. Detailed implementation manners

[0050] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art without making creative efforts based on the embodiments in this application belong to the scope of protection of this application.

[0051] The flowcharts shown in the accompanying drawings are only illustrative, and do not necessarily include all the contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined or partially merged, so the actual execution order may be changed according to the actual situation.

[0052] It should be understood that, in order to facilitate the clear description of the technical solutions in the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and roles. Those skilled in the art can understand that the terms "first", "second", etc. do not limit the quantity and execution order, and the terms "first", "second", etc. do not necessarily mean different.

[0053] It should be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0054] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0055] The following will describe in detail some implementation manners of this application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0056] With the continuous growth of global energy demand and the increasingly severe environmental problems, photovoltaic power generation, as a clean and renewable energy form, has received extensive attention. Distributed photovoltaic power generation systems are widely used in scenarios such as rooftops and building facades due to their flexibility and adaptability. However, existing distributed photovoltaic management methods still have many deficiencies in terms of operation efficiency, data collection and analysis, system optimization, etc., and there is an urgent need to propose an innovative management method to improve system performance.

[0057] Traditional photovoltaic management methods mainly rely on a single data source (such as meteorological data or local sensor data) for power generation prediction and system management. It is difficult to comprehensively reflect the operating status of photovoltaic modules in a complex environment, resulting in the difficulty of further improving the operating efficiency and reliability of photovoltaic power generation systems.

[0058] Therefore, there is an urgent need for a method to improve the operating efficiency and reliability of photovoltaic power generation systems.

[0059] To solve the above problems, please refer to Figure 1 , this application provides a distributed photovoltaic module power generation management system, including: a plurality of photovoltaic modules ( Figure 1 Three is just an example, and this application places no limit on the number of photovoltaic modules); a multi-modal sensor array; the multi-modal sensor array includes at least a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager; a control module, the control module includes a memory and a processor; the memory is used to store computer programs; the processor is used to execute the computer programs and, when executing the computer programs, implement the method provided in any embodiment of this application.

[0060] Specifically, the distributed photovoltaic module power generation management system proposed in this application aims to improve the operating efficiency and reliability of photovoltaic power generation systems through multi-modal data fusion and advanced algorithms. The system mainly includes the following parts:

[0061] Multi-modal sensor array: including a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager, used to comprehensively collect the operating status data of photovoltaic modules;

[0062] Control module: including a memory and a processor, used to store and execute computer programs to implement the intelligent management function of the system;

[0063] Data acquisition and processing: The system collects the operating data of photovoltaic modules through a multi-modal sensor array, fuses satellite cloud map and UAV aerial photography data, and inputs them into a spatio-temporal attention prediction network to predict the future shadow distribution heat map;

[0064] Node contribution degree and hybrid topology structure: Construct a hybrid topology structure according to the node contribution degree of each photovoltaic module to optimize the system layout;

[0065] Management information generation: Generate management information for each photovoltaic module according to the operating data, future shadow distribution heat map, and hybrid topology structure, including tilt angle adjustment information, to achieve distributed management of multiple photovoltaic modules.

[0066] By installing a multi-modal sensor array on the photovoltaic module, the light intensity, temperature, IV curve, and hot spot imaging data are collected in real time. The sensor data is combined with the fused satellite cloud map and UAV aerial photography data, and through spatio-temporal attention prediction network analysis, the future shadow distribution is predicted. According to the prediction results and the node contribution degree of the photovoltaic module, a hybrid topology structure is constructed to optimize the layout and operation strategy of the photovoltaic module. According to the optimization results, the management information of each photovoltaic module is generated, such as tilt angle adjustment, and automated management is achieved through the control module.

[0067] Through multi-modal data fusion and advanced algorithms, the system can more accurately predict and adjust the operating state of the photovoltaic module, thereby improving the overall power generation efficiency. The system can monitor the health status of the photovoltaic module in real time, detect and handle potential problems in a timely manner, reduce the failure rate, and improve the system reliability. The distributed management method enables the system to flexibly adapt to different environmental conditions, such as weather changes and shadow occlusion, and maintain efficient operation. Through automated management and intelligent optimization, manual intervention is reduced, operation and maintenance costs are lowered, and management efficiency is improved.

[0068] In summary, the distributed photovoltaic module power generation management system provided by this application effectively improves the operating efficiency and reliability of the photovoltaic power generation system through multi-modal data fusion, advanced algorithms, and intelligent management, and has significant technical advantages and application values.

[0069] Please refer to Figure 2 , Figure 2 which is a schematic flow chart of a distributed photovoltaic module power generation management method provided by an embodiment of this application. The execution device of the method is the control module of the distributed photovoltaic module power generation management system provided by any embodiment of this application.

[0070] As Figure 2 shown, the provided method includes steps S101 to S105. Among them, the control module can be a handheld terminal, a laptop, a wearable device, or a robot, etc. It is used to implement steps S101 to S105 and their corresponding embodiments.

[0071] Step S101. Obtain the operation data of multiple photovoltaic modules collected by the multi-modal sensor array; the multi-modal sensor array includes a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager.

[0072] Specifically, the core of step S101 is to collect the operation data of the photovoltaic module through the multi-modal sensor array. The multi-modal sensor array includes a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager. These sensors monitor the operation state of the photovoltaic module from different dimensions:

[0073] Light intensity sensor: Monitors the light intensity received by the photovoltaic module in real time, providing basic data for the evaluation of power generation efficiency;

[0074] Temperature sensor: Monitors the surface temperature of the photovoltaic module. Excessive temperature will reduce the power generation efficiency and accelerate the aging of the module;

[0075] IV curve detector: Evaluates the electrical performance of the photovoltaic module by measuring the current-voltage curve, and discovers potential faults or performance degradation;

[0076] Hot spot imager: Detects whether there is a hot spot phenomenon in the photovoltaic module through infrared imaging technology. Hot spots will reduce the module life and pose safety hazards.

[0077] Install a multi-modal sensor array on each photovoltaic module to ensure that the sensors can accurately collect data. Transmit the sensor data to the control module through wired or wireless communication technologies (such as LoRa, ZigBee or 5G). The control module preprocesses the data, including denoising, formatting and storage, providing high-quality data for subsequent analysis.

[0078] Comprehensively monitor the status of the photovoltaic module from multiple dimensions such as light, temperature, electrical performance and thermal imaging through multi-modal sensors, avoiding the limitations of a single data source. Real-time data collection can promptly detect abnormal states of the photovoltaic module, such as hot spots or performance degradation, facilitating quick response and handling. Provide reliable data support for subsequent shadow prediction, topology optimization and management information generation.

[0079] Step S102. Obtain the fused satellite cloud map and UAV aerial photography data corresponding to multiple photovoltaic modules.

[0080] Specifically, the core of step S102 is to obtain the environmental information of the area where the photovoltaic module is located by fusing the satellite cloud map and UAV aerial photography data.

[0081] Satellite cloud map: Provides large-scale meteorological data, such as cloud cover, light intensity and weather change trends.

[0082] UAV aerial photography data: Provides high-precision local environmental information, such as the location and height of obstacles such as buildings and trees.

[0083] Obtain the satellite cloud map data of the area where the photovoltaic module is located from the meteorological satellite. Use the UAV to conduct aerial photography of the area where the photovoltaic module is located to obtain high-resolution environmental data. Fuse the satellite cloud map and UAV aerial photography data to generate comprehensive environmental data containing large-scale meteorological information and local occlusion information.

[0084] By integrating data, comprehensively understand the environmental characteristics of the area where the photovoltaic modules are located, including weather changes and the distribution of obstacles. Provide high-precision input data for subsequent shadow distribution prediction and improve prediction accuracy. The system can dynamically adjust the operation strategy of the photovoltaic modules according to environmental changes, enhancing the overall adaptability.

[0085] Step S103. Input the fused satellite cloud image and UAV aerial photography data into a preset spatio-temporal attention prediction network to output a future shadow distribution heat map.

[0086] Specifically, the core of step S103 is to use the spatio-temporal attention prediction network to predict the future shadow distribution based on the fused data. The spatio-temporal attention prediction network is a deep learning model that can capture complex relationships in the time and space dimensions and is suitable for shadow prediction in the area where the photovoltaic modules are located.

[0087] Input the fused satellite cloud image and UAV aerial photography data into the spatio-temporal attention prediction network. The model analyzes historical data and current environmental characteristics to predict the shadow distribution situation in the future for a period of time. Output a future shadow distribution heat map, which visually shows the location, range, and intensity of the shadows.

[0088] The spatio-temporal attention prediction network can capture complex environmental changes, provide high-precision shadow distribution prediction. The prediction results can early warn of the impact of shadows on the photovoltaic modules, facilitating the adoption of adjustment measures. Provide key input for subsequent topology optimization and management information generation, improving the system operation efficiency.

[0089] Step S104. Obtain the node contribution degree corresponding to each photovoltaic module, and construct a hybrid topology structure corresponding to multiple photovoltaic modules according to each node contribution degree.

[0090] Specifically, the core of step S104 is to construct a hybrid topology structure according to the node contribution degree of the photovoltaic modules. The node contribution degree refers to the importance of each photovoltaic module in the overall system, usually evaluated based on factors such as power generation efficiency, location, and environmental impact.

[0091] Calculate the node contribution degree of each photovoltaic module based on historical operation data and environmental characteristics. Based on the node contribution degree, divide the photovoltaic modules into different groups and construct a hybrid topology structure. The hybrid topology structure can be a star, mesh, or hierarchical structure, and the specific form is determined according to actual needs.

[0092] By constructing a hybrid topology structure, optimize the layout and connection method of the photovoltaic modules, improving the overall efficiency of the system. Reasonably allocate resources according to the node contribution degree to ensure that important components are preferentially managed. The hybrid topology structure can adapt to different environments and operation requirements, enhancing the flexibility of the system.

[0093] Step S105. Generate management information corresponding to each photovoltaic module based on the operation data, future shadow distribution heat map, and hybrid topology structure of multiple photovoltaic modules; the management information at least includes the tilt angle adjustment information of the photovoltaic module; complete the distributed management of multiple photovoltaic modules.

[0094] Specifically, the core of step S105 is to generate management information for each photovoltaic module based on the operation data, shadow distribution heat map, and hybrid topology structure. The management information includes tilt angle adjustment information, cleaning and maintenance suggestions, and fault handling solutions, etc.

[0095] Comprehensively analyze the operation data, shadow distribution heat map, and hybrid topology structure to evaluate the operation status of each photovoltaic module. Generate management information for each photovoltaic module, such as adjusting the tilt angle to optimize light reception, or arranging cleaning and maintenance to remove obstacles. Send the management information to the execution device (such as a robot or an automatic adjustment device) through the control module to complete the distributed management.

[0096] The management information generated based on multi-dimensional data can accurately optimize the operation status of each photovoltaic module. By executing the management information through automated devices, manual intervention is reduced, and the operation and maintenance costs are lowered. Through dynamic adjustment and optimization, the overall efficiency and reliability of the photovoltaic power generation system are improved.

[0097] Steps S101 to S105 together constitute a distributed photovoltaic module power generation management method based on the Internet of Things. Through multi-modal data collection, environmental perception, shadow prediction, topology structure optimization, and intelligent management, the system can significantly improve the operation efficiency and reliability of the photovoltaic power generation system, providing strong technical support for the efficient utilization of clean energy.

[0098] In some embodiments, the inputting of the fused satellite cloud map and UAV aerial photography data into the preset spatio-temporal attention prediction network includes: respectively obtaining the geographical coordinate systems corresponding to the fused satellite cloud map and UAV aerial photography data; aligning the fused satellite cloud map and UAV aerial photography data spatially and temporally according to the geographical coordinate systems; adjusting the resolutions of the fused satellite cloud map and UAV aerial photography data based on interpolation or downsampling techniques; respectively extracting satellite feature information and aerial photography feature information from the adjusted fused satellite cloud map and UAV aerial photography data; the satellite feature information at least includes cloud layer distribution and cloud layer thickness; the aerial photography feature information at least includes terrain features and obstacle features; inputting the satellite feature information and aerial photography feature information into the spatio-temporal attention prediction network to output the future shadow distribution heat map.

[0099] The core of this embodiment is to preprocess and extract features from the fused satellite cloud map and UAV aerial photography data to improve the quality of the input data of the spatio-temporal attention prediction network, thereby improving the prediction accuracy of the future shadow distribution heat map. The specific steps are as follows:

[0100] Extract geographic coordinate system information, such as longitude and latitude, altitude, etc., from satellite cloud images and UAV aerial photography data respectively. Ensure that the geographic coordinate systems of the two data are consistent for subsequent spatial alignment.

[0101] According to the geographic coordinate system, spatially align the satellite cloud images and UAV aerial photography data to ensure that they can match at the same geographical location. Align the timestamps to ensure that the time dimensions of the two data are consistent (such as the same day, the same moment, or the same time period).

[0102] Use interpolation or downsampling techniques to adjust the resolutions of the satellite cloud images and UAV aerial photography data to make their spatial resolutions consistent. For example, downsample the high-resolution UAV aerial photography data to the same resolution as the satellite cloud images, or interpolate the low-resolution satellite cloud images to a high resolution.

[0103] Extract satellite feature information from the adjusted satellite cloud images, including cloud distribution, cloud thickness, cloud movement speed, etc. Extract aerial photography feature information from the adjusted UAV aerial photography data, including topographic features (such as slope and aspect) and occlusion features (such as the height and position of buildings and trees).

[0104] Input the extracted satellite feature information and aerial photography feature information into the spatio-temporal attention prediction network. The network analyzes these feature information, captures the impacts of clouds and occlusions on photovoltaic modules, and outputs a future shadow distribution heat map.

[0105] Through geographic coordinate alignment and resolution adjustment, ensure the consistency of satellite cloud images and UAV aerial photography data in the spatial and time dimensions, providing high-quality input data for subsequent analysis.

[0106] The feature information (such as cloud distribution and occlusion features) extracted from satellite cloud images and UAV aerial photography data can comprehensively reflect the environmental features of the area where the photovoltaic modules are located, improving the richness of the input information of the spatio-temporal attention prediction network. Based on high-precision feature information, the spatio-temporal attention prediction network can more accurately predict the future shadow distribution, reduce prediction errors, and provide a reliable basis for the operation optimization of photovoltaic modules. The embodiment can effectively handle shadow prediction problems in complex environments, such as cloudy weather, terrain undulation, and uneven occlusion distribution, improving the adaptability and robustness of the system. Adjust the resolution through interpolation or downsampling techniques to reduce the data volume, lower the computational complexity of the spatio-temporal attention prediction network, and improve the prediction efficiency.

[0107] In cloudy weather, the rapid movement of clouds will cause the light intensity received by photovoltaic modules to change frequently. Through extracting cloud distribution and thickness information, Embodiment 1 can accurately predict the shadow impact of clouds on photovoltaic modules, facilitating the early adjustment of the module tilt angle or operation strategy.

[0108] In mountainous or urban environments, terrain undulations and obstacles such as buildings and trees can have a significant impact on the power generation efficiency of photovoltaic modules. Through the extraction of terrain features and obstacle features, the embodiments can accurately predict the shadow distribution caused by these factors and optimize the layout and operation of photovoltaic modules. It can monitor environmental changes in real time (such as cloud movement, addition or removal of obstacles), dynamically update the heat map of shadow distribution, and ensure that the photovoltaic modules are always in the best operating state.

[0109] Through the preprocessing and feature extraction of the fused satellite cloud image and UAV aerial photography data, the embodiments significantly improve the quality of the input data of the spatio-temporal attention prediction network, thereby improving the prediction accuracy of the future heat map of shadow distribution. This method has significant advantages in scenarios such as cloudy weather, complex terrain, and dynamic environments, and can provide reliable environmental perception and operation optimization support for the distributed photovoltaic module power generation management system, ultimately improving the overall efficiency and reliability of the system.

[0110] Exemplarily, the spatio-temporal attention prediction network includes a convolutional layer, a long short-term memory layer, and an attention module; the inputting of the satellite feature information and the aerial photography feature information into the spatio-temporal attention prediction network to output the future heat map of shadow distribution includes: respectively inputting the satellite feature information and the aerial photography feature information into the convolutional layer and the long short-term memory layer, the convolutional layer outputs the spatial features corresponding to the satellite feature information and the aerial photography feature information, and the long short-term memory layer outputs the time feature sequences corresponding to the satellite feature information and the aerial photography feature information; respectively inputting the spatial features and the time feature sequences into the attention module, the attention module respectively outputs time attention information and spatial attention information; the time attention information is used to determine the key change moments in the time feature sequence; the spatial attention information is used to determine the occlusion region features corresponding to the spatial features; and outputting the future heat map of shadow distribution according to the occlusion region features and the key change moments.

[0111] This example details the structure and working process of the spatio-temporal attention prediction network. This network consists of a convolutional layer, a long short-term memory layer (LSTM), and an attention module, aiming to extract spatial and time features from satellite feature information and aerial photography feature information, and capture key change moments and occlusion region features through the attention mechanism, and finally output the future heat map of shadow distribution. The specific steps are as follows:

[0112] Respectively input the satellite feature information (such as cloud distribution, cloud thickness) and the aerial photography feature information (such as terrain features, obstacle features) into the spatio-temporal attention prediction network.

[0113] The convolutional layer is used to extract the spatial features of the input feature information. Convolutional operations are performed on the satellite feature information and the aerial photography feature information respectively, and the corresponding spatial features are output. The spatial features can reflect the environmental features of the area where the photovoltaic module is located, such as the spatial distribution of clouds and the positions of obstacles.

[0114] The long short-term memory layer (LSTM) is used to extract the time feature sequence of the input feature information. LSTM processing is performed on the satellite feature information and the aerial photography feature information respectively, and the corresponding time feature sequences are output. The time feature sequence can reflect the changing trend of environmental features over time, such as the moving speed of clouds and the dynamic changes of obstacles.

[0115] The spatial features output by the convolutional layer and the time feature sequence output by the LSTM layer are respectively input into the attention module. The attention module includes a time attention mechanism and a spatial attention mechanism. Time attention mechanism: Analyze the time feature sequence to determine the key change moments (such as the moments when clouds move rapidly or new obstacles appear). Spatial attention mechanism: Analyze the spatial features to determine the features of the occlusion area (such as the position and range of obstacles). The attention module outputs time attention information and spatial attention information respectively. According to the time attention information and the spatial attention information, combined with the features of the occlusion area and the key change moments, a future shadow distribution heat map is generated. The heat map visually displays the position, range, and intensity of shadows in the future for a period of time.

[0116] The convolutional layer and the long short-term memory layer respectively extract spatial features and time features, which can comprehensively reflect the environmental changes in the area where the photovoltaic module is located. The time attention mechanism can capture the key change moments in the time feature sequence, such as the moments when clouds move rapidly or new obstacles appear, providing key time nodes for shadow prediction. The spatial attention mechanism can identify the features of the occlusion area in the spatial features, such as the position and range of obstacles, providing key spatial information for shadow prediction. By combining the time attention information and the spatial attention information, the spatio-temporal attention prediction network can more accurately predict the future shadow distribution and reduce the prediction error. The method can process dynamic environmental changes (such as cloud movement, new appearance or removal of obstacles) in real time, dynamically update the shadow distribution heat map, and ensure the timeliness and accuracy of the prediction results. The attention mechanism can focus on the key change moments and the features of the occlusion area, reduce unnecessary calculations, and improve the prediction efficiency.

[0117] Under cloudy weather conditions, the rapid movement of clouds will cause the light intensity received by the photovoltaic module to change frequently. By capturing the critical moments of cloud movement through the time attention mechanism and combining the spatial attention mechanism to identify the spatial distribution of clouds, the shadow impact of clouds on the photovoltaic module can be accurately predicted.

[0118] In mountainous or urban environments, terrain undulations and obstacles such as buildings and trees can have a significant impact on the power generation efficiency of photovoltaic modules. By using a spatial attention mechanism to identify the location and extent of obstacles and combining it with a temporal attention mechanism to capture the dynamic changes of obstacles, the shadow distribution caused by these factors can be accurately predicted. Examples can monitor environmental changes in real time (such as cloud movement, addition or removal of obstacles), dynamically update the heat map of shadow distribution, and ensure that the photovoltaic modules are always in the best operating state.

[0119] By combining convolutional layers, long short-term memory layers, and attention modules, the spatial and temporal features of the area where the photovoltaic modules are located are comprehensively captured, and the key change moments and the features of the occluded areas are accurately located through the attention mechanism. Finally, a high-precision heat map of future shadow distribution is output. This method has significant advantages in scenarios such as cloudy weather, complex terrain, and dynamic environments, and can provide reliable environmental perception and operation optimization support for the distributed photovoltaic module power generation management system, ultimately improving the overall efficiency and reliability of the system.

[0120] It should be noted that in some embodiments, outputting the heat map of future shadow distribution according to the occluded area features and key change moments includes: obtaining the shadow distribution influence weight corresponding to the occluded area features; obtaining the environmental change information corresponding to the key change moments; the environmental change information at least includes cloud movement and solar incident angle change; adjusting the shadow distribution influence weight according to the environmental change information; generating the heat map of future shadow distribution according to the adjusted shadow distribution influence weight.

[0121] The process of generating the heat map of future shadow distribution according to the occluded area features and key change moments is further refined. This method dynamically adjusts the shadow distribution prediction result by introducing the shadow distribution influence weight and environmental change information, thereby improving the accuracy and practicality of the heat map. The specific steps are as follows:

[0122] According to the occluded area features (such as the location, height, and extent of the obstacle), calculate the influence weight on the shadow distribution of the photovoltaic module. The influence weight reflects the degree of influence of the obstacle on the power generation efficiency of the photovoltaic module. For example, a tall building may have a larger influence weight.

[0123] Extract the key change moments from the temporal attention information and obtain the corresponding environmental change information. The environmental change information includes cloud movement speed, cloud thickness change, solar incident angle change, etc. These information can reflect the dynamic influence of the environment on the shadow distribution of the photovoltaic module.

[0124] Dynamically adjust the influence weight of the occlusion area characteristics according to the environmental change information. For example, when the clouds move rapidly, the influence weight of the occluder may decrease; when the solar incident angle changes, the shadow range of the occluder may expand or shrink. Generate a future shadow distribution heat map according to the adjusted influence weight of the shadow distribution. The heat map visually displays the position, range, and intensity of the shadows within a future period of time, facilitating the optimization of the operation of photovoltaic modules.

[0125] By introducing environmental change information and dynamically adjusting the influence weight of the shadow distribution, it can more accurately reflect the dynamic influence of the environment on the shadow distribution of photovoltaic modules. Combining the occlusion area characteristics and environmental change information can generate a more accurate future shadow distribution heat map, reducing prediction errors. It can effectively handle shadow prediction problems in complex environments, such as cloudy weather, terrain undulations, and uneven occluder distributions, improving the adaptability and robustness of the system. The high-precision future shadow distribution heat map provides a reliable basis for the operation optimization of photovoltaic modules, such as adjusting the module tilt angle or cleaning and maintenance arrangements, enhancing the overall power generation efficiency. By accurately predicting the shadow distribution, unnecessary operation and maintenance operations are reduced, and the operation and maintenance costs of the photovoltaic power generation system are lowered.

[0126] In some embodiments, the obtaining of the node contribution degree corresponding to each photovoltaic module includes: obtaining the operation data corresponding to each photovoltaic module; the operation data only includes power output information, current information, and voltage information; obtaining the topological structure information corresponding to each photovoltaic module; the topological structure information is used to determine the connection relationship between each photovoltaic module and the remaining photovoltaic modules; obtaining the environmental data corresponding to each photovoltaic module; the environmental data at least includes light intensity, temperature, and wind speed; calculating the node contribution degree corresponding to each photovoltaic module according to the operation data, topological structure information, and environmental data.

[0127] By comprehensively considering the operation data, topological structure information, and environmental data of the photovoltaic modules, calculate the node contribution degree of each photovoltaic module. The node contribution degree reflects the importance of the photovoltaic module in the overall system and is a key indicator for constructing a hybrid topological structure and optimizing the operation strategy. The specific steps are as follows:

[0128] Obtain the operation data of each photovoltaic module from the multimodal sensor array, including power output information, current information, and voltage information. These data reflect the power generation performance and operation status of the photovoltaic modules. Obtain the topological structure information of each photovoltaic module, including its connection relationship with other photovoltaic modules (such as series connection, parallel connection, or hybrid connection). The topological structure information is used to evaluate the position and role of the photovoltaic module in the system. Obtain the environmental data of the area where each photovoltaic module is located from the environmental sensors, including light intensity, temperature, and wind speed. These data reflect the impact of the environment on the power generation efficiency of the photovoltaic modules. Calculate the node contribution degree of each photovoltaic module according to the operation data, topological structure information, and environmental data. By comprehensively considering the operation data, topological structure information, and environmental data, the importance of each photovoltaic module in the system can be comprehensively evaluated, avoiding the limitations of a single indicator. The node contribution degree provides a key basis for constructing a hybrid topological structure, ensuring that important components are preferentially managed and optimized in the system. The optimization strategy based on the node contribution degree can improve the overall efficiency of the photovoltaic power generation system and reduce resource waste. The method can effectively handle the calculation problem of the node contribution degree in complex environments, such as cloudy weather, terrain undulation, and uneven distribution of obstacles, improving the adaptability and robustness of the system. Dynamically adjust the operation strategy of the photovoltaic module (such as tilt angle adjustment, cleaning and maintenance) according to the node contribution degree to ensure that the system is always in the best operation state.

[0129] Exemplarily, calculating the node contribution degree corresponding to each photovoltaic module according to the operation data, topological structure information, and environmental data includes: calculating the energy contribution degree corresponding to each photovoltaic module according to the operation data; calculating the reliability information corresponding to each photovoltaic module according to the operation data and environmental data; the reliability information is used to determine the stability of each photovoltaic module under abnormal conditions; calculating the network influence coefficient of each photovoltaic module according to the topological structure information and operation data; the network influence coefficient is used to determine the impact of the position of each photovoltaic module on the communication and energy transmission of multiple photovoltaic modules.

[0130] By comprehensively considering the energy contribution degree, reliability information, and network influence coefficient, the importance of each photovoltaic module in the system can be comprehensively evaluated, avoiding the limitations of a single indicator. The node contribution degree provides a key basis for constructing a hybrid topological structure, ensuring that important components are preferentially managed and optimized in the system. The optimization strategy based on the node contribution degree can improve the overall efficiency of the photovoltaic power generation system and reduce resource waste. It can effectively handle the calculation problem of the node contribution degree in complex environments, such as cloudy weather, terrain undulation, and uneven distribution of obstacles, improving the adaptability and robustness of the system. Dynamically adjust the operation strategy of the photovoltaic module (such as tilt angle adjustment, cleaning and maintenance) according to the node contribution degree to ensure that the system is always in the best operation state.

[0131] Under cloudy weather conditions, the light intensities received by different photovoltaic modules may vary significantly. By introducing reliability information, the node contribution of each module can be accurately evaluated, facilitating the optimization of operation strategies. In mountainous or urban environments, terrain undulations and obstacles such as buildings and trees can have a significant impact on the power generation efficiency of photovoltaic modules. By comprehensively considering environmental data, the node contribution of each module can be precisely calculated to optimize the system layout. It is possible to monitor environmental changes in real time (such as cloud movement, the addition or removal of obstacles), dynamically update the node contribution, and ensure that the system always operates at its optimal state.

[0132] By introducing energy contribution, reliability information, and network influence coefficients, the node contribution of each photovoltaic module is comprehensively evaluated, providing a key basis for constructing a hybrid topology and optimizing operation strategies. This method has significant advantages in scenarios such as cloudy weather, complex terrain, and dynamic environments, and can provide reliable environmental perception and operation optimization support for distributed photovoltaic module power generation management systems, ultimately enhancing the overall efficiency and reliability of the system.

[0133] It should be noted that in some embodiments, the node contribution is a key indicator for evaluating the importance of photovoltaic modules in the system. The following is the calculation formula for the node contribution:

[0134] Ci = α ⋅ Ei + β ⋅ Hi + γ ⋅ Si + δ ⋅ Ii; Ci is the node contribution of the i-th photovoltaic module. Ei is the efficiency impact information of the i-th photovoltaic module, describing the impact of environmental factors (such as light intensity and temperature) on the power generation efficiency of the photovoltaic module. Hi is the component health information of the i-th photovoltaic module, describing the operating stability and potential failure risk of the photovoltaic module. Si is the shadow impact information of the i-th photovoltaic module, describing the impact of obstacles on the power generation efficiency of the photovoltaic module. Ii is the importance information of the i-th photovoltaic module, describing the position and role of the photovoltaic module in the system. The importance information is related to the level (sensing layer, transmission layer, management layer) of the photovoltaic module in the hybrid topology and can be assigned values according to the following rules:

[0135] Sensing layer: Ii = 0.3; Transmission layer: Ii = 0.5; Management layer: Ii = 0.8. α, β, γ, and δ are weight coefficients used to adjust the weights of the efficiency impact information, component health information, shadow impact information, and importance information in the node contribution. In this application, α, β, γ, and δ are taken as 0.4, 0.3, 0.2, and 0.1 respectively.

[0136] In some embodiments, constructing the hybrid topology structures corresponding to multiple photovoltaic modules according to each node contribution degree includes: dividing multiple photovoltaic modules into any one of a sensing layer, a transmission layer, and a management layer according to the node contribution degree; wherein, each photovoltaic module in the sensing layer adopts a mesh topology, each photovoltaic module in the transmission layer adopts a tree topology, and the photovoltaic modules in the management layer adopt a star topology; constructing the hybrid topology structure according to the sensing layer, the transmission layer, and the management layer.

[0137] The core of this embodiment is to divide photovoltaic modules into a sensing layer, a transmission layer, and a management layer according to their node contribution degrees, and respectively adopt different topology structures (mesh topology, tree topology, and star topology), and finally construct a hybrid topology structure. This method improves the efficiency and reliability of the photovoltaic power generation system through hierarchical design and optimized topology structure. The specific steps are as follows:

[0138] Divide each photovoltaic module into a sensing layer, a transmission layer, or a management layer according to its node contribution degree.

[0139] The division rules are as follows:

[0140] Sensing layer: Photovoltaic modules with lower node contribution degrees are mainly responsible for data collection and environmental perception;

[0141] Transmission layer: Photovoltaic modules with medium node contribution degrees are mainly responsible for data transmission and energy transmission;

[0142] Management layer: Photovoltaic modules with higher node contribution degrees are mainly responsible for system management and optimization decisions;

[0143] Sensing layer: Adopt a mesh topology structure.

[0144] The mesh topology has high redundancy and high reliability, and is suitable for data collection and environmental perception tasks. Each photovoltaic module is directly connected to multiple adjacent modules to ensure the stability and fault tolerance of data transmission. Transmission layer: Adopt a tree topology structure. The tree topology has an efficient data transmission path and is suitable for energy transmission and data relay tasks. Photovoltaic modules are connected according to a hierarchical relationship to form a transmission path from the sensing layer to the management layer. Management layer: Adopt a star topology structure. The star topology has the characteristics of centralized management and is suitable for system optimization and decision-making tasks. All photovoltaic modules are directly connected to the central management node, which is convenient for data aggregation and instruction issuance.

[0145] Integrate the sensing layer, the transmission layer, and the management layer according to their functions and topology structures to form a hybrid topology structure. The hybrid topology structure combines the advantages of the mesh topology, the tree topology, and the star topology, and can simultaneously meet the requirements of data collection, transmission, and management.

[0146] Optimize the architecture of the photovoltaic power generation system through hierarchical design and hybrid topology structure to improve the overall efficiency and reliability of the system. The combination of mesh topology and tree topology can ensure the efficient transmission of data in the sensing layer and transmission layer, reducing latency and packet loss rate. The centralized management feature of star topology facilitates real-time monitoring and optimization decision-making of the system by the management layer, improving the operating efficiency of the system. The high redundancy of mesh topology and the efficient transmission path of tree topology can improve the fault tolerance of the system, ensuring that the system can still operate normally when some components fail. The hybrid topology structure can effectively handle system architecture problems in complex environments, such as cloudy weather, terrain undulation, and uneven distribution of obstacles, improving the adaptability and robustness of the system. By optimizing the system architecture and improving the operating efficiency, unnecessary operation and maintenance operations are reduced, and the operation and maintenance costs of the photovoltaic power generation system are lowered.

[0147] Exemplarily, constructing the hybrid topology structure according to the sensing layer, transmission layer, and management layer includes: obtaining a preset topology optimization goal; the topology optimization goal at least includes a target energy transmission efficiency, a target communication latency, and a target reliability; adjusting the connection relationship between the sensing layer, transmission layer, and management layer according to the topology optimization goal to complete the construction of the topology structure.

[0148] The preset topology optimization goal includes, but is not limited to: Target energy transmission efficiency: The efficiency requirement of the system during energy transmission. Target communication latency: The latency requirement of the system during data transmission. Target reliability: The stability requirement of the system under abnormal conditions.

[0149] Adjust the connection relationship of the photovoltaic components in the sensing layer according to the target communication latency and target reliability. Adopt a mesh topology structure to increase redundant connections to ensure the stability and fault tolerance of data transmission. Adjust the connection relationship of the photovoltaic components in the transmission layer according to the target energy transmission efficiency and target communication latency. Adopt a tree topology structure to optimize the data transmission path and reduce energy loss and communication latency. Adjust the connection relationship of the photovoltaic components in the management layer according to the target reliability and target communication latency. Adopt a star topology structure to centrally manage data aggregation and instruction issuance to ensure the reliability of system operation.

[0150] Integrate the sensing layer, transmission layer, and management layer according to their functions and connection relationships according to the topology optimization goal to form a hybrid topology structure. The hybrid topology structure combines the advantages of mesh topology, tree topology, and star topology, and can simultaneously meet the requirements of energy transmission, data transmission, and system management.

[0151] By introducing a topology optimization objective, dynamically adjusting the connection relationships between layers, optimizing the architecture of the photovoltaic power generation system, and improving the overall efficiency and reliability of the system. The tree-shaped topology structure of the transmission layer can optimize the energy transmission path, reduce energy loss, and improve the energy transmission efficiency of the system. The mesh topology structure of the sensing layer and the tree-shaped topology structure of the transmission layer can optimize the data transmission path, reduce communication latency, and ensure the real-time nature of data transmission. The mesh topology structure of the sensing layer and the star-shaped topology structure of the management layer can improve the redundancy and fault tolerance of the system, ensuring that the system can still operate normally when some components fail. The hybrid topology structure can effectively handle system architecture problems in complex environments, such as scenes with cloudy weather, terrain undulations, and uneven distribution of obstacles, improving the adaptability and robustness of the system. By optimizing the system architecture and enhancing the operating efficiency, unnecessary operation and maintenance operations are reduced, and the operation and maintenance costs of the photovoltaic power generation system are lowered.

[0152] In some embodiments, generating management information corresponding to each of the plurality of photovoltaic modules according to the operating data corresponding to the plurality of photovoltaic modules, the future shadow distribution heat map, and the hybrid topology structure includes: parsing the operating data, obtaining the efficiency impact information of each of the photovoltaic modules according to the light intensity information and the temperature information, and obtaining the component health information of each of the photovoltaic modules according to the IV curve information and the hot spot information; parsing the future shadow distribution heat map, obtaining the occlusion area and the occlusion time corresponding to the occlusion area, and calculating the shadow impact information corresponding to each photovoltaic module according to the occlusion area and the corresponding occlusion time; obtaining the importance information corresponding to each of the photovoltaic modules according to the hybrid topology structure; and outputting the management information corresponding to each of the photovoltaic modules based on a preset optimization algorithm according to the efficiency impact information, the component health information, the shadow impact information, and the importance information corresponding to each of the photovoltaic modules to maximize the power generation amount corresponding to the plurality of photovoltaic modules.

[0153] By extracting light intensity information and temperature information from the operation data, the efficiency impact information of each photovoltaic module is calculated. The efficiency impact information reflects the impact of environmental factors on the power generation efficiency of the photovoltaic module. The IV curve information and hot spot information are extracted from the operation data to evaluate the health status of each photovoltaic module. The component health information reflects the operation stability and potential failure risk of the photovoltaic module. The occlusion area and its corresponding occlusion time are extracted from the future shadow distribution heat map to calculate the shadow impact information of each photovoltaic module. The shadow impact information reflects the impact of the occluder on the power generation efficiency of the photovoltaic module. The importance information of each photovoltaic module is extracted from the hybrid topology structure, reflecting its position and role in the system. According to the efficiency impact information, component health information, shadow impact information and importance information, a preset optimization algorithm (such as genetic algorithm, particle swarm optimization algorithm, etc.) is used to generate the management information corresponding to each photovoltaic module. The management information includes operation strategies (such as tilt angle adjustment, cleaning and maintenance) and optimization goals (such as maximizing power generation). The optimization strategy based on the management information can improve the overall efficiency of the photovoltaic power generation system and reduce resource waste. By evaluating the component health information and shadow impact information, potential failure risks can be detected in time to ensure the stable operation of the system.

[0154] The embodiment of the present application also provides a distributed photovoltaic module power generation management device. The distributed photovoltaic module power generation management device is used to execute the steps of the distributed photovoltaic module power generation management method based on the Internet of Things shown in the above embodiments. The distributed photovoltaic module power generation management device can be a single server or a server cluster, or the distributed photovoltaic module power generation management device can be a terminal, and the terminal can be a handheld terminal, a laptop computer, a wearable device or a robot, etc.

[0155] The distributed photovoltaic module power generation management device includes:

[0156] An information acquisition unit, configured to acquire the user power consumption information of the user terminal corresponding to the smart socket system, and construct the power consumption behavior information corresponding to the user terminal according to the user power consumption information;

[0157] A type acquisition unit, configured to acquire the device type corresponding to the electrical device connected to the smart socket system;

[0158] A sensing acquisition unit, configured to acquire the circuit sensing information collected by the sensor array of each independent control circuit;

[0159] A timing generation unit, configured to generate the timing control information corresponding to each independent control circuit according to the multiple circuit sensing information, power consumption behavior information and the device type corresponding to each independent control circuit;

[0160] A power supply control unit is configured to control a relay of each of the independent control circuits to supply power to the electrical equipment according to the timing control information.

[0161] It should be noted that those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described distributed photovoltaic module power generation management device and each unit can refer to the corresponding processes in the embodiments of the distributed photovoltaic module power generation management method based on the Internet of Things described in the above embodiments, and will not be elaborated herein.

[0162] The above-described distributed photovoltaic module power generation management method is implemented in the form of a computer program, and this computer program can run on the above device.

[0163] Please refer to Figure 3 , Figure 3 which is a schematic block diagram of the structure of the control module provided by an embodiment of the present application. The control module includes a processor, a memory, and a network interface connected through a device bus. Among them, the memory can include a storage medium and an internal memory.

[0164] The storage medium can store an operating device and a computer program. This computer program includes program instructions, and when the program instructions are executed, the processor can execute an embodiment of any distributed photovoltaic module power generation management method.

[0165] The processor is configured to provide computing and control capabilities to support the operation of the entire control module.

[0166] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any distributed photovoltaic module power generation management system method.

[0167] This network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 3 the structure shown in

[0168] It should be understood that the processor can be a Central Processing Unit (CPU), and the processor can also be 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. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0169] Among them, in one embodiment, the processor is used to run a computer program stored in the memory to obtain the operation data of multiple photovoltaic modules collected by a multi-modal sensor array; the multi-modal sensor array includes a light intensity sensor, a temperature sensor, an IV curve detector, and a hot spot imager;

[0170] Obtain the fused satellite cloud map and UAV aerial photography data corresponding to multiple photovoltaic modules;

[0171] Input the fused satellite cloud map and UAV aerial photography data into a preset spatio-temporal attention prediction network to output a future shadow distribution heat map;

[0172] Obtain the node contribution degree corresponding to each photovoltaic module, and construct a hybrid topology corresponding to multiple photovoltaic modules according to each node contribution degree;

[0173] Generate management information corresponding to each photovoltaic module according to the operation data, future shadow distribution heat map, and hybrid topology corresponding to multiple photovoltaic modules; the management information at least includes the tilt angle adjustment information of the photovoltaic module; complete the distributed management of multiple photovoltaic modules.

[0174] In some embodiments, inputting the fused satellite cloud image and the UAV aerial photography data into a preset spatio-temporal attention prediction network includes: respectively obtaining the geographic coordinate systems corresponding to the fused satellite cloud image and the UAV aerial photography data; spatially and temporally aligning the fused satellite cloud image and the UAV aerial photography data according to the geographic coordinate systems; adjusting the resolutions of the fused satellite cloud image and the UAV aerial photography data based on interpolation or downsampling techniques; respectively extracting satellite feature information and aerial photography feature information from the adjusted fused satellite cloud image and UAV aerial photography data; the satellite feature information at least includes cloud distribution and cloud thickness; the aerial photography feature information at least includes terrain features and occlusion features; inputting the satellite feature information and the aerial photography feature information into the spatio-temporal attention prediction network to output the future shadow distribution heat map.

[0175] Exemplarily, the spatio-temporal attention prediction network includes a convolutional layer, a long short-term memory layer, and an attention module; inputting the satellite feature information and the aerial photography feature information into the spatio-temporal attention prediction network to output the future shadow distribution heat map includes: respectively inputting the satellite feature information and the aerial photography feature information into the convolutional layer and the long short-term memory layer, the convolutional layer outputs the spatial features corresponding to the satellite feature information and the aerial photography feature information, and the long short-term memory layer outputs the time feature sequences corresponding to the satellite feature information and the aerial photography feature information; respectively inputting the spatial features and the time feature sequences into the attention module, and the attention module respectively outputs time attention information and spatial attention information; the time attention information is used to determine the key change moments in the time feature sequence; the spatial attention information is used to determine the occlusion area features corresponding to the spatial features; outputting the future shadow distribution heat map according to the occlusion area features and the key change moments.

[0176] It should be noted that, in some embodiments, outputting the future shadow distribution heat map according to the occlusion area features and the key change moments includes: obtaining the shadow distribution influence weight corresponding to the occlusion area features; obtaining the environmental change information corresponding to the key change moments; the environmental change information at least includes cloud movement and solar incidence angle change; adjusting the shadow distribution influence weight according to the environmental change information; generating the future shadow distribution heat map according to the adjusted shadow distribution influence weight.

[0177] In some embodiments, obtaining the node contribution degree corresponding to each photovoltaic module includes: obtaining the operation data corresponding to each photovoltaic module; the operation data only includes power output information, current information, and voltage information; obtaining the topology structure information corresponding to each photovoltaic module; the topology structure information is used to determine the connection relationship between each photovoltaic module and the remaining photovoltaic modules; obtaining the environmental data corresponding to each photovoltaic module; the environmental data at least includes light intensity, temperature, and wind speed; calculating the node contribution degree corresponding to each photovoltaic module according to the operation data, topology structure information, and environmental data.

[0178] Exemplarily, calculating the node contribution degree corresponding to each photovoltaic module according to the operation data, topology structure information, and environmental data includes: calculating the energy contribution degree corresponding to each photovoltaic module according to the operation data; calculating the reliability information corresponding to each photovoltaic module according to the operation data and environmental data; the reliability information is used to determine the stability of each photovoltaic module under abnormal conditions; calculating the network influence coefficient corresponding to each photovoltaic module according to the topology structure information and operation data; the network influence coefficient is used to determine the influence of the position of each photovoltaic module on the communication and energy transmission of multiple photovoltaic modules.

[0179] In some embodiments, constructing the hybrid topology structure corresponding to multiple photovoltaic modules according to each node contribution degree includes: respectively dividing multiple photovoltaic modules into any one of a sensing layer, a transmission layer, and a management layer according to the node contribution degree; wherein, each photovoltaic module in the sensing layer adopts a mesh topology, each photovoltaic module in the transmission layer adopts a tree topology, and the photovoltaic module in the management layer adopts a star topology; constructing the hybrid topology structure according to the sensing layer, transmission layer, and management layer.

[0180] Exemplarily, constructing the hybrid topology structure according to the sensing layer, transmission layer, and management layer includes: obtaining a preset topology optimization target; the topology optimization target at least includes a target energy transmission efficiency, a target communication delay, and a target reliability; adjusting the connection relationship between the sensing layer, transmission layer, and management layer according to the topology optimization target to complete the construction of the topology structure.

[0181] In some embodiments, generating management information corresponding to each of the photovoltaic modules based on the operation data corresponding to a plurality of photovoltaic modules, the future shadow distribution heat map, and the hybrid topology structure includes: parsing the operation data, obtaining the efficiency impact information of each photovoltaic module according to the light intensity information and the temperature information, and obtaining the component health information of each photovoltaic module according to the IV curve information and the hot spot information; parsing the future shadow distribution heat map, obtaining the occlusion area and the occlusion time corresponding to the occlusion area, and calculating the shadow impact information corresponding to each photovoltaic module according to the occlusion area and the corresponding occlusion time; obtaining the importance information corresponding to each photovoltaic module according to the hybrid topology structure; and outputting the management information corresponding to each photovoltaic module based on a preset optimization algorithm according to the efficiency impact information, the component health information, the shadow impact information, and the importance information corresponding to each photovoltaic module, so as to maximize the power generation amount corresponding to the plurality of photovoltaic modules.

[0182] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described processor can refer to the corresponding process in the method embodiments described in the above-mentioned embodiments, and will not be repeated here.

[0183] An embodiment of the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. The processor executes the program instructions to implement the steps of the method for managing distributed photovoltaic module power generation based on the Internet of Things provided in the above-mentioned embodiments of the present application.

[0184] Among them, the computer-readable storage medium may be an internal storage unit of the control module described in the foregoing embodiments, such as the hard disk or memory of the control module. The computer-readable storage medium may also be an external storage device of the control module, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the control module.

[0185] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and these modifications or substitutions should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A distributed photovoltaic assembly power generation management method based on the Internet of Things, characterized in that: A control module applied to a distributed photovoltaic assembly power generation management system; the method comprises: Acquiring operation data of a plurality of photovoltaic modules collected by a multimodal sensor array; the multimodal sensor array comprises a light intensity sensor, a temperature sensor, an IV curve detector and a hot spot imager; Obtain fused satellite cloud images and drone aerial photography data corresponding to multiple photovoltaic modules; Input the fused satellite cloud image and drone aerial photography data into a preset spatiotemporal attention prediction network, and output a future shadow distribution heat map; Acquire a node contribution corresponding to each of the photovoltaic components, and construct a hybrid topology structure corresponding to a plurality of the photovoltaic components according to each of the node contributions; Management information corresponding to each photovoltaic component is generated according to the corresponding operating data of multiple photovoltaic components, future shadow distribution thermal map and hybrid topology structure; the management information at least includes the tilt adjustment information of the photovoltaic component; and the distributed management of the multiple photovoltaic components is completed.

2. The method according to claim 1, characterized in that The step of inputting the fused satellite cloud image and drone aerial photography data into a preset spatiotemporal attention prediction network includes: Respectively obtain the geographic coordinate systems corresponding to the fused satellite cloud image and the drone aerial photography data; Aligning the fused satellite cloud image with the drone aerial photography data in space and time according to the geographic coordinate system; Adjusting the resolution of the fused satellite cloud image and the drone aerial photography data based on interpolation or downsampling technology; Extract satellite feature information and aerial photography feature information from the adjusted fused satellite cloud image and drone aerial photography data respectively; the satellite feature information at least includes cloud layer distribution and cloud layer thickness; the aerial photography feature information at least includes terrain features and obstruction features; The satellite feature information and the aerial photography feature information are input into the spatiotemporal attention prediction network to output the future shadow distribution heat map.

3. The method according to claim 2, characterized in that The spatiotemporal attention prediction network includes a convolutional layer, a long short-term memory layer and an attention module; the inputting of the satellite feature information and the aerial photography feature information into the spatiotemporal attention prediction network to output the future shadow distribution heat map includes: The satellite feature information and the aerial photography feature information are input into the convolution layer and the long short-term memory layer respectively, the convolution layer outputs the spatial features corresponding to the satellite feature information and the aerial photography feature information, and the long short-term memory layer outputs the temporal feature sequence corresponding to the satellite feature information and the aerial photography feature information; The spatial feature and the temporal feature sequence are respectively input into the attention module, and the attention module outputs temporal attention information and spatial attention information respectively; the temporal attention information is used to determine the key change moment in the temporal feature sequence; the spatial attention information is used to determine the occlusion area feature corresponding to the spatial feature; The future shadow distribution heat map is output according to the occlusion area characteristics and key change moments.

4. The method according to claim 3, characterized in that Outputting the future shadow distribution heat map according to the occlusion area features and key change moments includes: Obtaining the shadow distribution influence weight corresponding to the occlusion area feature; Acquire environmental change information corresponding to the key change moment; the environmental change information at least includes cloud movement and change in the sun's incident angle; Adjusting the shadow distribution influence weight according to the environmental change information; The future shadow distribution heat map is generated according to the adjusted shadow distribution influence weight.

5. The method according to claim 1, characterized in that The obtaining of the node contribution corresponding to each photovoltaic component includes: Acquire operation data corresponding to each photovoltaic module; the operation data includes power output information, current information and voltage information; Acquire topological structure information corresponding to each photovoltaic component; the topological structure information is used to determine the connection relationship between each photovoltaic component and the remaining photovoltaic components; Acquire environmental data corresponding to each photovoltaic module; the environmental data at least includes light intensity, temperature and wind speed; The node contribution corresponding to each photovoltaic component is calculated according to the operating data, topological structure information and environmental data.

6. The method according to claim 5, characterized in that The calculating the node contribution corresponding to each photovoltaic component according to the operation data, topology information and environmental data includes: Calculate the energy contribution corresponding to each photovoltaic component according to the operating data; Calculating reliability information corresponding to each photovoltaic module according to the operating data and the environmental data; the reliability information is used to determine the stability of each photovoltaic module under abnormal conditions; A network influence coefficient of each photovoltaic component is calculated according to the topology information and the operation data; the network influence coefficient is used to determine the influence of the position of each photovoltaic component on the communication and energy transmission of the plurality of photovoltaic components.

7. The method according to claim 1, characterized in that The step of constructing a hybrid topology structure corresponding to a plurality of photovoltaic components according to the contribution of each node includes: Divide the plurality of photovoltaic components into any one of a perception layer, a transmission layer and a management layer according to the node contribution; wherein each photovoltaic component in the perception layer adopts a mesh topology, each photovoltaic component in the transmission layer adopts a tree topology, and the photovoltaic components in the management layer adopt a star topology; The hybrid topology is constructed according to the perception layer, the transmission layer and the management layer.

8. The method according to claim 7, characterized in that The step of constructing the hybrid topology structure according to the perception layer, the transmission layer and the management layer includes: Obtaining a preset topology optimization target; the topology optimization target at least includes a target energy transmission efficiency, a target communication delay, and a target reliability; The connection relationship between the perception layer, the transmission layer and the management layer is adjusted according to the topology optimization target to complete the construction of the topology structure.

9. The method according to claim 1, characterized in that: The generating of management information corresponding to each photovoltaic component according to the operation data corresponding to the plurality of photovoltaic components, the future shadow distribution thermal map and the hybrid topology structure includes: Parsing the operating data, obtaining efficiency impact information of each photovoltaic module according to light intensity information and temperature information, and obtaining component health information of each photovoltaic module according to IV curve information and hot spot information; Analyze the future shadow distribution heat map, obtain the shaded area and the shaded time corresponding to the shaded area, and calculate the shadow impact information corresponding to each photovoltaic module according to the shaded area and the corresponding shaded time; Acquire importance information corresponding to each photovoltaic component according to the hybrid topology structure; Based on a preset optimization algorithm, management information corresponding to each photovoltaic component is output according to the efficiency impact information, component health information, shadow impact information and importance information corresponding to each photovoltaic component, so as to maximize the power generation corresponding to the plurality of photovoltaic components.

10. A distributed photovoltaic module power generation management system, characterized in that ,include: Multiple photovoltaic panels; A multimodal sensor array; the multimodal sensor array comprises at least a light intensity sensor, a temperature sensor, an IV curve detector and a hot spot imager; A control module, the control module comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method as claimed in any one of claims 1 to 9 when executing the computer program.

Images