Photovoltaic module surface dust prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a surface dust prediction method and device for a photovoltaic module, electronic equipment and a storage medium, and the method and device are applied to the electronic equipment, and specifically comprise the steps: preparing modeling data of a to-be-predicted photovoltaic power generation field; constructing an irradiance-active power model based on the modeling data; calculating the current irradiance of the photovoltaic power generation field based on an irradiance-active power model to obtain the generating capacity deviation of the photovoltaic power generation field; and determining the surface dust state of the photovoltaic module of the photovoltaic power generation field based on the generating capacity deviation. According to the scheme, the dust covering state on the surface of the photovoltaic module can be accurately predicted based on the theoretical electric quantity of the photovoltaic power station, so that a user can formulate an optimal cleaning scheme based on the dust covering state, the power generation efficiency is not affected, and waste of manpower and material resources is avoided.

Description

Technical Field

[0001] The present application relates to the field of new energy technology, and more specifically, to a method, device, electronic device and storage medium for predicting surface dust of a photovoltaic module. Background Art

[0002] Photovoltaic power plants need to generate electricity based on sunlight. When photovoltaic modules are covered with dust, the blocking of sunlight will lead to a decrease in power generation capacity. Therefore, the photovoltaic modules need to be cleaned according to the blocking situation. At present, photovoltaic power generation generally performs regular cleaning of photovoltaic modules. Since the dust coverage of photovoltaic modules is not limited to time factors, but also affected by seasonal and climatic factors, the timing of each cleaning is not the optimal cleaning time. Sometimes the dust coverage is already very serious, and the photovoltaic modules cannot be cleaned because it is not yet time for cleaning, which seriously affects the power generation efficiency. Or the degree of pollution during cleaning is not enough to have a significant impact on the power generation efficiency of the photovoltaic modules, which will cause a waste of manpower and material resources. Therefore, the existing cleaning scheme for photovoltaic modules is not optimal, sometimes it will affect the power generation efficiency, and sometimes it will cause a waste of manpower and material resources. Summary of the invention

[0003] In view of this, the present application provides a surface dust prediction method, device, electronic device and storage medium for accurately predicting the dust coverage status on the surface of a photovoltaic component based on the theoretical power of the photovoltaic power station, so that the user can formulate the optimal cleaning plan based on the dust coverage status.

[0004] In order to achieve the above objectives, the proposed solution is as follows:

[0005] A method for predicting surface dust of a photovoltaic module is applied to electronic equipment. The method comprises the following steps:

[0006] Prepare modeling data of the photovoltaic power plant to be predicted;

[0007] constructing an irradiance-active power model based on the modeling data;

[0008] Calculating the current irradiance of the photovoltaic power plant based on the irradiance-active power model to obtain a power generation deviation of the photovoltaic power plant;

[0009] The surface dust status of the photovoltaic components of the photovoltaic power plant is determined based on the power generation deviation.

[0010] Optionally, the step of preparing modeling data of a photovoltaic power plant to be predicted comprises the following steps:

[0011] Acquiring the total active power of the photovoltaic power plant and correcting the total active power;

[0012] Obtain the modeling period, modeling season, modeling month and irradiance time series data, as well as the maximum and minimum ambient temperatures on the modeling day;

[0013] The irradiance time series data is screened based on the maximum ambient temperature and the minimum ambient temperature, and the modeling data is obtained based on the average daily irradiance value of the irradiance data.

[0014] Optionally, the irradiance-active power model is a linear regression model, a polynomial regression model, a K-nearest neighbor regression model or an SVR regression model.

[0015] Optionally, the step of calculating the current irradiance of the photovoltaic power plant based on the irradiance-active power model to obtain the power generation deviation of the photovoltaic power plant comprises the following steps:

[0016] Calculating the actual active power of the photovoltaic power plant on that day;

[0017] Calculating the current irradiance based on the irradiance-active power model to obtain the predicted active power for the day;

[0018] The power generation deviation is obtained by performing calculation based on the actual active power and the predicted active power.

[0019] Optionally, the determining the surface dust state of the photovoltaic components of the photovoltaic power plant based on the power generation deviation comprises the steps of:

[0020] Calculating theoretical power generation loss under dust shielding based on the power generation deviation;

[0021] Calculating a relative deviation rate and a changing trend of the relative deviation rate based on the theoretical power generation loss;

[0022] Calculating a warning level based on the relative deviation rate and the change trend;

[0023] A sliding average data is calculated based on the warning level, and the surface dust state includes the sliding average data.

[0024] Optionally, the following steps are also included:

[0025] The photovoltaic component is cleaned based on the surface dust status.

[0026] A surface dust prediction device for a photovoltaic module is applied to electronic equipment, and the surface dust prediction device comprises:

[0027] A data preparation module, configured to prepare modeling data of a photovoltaic power plant to be predicted;

[0028] A model building module, configured to build an irradiance-active power model based on the modeling data;

[0029] A first calculation module is configured to calculate the current irradiance of the photovoltaic power plant based on the irradiance-active power model to obtain a power generation deviation of the photovoltaic power plant;

[0030] The second calculation module is configured to determine the surface dust status of the photovoltaic components of the photovoltaic power plant based on the power generation deviation.

[0031] Optionally, also include:

[0032] The cleaning control module is configured to clean the photovoltaic component based on the surface dust status.

[0033] An electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0034] The memory is used to store computer programs or instructions;

[0035] The processor is used to execute the computer program or instruction so that the electronic device implements the surface dust prediction method as described above.

[0036] A computer-readable storage medium is applied to an electronic device, wherein the storage medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, so that the electronic device implements the surface dust prediction method as described above.

[0037] It can be seen from the above technical scheme that the present application discloses a method, device, electronic device and storage medium for predicting the surface dust of photovoltaic modules. The method and device are applied to electronic devices, specifically to prepare modeling data of the photovoltaic power field to be predicted; construct an irradiance-active power model based on the modeling data; calculate the current irradiance of the photovoltaic power field based on the irradiance-active power model to obtain the power generation deviation of the photovoltaic power field; determine the surface dust state of the photovoltaic modules of the photovoltaic power field based on the power generation deviation. Through this scheme, it is possible to accurately predict the dust coverage state on the surface of the photovoltaic module based on the theoretical power of the photovoltaic power station, so that the user can formulate the optimal cleaning plan based on the dust coverage state, which will neither affect the power generation efficiency nor cause waste of manpower and material resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A flow chart of a method for predicting surface dust of a photovoltaic module according to an embodiment of the present application;

[0040] Figure 2 A flow chart of another method for predicting surface dust of a photovoltaic module according to an embodiment of the present application;

[0041] Figure 3 A block diagram of a surface dust prediction device for a photovoltaic module according to an embodiment of the present application;

[0042] Figure 4 A block diagram of another surface dust prediction device for a photovoltaic module according to an embodiment of the present application;

[0043] Figure 5 A block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] This application uses an innovative power prediction and evaluation method based on theoretical electricity, taking into account factors such as photovoltaic business development trends, operation and maintenance concepts, data fullness and data quality. The research process first determines the analysis algorithm of this study based on multiple working conditions, selects appropriate time series data according to the algorithm principle, checks the time series data form, studies the time series data cleaning rules, and establishes a suitable irradiance-active power model. According to the model and irradiance time series data, the active power value of the station is predicted when dust obstruction is small or there is no obstruction, and dust warning levels and cleaning recommendations are given based on the prediction results. The implementation method greatly overcomes the bottleneck of the existing technology, accurately warns of the "dust obstruction" problem that affects the revenue of the power station, realizes timely detection of dust accumulation on equipment, and timely warns of inefficient equipment operation, so that the optimal cleaning plan can be formulated. Based on this, the following specific embodiments are specially proposed.

[0046] Figure 1 This is a flow chart of a method for predicting surface dust of a photovoltaic module according to an embodiment of the present application.

[0047] like Figure 1 As shown, the surface dust prediction method provided in this embodiment is applied to an electronic device, and is used to predict the dust state on the surface of a photovoltaic module based on the theoretical power of a photovoltaic power generation field. The electronic device can be understood as a computer, server or cloud platform with data computing and information processing capabilities. The surface dust prediction method includes the following steps:

[0048] S1. Prepare modeling data for photovoltaic power plants.

[0049] The photovoltaic power plant here refers to a photovoltaic power station whose dust status of photovoltaic modules needs to be predicted, which specifically includes the following steps:

[0050] Firstly, the total active power of the photovoltaic power plant is obtained, and the obtained total active power is corrected.

[0051] Then, obtain the modeling cycle, modeling season, modeling month and irradiance time series data, and also obtain the maximum ambient temperature and the minimum ambient temperature on the day of modeling. The modeling cycle here refers to the period or frequency of constructing the irradiance-active power model in this application. The modeling season and modeling month refer to the season and month for constructing the irradiance-active power model. The irradiance time series data here refers to the irradiance data of the photovoltaic power plant in time sequence on the day of modeling.

[0052] Finally, the above irradiance time series data is screened based on the maximum ambient temperature and the minimum ambient temperature. Specifically, the daily irradiance mean of the above irradiance time series data is calculated, and the irradiance time series data with a daily irradiance mean greater than 30% of the maximum daily irradiance mean in the model data is screened as valid data; if the number of days of valid data is greater than a set threshold, the valid data is used as the modeling data. The threshold can be obtained based on empirical data.

[0053] S2. Construct an irradiance-active power model based on the modeling data.

[0054] After the modeling data is obtained, a model is constructed based on the modeling data to obtain an active power that can predict the photovoltaic power generation field. The appropriate algorithm is selected to establish the irradiance-active power model of the photovoltaic field station.

[0055] The selection of the above-mentioned irradiance-active power model can be considered from three aspects. First, consider the model accuracy. Model accuracy is the most important factor in evaluating the model effect. If the model accuracy is low, even if other performance indicators are very good, it is difficult to use it for prediction in actual production; then consider the overfitting and underfitting risks of the model. Even if parameters that try to balance the risks of overfitting and underfitting have been selected during the parameter selection process, horizontal comparisons between different types of models require the selection of a better modeling method based on the characteristics of the model; finally, the modeling and prediction speed of the model and the resource usage during the calculation process must also be considered.

[0056] The irradiance-active power model should be a linear relationship, but in the actual production process, it may be a nonlinear relationship due to the interference of various external factors. The independent variable of the model is irradiance, the dependent variable is active power, the number of features is small, and it is not a binary classification scenario. Therefore, the modeling methods that can be used for this topic mainly include linear regression, polynomial regression, K-nearest neighbor regression, and SVR regression.

[0057] According to the characteristics of the working conditions, by evaluating the advantages and disadvantages of various technical means, it is determined that this project uses polynomial regression technology to establish a model for the relationship between station irradiance and active power. Polynomial regression adds higher powers of independent variables (such as square terms or cubic terms), which is equivalent to increasing the degree of freedom of the model to capture nonlinear changes in the data. The polynomial regression model can be expressed as:

[0058]

[0059] The most important parameter for training a polynomial regression model is the highest power. The presence of higher-order terms increases the complexity of the model. As the complexity of the model increases, the capacity of the model and its ability to fit data increase, which can further reduce the training error.

[0060] S3. Calculate the power generation deviation of the photovoltaic power plant based on the irradiance-active power model.

[0061] The so-called power generation deviation refers to the deviation value or deviation rate between the theoretical power generation and the actual power generation of the photovoltaic power plant. Specifically, the current irradiance of the photovoltaic power plant is calculated based on the irradiance-active power model, and the difference between the obtained theoretical power generation and the actual grid-connected power of the power plant is calculated to obtain the deviation value or deviation rate.

[0062] First, the actual active power of the photovoltaic power plant on that day is calculated.

[0063] The actual active power can be obtained through the actual grid-connected power of the photovoltaic power plant, which is an actual value.

[0064] Then, the current irradiance is calculated based on the irradiance-active power model to obtain the theoretical active power of the photovoltaic power field, specifically the theoretical active power if the photovoltaic components of the photovoltaic power field are not covered by dust or dirt, or the actual active power when the corresponding photovoltaic components are in the optimal state after installation.

[0065] Finally, the power generation deviation rate or power generation deviation is calculated based on the actual active power and the predicted active power.

[0066] In this application, the predicted active power = model slope * actual total irradiance + intercept, the actual daily power generation is calculated, the predicted daily power generation is calculated, the power generation deviation = actual power generation - predicted power generation, the power generation deviation rate = power generation deviation / predicted power generation. If the power generation deviation exceeds the threshold, the calculation will no longer continue.

[0067] Merge multiple data. If the number of merged data exceeds the threshold, start the subsequent calculation. Get the latest 180 valid data and sort them. Select the 10% of the data from the sorted data. The maximum deviation rate = the median of this part of the data. Then calculate the power generation deviation rate and the theoretical power generation loss. Theoretical power generation loss = predicted power generation * (1 + maximum deviation rate) - actual power generation.

[0068] S4. Determine the surface dust status of the photovoltaic module based on the power generation deviation rate.

[0069] Firstly, the theoretical power generation loss of PV modules under dust shading is calculated based on the power generation deviation.

[0070] Merge multiple data. If the number of merged data exceeds the threshold, start the subsequent calculation. Get the latest 180 valid data and sort them. Select the 10% of the data from the sorted data. The maximum deviation rate = the median of this part of the data. Then calculate the power generation deviation rate and the theoretical power generation loss. Theoretical power generation loss = predicted power generation * (1 + maximum deviation rate) - actual power generation.

[0071] Then, the theoretical power generation loss is calculated to calculate the relative deviation rate and its changing trend.

[0072] Get the date list of the merged data. When the time span of the merged data is greater than the trend judgment window and the number of merged data is greater than 50% of the trend judgment window, perform subsequent trend judgment. Specifically, get the latest 30 data, perform sliding average on the deviation rate, relative deviation rate = 1-deviation rate after sliding average, and use MK test to judge the change trend of relative deviation rate.

[0073] Then, the warning level is calculated based on the relative deviation rate and change trend.

[0074] Filter out the trend mark and relative deviation rate of the day. If there is cleaning data entered by the user, keep the most recent record. If the day is greater than or equal to 15 days from the last cleaning completion date, start calculating the warning level. If there is no cleaning data entered by the user, calculate the warning level directly.

[0075] Finally, the sliding average data is calculated based on the warning level, that is, the surface dust status of the PV module.

[0076] Specifically, it calculates the 5-day sliding average data of the warning level. Combine the warning level data of the day and the history; start the subsequent calculation when the time span of the combined data is greater than the sliding window of the warning level; obtain the latest 30 data for smoothing calculation; calculate the sliding average data of the warning level, and obtain the sliding average of the warning level of the day.

[0077] It can be seen from the above technical scheme that this embodiment provides a method for predicting the surface dust of photovoltaic components. The method is applied to electronic devices, specifically preparing modeling data of the photovoltaic power field to be predicted; constructing an irradiance-active power model based on the modeling data; calculating the current irradiance of the photovoltaic power field based on the irradiance-active power model to obtain the power generation deviation of the photovoltaic power field; and determining the surface dust state of the photovoltaic components of the photovoltaic power field based on the power generation deviation. This scheme can accurately predict the dust coverage state on the surface of the photovoltaic components based on the theoretical power of the photovoltaic power station, so that the user can formulate the optimal cleaning plan based on the dust coverage state, which will neither affect the power generation efficiency nor cause waste of manpower and material resources.

[0078] In a specific implementation of the present application, the following steps are also included: Figure 2 shown.

[0079] S5. Clean the photovoltaic modules based on the dust status on the surface.

[0080] That is, the cleaning equipment is controlled to clean the PV modules based on the surface dust status. If the sliding average of the warning level on the day is greater than the threshold, it is determined whether the PV modules have been cleaned in the previous 10 days. If not, the cleaning equipment is controlled to perform the cleaning operation, otherwise, no cleaning is performed.

[0081] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0082] Although operations are depicted in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in a sequential order.Multitasking and parallel processing may be advantageous under certain circumstances.

[0083] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0084] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate 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 a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.

[0085] Figure 3 This is a block diagram of a surface dust prediction device for a photovoltaic module according to an embodiment of the present application.

[0086] like Figure 3As shown, the surface dust prediction device provided in this embodiment is applied to an electronic device, and is used to predict the dust state on the surface of a photovoltaic module based on the theoretical power of a photovoltaic power field. The electronic device can be understood as a computer, server or cloud platform with data computing and information processing capabilities. The surface dust prediction device includes a data preparation module 10, a model building module 20, a first computing module 30 and a second computing module 40.

[0087] The data preparation module is used to prepare the modeling data of the photovoltaic power plant.

[0088] The photovoltaic power plant here refers to a photovoltaic power station whose dust status of photovoltaic modules needs to be predicted, which specifically includes the following steps:

[0089] Firstly, the total active power of the photovoltaic power plant is obtained, and the obtained total active power is corrected.

[0090] Then, obtain the modeling cycle, modeling season, modeling month and irradiance time series data, and also obtain the maximum ambient temperature and the minimum ambient temperature on the day of modeling. The modeling cycle here refers to the period or frequency of constructing the irradiance-active power model in this application. The modeling season and modeling month refer to the season and month for constructing the irradiance-active power model. The irradiance time series data here refers to the irradiance data of the photovoltaic power plant in time sequence on the day of modeling.

[0091] Finally, the above irradiance time series data is screened based on the maximum ambient temperature and the minimum ambient temperature. Specifically, the daily irradiance mean of the above irradiance time series data is calculated, and the irradiance time series data with a daily irradiance mean greater than 30% of the maximum daily irradiance mean in the model data is screened as valid data; if the number of days of valid data is greater than a set threshold, the valid data is used as the modeling data. The threshold can be obtained based on empirical data.

[0092] The model building module is used to build an irradiance-active power model based on modeling data.

[0093] After the modeling data is obtained, a model is constructed based on the modeling data to obtain an active power that can predict the photovoltaic power generation field. The appropriate algorithm is selected to establish the irradiance-active power model of the photovoltaic field station.

[0094] The selection of the above-mentioned irradiance-active power model can be considered from three aspects. First, consider the model accuracy. Model accuracy is the most important factor in evaluating the model effect. If the model accuracy is low, even if other performance indicators are very good, it is difficult to use it for prediction in actual production; then consider the overfitting and underfitting risks of the model. Even if parameters that try to balance the risks of overfitting and underfitting have been selected during the parameter selection process, horizontal comparisons between different types of models require the selection of a better modeling method based on the characteristics of the model; finally, the modeling and prediction speed of the model and the resource usage during the calculation process must also be considered.

[0095] The irradiance-active power model should be a linear relationship, but in the actual production process, it may be a nonlinear relationship due to the interference of various external factors. The independent variable of the model is irradiance, the dependent variable is active power, the number of features is small, and it is not a binary classification scenario. Therefore, the modeling methods that can be used for this topic mainly include linear regression, polynomial regression, K-nearest neighbor regression, and SVR regression.

[0096] According to the characteristics of the working conditions, by evaluating the advantages and disadvantages of various technical means, it is determined that this project uses polynomial regression technology to establish a model for the relationship between station irradiance and active power. Polynomial regression adds higher powers of independent variables (such as square terms or cubic terms), which is equivalent to increasing the degree of freedom of the model to capture nonlinear changes in the data. The polynomial regression model can be expressed as:

[0097]

[0098] The most important parameter for training a polynomial regression model is the highest power. The presence of higher-order terms increases the complexity of the model. As the complexity of the model increases, the capacity of the model and its ability to fit data increase, which can further reduce the training error.

[0099] The first calculation module is used to calculate the power generation deviation of the photovoltaic power plant based on the irradiance-active power model.

[0100] The so-called power generation deviation refers to the deviation value or deviation rate between the theoretical power generation and the actual power generation of the photovoltaic power plant. Specifically, the current irradiance of the photovoltaic power plant is calculated based on the irradiance-active power model, and the difference between the obtained theoretical power generation and the actual grid-connected power of the power plant is calculated to obtain the deviation value or deviation rate.

[0101] First, the actual active power of the photovoltaic power plant on that day is calculated.

[0102] The actual active power can be obtained through the actual grid-connected power of the photovoltaic power plant, which is an actual value.

[0103] Then, the current irradiance is calculated based on the irradiance-active power model to obtain the theoretical active power of the photovoltaic power field, specifically the theoretical active power if the photovoltaic components of the photovoltaic power field are not covered by dust or dirt, or the actual active power when the corresponding photovoltaic components are in the optimal state after installation.

[0104] Finally, the power generation deviation rate or power generation deviation is calculated based on the actual active power and the predicted active power.

[0105] In this application, the predicted active power = model slope * actual total irradiance + intercept, the actual daily power generation is calculated, the predicted daily power generation is calculated, the power generation deviation = actual power generation - predicted power generation, the power generation deviation rate = power generation deviation / predicted power generation. If the power generation deviation exceeds the threshold, the calculation will no longer continue.

[0106] Merge multiple data. If the number of merged data exceeds the threshold, start the subsequent calculation. Get the latest 180 valid data and sort them. Select the 10% of the data from the sorted data. The maximum deviation rate = the median of this part of the data. Then calculate the power generation deviation rate and the theoretical power generation loss. Theoretical power generation loss = predicted power generation * (1 + maximum deviation rate) - actual power generation.

[0107] The second calculation module is used to determine the surface dust state of the photovoltaic component based on the power generation deviation rate.

[0108] Firstly, the theoretical power generation loss of PV modules under dust shading is calculated based on the power generation deviation.

[0109] Merge multiple data. If the number of merged data exceeds the threshold, start the subsequent calculation. Get the latest 180 valid data and sort them. Select the 10% of the data from the sorted data. The maximum deviation rate = the median of this part of the data. Then calculate the power generation deviation rate and the theoretical power generation loss. Theoretical power generation loss = predicted power generation * (1 + maximum deviation rate) - actual power generation.

[0110] Then, the theoretical power generation loss is calculated to calculate the relative deviation rate and its changing trend.

[0111] Get the date list of the merged data. When the time span of the merged data is greater than the trend judgment window and the number of merged data is greater than 50% of the trend judgment window, perform subsequent trend judgment. Specifically, get the latest 30 data, perform sliding average on the deviation rate, relative deviation rate = 1-deviation rate after sliding average, and use MK test to judge the change trend of relative deviation rate.

[0112] Then, the warning level is calculated based on the relative deviation rate and change trend.

[0113] Filter out the trend mark and relative deviation rate of the day. If there is cleaning data entered by the user, keep the most recent record. If the day is greater than or equal to 15 days from the last cleaning completion date, start calculating the warning level. If there is no cleaning data entered by the user, calculate the warning level directly.

[0114] Finally, the sliding average data is calculated based on the warning level, that is, the surface dust status of the PV module.

[0115] Specifically, it calculates the 5-day sliding average data of the warning level. Combine the warning level data of the day and the history; start the subsequent calculation when the time span of the combined data is greater than the sliding window of the warning level; obtain the latest 30 data for smoothing calculation; calculate the sliding average data of the warning level, and obtain the sliding average of the warning level of the day.

[0116] It can be seen from the above technical scheme that this embodiment provides a device for predicting the surface dust of photovoltaic modules, which is applied to electronic devices, specifically preparing modeling data of the photovoltaic power field to be predicted; constructing an irradiance-active power model based on the modeling data; calculating the current irradiance of the photovoltaic power field based on the irradiance-active power model to obtain the power generation deviation of the photovoltaic power field; and determining the surface dust state of the photovoltaic modules of the photovoltaic power field based on the power generation deviation. This scheme can accurately predict the dust coverage state on the surface of the photovoltaic module based on the theoretical power of the photovoltaic power station, so that the user can formulate the optimal cleaning plan based on the dust coverage state, which will neither affect the power generation efficiency nor cause waste of manpower and material resources.

[0117] In a specific embodiment of the present application, a cleaning control module 50 is also included, such as Figure 4 shown.

[0118] The cleaning control module is used to clean the photovoltaic components based on the surface dust status.

[0119] That is, the cleaning equipment is controlled to clean the PV modules based on the surface dust status. If the sliding average of the warning level on the day is greater than the threshold, it is determined whether the PV modules have been cleaned in the previous 10 days. If not, the cleaning equipment is controlled to perform the cleaning operation, otherwise, no cleaning is performed.

[0120] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0121] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0122] Figure 5 A block diagram of an electronic device according to an embodiment of the present application.

[0123] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0124] The electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 502 or a program loaded from an input device 506 into a random access memory RAM 503. Various programs and data required for the operation of the electronic device are also stored in the RAM. The processing device, ROM, and RAM are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0125] Typically, the following devices may be connected to the I / O interface: input devices including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication device 509 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0126] The present application also provides a computer-readable storage medium embodiment.

[0127] The computer-readable storage medium is applied to an electronic device and carries one or more computer programs. When the one or more computer programs are executed by the electronic device, the electronic device prepares the modeling data of the photovoltaic power field to be predicted; constructs an irradiance-active power model based on the modeling data; calculates the current irradiance of the photovoltaic power field based on the irradiance-active power model to obtain the power generation deviation of the photovoltaic power field; and determines the surface dust state of the photovoltaic components of the photovoltaic power field based on the power generation deviation. This solution can accurately predict the dust coverage state on the surface of the photovoltaic components based on the theoretical power of the photovoltaic power station, so that the user can formulate the optimal cleaning plan based on the dust coverage state, which will neither affect the power generation efficiency nor cause waste of manpower and material resources.

[0128] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0129] In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0130] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0131] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0132] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0133] The technical solution provided by the present invention is introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for predicting surface dust on a photovoltaic module, applied to electronic equipment, characterized in that: The surface dust prediction method comprises the steps of: Prepare modeling data of the photovoltaic power plant to be predicted; constructing an irradiance-active power model based on the modeling data; Calculating the current irradiance of the photovoltaic power plant based on the irradiance-active power model to obtain a power generation deviation of the photovoltaic power plant; The surface dust status of the photovoltaic components of the photovoltaic power plant is determined based on the power generation deviation.

2. The surface dust prediction method according to claim 1, characterized in that: The step of preparing the modeling data of the photovoltaic power plant to be predicted comprises the following steps: Acquiring the total active power of the photovoltaic power plant and correcting the total active power; Obtain the modeling period, modeling season, modeling month and irradiance time series data, as well as the maximum and minimum ambient temperatures on the modeling day; The irradiance time series data is screened based on the maximum ambient temperature and the minimum ambient temperature, and the modeling data is obtained based on the average daily irradiance value of the irradiance data.

3. The surface dust prediction method according to claim 1, characterized in that: The irradiance-active power model is a linear regression model, a polynomial regression model, a K-nearest neighbor regression model or an SVR regression model.

4. The surface dust prediction method according to claim 1, characterized in that: The step of calculating the current irradiance of the photovoltaic power plant based on the irradiance-active power model to obtain the power generation deviation of the photovoltaic power plant comprises the following steps: Calculating the actual active power of the photovoltaic power plant on that day; Calculating the current irradiance based on the irradiance-active power model to obtain the predicted active power for the day; The power generation deviation is obtained by performing calculation based on the actual active power and the predicted active power.

5. The surface dust prediction method according to claim 1, characterized in that: The method of determining the surface dust state of the photovoltaic components of the photovoltaic power generation field based on the power generation deviation comprises the steps of: Calculating theoretical power generation loss under dust shielding based on the power generation deviation; Calculating a relative deviation rate and a changing trend of the relative deviation rate based on the theoretical power generation loss; Calculating a warning level based on the relative deviation rate and the change trend; A sliding average data is calculated based on the warning level, and the surface dust state includes the sliding average data.

6. The surface dust prediction method according to any one of claims 1 to 5, characterized in that: Also includes the steps: The photovoltaic component is cleaned based on the surface dust status.

7. A surface dust prediction device for a photovoltaic module, applied to electronic equipment, characterized in that: The surface dust prediction device comprises: A data preparation module, configured to prepare modeling data of a photovoltaic power plant to be predicted; A model building module, configured to build an irradiance-active power model based on the modeling data; A first calculation module is configured to calculate the current irradiance of the photovoltaic power plant based on the irradiance-active power model to obtain a power generation deviation of the photovoltaic power plant; The second calculation module is configured to determine the surface dust status of the photovoltaic components of the photovoltaic power plant based on the power generation deviation.

8. The surface dust prediction device according to claim 7, characterized in that: Also includes: The cleaning control module is configured to clean the photovoltaic component based on the surface dust status.

9. An electronic device, characterized in that: The electronic device comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs or instructions; The processor is used to execute the computer program or instruction so that the electronic device implements the surface dust prediction method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, applied to an electronic device, characterized in that: The storage medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, so that the electronic device implements the surface dust prediction method as described in any one of claims 1 to 6.

Images