Full-aperture photovoltaic operation monitoring system and method

Abstract

The invention discloses a full-aperture photovoltaic operation monitoring system and method. The system comprises a plurality of distributed photovoltaic power generation devices in a target area, a plurality of data acquisition devices arranged in the target area, a data interaction server, a transformer area monitoring server and a regulation and control cloud platform. The regulation and control cloud platform is used for dividing a target area into a plurality of sub-areas based on the installation position and the installation capacity of the distributed photovoltaic power generation device; the data acquisition device is used for performing full-aperture data acquisition on the distributed photovoltaic power generation device in a target area; and the transformer area monitoring server performs power prediction on the distributed photovoltaic power generation devices in the sub-areas by using a power prediction model. A large number of sensors are prevented from being arranged at each distributed photovoltaic power generation device, manpower and material resources are saved, and the system efficiency is improved. According to the invention, the power prediction value is corrected based on the number of accessed photovoltaic modules and the number of faults, and the accuracy of power prediction is improved.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, and in particular to a full-caliber photovoltaic operation monitoring system and method. Background Technology

[0002] Photovoltaic power generation is divided into centralized and distributed systems. Centralized photovoltaic systems are generally equipped with power prediction systems. However, distributed photovoltaic systems, due to their lower grid connection voltage levels, smaller installed capacity, and more dispersed grid connections, typically only collect power generation information, resulting in limited data collection and difficulties in real-time monitoring and prediction. Therefore, comprehensive data collection and monitoring of distributed photovoltaic systems is a necessary technical challenge. Currently, distributed photovoltaic systems are developing rapidly and are widely distributed. Installing numerous sensors and communication devices at each distributed photovoltaic unit would consume significant manpower and resources, leading to prohibitively high costs. How to efficiently and cost-effectively achieve comprehensive data collection, monitoring, and prediction for distributed photovoltaic systems is a crucial issue for industry professionals. Furthermore, many distributed photovoltaic systems in various regions have been in operation for years and, due to their remote locations, often lack maintenance, leading to equipment wear and tear, inability to connect to grids, or the need for upgrades and renovations. These issues can affect the accuracy of photovoltaic power prediction.

[0003] Existing technology, patent application CN116205377A, proposes a method, system, computer, and storage medium for predicting the output of a distributed photovoltaic power station. The method includes collecting periodic historical data of the target distributed photovoltaic power station; obtaining effective output data from the periodic historical data through a preprocessing algorithm; optimizing the relevant parameters of a binary classification model using a particle swarm optimization algorithm based on the effective output data to obtain a pre-predicted prediction algorithm; and using the pre-predicted prediction algorithm to perform short-term output prediction for the predicted day based on weather data of the target distributed photovoltaic power station on the predicted day. This patent application improves data quality by deleting and interpolating abnormal and missing data, and by using a particle swarm optimization algorithm to optimize the regularization and kernel parameters of the binary classification model, it improves the prediction accuracy and solution speed of the pre-predicted prediction algorithm for photovoltaic power generation, and has stronger generalization ability and result stability. However, this patent application does not solve the technical problem mentioned above in this invention. Summary of the Invention

[0004] Purpose of the invention: To address the above problems, this invention proposes a full-caliber photovoltaic operation monitoring system and method.

[0005] Technical solution:

[0006] In a first aspect, the present invention provides a comprehensive photovoltaic operation monitoring system, comprising:

[0007] Several distributed photovoltaic power generation devices within the target area, several data acquisition devices set up within the target area, data interaction server, transformer area monitoring server, and control cloud platform;

[0008] Preferably, the control cloud platform is used to divide the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic power generation devices;

[0009] The data acquisition device is used to collect full-caliber data from distributed photovoltaic power generation devices within the target area.

[0010] The data acquisition device includes a first data acquisition device and a second data acquisition device;

[0011] The first data acquisition device is used to collect current data, voltage data, power data, and switching data of the photovoltaic power generation device.

[0012] The second data acquisition device is used to collect light data, temperature data, humidity data, wind speed data, air pressure data, and equipment self-test data of photovoltaic power generation devices in the sub-region;

[0013] The data exchange server is used to process the collected data and send the processed data to the monitoring server and the control cloud platform.

[0014] The monitoring server for the distribution area uses a power prediction model to predict the power of distributed photovoltaic power generation devices in each sub-area.

[0015] The control cloud platform is also used to correct the power prediction value of the power prediction model by using the switching data of the switching equipment and the equipment self-test data.

[0016] Preferably, the control cloud platform includes a statistical analysis module and a regional division module;

[0017] The statistical analysis module is used to collect and record the installation location and capacity of each distributed photovoltaic power generation device in the target area;

[0018] The region division module is used to determine the first node based on the installed capacity of each distributed photovoltaic power generation device. The location of the first node is the location of the distributed photovoltaic power generation device whose installed capacity exceeds the first threshold.

[0019] The target node is determined based on whether the distance between the first nodes is less than a first distance threshold.

[0020] The target region is divided into several sub-regions based on the location of each target node, and each sub-region contains only one target node.

[0021] Each second node is assigned to the sub-region containing the nearest target node;

[0022] The location of the second node is the location of distributed photovoltaic power generation devices whose installed capacity does not exceed the first threshold.

[0023] Preferably, the first data acquisition device is located at each first node and the second node;

[0024] The second data acquisition device is installed at each target node.

[0025] Preferably, the transformer area monitoring server includes a power prediction model;

[0026] The power prediction model is used to predict the total power of photovoltaic power generation devices within a sub-region;

[0027] The input data for the power prediction model includes illumination data, temperature data, humidity data, wind speed data, air pressure data, and historical power data; the output of the power prediction model is the predicted power value.

[0028] Preferably, the control cloud platform is used to determine the number of photovoltaic modules connected to the system in the photovoltaic power generation device based on the opening and closing data of the switching equipment, which is a first number;

[0029] The number of faulty photovoltaic modules in the photovoltaic power generation device is determined based on the self-test data of the equipment, and this number is the second quantity.

[0030] The output of the power prediction model is corrected based on the first and second quantities.

[0031] Secondly, the present invention also provides a method for full-caliber photovoltaic operation monitoring, the method comprising:

[0032] S1. Statistically determine the installation location and capacity of each distributed photovoltaic power generation device in the target area;

[0033] S2. The control cloud platform divides the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic power generation device;

[0034] S3. Set up data acquisition devices in the target area to achieve full-caliber data acquisition of distributed photovoltaic power generation devices;

[0035] S4. The data exchange server processes the collected data and sends the processed data to the monitoring server and the control cloud platform.

[0036] S5, the area monitoring server performs power prediction on distributed photovoltaic power generation devices in each sub-area based on the power prediction model;

[0037] S6. The control cloud platform corrects the power prediction value of the power prediction model based on the switching data of the switching equipment and the equipment self-test data.

[0038] Preferably, step S2, dividing the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic power generation device, includes:

[0039] S21. Determine the first node A based on the installed capacity of each distributed photovoltaic power generation device. i The location of the first node is the location of the distributed photovoltaic power generation device whose installed capacity exceeds the first threshold.

[0040] S22, For each first node A i Calculate the interval distance between each other first node; determine whether the interval distance is less than a first distance threshold; if not, determine the first node Ai as the target node;

[0041] S23. If there are other first nodes A j With the first node A i If the distance between them is less than the first distance threshold, then A is determined. i With A j The midpoint of the line connecting the nodes is the target node; where i and j are the numbers of the distributed photovoltaic power generation devices, 1≤i,j≤n, and n is the number of distributed photovoltaic power generation devices in the target area;

[0042] S24. Divide the target area into several sub-regions according to the location of each target node, wherein there is only one target node in each sub-region; assign each second node to the sub-region where the nearest target node is located; the location of the second node is the location of the distributed photovoltaic power generation device whose installed capacity does not exceed the first threshold.

[0043] Preferably, step S3, setting up a data acquisition device in the target area to achieve full-caliber data acquisition of distributed photovoltaic power generation devices, includes:

[0044] S31. A first data acquisition device is set up at each first node and a second node respectively. The first data acquisition device is used to collect current data, voltage data, power data and switching data of the photovoltaic power generation device.

[0045] S32. A second data acquisition device is set up at each target node. The second data acquisition device is used to collect the target node's light data, temperature data, humidity data, wind speed data, air pressure data, and equipment self-test data of the photovoltaic power generation devices in the sub-area.

[0046] Preferably, the S5 method, whereby the area monitoring server performs power prediction on the distributed photovoltaic power generation devices in each sub-region based on a power prediction model, includes:

[0047] S51. Construct a power prediction model for the photovoltaic power generation devices in each sub-region. The power prediction model is a machine learning model.

[0048] S52. The inputs of the power prediction model include illumination data, temperature data, humidity data, wind speed data, air pressure data, and historical power data; the output of the power prediction model is the power prediction value.

[0049] Preferably, step S6, whereby the control cloud platform corrects the power prediction value of the power prediction model based on the switching data and equipment self-test data of the switching equipment, includes:

[0050] S61. Determine the number of photovoltaic modules connected to the system in the photovoltaic power generation device based on the opening and closing data of the switching equipment, and set it as the first number;

[0051] S62. Determine the number of photovoltaic modules that have malfunctioned in the photovoltaic power generation device based on the self-test data of the equipment, and this number is the second number;

[0052] S63. The output of the power prediction model is corrected based on the first quantity and the second quantity.

[0053] The present invention has the following advantages over the prior art:

[0054] This invention divides the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic (PV) power generation devices. A first data acquisition device collects current, voltage, power, and switching data from the PV power generation devices; a second data acquisition device collects sunlight, temperature, humidity, wind speed, air pressure, and equipment self-test data from the PV power generation devices within each sub-region. This efficiently achieves comprehensive data collection for a large area of ​​distributed PV power generation devices within the target area. In each sub-region, a monitoring server is set up to predict the power output of the sub-region. The model data collection process utilizes environmental data from the target nodes and electrical variable data from each PV power generation device, avoiding the need for numerous sensors at each distributed PV power generation device, saving manpower and resources, and improving system efficiency. Furthermore, this invention statistically analyzes the number of malfunctioning PV modules and the number of PV modules connected to the system, and corrects the predicted values ​​output by the model based on this analysis, improving the accuracy of the predictions. Attached Figure Description

[0055] Figure 1A schematic diagram of a full-caliber photovoltaic operation monitoring system provided in an embodiment of the present invention;

[0056] Figure 2 A flowchart of a full-caliber photovoltaic operation monitoring method provided in an embodiment of the present invention;

[0057] Figure 3 This is a photovoltaic power prediction and monitoring diagram provided in an embodiment of the present invention. Detailed Implementation

[0058] Obviously, many modifications and variations made by those skilled in the art based on the spirit of this invention fall within the scope of protection of this invention.

[0059] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when an element or component is referred to as “connected” to another element or component, it may be directly connected to the other element or component, or there may be intermediate elements or components. The term “and / or” as used herein includes any and all combinations of one or more of the associated listed items.

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Example 1:

[0062] This invention provides a full-scope photovoltaic operation monitoring system; please refer to the following for details. Figure 1 , Figure 1 A schematic diagram of a full-caliber photovoltaic operation monitoring system is provided as an embodiment of the present invention. The system includes:

[0063] Several distributed photovoltaic power generation devices within the target area, several data acquisition devices set up within the target area, data interaction server, transformer area monitoring server, and control cloud platform;

[0064] Preferably, the control cloud platform is used to divide the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic power generation devices;

[0065] The data acquisition device is used to collect full-caliber data from distributed photovoltaic power generation devices within the target area.

[0066] The data acquisition device includes a first data acquisition device and a second data acquisition device;

[0067] The first data acquisition device is used to collect current data, voltage data, power data, and switching data of the photovoltaic power generation device.

[0068] The second data acquisition device is used to collect light data, temperature data, humidity data, wind speed data, air pressure data, and equipment self-test data of photovoltaic power generation devices in the sub-region;

[0069] The data exchange server is used to process the collected data and send the processed data to the monitoring server and the control cloud platform.

[0070] The monitoring server for the distribution area uses a power prediction model to predict the power of distributed photovoltaic power generation devices in each sub-area.

[0071] The control cloud platform is also used to correct the power prediction value of the power prediction model by using the switching data of the switching equipment and the equipment self-test data.

[0072] Preferably, the control cloud platform includes a statistical analysis module and a regional division module;

[0073] The statistical analysis module is used to collect and record the installation location and capacity of each distributed photovoltaic power generation device in the target area;

[0074] The region division module is used to determine the first node based on the installed capacity of each distributed photovoltaic power generation device. The location of the first node is the location of the distributed photovoltaic power generation device whose installed capacity exceeds the first threshold.

[0075] The target node is determined based on whether the distance between the first nodes is less than a first distance threshold.

[0076] The target region is divided into several sub-regions based on the location of each target node, and each sub-region contains only one target node.

[0077] Each second node is assigned to the sub-region containing the nearest target node;

[0078] The location of the second node is the location of distributed photovoltaic power generation devices whose installed capacity does not exceed the first threshold.

[0079] Preferably, the first data acquisition device is located at each first node and the second node;

[0080] The second data acquisition device is installed at each target node.

[0081] Preferably, the transformer area monitoring server includes a power prediction model;

[0082] The power prediction model is used to predict the total power of photovoltaic power generation devices within a sub-region;

[0083] The input data for the power prediction model includes illumination data, temperature data, humidity data, wind speed data, air pressure data, and historical power data; the output of the power prediction model is the predicted power value.

[0084] This invention divides the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic (PV) power generation devices. A first data acquisition device collects current, voltage, and power data from the PV power generation devices, as well as the on / off data of the switching equipment. A second data acquisition device collects sunlight, temperature, humidity, wind speed, air pressure, and equipment self-test data from the PV power generation devices within each sub-region. This efficiently achieves comprehensive data collection for a large area of ​​distributed PV power generation devices within the target area. In each sub-region, a monitoring server is set up to predict the power output of the sub-region. The model data collection process utilizes environmental data from the target nodes and electrical variable data from each PV power generation device, avoiding the need for numerous sensors at each distributed PV power generation device, saving manpower and resources, and improving system efficiency.

[0085] Preferably, the control cloud platform is used to determine the number of photovoltaic modules connected to the system in the photovoltaic power generation device based on the opening and closing data of the switching equipment, which is a first number;

[0086] The number of faulty photovoltaic modules in the photovoltaic power generation device is determined based on the self-test data of the equipment, and this number is the second quantity.

[0087] The output of the power prediction model is corrected based on the first and second quantities.

[0088] This invention statistically analyzes the number of photovoltaic modules that malfunction in photovoltaic power generation devices and the number of photovoltaic modules connected to the system, and corrects the predicted values ​​output by the model based on this, thereby improving the accuracy of the prediction.

[0089] Example 2:

[0090] This invention also provides a comprehensive photovoltaic operation monitoring method, please refer to the following for details. Figure 2 , Figure 2A flowchart of a full-caliber photovoltaic operation monitoring method is provided in this embodiment of the invention. The method includes the following steps:

[0091] S1. Statistically determine the installation location and capacity of each distributed photovoltaic power generation device in the target area;

[0092] S2. The control cloud platform divides the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic power generation device;

[0093] Preferably, S2 includes:

[0094] S21. Determine the first node A based on the installed capacity of each distributed photovoltaic power generation device. i The location of the first node is the location of the distributed photovoltaic power generation device whose installed capacity exceeds the first threshold.

[0095] S22, For each first node A i Calculate the interval distance between each other first node; determine whether the interval distance is less than a first distance threshold; if not, determine the first node Ai as the target node;

[0096] S23. If there are other first nodes A j With the first node A i If the distance between them is less than the first distance threshold, then A is determined. i With A j The midpoint of the line connecting the nodes is the target node; where i and j are the numbers of the distributed photovoltaic power generation devices, 1≤i,j≤n, and n is the number of distributed photovoltaic power generation devices in the target area;

[0097] In addition, it is generally not possible for the distance between more than three first nodes to be less than the first distance threshold. If the special terrain causes the distance between more than three first nodes to be less than the first distance threshold when arranging distributed photovoltaic power generation devices, then the center point of the polygon formed by these first nodes is determined as the target node.

[0098] S24. Divide the target area into several sub-regions according to the location of each target node, wherein there is only one target node in each sub-region; assign each second node to the sub-region where the nearest target node is located; the location of the second node is the location of the distributed photovoltaic power generation device whose installed capacity does not exceed the first threshold.

[0099] S3. Set up data acquisition devices in the target area to achieve full-caliber data acquisition of distributed photovoltaic power generation devices;

[0100] Preferably, S3 includes:

[0101] S31. A first data acquisition device is set up at each first node and a second node respectively. The first data acquisition device is used to collect current data, voltage data, power data and switching data of the photovoltaic power generation device.

[0102] S32. A second data acquisition device is set up at each target node. The second data acquisition device is used to collect the target node's light data, temperature data, humidity data, wind speed data, air pressure data, and equipment self-test data of the photovoltaic power generation devices in the sub-area.

[0103] S4. The data exchange server processes the collected data and sends the processed data to the monitoring server and the control cloud platform.

[0104] Due to various reasons such as sensor malfunctions, communication transmission equipment failures, electromagnetic interference, and operator error, the collected data may contain certain problems. If the data is used directly for power prediction, the prediction accuracy will be greatly reduced. Therefore, it is necessary to process the massive amount of data after collection, including missing value imputation and outlier removal. These data processing steps are implemented through a data exchange server.

[0105] S5, the area monitoring server performs power prediction on distributed photovoltaic power generation devices in each sub-area based on the power prediction model;

[0106] Preferably, S5 includes:

[0107] S51. Construct a power prediction model for the photovoltaic power generation devices in each sub-region. The power prediction model is a machine learning model.

[0108] The power prediction model is used to predict the total power within a sub-region, rather than the power of each distributed photovoltaic power generation device.

[0109] S52. The inputs of the power prediction model include illumination data, temperature data, humidity data, wind speed data, air pressure data, and historical power data; the output of the power prediction model is the power prediction value.

[0110] The specific type of the power prediction model is selected from a variety of prediction models used in the prior art, which is not the focus of this invention and will not be elaborated here.

[0111] This invention sets up a monitoring server in each sub-region to predict the power of the sub-region. In the process of model data acquisition, the environmental data of the target node and the electrical variable data of each photovoltaic power generation device are used, which avoids setting up a large number of sensors at each distributed photovoltaic power generation device, saves manpower and resources, and improves system efficiency.

[0112] S6. The control cloud platform corrects the power prediction value of the power prediction model based on the switching data of the switching equipment and the equipment self-test data.

[0113] Preferably, S6 includes:

[0114] S61. Determine the number of photovoltaic modules connected to the system in the photovoltaic power generation device based on the opening and closing data of the switching equipment, and set it as the first number;

[0115] S62. Determine the number of photovoltaic modules that have malfunctioned in the photovoltaic power generation device based on the self-test data of the equipment, and this number is the second number;

[0116] S63. The output of the power prediction model is corrected based on the first quantity and the second quantity.

[0117] S6. The control cloud platform corrects the power prediction value of the power prediction model based on the switching data of the switching equipment and the equipment self-test data.

[0118] S61. Determine the number of photovoltaic modules connected to the system in the photovoltaic power generation device based on the opening and closing data of the switching equipment, and set it to the first number N1.

[0119] S62. Determine the number of photovoltaic modules that have malfunctioned in the photovoltaic power generation device based on the self-test data of the equipment, and set it as the second number N2;

[0120] S63. Correct the output of the power prediction model based on the first quantity and the second quantity;

[0121] ;

[0122] ;

[0123] ;

[0124] Where P is the corrected power prediction value, P1 is the power prediction value output by the power prediction model, Q is the first correction coefficient, and P D U1 is the fault correction value, N is the initial number of photovoltaic modules, α is the first correction coefficient, β is the second correction coefficient, R is the impedance of the faulty photovoltaic module, U1 is the normal voltage value of the faulty photovoltaic module, and U2 is the fault voltage value of the faulty photovoltaic module.

[0125] Due to the rapid development of distributed photovoltaic (PV) power generation systems, many PV modules in PV installations require replacement, repair, and / or expansion, resulting in a constant change in the number of effectively operating PV modules. In this situation, continuing to use a fixed prediction model for power forecasting will inevitably lead to a significant reduction in the accuracy of the prediction results.

[0126] Therefore, this invention statistically analyzes the number of photovoltaic modules that malfunction in photovoltaic power generation devices and the number of photovoltaic modules connected to the system, and corrects the predicted values ​​output by the model based on this, thereby improving the accuracy of the prediction.

[0127] Furthermore, staff can use the cloud platform to collect, monitor, and predict the power output of distributed photovoltaic systems across the entire data range. See details... Figure 3 , Figure 3 This invention provides a photovoltaic power prediction and monitoring chart, which can be remotely monitored by staff through a terminal login.

[0128] Example 3:

[0129] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. Preferably, when the processor executes the computer program, it implements the steps in the full-caliber photovoltaic operation monitoring method.

[0130] Example 4:

[0131] This invention also provides a computer-readable storage medium storing a computer program thereon. Preferably, when the computer program is executed by a processor, it implements the steps in the full-caliber photovoltaic operation monitoring method.

[0132] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0133] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0134] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

Claims

1. A full-caliber photovoltaic operation monitoring system, comprising a plurality of distributed photovoltaic power generation devices within a target area, a plurality of data acquisition devices installed within the target area, a data interaction server, a transformer area monitoring server, and a control cloud platform; characterized in that, The control cloud platform is used to divide the target area into several sub-regions based on the installation location and capacity of distributed photovoltaic power generation devices. The data acquisition device is used to collect full-caliber data from the distributed photovoltaic power generation devices within the target area. The data acquisition device includes a first data acquisition device and a second data acquisition device. The first data acquisition device is used to collect current data, voltage data, power data, and switching data of the photovoltaic power generation devices. The second data acquisition device is used to collect sunlight data, temperature data, humidity data, wind speed data, air pressure data, and equipment self-test data of the photovoltaic power generation devices within the sub-regions. The data exchange server is used to process the collected data and send the processed data to the monitoring server and the control cloud platform. The transformer area monitoring server uses a power prediction model to predict the power of the distributed photovoltaic power generation devices in each sub-region. The control cloud platform is also used to correct the power prediction value of the power prediction model using the switching data and equipment self-test data.

2. The full-caliber photovoltaic operation monitoring system according to claim 1, characterized in that, The control cloud platform includes a statistical analysis module and a region division module. The statistical analysis module is used to collect and record the installation location and capacity of each distributed photovoltaic power generation device in the target area. The region division module is used to determine a first node based on the installation capacity of each distributed photovoltaic power generation device, where the location of the first node is the location of distributed photovoltaic power generation devices whose installed capacity exceeds a first threshold. A target node is determined based on whether the distance between the first nodes is less than a first distance threshold. The target area is divided into several sub-regions based on the location of each target node, where each sub-region contains only one target node. Each second node is assigned to the sub-region where the nearest target node is located. The location of the second node is the location of distributed photovoltaic power generation devices whose installed capacity does not exceed the first threshold.

3. The full-caliber photovoltaic operation monitoring system according to claim 2, characterized in that, The first data acquisition device is installed at each first node and second node; The second data acquisition device is installed at each target node.

4. The full-caliber photovoltaic operation monitoring system according to claim 3, characterized in that, The monitoring server for the transformer area includes a power prediction model; The power prediction model is used to predict the total power of photovoltaic power generation devices within a sub-region; The input data for the power prediction model includes illumination data, temperature data, humidity data, wind speed data, air pressure data, and historical power data; the output of the power prediction model is the predicted power value.

5. The full-caliber photovoltaic operation monitoring system according to claim 4, characterized in that, The control cloud platform is used to determine the number of photovoltaic modules connected to the system in the photovoltaic power generation device based on the opening and closing data of the switching equipment, which is the first number; The number of faulty photovoltaic modules in the photovoltaic power generation device is determined based on the self-test data of the equipment, and this number is the second quantity. The output of the power prediction model is corrected based on the first and second quantities.

6. A method for monitoring the operation of a full-caliber photovoltaic system, applied to the full-caliber photovoltaic system described in any one of claims 1-5, characterized in that, The method includes: S1. Statistically determine the installation location and capacity of each distributed photovoltaic power generation device in the target area; S2. The control cloud platform divides the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic power generation device; S3. Set up data acquisition devices in the target area to achieve full-caliber data acquisition of distributed photovoltaic power generation devices; S4. The data exchange server processes the collected data and sends the processed data to the monitoring server and the control cloud platform. S5, the area monitoring server performs power prediction on distributed photovoltaic power generation devices in each sub-area based on the power prediction model; S6. The control cloud platform corrects the power prediction value of the power prediction model based on the switching data of the switching equipment and the equipment self-test data.

7. The full-caliber photovoltaic operation monitoring method according to claim 6, characterized in that, S2, dividing the target area into several sub-regions based on the installation location and capacity of the distributed photovoltaic power generation device, includes: S21. Determine the first node A based on the installed capacity of each distributed photovoltaic power generation device. i The location of the first node is the location of the distributed photovoltaic power generation device whose installed capacity exceeds the first threshold. S22, For each first node A i Calculate the interval distance between each other first node; determine whether the interval distance is less than a first distance threshold; if not, determine the first node Ai as the target node; S23. If there are other first nodes A j With the first node A i If the distance between them is less than the first distance threshold, then A is determined. i With A j The midpoint of the line connecting the nodes is the target node; where i and j are the numbers of the distributed photovoltaic power generation devices, 1≤i,j≤n, and n is the number of distributed photovoltaic power generation devices in the target area; S24. Divide the target area into several sub-regions according to the location of each target node, wherein there is only one target node in each sub-region; assign each second node to the sub-region where the nearest target node is located; the location of the second node is the location of the distributed photovoltaic power generation device whose installed capacity does not exceed the first threshold.

8. The full-caliber photovoltaic operation monitoring method according to claim 7, characterized in that, S3, setting up a data acquisition device in the target area to achieve full-caliber data acquisition of distributed photovoltaic power generation devices, includes: S31. A first data acquisition device is set up at each first node and a second node respectively. The first data acquisition device is used to collect current data, voltage data, power data and switching data of the photovoltaic power generation device. S32. A second data acquisition device is set up at each target node. The second data acquisition device is used to collect the target node's light data, temperature data, humidity data, wind speed data, air pressure data, and equipment self-test data of the photovoltaic power generation devices in the sub-area.

9. The full-caliber photovoltaic operation monitoring method according to claim 8, characterized in that, The S5 and the area monitoring server perform power prediction for distributed photovoltaic power generation devices in each sub-region based on the power prediction model, including: S51. Construct a power prediction model for the photovoltaic power generation devices in each sub-region. The power prediction model is a machine learning model. S52. The inputs of the power prediction model include illumination data, temperature data, humidity data, wind speed data, air pressure data, and historical power data; the output of the power prediction model is the power prediction value.

10. The full-caliber photovoltaic operation monitoring method according to claim 9, characterized in that, The S6 step, where the control cloud platform corrects the power prediction value of the power prediction model based on the switching data and equipment self-test data of the switching equipment, includes: S61. Determine the number of photovoltaic modules connected to the system in the photovoltaic power generation device based on the opening and closing data of the switching equipment, and set it as the first number; S62. Determine the number of photovoltaic modules that have malfunctioned in the photovoltaic power generation device based on the self-test data of the equipment, and this number is the second number; S63. The output of the power prediction model is corrected based on the first quantity and the second quantity.

Images