Photovoltaic power station state prediction method and device

Abstract

The application provides a photovoltaic power station state prediction method and device, and belongs to the technical field of photovoltaic power generation. The method comprises the following steps: predicting fault data of a photovoltaic power station based on operation data of a target device; the target device is a power generation device of the photovoltaic power station; predicting power generation of the photovoltaic power station based on the operation data of the target device and first meteorological data, to obtain predicted power generation of the photovoltaic power station; the first meteorological data is predicted meteorological data of the photovoltaic power station; and correcting the predicted power generation of the photovoltaic power station based on the fault data. The photovoltaic power station state prediction method and device provided by the application can improve the accuracy of power generation prediction of the photovoltaic power station.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of photovoltaic power generation, and more particularly relates to a photovoltaic power station state prediction method and device. BACKGROUND

[0002] Photovoltaic power stations can generate electricity using solar energy and do not produce pollutants and greenhouse gas emissions, and are a clean and renewable energy source. In the context of addressing global climate change and reducing carbon emissions, photovoltaic power stations are of great significance to achieving sustainable energy supply.

[0003] As a distributed power source, the output power of a photovoltaic power station is intermittent and fluctuating. In order to avoid the fluctuations of the photovoltaic power station affecting the safe and stable operation of the power grid, it is necessary to accurately predict the power generation of the photovoltaic power station and take timely scheduling measures. Therefore, in order to improve the quality and stability of the power grid, it is urgent to improve the power generation prediction method and fault prediction method of the photovoltaic power station. SUMMARY

[0004] The purpose of the present application is to provide a photovoltaic power station state prediction method and device to improve the accuracy of photovoltaic power station power generation prediction.

[0005] The first aspect of the embodiment of the present application provides a photovoltaic power station state prediction method, comprising:

[0006] predicting fault data of the photovoltaic power station based on operation data of a target device; the target device being a power generation device of the photovoltaic power station;

[0007] predicting power generation of the photovoltaic power station based on the operation data of the target device and first meteorological data, to obtain predicted power generation of the photovoltaic power station; the first meteorological data being predicted meteorological data of the photovoltaic power station;

[0008] correcting the predicted power generation of the photovoltaic power station based on the fault data.

[0009] Preferably, the fault data includes fault types and corresponding severity levels, and the correcting the predicted power generation of the photovoltaic power station based on the fault data comprises:

[0010] determining a first correction parameter based on the fault type;

[0011] adjusting the first correction parameter based on the severity level corresponding to the fault type to obtain a second correction parameter;

[0012] correcting the predicted power generation of the photovoltaic power station based on the second correction parameter.

[0013] Preferably, the correcting the predicted power generation of the photovoltaic power station based on the second correction parameter comprises:

[0014] If the fault data comprises a plurality of fault types, the second correction parameters corresponding to the plurality of fault types are weighted and summed to obtain a third correction parameter;

[0015] The predicted power generation of the photovoltaic power station is corrected based on the third correction parameter.

[0016] Preferably, the correcting the predicted power generation of the photovoltaic power station based on the second correction parameter comprises:

[0017] If the fault data comprises a plurality of fault types, and there is a synergistic deterioration relationship between a first fault type and a second fault type, the second correction parameters corresponding to the first fault type and the second fault type are added to obtain a fourth correction parameter; specifically, when the predicted fault type is multiple, the fault types with synergistic deterioration relationship are first screened; for each fault type, other fault types with synergistic deterioration relationship with the fault type are pre-stored in a first storage space; in the actual operation process of the photovoltaic power station, if the predicted fault type is multiple, the plurality of fault types are randomly sorted to obtain a fault type queue, and then starting from the first fault type in the fault type queue, the fault types with synergistic relationship are screened by comparing with the fault types stored in the first storage space to obtain a combination of fault types with synergistic relationship;

[0018] The second correction parameter corresponding to a third fault type is weighted and summed with the fourth correction parameter to obtain a fifth correction parameter; the first fault type, the second fault type, and the third fault type are different fault types;

[0019] The predicted power generation of the photovoltaic power station is corrected based on the fifth correction parameter.

[0020] Preferably, the method further comprises:

[0021] A first difference value is determined based on the corrected predicted power generation and a first power generation; the first power generation is an actual power generation of the photovoltaic power station;

[0022] In response to the first difference value being greater than a first threshold value, and a similarity between the first meteorological data and second meteorological data being greater than a second threshold value, a first alarm information is output; the second meteorological data is actual meteorological data of the photovoltaic power station;

[0023] Specifically, considering the influence of meteorological factors on power generation, when the first difference value between the corrected predicted power generation and the first power generation is greater than the first threshold value, the influence of meteorological factors on power generation is further determined.

[0024] The first meteorological data in a set period is regarded as a plurality of variables to construct a first meteorological sequence, and then the second meteorological data in the same period is used to construct a second meteorological sequence, and the correlation coefficient between the first meteorological sequence and the second meteorological sequence is calculated to obtain the similarity between the first meteorological data and the second meteorological data; the value range of the correlation coefficient is between-1 and 1, and the closer the correlation coefficient is to 1, the more similar the two first meteorological data and the second meteorological data are, and the smaller the influence of the meteorological factor on the power generation is.

[0025] The first meteorological data in a set period is regarded as a plurality of variables to construct a first meteorological sequence, and then the second meteorological data in the same period is used to construct a second meteorological sequence, and the correlation coefficient between the first meteorological sequence and the second meteorological sequence is calculated to obtain the similarity between the first meteorological data and the second meteorological data; the value range of the correlation coefficient is between-1 and 1, and the closer the correlation coefficient is to 1, the more similar the two first meteorological data and the second meteorological data are, and the smaller the influence of the meteorological factor on the power generation is.

[0026] Preferably, the method further comprises:

[0027] In response to the current date belonging to a specified date range, the first threshold value is set to a first numerical value;

[0028] In response to the current date exceeding the specified date range, the first threshold value is set to a second numerical value;

[0029] The first numerical value is smaller than the second numerical value.

[0030] Preferably, the method further comprises:

[0031] In response to the output frequency of the first alarm information being greater than a third threshold value within a set time, a second alarm information is output, and the second alarm information is used to indicate that the fault prediction model and the power generation prediction model are updated;

[0032] The fault prediction model is used to predict the fault data of the photovoltaic power station based on the operation data of the target device, and the power generation prediction model is used to predict the power generation of the photovoltaic power station based on the operation data of the target device and the first meteorological data.

[0033] The second aspect of the embodiment of the application provides a photovoltaic power station state prediction device, which comprises:

[0034] A fault prediction module is used to predict the fault data of the photovoltaic power station based on the operation data of the target device; the target device is a power generation device of the photovoltaic power station;

[0035] A power generation prediction module is used to predict the power generation of the photovoltaic power station based on the operation data of the target device and the first meteorological data, and obtain the predicted power generation of the photovoltaic power station; the first meteorological data is the predicted meteorological data of the photovoltaic power station;

[0036] The power generation correction module is configured to correct the predicted power generation of the photovoltaic power station based on the fault data.

[0037] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the photovoltaic power station state prediction method when running the computer program.

[0038] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program implements the steps of the photovoltaic power station state prediction method when executed by a processor.

[0039] The photovoltaic power station state prediction method and device provided by the embodiments of the present application have the following advantages:

[0040] In the embodiments of the present application, the fault data of the photovoltaic power station is predicted based on the operation data of the target device, so that potential faults of the device can be found in advance, and the accuracy of fault prediction is improved; the power generation of the photovoltaic power station is predicted based on the operation data of the target device and the first meteorological data, so that more accurate basis can be provided for power dispatching and operation management. Meanwhile, considering that the occurrence of faults may affect the actual power generation of the photovoltaic power station, the power generation of the photovoltaic power station is corrected based on the fault data, so that the power generation prediction is closer to the actual situation, which helps to better balance power supply and demand and enhance the stability of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0042] Figure 1 A flowchart of the photovoltaic power station state prediction method provided by an embodiment of the present application is shown in the figure.

[0043] Figure 2 A structural block diagram of the photovoltaic power station state prediction device provided by an embodiment of the present application is shown in the figure.

[0044] Figure 3 A schematic block diagram of the electronic device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0045] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, technologies, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0046] In order to make the objects, technical solutions and advantages of the present application clearer, the following will be described by specific embodiments in conjunction with the accompanying drawings.

[0047] Reference will be made to Figure 1 , Figure 1 The flowchart of the photovoltaic power station state prediction method provided by an embodiment of the present application is shown in the figure, and the method comprises the following steps.

[0048] S101: predicting fault data of the photovoltaic power station based on operation data of a target device; the target device is a power generation device of the photovoltaic power station.

[0049] In the embodiment, the target device can include power generation devices such as photovoltaic components, inverters, transformers, etc. in the photovoltaic power station. By collecting historical operation data (such as voltage, current, power, temperature, working frequency, fault, etc.) of the target device to train a neural network model, a fault prediction model of the photovoltaic power station can be obtained. During the operation of the photovoltaic power station, data acquisition devices such as sensors can be set to collect operation data of the photovoltaic power station, for example, temperature sensors and current sensors can be installed on the photovoltaic components to monitor the working temperature and output current of the photovoltaic components in real time, and power monitoring devices can be installed on the inverters to monitor the output power of the inverters in real time. The real-time collected operation data is input into the fault prediction model, and the fault prediction model can output fault data.

[0050] S102: predicting power generation of the photovoltaic power station based on the operation data of the target device and first meteorological data, to obtain predicted power generation of the photovoltaic power station.

[0051] In the embodiment, considering that the power generation capacity of the photovoltaic power station is not only related to the operation data of the target device, but also affected by meteorological data such as solar radiation intensity, temperature, wind speed, humidity, etc., which will affect the power generation of the photovoltaic power station, therefore, the historical operation data of the photovoltaic power station and the first meteorological data (i.e. predicted meteorological data of the photovoltaic power station) can be combined to train a power generation prediction model. During the operation of the photovoltaic power station, the photovoltaic power station and the first meteorological data are input into the power generation prediction model, and the power generation prediction model can output the power generation of the photovoltaic power station in a future period of time.

[0052] S103: correcting the predicted power generation of the photovoltaic power station based on the fault data.

[0053] In the embodiment, considering that the occurrence of the fault can affect the actual power generation of the photovoltaic power station, the partial shading fault of the photovoltaic component can cause the output power of the component to decrease, thereby affecting the power generation of the entire photovoltaic power station. Therefore, the predicted power generation of the photovoltaic power station can be corrected based on the fault data, so that the predicted power generation is closer to the actual power generation.

[0054] Specifically, a plurality of specific fault types that have a greater impact on power generation can be pre-stored, and when one or more specific fault types occur, the predicted power generation of the photovoltaic power station is reduced by a certain proportion, and the proportion is determined according to the number of specific faults. When one specific fault type occurs, a pre-set first proportion coefficient is used as the reduced proportion, and when a plurality of specific fault types occur, the first proportion coefficient can be adjusted based on the number of specific fault types, and the adjusted proportion coefficient is used as the reduced proportion. The more the number of specific fault types, the greater the first proportion coefficient, and the lower the predicted power generation of the photovoltaic power station.

[0055] From the above, it can be concluded that the embodiment predicts the fault data of the photovoltaic power station based on the operation data of the target device, can discover potential faults of the device in advance, and improves the accuracy of fault prediction; predicts the power generation of the photovoltaic power station based on the operation data of the target device and the first meteorological data, and can provide more accurate basis for power dispatching and operation management. At the same time, considering that the occurrence of the fault can affect the actual power generation of the photovoltaic power station, therefore, the power generation of the photovoltaic power station is corrected based on the fault data, which can make the power generation prediction closer to the actual situation, and help to better balance the power supply and demand, and enhance the stability of the power grid.

[0056] In an embodiment of the present application, the fault data includes a fault type and a corresponding severity level, and the predicted power generation of the photovoltaic power station is corrected based on the fault data, including:

[0057] determining a first correction parameter based on the fault type;

[0058] adjusting the first correction parameter based on the severity level corresponding to the fault type to obtain a second correction parameter;

[0059] correcting the predicted power generation of the photovoltaic power station based on the second correction parameter.

[0060] In this embodiment, a specific implementation of correcting the predicted power generation of the photovoltaic power station based on fault data is given. When training the fault prediction model, the historical operation data of the target device can be used as input data, and the fault type and its corresponding severity level can be used as output data. During the operation of the photovoltaic power station, by inputting the real-time collected operation data into the trained fault prediction model, the corresponding fault type and its severity level can be obtained. The fault types can include photovoltaic component hot spot fault, photovoltaic component open circuit fault, photovoltaic component short circuit fault, inverter overvoltage fault, inverter overcurrent fault, inverter overheat fault, transformer winding fault, transformer core fault, etc., and the severity level can be divided into three levels of slight, medium and severe.

[0061] On this basis, considering that different fault types have different degrees of influence on power generation, a mapping relationship between fault types and first correction parameters can be constructed in advance. For example, for hot spot effect fault, according to historical data, hot spot effect makes the power generation decrease by 10%, and the first correction parameter corresponding to the hot spot effect can be set to 0.1.

[0062] At the same time, considering that for the same fault type, the corresponding severity level is different, the degree of influence on power generation will also be different. For example, for hot spot fault, slight hot spot may only cause local temperature to rise slightly, and has little influence on power generation; medium hot spot may cause power generation to decrease significantly; severe hot spot may damage the photovoltaic component, causing power generation to decrease significantly. Therefore, for each fault type, different first adjustment parameters can be set according to its severity level to adjust the first correction parameter to obtain a second correction parameter. The higher the severity level, the larger the first adjustment parameter, and the larger the second correction parameter.

[0063] For example, if only slight level hot spot fault occurs, a smaller first adjustment parameter (such as 0.5) can be set, and the first adjustment parameter is multiplied by the first correction parameter to obtain a smaller second correction parameter; if the severity level of the hot spot fault is severe, a larger first adjustment parameter (such as 1.2) can be set, and the first adjustment parameter is multiplied by the first correction parameter to obtain a larger second correction parameter; if the severity level of the hot spot fault is medium, the first correction parameter is not adjusted.

[0064] The predicted power generation is multiplied by the second correction parameter to obtain the reduced power generation, and then the corrected power generation is obtained. For example, the predicted power generation is 1000 kWh, the severity of the hot spot fault is slight, the corresponding first correction parameter is 0.1, and the first adjustment parameter is 0.5, then the second correction parameter is 0.05, and the corrected power generation is 1000 x (1-0.1 x 0.5) = 950 kWh.

[0065] From the above, it can be concluded that the embodiment considers that different fault types and different fault severity levels will cause different power generation, and the predicted power generation is corrected based on the fault type and the corresponding severity level, so that the predicted power generation is closer to the actual power generation.

[0066] In an embodiment of the present application, the predicted power generation of the photovoltaic power station is corrected based on the second correction parameter, comprising:

[0067] If the fault data includes multiple fault types, the second correction parameters corresponding to the multiple fault types are weighted and summed to obtain a third correction parameter;

[0068] The predicted power generation of the photovoltaic power station is corrected based on the third correction parameter.

[0069] In the embodiment, if the predicted fault type is multiple, the second correction parameters corresponding to the multiple fault types can be weighted and summed (for example, weighted average summation) to obtain a third correction parameter, and the predicted power generation of the photovoltaic power station is corrected based on the third correction parameter, so as to comprehensively consider the influence of multiple fault types on power generation.

[0070] From the above, it can be concluded that the embodiment comprehensively considers the influence of multiple fault types on the predicted power generation, which can realize accurate prediction of power generation, and further more accurately perform power dispatching to balance supply and demand, and improve the stability and reliability of the power grid.

[0071] In an embodiment of the present application, the predicted power generation of the photovoltaic power station is corrected based on the second correction parameter, comprising:

[0072] If the fault data includes multiple fault types, and there is a synergistic deterioration relationship between the first fault type and the second fault type, the second correction parameters corresponding to the first fault type and the second fault type are added to obtain a fourth correction parameter;

[0073] The second correction parameter corresponding to the third fault type is weighted and summed with the fourth correction parameter to obtain a fifth correction parameter; the first fault type, the second fault type and the third fault type are different fault types;

[0074] The predicted power generation of the photovoltaic power station is corrected based on the fifth correction parameter.

[0075] In the embodiment, there is a synergistic deterioration relationship between the first fault type and the second fault type, that is, when the two fault types occur simultaneously, the impact on the power generation of the photovoltaic power station will be much greater than the impact of a single fault type on the power generation of the photovoltaic power station. For example, the first fault type is hot spot failure of a photovoltaic module, and the second fault type is overvoltage failure of an inverter. When the two faults occur simultaneously, the power generation of the photovoltaic power station can decrease by a much greater margin than when a single fault occurs.

[0076] Therefore, when there are multiple predicted fault types, the fault types with synergistic deterioration relationship can be screened first. Specifically, for each fault type, other fault types with synergistic deterioration relationship with the fault type can be pre-stored in a first storage space. During actual operation of the photovoltaic power station, if there are multiple predicted fault types, the multiple fault types can be randomly sorted to obtain a fault type queue, and then starting from the first fault type in the fault type queue, the combination of fault types with synergistic relationship can be screened by comparing with the fault types stored in the first storage space. Assuming that the fault type queue is: photovoltaic module hot spot failure, inverter overvoltage failure, inverter overcurrent failure, and transformer winding failure, starting from the first fault type in the fault type queue (i.e., photovoltaic module hot spot failure), if there is a fault type with synergistic deterioration relationship with the photovoltaic module hot spot failure in the first storage space, and the fault type is inverter overvoltage failure, then the combination of the photovoltaic module hot spot failure and the inverter overvoltage failure is screened from the fault type queue. The above process is repeated to continue screening fault types with synergistic deterioration relationship from the remaining fault type queue until the last fault type in the fault type queue.

[0077] Taking the combination of the screened fault types with synergistic deterioration relationship including the first fault type and the second fault type as an example, the second correction parameter corresponding to the first fault type and the second fault type is added first to obtain a fourth correction parameter, and the fourth correction parameter is used as the correction parameter corresponding to the two fault types. Then the fourth correction parameter and the second correction parameter corresponding to the remaining fault type (i.e., the third fault type) in the fault type queue are weighted and averaged to obtain a fifth correction parameter, and the predicted power generation of the photovoltaic power station is corrected based on the fifth correction parameter.

[0078] From the above, it can be concluded that the fifth correction parameter is determined based on the synergistic deterioration relationship between different fault types in the embodiment, which can more accurately evaluate the impact of multiple faults occurring simultaneously on power generation, and the correction of the predicted power generation based on the fifth correction parameter can improve the accuracy of the predicted power generation.

[0079] In an embodiment of the present application, the photovoltaic power station state prediction method further comprises:

[0080] determine a first difference value based on the corrected predicted power generation and the first power generation; the first power generation is an actual power generation of the photovoltaic power station;

[0081] In response to the first difference value being greater than a first threshold value and a similarity between the first meteorological data and the second meteorological data being greater than a second threshold value, output first alarm information; the second meteorological data is actual meteorological data of the photovoltaic power station.

[0082] In the embodiment, the first power generation is the actual power generation of the photovoltaic power station, and ideally, the corrected predicted power generation is close to the first power generation. If the first difference value between the corrected predicted power generation and the first power generation is greater than the first threshold value, it indicates that the corrected predicted power generation and the first power generation differ greatly, and it can be judged that the photovoltaic power station may have a fault.

[0083] Considering the influence of meteorological factors on power generation, when the first difference value between the corrected predicted power generation and the first power generation is greater than the first threshold value, it is further determined that the influence of meteorological factors on power generation.

[0084] Specifically, a first multi-dimensional vector can be constructed based on the first meteorological data (including temperature, humidity, solar radiation intensity, wind speed, etc.) in a set period, and then a second multi-dimensional vector can be constructed based on the second meteorological data in the same period. The similarity between the first meteorological data and the second meteorological data is obtained by calculating the Euclidean distance between the first multi-dimensional vector and the second multi-dimensional vector. The greater the Euclidean distance, the smaller the similarity between the first meteorological data and the second meteorological data, and the greater the influence of meteorological factors on power generation.

[0085] The first meteorological data (including temperature, humidity, solar radiation intensity, wind speed, etc.) in a set period can also be regarded as a plurality of variables to construct a first meteorological sequence, and then a second meteorological sequence can be constructed based on the second meteorological data in the same period. The similarity between the first meteorological data and the second meteorological data is obtained by calculating the correlation coefficient between the first meteorological sequence and the second meteorological sequence. The correlation coefficient has a value range of -1 to 1. The closer the correlation coefficient is to 1, the more similar the two first meteorological data and the second meteorological data are, and the smaller the influence of meteorological factors on power generation.

[0086] If the first difference value between the corrected predicted power generation and the first power generation is greater than the first threshold value, and the similarity between the first meteorological data and the second meteorological data is greater than the second threshold value, it indicates that the influence of meteorological factors on power generation is small, and the difference between the predicted power generation and the first power generation is likely to be caused by a fault of the photovoltaic power station. At this time, the first alarm information can be output to remind the operation and maintenance personnel to promptly troubleshoot.

[0087] In some cases, the photovoltaic power station can also be managed in sections. If the first difference between the predicted power generation of a certain area (for example, area A) and the first power generation is greater than the first threshold value, and the first difference between the predicted power generation of other areas and the first power generation is less than the third threshold value, that is, the predicted power generation of other areas except area A is relatively close to the actual power generation, it indicates that area A may have a fault, and area A can be focused on for troubleshooting. The first threshold value, the second threshold value, and the third threshold value are all preset constants.

[0088] From the above, it can be seen that the embodiment compares the corrected predicted power generation with the actual power generation to judge the fault of the photovoltaic power station, and further judges in combination with the similarity of the meteorological data, so that the abnormal condition of the photovoltaic power station can be found in time, the operation and maintenance personnel are reminded to check and handle in time, and the problem is avoided from being further expanded.

[0089] In an embodiment of the present application, the photovoltaic power station state prediction method further comprises:

[0090] In response to the current date belonging to a specified date range, the first threshold value is set to a first value;

[0091] In response to the current date exceeding the specified date range, the first threshold value is set to a second value;

[0092] The first value is less than the second value.

[0093] In the embodiment, the specified date range can be the date range corresponding to spring and autumn. Considering that the meteorological data will have different variation amplitudes in different seasons, for example, the weather is relatively sunny in spring and autumn, the precipitation is relatively less and uniform, and the atmospheric circulation is relatively stable, that is, the meteorological data in spring and autumn is relatively stable, and the influence of the meteorological data on the power generation of the photovoltaic power station is small. At this time, the first threshold value can be set to a smaller first value, so as to detect potential faults in time and improve the accuracy of fault detection. The climate is changeable in summer, and strong convective weather is frequent. There are many extreme weather phenomena such as high temperature, rainstorm, lightning, and typhoon, which have a greater impact on the photovoltaic power station. In winter, the climate is cold, and extreme weather such as snowstorm, freezing, and gale may occur, which also affects the power generation of the photovoltaic power station. Therefore, in summer and winter, the first threshold value can be set to a larger second value to avoid triggering an alarm due to some small fluctuations.

[0094] From the above, it can be seen that the embodiment sets different first threshold values according to different date ranges, which can better adapt to the operation characteristics of the photovoltaic power station in different time periods and ensure the reliable operation of the photovoltaic power station.

[0095] In an embodiment of the present application, the photovoltaic power station state prediction method further comprises:

[0096] in response to the output frequency of the first alarm information within the set time being greater than a third threshold value, output second alarm information, the second alarm information being used to instruct to update the fault prediction model and the power generation prediction model;

[0097] The fault prediction model is used to predict fault data of the photovoltaic power station based on the operation data of the target device, and the power generation prediction model is used to predict power generation of the photovoltaic power station based on the operation data of the target device and the first meteorological data.

[0098] In the embodiment, the performance of the target device may change as the photovoltaic power station operates, for example, if some devices in the photovoltaic power station are aged or fail after a period of operation, and the original fault prediction model does not take these changes into account, which may result in inaccurate prediction. Therefore, the model needs to be updated constantly to better capture changes in the target device and improve the accuracy of prediction.

[0099] Specifically, the update time of the model can be determined based on the output frequency of the first alarm information within the set time. If the output frequency of the first alarm information within the set time is greater than a third threshold value, it indicates that the predicted power generation is greater than the actual power generation frequently, and the fault prediction model cannot accurately predict the fault of the photovoltaic power station, or the power generation prediction model cannot accurately predict the power generation. At this time, the second alarm information can be output to prompt the operation and maintenance personnel to update the fault prediction model and the power generation prediction model in time.

[0100] Specifically, the fault prediction model can be retrained based on the latest historical operation data to realize the update of the fault prediction model, or the power generation prediction model can be retrained based on the latest historical operation data to realize the update of the power generation prediction model.

[0101] From the above, it can be concluded that the embodiment determines the update time of the fault prediction model and the power generation prediction model based on the monitoring of the first alarm information, which can make the fault prediction model and the power generation prediction model constantly adapt to new situations and improve the accuracy of prediction.

[0102] The photovoltaic power station state prediction method corresponding to the above embodiment, Figure 2 The structure block diagram of the photovoltaic power station state prediction device provided by an embodiment of the present application is shown. For ease of illustration, only parts related to the embodiments of the present application are shown. For reference Figure 2 The photovoltaic power station state prediction device 20 comprises a fault prediction module 21, a power generation prediction module 22 and a power generation correction module 23.

[0103] The fault prediction module 21 is used to predict fault data of the photovoltaic power station based on the operation data of the target device; the target device is a power generation device of the photovoltaic power station;

[0104] The power generation prediction module 22 is configured to predict the power generation of the photovoltaic power station based on the operation data of the target device and the first meteorological data, to obtain predicted power generation of the photovoltaic power station; the first meteorological data is predicted meteorological data of the photovoltaic power station.

[0105] The power generation correction module 23 is configured to correct the predicted power generation of the photovoltaic power station based on the fault data.

[0106] In an embodiment of the present application, the fault data includes fault types and corresponding severity levels, and the power generation correction module 23 is specifically configured to:

[0107] determine a first correction parameter based on the fault type;

[0108] adjust the first correction parameter based on the severity level corresponding to the fault type, to obtain a second correction parameter;

[0109] correct the predicted power generation of the photovoltaic power station based on the second correction parameter.

[0110] In an embodiment of the present application, the power generation correction module 23 is specifically further configured to:

[0111] if the fault data includes a plurality of fault types, weight and sum the second correction parameters corresponding to the plurality of fault types to obtain a third correction parameter;

[0112] correct the predicted power generation of the photovoltaic power station based on the third correction parameter.

[0113] In an embodiment of the present application, the power generation correction module 23 is specifically further configured to:

[0114] if the fault data includes a plurality of fault types, and there is a synergistic deterioration relationship between the first fault type and the second fault type, add the second correction parameters corresponding to the first fault type and the second fault type to obtain a fourth correction parameter;

[0115] weight and sum the second correction parameter corresponding to the third fault type and the fourth correction parameter to obtain a fifth correction parameter; the first fault type, the second fault type and the third fault type are different fault types;

[0116] correct the predicted power generation of the photovoltaic power station based on the fifth correction parameter.

[0117] In an embodiment of the present application, the fault prediction module 21 is specifically configured to:

[0118] determine a first difference based on the corrected predicted power generation and a first power generation; the first power generation is an actual power generation of the photovoltaic power station;

[0119] In response to a first difference greater than a first threshold and a similarity between the first meteorological data and the second meteorological data greater than a second threshold, a first alarm message is output; the second meteorological data is the actual meteorological data of the photovoltaic power station.

[0120] In one embodiment of the present invention, the fault prediction module 21 is further configured to:

[0121] In response to the current date falling within a specified date range, the first threshold is set to a first value;

[0122] In response to the current date exceeding the specified date range, the first threshold is set to the second value;

[0123] The first value is less than the second value.

[0124] In one embodiment of the present invention, the fault prediction module 21 is further configured to:

[0125] If the number of times the first alarm message is output within a set time exceeds the third threshold, a second alarm message is output. The second alarm message is used to indicate that the fault prediction model and the power generation prediction model should be updated.

[0126] The fault prediction model is used to predict the fault data of the photovoltaic power station based on the operating data of the target equipment, and the power generation prediction model is used to predict the power generation of the photovoltaic power station based on the operating data of the target equipment and the first meteorological data.

[0127] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of the present invention. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The functions of modules 21 to 23 are shown.

[0128] It should be appreciated that in the embodiments of the present application, the processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0129] The input device 302 can include a touchpad, a fingerprint collection sensor (for collecting fingerprint information and direction information of a fingerprint of a user), a microphone, etc., and the output device 303 can include a display (LCD, etc.), a speaker, etc.

[0130] The memory 304 can include a read-only memory and a random access memory, and provide instructions and data for the processor 301. A portion of the memory 304 can also include a non-volatile random access memory. For example, the memory 304 can also store device type information.

[0131] In specific implementations, the processor 301, the input device 302 and the output device 303 described in the embodiments of the present application can execute the implementation manners described in the first and second embodiments of the photovoltaic power station state prediction method provided by the embodiments of the present application, and can also execute the implementation manners of the electronic device described in the embodiments of the present application, which will not be described here.

[0132] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiment methods. The computer program can also instruct related hardware to complete the implementation. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0133] The computer readable storage medium can be an internal storage unit of the electronic device of any of the above-mentioned embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0134] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic device and the units described above can refer to the corresponding processes in the above-mentioned method embodiments, which will not be described here.

[0136] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other manners. For example, the embodiments of the apparatus described above are merely schematic; for example, the division of the units is only a logical function division; there can be another division manner for the actual implementation; for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, or the among different units, can be indirect couplings or communication connections through some interfaces, or can be in electrical, mechanical or other forms.

[0137] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0138] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0139] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto; any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for predicting the state of a photovoltaic power plant, characterized in that, include: Predicting fault data of photovoltaic power plants based on the operating data of target equipment; The target equipment is the power generation equipment of a photovoltaic power station; By collecting historical operating data of the target equipment, including voltage, current, power, temperature, operating frequency, and faults, a neural network model is trained to obtain a fault prediction model for the photovoltaic power station. During the operation of a photovoltaic power station, data acquisition equipment is set up to collect the operating data of the photovoltaic power station. The real-time collected operating data is input into the fault prediction model, and the fault prediction model outputs fault data. The power generation of the photovoltaic power station is predicted based on the operating data of the target equipment and the first meteorological data; the predicted power generation of the photovoltaic power station is obtained; the first meteorological data is the predicted meteorological data of the photovoltaic power station. By combining historical operating data and first meteorological data of photovoltaic power plants, a power generation prediction model is trained. During the operation of photovoltaic power plants, the first meteorological data of photovoltaic power plants is input into the power generation prediction model, and the power generation prediction model outputs the power generation of photovoltaic power plants in the future period. The predicted power generation of the photovoltaic power station is corrected based on the fault data. Wherein: the fault data includes fault type and corresponding severity level; the correction of the predicted power generation of the photovoltaic power station based on the fault data includes: Determine the first correction parameter based on the fault type; The first correction parameter is adjusted based on the severity level corresponding to the fault type to obtain the second correction parameter; The predicted power generation of the photovoltaic power station is corrected based on the second correction parameter; Wherein: the correction of the predicted power generation of the photovoltaic power station based on the second correction parameter includes: If the fault data includes multiple fault types, and there is a synergistic deterioration relationship between the first fault type and the second fault type, the second correction parameters corresponding to the first fault type and the second fault type are added together to obtain the fourth correction parameter. Specifically, when multiple fault types are predicted, fault types with synergistic deterioration relationships are first screened. For each fault type, other fault types with synergistic deterioration relationships with that fault type are pre-stored in the first storage space. During the actual operation of the photovoltaic power station, if multiple fault types are predicted, the multiple fault types are randomly sorted to obtain a fault type queue. Then, starting from the first fault type in the fault type queue, the combination of fault types with synergistic relationships is screened by comparing it with the fault types stored in the first storage space. The second correction parameter corresponding to the third fault type is weighted and summed with the fourth correction parameter to obtain the fifth correction parameter; the first fault type, the second fault type and the third fault type are different fault types; The predicted power generation of the photovoltaic power station is corrected based on the fifth correction parameter. Also includes: The first difference is determined based on the revised predicted power generation and the first power generation; the first power generation is the actual power generation of the photovoltaic power station. In response to the first difference being greater than a first threshold and the similarity between the first meteorological data and the second meteorological data being greater than a second threshold, a first alarm message is output; the second meteorological data is the actual meteorological data of the photovoltaic power station. Specifically, considering the impact of meteorological factors on power generation, when the first difference between the corrected predicted power generation and the first power generation is greater than the first threshold, the impact of meteorological factors on power generation is further determined. A first multidimensional vector is constructed based on the first meteorological data within a set time period, and a second multidimensional vector is constructed based on the second meteorological data within the same time period. The similarity between the first and second meteorological data is obtained by calculating the Euclidean distance between the first and second multidimensional vectors. The larger the Euclidean distance, the smaller the similarity between the first and second meteorological data, and the greater the impact of meteorological factors on power generation. Alternatively, the first meteorological data within a set time period can be treated as multiple variables to construct a first meteorological sequence. Then, a second meteorological sequence can be constructed based on the second meteorological data within the same time period. By calculating the correlation coefficient between the first and second meteorological sequences, the similarity between the first and second meteorological data can be obtained. The correlation coefficient ranges from -1 to 1. The closer the correlation coefficient is to 1, the more similar the two sets of first and second meteorological data are, and the smaller the impact of meteorological factors on power generation.

2. The photovoltaic power plant state prediction method as described in claim 1, characterized in that, Also includes: In response to the current date falling within a specified date range, the first threshold is set to a first value; In response to the current date exceeding the specified date range, the first threshold is set to the second value; The first value is less than the second value.

3. The photovoltaic power plant state prediction method as described in claim 1, characterized in that, Also includes: If the number of times the first alarm information is output within a set time exceeds a third threshold, a second alarm information is output. The second alarm information is used to indicate that the fault prediction model and the power generation prediction model should be updated. The fault prediction model is used to predict the fault data of the photovoltaic power station based on the operating data of the target equipment, and the power generation prediction model is used to predict the power generation of the photovoltaic power station based on the operating data of the target equipment and the first meteorological data.

4. A photovoltaic power plant status prediction device, characterized in that, The photovoltaic power plant state prediction device performs the steps of the method as described in any one of claims 1 to 3, including: The fault prediction module is used to predict fault data of the photovoltaic power station based on the operating data of the target equipment; the target equipment is the power generation equipment of the photovoltaic power station. The power generation prediction module is used to predict the power generation of the photovoltaic power station based on the operating data of the target equipment and the first meteorological data, and to obtain the predicted power generation of the photovoltaic power station; the first meteorological data is the predicted meteorological data of the photovoltaic power station. The power generation correction module is used to correct the predicted power generation of the photovoltaic power station based on the fault data.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 3.

Images