Remote photovoltaic power station fault identification and power loss estimation method and device and storage medium

Abstract

This disclosure provides a method, apparatus, and storage medium for remote photovoltaic (PV) power plant fault identification and power loss estimation. The method includes: determining the hierarchical relationship of the PV power plant equipment and the operating status of each component based on current image data of the target PV power plant; determining the inverter operating status of each inverter in the target PV power plant based on currently collected data, the operating status of each component, a pre-trained string operation data prediction model, and the hierarchical relationship of the equipment; and estimating the power loss of the target PV power plant based on the currently collected data and the string operation data prediction model. This disclosure enables remote identification of PV power plant faults and assessment of power loss without access to PV power plant operation data.

Description

Technical Field

[0001] This disclosure relates to the field of photovoltaic power plant technology, and in particular to a method, apparatus and storage medium for remote photovoltaic power plant fault identification and power loss estimation. Background Technology

[0002] With the increasing global demand for renewable energy, photovoltaic (PV) power generation, as an important form of clean energy, has been widely applied and developed. PV power plants are deployed not only on urban rooftops and in rural areas, but also in desert regions, providing a stable power supply for society.

[0003] Traditional photovoltaic (PV) power plants typically rely on regular manual inspections for routine maintenance. However, these manual inspections are insufficient to capture all the necessary operational data. While PV power plants employ automated monitoring systems, various sensors can monitor operational data in real time. However, to protect the security of this data, owners typically do not disclose it to remote maintenance companies. Therefore, regardless of whether manual inspections or automated monitoring are used, maintenance companies cannot obtain complete operational data, hindering their ability to identify faults and assess power loss. Summary of the Invention

[0004] This disclosure provides a method, apparatus, and storage medium for remote photovoltaic power plant fault identification and power loss estimation, enabling remote identification of photovoltaic power plant faults and assessment of power loss without access to photovoltaic power plant operation data.

[0005] In a first aspect, embodiments of this disclosure provide a method for fault identification and power loss estimation in a remote photovoltaic power station, the method comprising:

[0006] Based on the current image data of the target photovoltaic power station, determine the hierarchical relationship of the power station equipment and the operating status of each component;

[0007] Based on the current collected data of the target photovoltaic power station, the operating status of each component of the target photovoltaic power station, the pre-trained string operation data prediction model, and the equipment hierarchy of the power station, the inverter operating status of each inverter of the target photovoltaic power station is determined.

[0008] Based on the currently collected data and the string operation data prediction model, the power loss of the target photovoltaic power station is estimated.

[0009] Optionally, the process of obtaining the string running data prediction model includes:

[0010] Based on historical data collected from multiple photovoltaic power plants and photovoltaic power plant information for each of the aforementioned photovoltaic power plants, a string operation data prediction model is constructed; wherein, the historical data collected includes historical image data of the entire station, historical operation data of each string, historical irradiance data of each string, and historical environmental data of the entire station;

[0011] The steps for constructing the string running data prediction model include:

[0012] The neural network algorithm model is trained based on the historical image data, historical operation data, historical irradiance data, historical environmental data, and photovoltaic power station information of each photovoltaic power station to obtain the string operation data prediction model.

[0013] Optionally, the step of determining the hierarchical relationship of the power station equipment in the target photovoltaic power station includes:

[0014] Based on the current image data, obtain a power station map of the target photovoltaic power station;

[0015] The power station map is segmented and labeled to determine the hierarchical relationship of the power station equipment in the target photovoltaic power station.

[0016] Optionally, the step of determining the operating status of each component of the target photovoltaic power station includes:

[0017] Based on the current image data, determine the brightness value, temperature value, occlusion coverage, dust coverage, and damage level of each component's image.

[0018] The component operating state corresponding to each component image is determined based on the brightness value, temperature value, occlusion coverage, dust coverage, and damage degree of the component image.

[0019] Optionally, the step of determining the inverter operating status of each inverter in the target photovoltaic power station includes:

[0020] The currently collected data is input into the string operation data prediction model to determine the current operation data of each string.

[0021] The running status of each string is determined based on the current running data of each string.

[0022] The power plant irradiance value and the string brightness value of each string are determined based on the currently collected data.

[0023] The inverter operating status of each inverter is determined based on the string operating status of each string, the component operating status of each component, the current operating data of each string, the irradiance value of each power station, and the hierarchical relationship of the power station equipment; or, the inverter operating status of each inverter is determined based on the string operating status of each string, the component operating status of each component, the string brightness value of each string, and the hierarchical relationship of the power station equipment.

[0024] Optionally, the inverter operating state includes a shutdown state, a normal state, and an abnormal state;

[0025] The step of determining the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the current operating data of each string, the power station irradiance value, and the power station equipment hierarchy includes:

[0026] Based on the string operation status of each string and the hierarchical relationship of the power station equipment, determine the inverters whose operation status is in the shutdown state;

[0027] Based on the component operating status of each component, the current operating data of each string, the power plant irradiance value, and the power plant equipment hierarchy, determine whether each inverter whose operating status is not the shutdown state should operate at reduced capacity.

[0028] If the inverter operates at a reduced rate, the inverter's operating state is abnormal; otherwise, the inverter's operating state is normal.

[0029] Optionally, the inverter operating state includes a shutdown state, a normal state, and an abnormal state;

[0030] The step of determining the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the string brightness value of each string, and the power station equipment hierarchy includes:

[0031] Based on the string operation status of each string and the hierarchical relationship of the power station equipment, determine the inverters whose operation status is in the shutdown state;

[0032] Based on the component operating status of each component, the string brightness value of a string, and the power station equipment hierarchy, determine whether each inverter whose operating status is not the shutdown state should be derated.

[0033] If the inverter operates at a reduced rate, the inverter's operating state is abnormal; otherwise, the inverter's operating state is normal.

[0034] Optionally, the currently collected data includes the current image data of the entire station, the current irradiance data of each standard string, the current environmental data of the entire station, the standard string data of each standard string, and the target photovoltaic power station information;

[0035] The estimated power loss of the target photovoltaic power plant includes:

[0036] The standard power generation of the target photovoltaic power station is calculated based on the standard string data of each standard string.

[0037] The current image data, the current irradiance data of each standard string, the current environmental data, the standard string data of each standard string, and the target photovoltaic power station information are input into the string operation data prediction model to determine the voltage and current data of each string of the target photovoltaic power station.

[0038] The actual power generation of the target photovoltaic power station is determined based on the voltage and current data of each string of the target photovoltaic power station.

[0039] Based on the standard power generation and the actual power generation, the power loss of the target photovoltaic power station is estimated.

[0040] Secondly, this disclosure also provides a remote photovoltaic power station fault identification and power loss estimation device, which includes:

[0041] The first fault identification module is used to determine the hierarchical relationship of the power station equipment and the component operating status of each component of the target photovoltaic power station based on the current image data of the target photovoltaic power station.

[0042] The second fault identification module is used to determine the inverter operating status of each inverter in the target photovoltaic power station based on the current collected data of the target photovoltaic power station, the operating status of each component of the target photovoltaic power station, the pre-trained string operation data prediction model, and the equipment hierarchy of the power station.

[0043] The power loss estimation module is used to estimate the power loss of the target photovoltaic power station based on the currently collected data and the string operation data prediction model.

[0044] Thirdly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the remote photovoltaic power station fault identification and power loss estimation method provided in any embodiment of this disclosure.

[0045] This embodiment of the invention can determine the hierarchical relationship of the equipment in the target photovoltaic power station and the operating status of each component based on the current image data of the target photovoltaic power station, thereby enabling the identification of component faults. Based on the currently collected data of the target photovoltaic power station, the operating status of each component, a pre-trained string operation data prediction model, and the hierarchical relationship of the equipment, the operating status of each inverter in the target photovoltaic power station can be determined, thereby enabling the identification of inverter faults. Based on the currently collected data and the string operation data prediction model, the power loss of the target photovoltaic power station can be accurately estimated. In other words, this embodiment of the invention only requires drone aerial photography data and standard string power generation data to achieve remote power loss assessment of photovoltaic power stations where operational data cannot be obtained. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A flowchart illustrating a method for fault identification and power loss estimation in a remote photovoltaic power station, as provided in this embodiment of the disclosure;

[0048] Figure 2 A flowchart illustrating the steps for determining the hierarchical relationship of power plant equipment in a target photovoltaic power plant, as provided in this embodiment of the disclosure;

[0049] Figure 3 A flowchart illustrating the steps for determining the operating status of each component of a target photovoltaic power station according to an embodiment of this disclosure;

[0050] Figure 4 A flowchart illustrating the steps for determining the inverter operating status of each inverter in a target photovoltaic power station, as provided in an embodiment of this disclosure;

[0051] Figure 5 A flowchart illustrating the steps for determining the running state of each string group, as provided in an embodiment of this disclosure;

[0052] Figure 6This is a flowchart illustrating a step for determining the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the current operating data of each string, and the hierarchical relationship of the power plant equipment, as provided in this embodiment of the disclosure.

[0053] Figure 7 This is a flowchart illustrating a step for determining the inverter operating state of each inverter based on the string operating state of each string, the component operating state of each component, the string brightness value of each string, and the hierarchical relationship of the power station equipment, as provided in this embodiment of the disclosure.

[0054] Figure 8 This is a flowchart illustrating the steps for estimating the power loss of a target photovoltaic power plant, as provided in an embodiment of this disclosure.

[0055] Figure 9 This is a schematic diagram of a remote photovoltaic power station fault identification and power loss estimation device provided in an embodiment of the present disclosure. Detailed Implementation

[0056] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0057] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0058] To facilitate understanding of this embodiment, the application scenario of this solution is first introduced. Since the operation and maintenance of photovoltaic (PV) power plants requires the use of dozens or even hundreds of artificial intelligence models, deploying these models locally at the PV power plant would be costly, and these models need frequent updates, which are not conducive to local deployment. Therefore, PV power plants require specialized remote operation and maintenance companies. Typically, a single remote operation and maintenance company will remotely operate and maintain hundreds or even thousands of PV power plants. In this embodiment, the remote operation and maintenance company refers to one that transmits the power plant's data to a remote server via the internet or a dedicated network, using various models deployed on the remote server for fault identification and power estimation. However, some power plants, for confidentiality and security reasons, do not provide the remote operation and maintenance company with their PV power plant operating data, such as the current and voltage of each component or string, the current of each inverter combiner box, and remote signaling, remote sensing, and telemetry data of the inverter. Without data, remote operation and maintenance cannot be achieved. Therefore, how to achieve remote operation and maintenance in the absence of overall PV power plant operating data is a pressing technical problem that needs to be solved.

[0059] To solve the above problems, Figure 1 This is a flowchart illustrating a method for remote photovoltaic power station fault identification and power loss estimation according to an embodiment of this disclosure. This embodiment is applicable to situations requiring remote fault identification and power loss estimation of photovoltaic power stations. The method can be executed by a remote photovoltaic power station fault identification and power loss estimation device. The method specifically includes the following steps:

[0060] S110. Based on the current image data of the target photovoltaic power station, determine the hierarchical relationship of the power station equipment and the operating status of each component.

[0061] The current image data of the target photovoltaic power station can be obtained through inspection and photography by drones. Using drones to replace manual inspections of the target photovoltaic power station can improve inspection efficiency and data collection accuracy. The current image data includes real-time infrared image data captured by the infrared camera carried by the drone and real-time visible light image data captured by the visible light camera carried by the drone.

[0062] Specifically, the connection structure of each device or component in the target photovoltaic power station can be obtained based on the current image data. Therefore, a power station map of the target photovoltaic power station can be generated from the current image data. By segmenting and labeling the power station map according to the connection relationship of collector lines-substations-inverters-combiner boxes-strings-modules, the precise hierarchical relationship of the power station equipment can be obtained.

[0063] In addition, the module's operating status includes hot spot fault status, crack fault status, shading fault status, fouling fault status, and normal power generation status. The operating status of each module is determined based on the current image data of the target photovoltaic power station. Specifically, image recognition technology can be used to identify the temperature distribution of each module in the target photovoltaic power station by recognizing the current infrared image data, thereby identifying hot spot faults and string zero-current faults. Image recognition technology can also be used to identify faults such as cracks, shading rates, and fouling deposits on the modules by recognizing visible light image data.

[0064] Furthermore, by processing the current image data using image recognition technology, a map of the target photovoltaic power station can be generated, thereby enabling rapid location of faulty components.

[0065] S120. Based on the current collected data of the target photovoltaic power station, the component operation status of each component of the target photovoltaic power station, the pre-trained string operation data prediction model, and the hierarchical relationship of the power station equipment, determine the inverter operation status of each inverter in the target photovoltaic power station.

[0066] The currently collected data includes current image data for the entire station, current irradiance data for each standard string, current environmental data for the entire station, standard string data for each standard string, and information about the target photovoltaic power station. Current image data refers to the infrared and visible light image data of the entire target photovoltaic power station captured by the drone. A standard string refers to one or more strings selected from the target photovoltaic power station whose data can be remotely collected via string metering boxes and high-precision environmental monitoring instruments. For each type of string in the target photovoltaic power station, one or more strings will be selected as standard strings. Current irradiance data for each standard string refers to the light intensity, light angle, light duration, and light distribution data monitored by the high-precision environmental monitoring instrument. Current environmental data for the entire station refers to the ambient temperature and humidity data detected by the drone inspection of the target photovoltaic power station. The current irradiance data for each type of standard string can be used as the current irradiance data for other strings of the same type in the target photovoltaic power station. Standard string data consists of the current, voltage, power, and energy output data of the standard strings detected by the string metering box. The standard string data for each model can be used as the standard data for other strings of the same model in the target photovoltaic power plant. The target photovoltaic power plant information includes the model and standard operating parameters of each piece of equipment in the target photovoltaic power plant, such as the model of the modules, the standard power output of the modules, the model of the inverters, and the standard operating power of the inverters.

[0067] Specifically, inverter operating states include shutdown, normal, and abnormal states. Based on the currently collected data and string operating data prediction models, the current operating data (voltage and current data) of each string can be determined. Furthermore, the string operating state (stop generating power or generating power) of each string can be determined based on the current operating data. The power station irradiance and string brightness of each string can be determined based on the currently collected data. Furthermore, based on the string operating state of each string, the component operating state of each module, the current operating data of each string, the power station irradiance, and the power station equipment hierarchy, the operating power of inverters at each inverter level with all components free from obstruction, dust cover, and other component problems under the same irradiance can be selected. By comparing the operating power of the selected inverters, it can be determined whether the inverter's operating state is normal or abnormal. Alternatively, based on the string operation status of each group, the component operation status of each module, the string brightness value of each group, and the hierarchical relationship of the power station equipment, the brightness values ​​of each group of inverters at each inverter level can be selected based on whether all modules are unobstructed, free of dust, have no other component problems, and are under the same irradiance. By using the brightness values ​​of each string of inverters, it is possible to determine whether the inverter is operating normally or abnormally.

[0068] Furthermore, based on the hierarchical relationship of the power plant equipment, the corresponding strings connected to each inverter can be identified, forming the components of each string. When the string operating state of each string connected to the inverter is in a stopped-generating state, the inverter will stop operating; that is, the inverter's operating state is a shutdown state. The string operating state of each string can be determined based on the operating state of each component that makes up the string. For example, if the operating state of each component that makes up the string is in a normal generating state, then the string operating state is in a generating state; if the operating state of each component that makes up the string is in a hot spot fault state, crack fault state, shading fault state, or fouling fault state, resulting in the inability to generate electricity, then the string operating state is a stopped-generating state.

[0069] S130. Based on the current collected data and string operation data prediction model, estimate the power loss of the target photovoltaic power station.

[0070] Based on previously acquired data, information about each standard string (current, voltage, and the number of strings of the same model as each standard string) can be obtained. Therefore, the ideal power generation of the target photovoltaic power station can be calculated based on the information of each standard string. Based on currently acquired data, the current image data of the entire station, the current irradiance data of each standard string, the current environmental data of the entire station, the standard string data of each standard string, and the target photovoltaic power station information can be obtained. By inputting the current image data, the current irradiance data of each standard string, the current environmental data, the standard string data of each standard string, and the target photovoltaic power station information into the string operation data prediction model, the predicted voltage and current of each string of the target photovoltaic power station can be predicted, thereby calculating the predicted power generation of the target photovoltaic power station. Therefore, by using the ideal power generation and predicted power generation of the target photovoltaic power station, the power loss of the target photovoltaic power station can be accurately estimated.

[0071] This disclosure embodiment, by using current image data of the target photovoltaic power station, can determine the hierarchical relationship of the power station equipment and the operating status of each component, thereby achieving component fault identification. Based on the currently collected data of the target photovoltaic power station, the operating status of each component, a pre-trained string operation data prediction model, and the hierarchical relationship of the power station equipment, the inverter operating status of each inverter in the target photovoltaic power station can be determined, thereby achieving inverter fault identification. Based on the currently collected data and the string operation data prediction model, the power loss of the target photovoltaic power station can be accurately estimated.

[0072] Based on the above embodiments, optionally, the process of obtaining the string running data prediction model includes:

[0073] Based on historical data collected from multiple photovoltaic power plants and information on each photovoltaic power plant, a string operation data prediction model is constructed. The historical data collected includes historical image data of the entire station, historical operation data of all strings, historical irradiance data of all strings, and historical environmental data of the entire station.

[0074] Historical image data refers to infrared and visible light image data of the entire photovoltaic power station taken by drones before the current time point. Historical operational data refers to various operational data (e.g., current, voltage, and power) of all strings (e.g., each string and each inverter) of the photovoltaic power station obtained through automated monitoring systems before the current time point. Historical irradiance data refers to data such as light intensity, angle, duration, and distribution of all strings monitored before the current time point. Historical environmental data refers to data such as ambient temperature and humidity of the entire photovoltaic power station detected by drone inspections before the current time point. Photovoltaic power station information includes the model and standard operating parameters of each piece of equipment in the photovoltaic power station, such as the model of the modules, the standard power output of the modules, the model of the inverters, and the standard operating power of the inverters.

[0075] The string operation data prediction model is a model that can predict the current and voltage data of each string in a photovoltaic power station using data that can be collected from the photovoltaic power station (e.g., standard string data collected by string metering boxes, image data collected by drones, irradiation data of standard strings detected by high-precision environmental monitoring instruments, and basic information of photovoltaic modules in the target photovoltaic power station).

[0076] Specifically, by inputting historical data collected from multiple photovoltaic power plants and information about each photovoltaic power plant into a neural network algorithm model, the neural network algorithm model is trained to establish the proportional relationship between the component image temperature, image brightness, and dust level of the photovoltaic power plant and the string current and voltage. In this way, a string operation data prediction model can be obtained to predict the current and voltage data of each string of the target photovoltaic power plant using the collectable data of the target photovoltaic power plant.

[0077] Therefore, remote operation and maintenance personnel can subsequently obtain the operating data of the target photovoltaic power station based on the string operation data prediction model and the data that can be collected from the target photovoltaic power station, providing a data basis for fault analysis and power loss estimation of the target photovoltaic power station.

[0078] The steps to build a string-based data prediction model include:

[0079] The neural network algorithm model is trained based on historical image data, historical operation data, historical irradiance data, historical environmental data, and photovoltaic power station information for each photovoltaic power station to obtain a string operation data prediction model.

[0080] The neural network algorithm model is trained using historical image data, historical operation data, historical irradiance data, historical environmental data, and information about each photovoltaic power station. The parameters of the neural network algorithm model can be continuously adjusted so that the data predicted by the neural network algorithm model gets closer and closer to the historical operation data. When the data predicted by the neural network algorithm model is consistent with the historical operation data, the training of the neural network algorithm model is completed. Thus, a string operation data prediction model can be obtained to predict the current and voltage data of each string of the target photovoltaic power station using the collectable data of the target photovoltaic power station.

[0081] Based on the above embodiments, optionally, Figure 2 This is a flowchart illustrating the steps for determining the hierarchical relationship of power plant equipment in a target photovoltaic power plant, as provided in an embodiment of this disclosure. Figure 2 The steps for determining the hierarchical relationship of equipment in a target photovoltaic power station are illustrated below:

[0082] S210. Based on the current image data, obtain the power station map of the target photovoltaic power station.

[0083] Among them, image processing of the current image data, such as image stitching, image geometric correction, geolocation, and coordinate transformation, can obtain a power station map of the target photovoltaic power station.

[0084] S220. Divide and label the power station map to determine the hierarchical relationship of the power station equipment in the target photovoltaic power station.

[0085] The connection structure of each device or component in a target photovoltaic power station can be obtained from the power station map. Therefore, by segmenting and labeling the power station map according to the connection relationship of collector lines-substations-inverters-combiner boxes-strings-modules, the precise hierarchical relationship of the power station equipment can be obtained. In practical applications, the power station map can be an ACD map, containing the number of each string, the branch to which the string belongs, and information such as the combiner box, inverter, array, and coordinates of each branch.

[0086] In summary, by determining the hierarchical relationship of the power plant equipment through the above steps, we can identify the components that make up each string and the strings connected to each inverter. This facilitates the subsequent inference of the string's operating status based on the operating status of each component that makes up the string, and the inference of the inverter's operating status based on the operating status of each string connected to the inverter.

[0087] Based on the above embodiments, optionally, Figure 3 This is a flowchart illustrating the steps for determining the operating status of each component in a target photovoltaic power station, as provided in an embodiment of this disclosure. Figure 3The steps for determining the operating status of each component in the target photovoltaic power station are illustrated below:

[0088] S310. Based on the current image data, determine the brightness value, temperature value, occlusion coverage, dust coverage, and damage level of each component's image.

[0089] Specifically, the current image data includes infrared image data and visible light image data. By identifying the current infrared image data using image recognition technology, the temperature distribution and brightness of each component in the target photovoltaic power station can be obtained, thereby determining the brightness and temperature values ​​corresponding to each component's image. By identifying the visible light image data using image recognition technology, cracks, shading rates, and dirt deposits on each component can be identified, thereby determining the shading coverage, dust coverage, and damage level corresponding to each component's image.

[0090] S320. Determine the component operation status of the component corresponding to each component image based on the brightness value, temperature value, occlusion coverage, dust coverage and damage degree of each component's component image.

[0091] The component's operating status includes hot spot fault status, crack fault status, shading fault status, dirt deposition fault status, and normal power generation status. By analyzing the brightness value, temperature value, shading coverage, dust coverage, and damage level of each component's image, the operating status of each component can be determined.

[0092] In summary, the above steps can quickly determine the operating status of each component and promptly report any faulty components to remote maintenance personnel. Maintenance personnel can then use drone maps for automatic navigation to manually troubleshoot component faults, thereby reducing power generation losses at the target photovoltaic power station.

[0093] Based on the above embodiments, optionally, Figure 4 This is a flowchart illustrating the steps for determining the inverter operating status of each inverter in a target photovoltaic power station, as provided in an embodiment of this disclosure. Figure 4 The steps for determining the inverter operating status of each inverter in a target photovoltaic power station are illustrated below:

[0094] S410. Input the currently collected data into the string running data prediction model to determine the current running data of each string.

[0095] By inputting the currently collected data into the string operation data prediction model, the current operation data (current data and voltage data) of each string in the target photovoltaic power station can be predicted.

[0096] S420. Determine the running status of each string group based on the current running data of each string group.

[0097] Based on the current operating data of each string, the voltage and current of each string can be obtained, and thus the operating status of each string (stop generating power and generating power) can be accurately determined.

[0098] S430. Determine the power station irradiance value and the string brightness value of each string based on the currently collected data.

[0099] Specifically, based on the current image data of the entire station included in the currently collected data, the brightness value of each string is determined; the current irradiance data of each standard string included in the currently collected data is used as reference data for the power station's irradiance value.

[0100] S440. Determine the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the current operating data of each string, the power station irradiance value, and the power station equipment hierarchy; or, determine the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the string brightness value of each string, and the power station equipment hierarchy.

[0101] For example, based on the string operation status of each group, the component operation status of each component, the current operation data of each group, the power station irradiance value, and the hierarchical relationship of the power station equipment, the operating power of inverters at each inverter level that have no obstruction, no dust coverage, and no other component problems under the same irradiance can be selected. By comparing the operating power of the selected inverters, it can be determined whether the inverter's operating status is normal or abnormal.

[0102] Alternatively, based on the string operation status of each group, the component operation status of each unit, the string brightness value of each group, and the hierarchical relationship of the power station equipment, the brightness values ​​of each string of inverters at each inverter level can be selected based on whether all components are unobstructed, free of dust, have no other component problems, and are under the same irradiance. The brightness values ​​of each string of inverters can then be used to determine whether the inverter is operating normally or abnormally.

[0103] Furthermore, based on the hierarchical relationship of the power plant equipment, the corresponding strings connected to each inverter can be identified, forming the components of each string. When the string connected to the inverter is in a stopped generating state, the inverter will stop operating, meaning the inverter's operating state is a shutdown state.

[0104] In summary, the above steps can quickly determine the operating status of each inverter and promptly report any faulty inverters to remote maintenance personnel. Maintenance personnel can then use drone maps for automatic navigation to manually troubleshoot faulty inverters, thereby reducing power generation losses at the target photovoltaic power station.

[0105] Based on the above embodiments, optionally, the string operating state includes a stopped power generation state and a power generation state.

[0106] In this context, "stop generating electricity" means the string cannot produce any electricity, i.e., it cannot convert solar energy into electrical energy. "Generating electricity" means the string can produce any electricity, i.e., it can convert solar energy into electrical energy.

[0107] Figure 5 A flowchart illustrating the steps for determining the running state of each string group, as provided in this embodiment of the disclosure, is shown below. Figure 5 The steps for determining the running state of each string group are explained as follows:

[0108] S510. Based on the current collected data and the prediction model of the string operation data, determine the voltage and current data of each string.

[0109] By inputting the currently collected data into the string operation data prediction model, the current and voltage data of each string in the target photovoltaic power station can be predicted.

[0110] S520. If both the voltage and current data of the string are not 0, then the string's operating state is the power generation state.

[0111] S530. If both the voltage and current data of the string are 0, then the string's operating state is "stop generating electricity".

[0112] In summary, based on the current collected data and the string operation data prediction model, the voltage and current data of each string can be accurately determined, thereby accurately determining the string operation status of each string. This facilitates the accurate prediction of the inverter's operation status based on the string operation status of each string connected to the inverter.

[0113] Based on the above embodiments, optionally, the inverter operating state includes a shutdown state, a normal state, and an abnormal state.

[0114] Among them, shutdown state means that the inverter stops running, normal state means that the inverter operates at rated power, and abnormal state means that the inverter operates at reduced power.

[0115] In one embodiment, Figure 6This is a flowchart illustrating the steps for determining the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the current operating data of each string, and the hierarchical relationship of the power plant equipment, as provided in this embodiment of the disclosure. Figure 6 The steps for determining the inverter operating status of each inverter based on the string operating status of each group, the component operating status of each component, the current operating data of each string, and the hierarchical relationship of the power plant equipment are described below:

[0116] S610. Based on the string operation status of each string and the hierarchical relationship of the power station equipment, determine the inverters whose operating status is in the shutdown state.

[0117] Based on the hierarchical relationship of the power plant equipment, the corresponding strings connected to each inverter can be identified, forming the components of each string. When the string connected to the inverter is in a stopped generating state, the inverter will stop operating, i.e., the inverter's operating state is in a shutdown state.

[0118] S620. Based on the component operating status of each component, the current operating data of each string, the power station irradiance value, and the power station equipment hierarchy, determine whether each inverter whose operating status is not in the shutdown state should be derated.

[0119] Based on the operating status of each component and the hierarchical relationship of the power station equipment, inverters at each inverter level with all components free from obstruction, dust cover, and other component problems can be selected. Based on the string irradiance value and current operating data of each string, the operating power of inverters at each inverter level with all components free from obstruction, dust cover, and other component problems under the same irradiance can be confirmed. Since inverters under the same conditions have equal operating power, comparing the operating power of inverters under the same conditions confirms that inverters with lower power are operating at derating. Inverters with equal operating power within a certain fluctuation range are all operating at rated power.

[0120] S630. If the inverter operates at a reduced rate, the inverter's operating status is abnormal; otherwise, the inverter's operating status is normal.

[0121] Inverters with low operating power are considered to be in an abnormal operating state; inverters with operating power at their rated power are considered to be in a normal operating state.

[0122] In another embodiment, Figure 7This is a flowchart illustrating a step for determining the inverter operating state of each inverter based on the string operating state of each string, the component operating state of each component, the string brightness value of each string, and the hierarchical relationship of the power station equipment, as provided in this embodiment of the disclosure. Figure 7 The steps for determining the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the string brightness value of each string, and the hierarchical relationship of the power station equipment are described below:

[0123] S710. Based on the string operation status of each string and the hierarchical relationship of the power station equipment, determine the inverters whose operating status is in the shutdown state.

[0124] S720. Based on the component operating status of each component, the string brightness value of each string, and the hierarchical relationship of the power station equipment, determine whether each inverter whose operating status is not in the shutdown state should be derated.

[0125] When an inverter is derating, some strings connected to the inverter will have reduced brightness. Therefore, the inverters derating can be identified based on the brightness of each string of each inverter.

[0126] For example, based on the operating status of each component and the hierarchical relationship of the power station equipment, inverters at each inverter level can be screened where all components are unobstructed, free of dust, and without other component problems. The brightness value of each string connected to the screened inverter is determined based on the string brightness value of each string group. Then, based on the brightness value of each string group connected to the inverter, it is determined whether the inverter is operating at a derating rate. If any string group connected to the inverter has a low brightness value, it can be confirmed that the inverter is operating at a derating rate; if no string group connected to the inverter has a low brightness value, it can be confirmed that the inverter is not operating at a derating rate.

[0127] S730. If the inverter operates at a reduced rate, the inverter's operating status is abnormal; otherwise, the inverter's operating status is normal.

[0128] Among the inverter strings connected to the inverter, the inverter operating state is abnormal if there are strings with low brightness values, and the inverter operating state is normal if the brightness values ​​of each string are equal within a certain fluctuation range.

[0129] Based on the above embodiments, optionally, Figure 8 This is a flowchart illustrating the steps for estimating the power loss of a target photovoltaic power plant, as provided in an embodiment of this disclosure. Figure 8 The steps for estimating the power loss of a target photovoltaic power plant are illustrated below:

[0130] S810. Calculate the standard power generation of the target photovoltaic power station based on the standard string data of each standard string.

[0131] The standard string data includes current and voltage data. The target photovoltaic power station includes multiple standard strings of different standards. The standard power generation of the target photovoltaic power station = (current data * voltage data of the first standard string) * number of standard strings of the first standard in the target photovoltaic power station + (current data * voltage data of the second standard string) * number of standard strings of the second standard in the target photovoltaic power station + ... + (current data * voltage data of the Nth standard string) * number of standard strings of the Nth standard in the target photovoltaic power station.

[0132] S820: Input the current image data, the current irradiance data of each standard string, the current environmental data, the standard string data of each standard string, and the target photovoltaic power station information into the string operation data prediction model to determine the voltage and current data of each string of the target photovoltaic power station.

[0133] By inputting current image data, current irradiance data, current environmental data, standard string data of each standard string of the target photovoltaic power station, and information about the target photovoltaic power station into the string operation data prediction model, the current and voltage data of each string of the photovoltaic power station can be accurately predicted.

[0134] S830. Determine the actual power generation of the target photovoltaic power station based on the voltage and current data of each string of the target photovoltaic power station.

[0135] Specifically, the actual power generation of the target photovoltaic power station = ∑ voltage data of each string * current data.

[0136] S840. Based on the standard power generation and the actual power generation, estimate the power loss of the target photovoltaic power station.

[0137] Specifically, power loss = standard power generation - actual power generation.

[0138] Figure 9 This is a schematic diagram of the structure of a remote photovoltaic power station fault identification and power loss estimation device provided in an embodiment of this disclosure, as shown below. Figure 9 As shown, the remote photovoltaic power station fault identification and power loss estimation device includes:

[0139] The first fault identification module 910 is used to determine the hierarchical relationship of the power station equipment and the operating status of each component of the target photovoltaic power station based on the current image data of the target photovoltaic power station.

[0140] The second fault identification module 920 is used to determine the inverter operating status of each inverter in the target photovoltaic power station based on the current collected data of the target photovoltaic power station, the component operating status of each component of the target photovoltaic power station, the pre-trained string operation data prediction model, and the hierarchical relationship of the power station equipment.

[0141] The power loss estimation module 930 is used to estimate the power loss of the target photovoltaic power station based on the current collected data and string operation data prediction model.

[0142] In this embodiment, the first fault identification module 910, based on the current image data of the target photovoltaic power station, can determine the hierarchical relationship of the power station equipment and the operating status of each component, thereby achieving component fault identification. The second fault identification module 920, based on the currently collected data of the target photovoltaic power station, the operating status of each component, a pre-trained string operation data prediction model, and the hierarchical relationship of the power station equipment, can determine the inverter operating status of each inverter in the target photovoltaic power station, thereby achieving inverter fault identification. The power loss estimation module 930, based on the currently collected data and the string operation data prediction model, can accurately estimate the power loss of the target photovoltaic power station.

[0143] Based on the above embodiments, the remote photovoltaic power station fault identification and power loss estimation device may optionally include: a prediction model construction module;

[0144] The prediction model building module is used to construct a string operation data prediction model based on historical data collected from multiple photovoltaic power plants and photovoltaic power plant information for each photovoltaic power plant. The historical data collected includes historical image data of the entire station, historical operation data of all strings, historical irradiance data of all strings, and historical environmental data of the entire station.

[0145] Based on the above embodiments, optionally, the prediction model building module is specifically used for:

[0146] The neural network algorithm model is trained based on historical image data, historical operation data, historical irradiance data, historical environmental data, and photovoltaic power station information for each photovoltaic power station to obtain a string operation data prediction model.

[0147] Based on the above embodiments, optionally, the first fault identification module includes a power plant equipment hierarchy relationship determination unit;

[0148] The unit for determining the hierarchical relationship of power plant equipment is specifically used for:

[0149] Based on the current image data, obtain a power station map of the target photovoltaic power station;

[0150] The power station map is segmented and labeled to determine the hierarchical relationship of the power station equipment in the target photovoltaic power station.

[0151] Based on the above embodiments, the first fault identification module may optionally further include a component operating status determination unit;

[0152] The component runtime status determination unit is specifically used for:

[0153] Based on the current image data, determine the brightness value, temperature value, occlusion coverage, dust coverage, and damage level of each component's image.

[0154] Based on the brightness value, temperature value, occlusion coverage, dust coverage, and damage level of each component's image, the component's operating status corresponding to each component image is determined.

[0155] Based on the above embodiments, optionally, the second fault identification module includes:

[0156] The string operation data determination unit is used to input the currently collected data into the string operation data prediction model to determine the current operation data of each string.

[0157] The string running status determination unit is used to determine the string running status of each string based on the current running data of each string.

[0158] The parameter determination unit is used to determine the power plant irradiance value and the string brightness value of each string based on the currently collected data.

[0159] The inverter operating status determination unit is used to determine the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the current operating data of each string, the power station irradiance value, and the power station equipment hierarchy; or, based on the string operating status of each string, the component operating status of each component, the string brightness value of each string, and the power station equipment hierarchy.

[0160] Based on the above embodiments, optionally, the string operating state includes a stopped power generation state and a power generation state;

[0161] The string parameter determination unit is specifically used for:

[0162] Based on the current collected data and the prediction model of string operation data, determine the voltage and current data of each string;

[0163] If both the voltage and current data of the string are not 0, then the string's operating state is the power generation state.

[0164] If both the voltage and current data of the string are 0, then the string's operating state is that it has stopped generating electricity.

[0165] Based on the above embodiments, optionally, the inverter operating state includes a shutdown state, a normal state, and an abnormal state;

[0166] The inverter operating status determination unit includes the inverter operating status first determination subunit;

[0167] The first sub-unit for determining the inverter's operating status is specifically used for:

[0168] Based on the string operation status of each string and the hierarchical relationship of the power station equipment, determine the inverters whose operation status is in the shutdown state.

[0169] Based on the component operating status of each component, the current operating data of each string, the power plant irradiance value, and the power plant equipment hierarchy, determine whether each inverter whose operating status is not shutdown should be derated.

[0170] If the inverter operates at reduced capacity, the inverter's operating status is abnormal; otherwise, the inverter's operating status is normal.

[0171] The inverter operating status determination unit also includes a second inverter operating status determination subunit;

[0172] The second sub-unit for determining the inverter's operating status is specifically used for:

[0173] Based on the string operation status of each string and the hierarchical relationship of the power station equipment, determine the inverters whose operation status is in the shutdown state.

[0174] Based on the component operating status of each component, the string brightness value of each string, and the hierarchical relationship of the power station equipment, determine whether each inverter whose operating status is not in the shutdown state should be derated.

[0175] If the inverter operates at reduced capacity, the inverter's operating status is abnormal; otherwise, the inverter's operating status is normal.

[0176] Based on the above embodiments, optionally, the currently collected data includes the current image data of the entire station, the current irradiance data of each standard string, the current environmental data of the entire station, the standard string data of each standard string, and the target photovoltaic power station information;

[0177] The power loss estimation module includes:

[0178] The standard power generation calculation unit is used to calculate the standard power generation of the target photovoltaic power station based on the standard string data of each standard string.

[0179] The string parameter prediction unit is used to input the current image data, the current irradiance data of each standard string, the current environmental data, the standard string data of each standard string, and the target photovoltaic power station information into the string operation data prediction model to determine the voltage and current data of each string of the target photovoltaic power station.

[0180] The actual power generation calculation unit is used to determine the actual power generation of the target photovoltaic power station based on the voltage and current data of each string of the target photovoltaic power station.

[0181] The power loss calculation unit is used to estimate the power loss of the target photovoltaic power plant based on the standard power generation and the actual power generation.

[0182] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the remote photovoltaic power station fault identification and power loss estimation method provided in any embodiment of this disclosure.

[0183] The computer storage medium of this disclosure can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. Computer-readable storage media include (a non-exhaustive list): electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), electrically erasable, programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0184] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, the data signals carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0185] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, radio frequency (RF), or any suitable combination thereof.

[0186] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination of programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, Ruby, and Go, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a Local Area Network (LAN) or a Wide Area Network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0187] Those skilled in the art will understand that the term user terminal encompasses any suitable type of wireless user equipment, such as mobile phones, portable data processing devices, portable web browsers, or vehicle-mounted mobile stations.

[0188] Generally, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. For example, some aspects can be implemented in hardware, while others can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device, although this disclosure is not limited thereto.

[0189] Embodiments of this disclosure can be implemented by executing computer program instructions through the data processor of a mobile device, for example, in a processor entity, or through hardware, or through a combination of software and hardware. The computer program instructions can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages.

[0190] Any block diagram of logical flow in the accompanying drawings of this disclosure may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions. The computer program may be stored in memory. The memory may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as, but not limited to, read-only memory (ROM), random access memory (RAM), optical storage devices and systems (Digital Multifunction Discs, DVDs, or CDs), etc. Computer-readable media may include non-transitory storage media. The data processor may be of any type suitable to the local technical environment, such as, but not limited to, general-purpose computers, special-purpose computers, microprocessors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), and processors based on multi-core processor architectures.

[0191] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0192] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for fault identification and power loss estimation in a remote photovoltaic power station, characterized in that, include: Based on the current image data of the target photovoltaic power station, determine the hierarchical relationship of the power station equipment and the operating status of each component; Based on the current collected data of the target photovoltaic power station, the operating status of each component of the target photovoltaic power station, the pre-trained string operation data prediction model, and the equipment hierarchy of the power station, the inverter operating status of each inverter of the target photovoltaic power station is determined. Based on the currently collected data and the string operation data prediction model, the power loss of the target photovoltaic power station is estimated.

2. The method for fault identification and power loss estimation in a remote photovoltaic power station according to claim 1, characterized in that, The process of obtaining the string running data prediction model includes: Based on historical data collected from multiple photovoltaic power plants and photovoltaic power plant information for each of the aforementioned photovoltaic power plants, a string operation data prediction model is constructed; wherein, the historical data collected includes historical image data of the entire station, historical operation data of all strings, historical irradiance data of all strings, and historical environmental data of the entire station; The steps for constructing the string running data prediction model include: The neural network algorithm model is trained based on the historical image data, historical operation data, historical irradiance data, historical environmental data, and photovoltaic power station information of each photovoltaic power station to obtain the string operation data prediction model.

3. The method for fault identification and power loss estimation in a remote photovoltaic power station according to claim 1, characterized in that, The step of determining the hierarchical relationship of the power station equipment in the target photovoltaic power station includes: Based on the current image data, obtain a power station map of the target photovoltaic power station; The power station map is segmented and labeled to determine the hierarchical relationship of the power station equipment in the target photovoltaic power station.

4. The method for fault identification and power loss estimation in a remote photovoltaic power station according to claim 1, characterized in that, The steps for determining the operating status of each component of the target photovoltaic power station include: Based on the current image data, determine the brightness value, temperature value, occlusion coverage, dust coverage, and damage level of each component's image. The component operating state corresponding to each component image is determined based on the brightness value, temperature value, occlusion coverage, dust coverage, and damage degree of the component image.

5. The method for fault identification and power loss estimation in a remote photovoltaic power station according to claim 1, characterized in that, The steps for determining the inverter operating status of each inverter in the target photovoltaic power station include: The currently collected data is input into the string operation data prediction model to determine the current operation data of each string. The running status of each string is determined based on the current running data of each string. The power plant irradiance value and the string brightness value of each string are determined based on the currently collected data. The inverter operating state of each inverter is determined based on the string operating state of each string, the component operating state of each component, the current operating data of each string, the power station irradiance value, and the power station equipment hierarchy; or, the inverter operating state of each inverter is determined based on the string operating state of each string, the component operating state of each component, the string brightness value of each string, and the power station equipment hierarchy.

6. The method for fault identification and power loss estimation in a remote photovoltaic power station according to claim 5, characterized in that, The inverter's operating status includes shutdown status, normal status, and abnormal status; The step of determining the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the current operating data of each string, and the power station equipment hierarchy includes: Based on the string operation status of each string and the hierarchical relationship of the power station equipment, determine the inverters whose operation status is in the shutdown state; Based on the component operating status of each component, the current operating data of each string, the power plant irradiance value, and the power plant equipment hierarchy, determine whether each inverter whose operating status is not the shutdown state should operate at reduced capacity. If the inverter operates at a reduced rate, the inverter's operating state is abnormal; otherwise, the inverter's operating state is normal.

7. The method for fault identification and power loss estimation in a remote photovoltaic power station according to claim 5, characterized in that, The inverter's operating status includes shutdown status, normal status, and abnormal status; The step of determining the inverter operating status of each inverter based on the string operating status of each string, the component operating status of each component, the string brightness value of each string, and the power station equipment hierarchy includes: Based on the string operation status of each string and the hierarchical relationship of the power station equipment, determine the inverters whose operation status is in the shutdown state; Based on the component operating status of each component, the string brightness value of each string, and the power station equipment hierarchy, determine whether each inverter whose operating status is not the shutdown state should operate at reduced capacity. If the inverter operates at a reduced rate, the inverter's operating state is abnormal; otherwise, the inverter's operating state is normal.

8. The method for fault identification and power loss estimation in a remote photovoltaic power station according to claim 1, characterized in that, The currently collected data includes the current image data of the entire station, the current irradiance data of each standard string, the current environmental data of the entire station, the standard string data of each standard string, and the target photovoltaic power station information; The estimated power loss of the target photovoltaic power plant includes: The standard power generation of the target photovoltaic power station is calculated based on the standard string data of each standard string. The current image data, the current irradiance data of each standard string, the current environmental data, the standard string data of each standard string, and the target photovoltaic power station information are input into the string operation data prediction model to determine the voltage and current data of each string of the target photovoltaic power station. The actual power generation of the target photovoltaic power station is determined based on the voltage and current data of each string of the target photovoltaic power station. Based on the standard power generation and the actual power generation, the power loss of the target photovoltaic power station is estimated.

9. A remote photovoltaic power station fault identification and power loss estimation device, characterized in that, include: The first fault identification module is used to determine the hierarchical relationship of the power station equipment and the component operating status of each component of the target photovoltaic power station based on the current image data of the target photovoltaic power station. The second fault identification module is used to determine the inverter operating status of each inverter in the target photovoltaic power station based on the current collected data of the target photovoltaic power station, the operating status of each component of the target photovoltaic power station, the pre-trained string operation data prediction model, and the equipment hierarchy of the power station. The power loss estimation module is used to estimate the power loss of the target photovoltaic power station based on the currently collected data and the string operation data prediction model.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the remote photovoltaic power station fault identification and power loss estimation method as described in any one of claims 1-8.

Images