Theoretical power generation amount determination method and device, server, and photovoltaic power generation system

Abstract

The application relates to a theoretical power generation amount determination method and device, a server and a photovoltaic power generation system. The power generation amount determination method is applied to a photovoltaic power generation system, the photovoltaic power generation system comprises a standard group string and a target group string corresponding to the standard group string in one-to-one mode, the standard group string is a maintained group string, and the target group string is a non-maintained group string. The method comprises the following steps: acquiring first power data of the standard group string in a current period; inputting the first power data into a preset power relationship model, so that the power relationship model outputs corresponding second power data of the target group string in the current period according to the first power data, wherein the mathematical form of the power relationship model is a monomial polynomial regression analysis model; and determining the power generation amount of the corresponding target group string in the current period according to the second power data. The power generation amount of the group string can be accurately determined at low cost.

Description

Technical Field

[0001] This application relates to the field of photovoltaic power generation technology, and in particular to a method and apparatus for determining theoretical power generation, a server, and a photovoltaic power generation system. Background Technology

[0002] As the global energy structure accelerates its transition to a low-carbon model, photovoltaic (PV) power generation has become a core component of the new energy system due to its clean and renewable characteristics. Accurately calculating the theoretical power generation of a PV power plant is crucial for evaluating its economic viability, improving operational efficiency, and reducing maintenance costs. Theoretically, PV power generation depends on multiple factors, including solar irradiance, module efficiency, and system losses. However, in practical applications, dynamic variables such as weather fluctuations, module degradation, and shading often lead to significant discrepancies between theoretical and actual values. Currently, various methods for estimating the power generation of PV systems have been proposed, but they all have certain limitations.

[0003] In some related technologies, the output power of a photovoltaic (PV) power generation system is calculated by establishing solar radiation models and PV system models, thereby determining the power generation. These methods mostly require environmental parameters and system design parameters. In practical applications, the cost of acquiring these parameters is high, and the timeliness of the parameters is difficult to guarantee. In other related technologies, artificial intelligence-based methods are used to establish PV power generation prediction and evaluation models. These models generally require acquiring meteorological parameters such as irradiance, temperature, and wind direction, as well as long-term historical operating data of the system for parameter training. Acquiring meteorological parameters requires the system itself to purchase environmental monitoring instruments or to obtain meteorological data from third-party meteorological agencies. However, PV power generation systems occupy large areas, especially in mountainous regions where meteorological parameters vary significantly from region to region. To improve accuracy, environmental monitoring instruments need to be set up in a gridded pattern, which increases the system's operational costs.

[0004] Furthermore, most of the aforementioned methods in related technologies focus on the overall output assessment of the system, making it difficult to calculate the theoretical power generation at the equipment level (such as strings, inverters, and transformer substations), which is detrimental to the refined operation and maintenance management of the system. Currently, against the backdrop of photovoltaic power generation gradually moving towards grid parity and low-cost grid connection, the field of photovoltaic power generation system operation and maintenance has formed a technological development trend of refinement, reduced manpower, unmanned operation, and low cost. Accurate assessment of the theoretical power generation of photovoltaic power generation systems is a key prerequisite for supporting the upgrading of system operation and maintenance models and improving efficiency. Summary of the Invention

[0005] Therefore, it is necessary to provide a method and device, server, and photovoltaic power generation system for determining theoretical power generation, which can accurately determine the theoretical power generation of the strings at low cost, in order to address the above-mentioned technical problems.

[0006] In a first aspect, this application provides a method for determining theoretical power generation, applied to a photovoltaic power generation system. The photovoltaic power generation system includes standard strings and target strings corresponding one-to-one with the standard strings. The standard strings are maintained strings, and the target strings are unmaintained strings. The method includes:

[0007] Obtain the first power data of the standard string in the current time period;

[0008] The first power data is input into a preset power relationship model so that the power relationship model outputs the second power data of the target string in the current time period based on the first power data, wherein the mathematical form of the power relationship model is a univariate polynomial regression analysis model.

[0009] The power generation of the corresponding target string in the current time period is determined based on the second power data.

[0010] In one embodiment, the method further includes:

[0011] Establish an initial model;

[0012] Acquire multiple third power data of the standard string and multiple fourth power data of the corresponding target string within the target historical time period;

[0013] Based on the initial model, the plurality of third power data, and the plurality of fourth power data, the model coefficients of the power relationship model are determined.

[0014] In one embodiment, determining the model coefficients of the power relationship model based on the initial model, the plurality of third power data, and the plurality of fourth power data includes:

[0015] Each input of the third power data and the fourth power data into the initial model yields an error.

[0016] The model coefficients that minimize the sum of squared errors will be used as the model coefficients of the power relationship model.

[0017] In one embodiment, the mathematical form of the initial model is:

[0018]

[0019] The matrix of model coefficients is as follows:

[0020]

[0021] in, The expression represents the error, and m represents the degree of the polynomial. Represents the model coefficients, The matrix representing the coefficients of the model. This refers to the third power data. This represents a matrix composed of the multiple third power data, where the superscript "T" indicates the transpose of the matrix and the superscript "-1" indicates the inverse of the matrix. This refers to the fourth power data. This represents a matrix composed of the plurality of fourth power data.

[0022] In one embodiment, obtaining the first power data of the standard string in the current time period includes:

[0023] Obtain the first current data and the first voltage data of the standard string during the current time period;

[0024] The first power data is determined by multiplying the first current data and the first voltage data.

[0025] In one embodiment, determining the power generation of the corresponding target string in the current time period based on the second power data includes:

[0026] The power generation is determined by integrating the second power data over time during the current period.

[0027] Based on the same inventive concept, in a second aspect, this application also provides a theoretical power generation determination device, applied to a photovoltaic power generation system, wherein the photovoltaic power generation system includes standard strings and target strings corresponding one-to-one with the standard strings, the standard strings being maintained strings and the target strings being unmaintained strings, and the device includes:

[0028] The data acquisition module is used to acquire the first power data of the standard string in the current time period;

[0029] The power calculation module is used to input the first power data into a preset power relationship model, so that the power relationship model outputs the second power data of the target string in the current time period according to the first power data, wherein the mathematical form of the power relationship model is a univariate polynomial regression analysis model.

[0030] The power calculation module is used to determine the power generation of the corresponding target string in the current time period based on the second power data.

[0031] Based on the same inventive concept, in a third aspect, this application also provides a server, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0032] Based on the same inventive concept, in a fourth aspect, this application also provides a photovoltaic power generation system, the system comprising:

[0033] A standard string and a target string that corresponds one-to-one with the standard string; the standard string is a maintained string, and the target string is an unmaintained string;

[0034] The server is pre-deployed with a power relationship model, the mathematical form of which is a univariate polynomial regression analysis model.

[0035] The server is configured to acquire the first power data of the standard string in the current time period, and input the first power data into a preset power relationship model, so that the power relationship model outputs the second power data of the target string in the current time period based on the first power data, and determines the power generation of the target string in the current time period based on the second power data.

[0036] In one embodiment, the system further includes:

[0037] Inverter, each inverter is connected to multiple photovoltaic strings, and each photovoltaic string is a target string;

[0038] The server is pre-deployed with multiple power relationship models that correspond one-to-one with the target string;

[0039] The server is used to determine the power generation of the corresponding target string based on each of the power relationship models, and to accumulate the power generation of the target strings connected to the same inverter to obtain the power generation of the inverter.

[0040] The aforementioned method and apparatus for determining theoretical power generation, along with a server and a photovoltaic power generation system, include a standard string and target strings corresponding to each standard string. The standard string can be one that requires regular cleaning and inspection by personnel based on local environmental conditions to ensure its power generation is affected only by irradiance and its own performance. The target string, unlike the standard string, does not require regular cleaning and inspection and operates naturally; its other equipment and environmental parameters can be the same as or different from the standard string. Based on this, by acquiring the first power data of the standard string in the current time period, and then inputting this first power data into a preset power relationship model, the power relationship model outputs the second power data of the corresponding target string in the current time period. Finally, the power generation of the corresponding target string in the current time period can be determined based on the second power data.

[0041] In this embodiment, the first power data of the standard string can be calculated based on the current and voltage data of the standard string. The current and voltage data of the string can be directly obtained from existing monitoring equipment in the photovoltaic power generation system. Therefore, there is no need to add additional data acquisition equipment or acquire additional environmental, meteorological, or equipment parameters, thus reducing costs and avoiding the impact of deviations between actual construction and design parameters. Based on the power relationship model between the standard string and the corresponding target string, only periodic maintenance of the standard string is needed to ensure the accurate determination of the power generation of the corresponding target string. Furthermore, the mathematical form of the power relationship model is a univariate polynomial regression analysis model, which has few parameters, low complexity, strong anti-interference capabilities, high tolerance to noise data, simple training, simple deployment, minimal resource consumption during operation, and is easy to implement on edge devices. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating a method for determining theoretical power generation in one embodiment;

[0044] Figure 2 This is a flowchart illustrating step S101 in one embodiment;

[0045] Figure 3 This is a flowchart illustrating the method for determining theoretical power generation in one embodiment.

[0046] Figure 4 This is a flowchart illustrating step S303 in one embodiment;

[0047] Figure 5 This is one of the structural block diagrams of the theoretical power generation determination device in one embodiment;

[0048] Figure 6 This is the second structural block diagram of the device for determining theoretical power generation in one embodiment. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0051] The theoretical power generation determination method provided in this application can be applied to photovoltaic power generation systems. A photovoltaic power generation system may include at least standard strings and target strings corresponding one-to-one with the standard strings. Both standard strings and target strings are photovoltaic strings. As an example, a photovoltaic string includes multiple photovoltaic modules, and each photovoltaic module includes multiple photovoltaic cells. A photovoltaic module can be understood as a photovoltaic panel. A standard string can be one that requires regular cleaning and inspection by personnel based on local environmental conditions to ensure that its power generation is affected only by irradiance and its own performance. A target string can be one that, compared to a standard string, does not require regular cleaning and inspection by personnel and operates naturally; its other equipment parameters and environmental parameters may be the same as or different from those of the standard string. In addition, photovoltaic power generation systems are typically equipped with relevant monitoring equipment to collect current and voltage data from the photovoltaic strings.

[0052] It is understood that in the embodiments of this application, the power generation determined by the theoretical power generation determination method and device is the theoretical power generation, that is, the amount of electricity that should theoretically be generated.

[0053] In one exemplary embodiment, reference is made to Figure 1 A method for determining theoretical power generation is provided, which may include the following steps S101 to S103.

[0054] S101, Obtain the first power data of the standard string in the current time period.

[0055] The current time period can be the target time period. The power data of the photovoltaic string can be calculated based on the current and voltage data of the photovoltaic string. The current and voltage data of the photovoltaic string can be obtained from the existing monitoring equipment in the photovoltaic power generation system. In other words, the first power data of the standard string in the current time period can be calculated based on the current and voltage data of the standard string in the current time period. The current and voltage data of the standard string can be obtained from the existing monitoring equipment in the photovoltaic power generation system, so there is no need to add other related data acquisition equipment, thereby reducing costs and avoiding the impact of deviations between actual construction and design parameters.

[0056] S102, the first power data is input into the preset power relationship model so that the power relationship model outputs the second power data of the target string in the current time period according to the first power data, wherein the mathematical form of the power relationship model is a univariate polynomial regression analysis model.

[0057] As an example, a photovoltaic power generation system may include at least one standard string and at least one target string. There is a one-to-one correspondence between the standard string and the target string. A power relationship model is established between a standard string and its corresponding target string. For example, standard string 1 corresponds to target string 1, and a power relationship model 1 is established between them. Standard string 1 requires regular cleaning and inspection by personnel based on local environmental conditions to ensure that its power generation is affected only by irradiance and its own performance. Target string 1, compared to standard string 1, does not require regular cleaning and inspection by personnel and operates naturally; its other equipment parameters and environmental parameters may be the same as or different from those of standard string 1. As an example, standard string 2 and target string 2 correspond to each other, and a power relationship model 2 is established between standard string 2 and target string 2. Standard string 2 requires staff to clean and inspect it regularly according to local environmental conditions to ensure that its power generation is only affected by irradiance and its own performance. Target string 2, compared with standard string 2, does not require staff to clean and inspect it regularly and operates naturally. Other equipment parameters and environmental parameters can be the same as or different from those of standard string 2.

[0058] The first power data of a standard string during the current time period is input into a preset power relationship model, so that the power relationship model outputs the second power data of the corresponding target string during the current time period based on the first power data. For example, the first power data of standard string 1 during the daytime of the current day is input into preset power relationship model 1, so that power relationship model 1 outputs the second power data of target string 1 during the daytime of the current day based on the first power data. Similarly, the first power data of standard string 2 during the daytime of the current day is input into preset power relationship model 2, so that power relationship model 2 outputs the second power data of target string 2 during the daytime of the current day based on the first power data.

[0059] In this embodiment, the mathematical form of the power relationship model is a univariate polynomial regression analysis model, which has few parameters, low complexity, strong anti-interference ability, high tolerance to noisy data, simple training, simple deployment, minimal resource consumption during operation, and is easy to implement on edge devices.

[0060] S103, determine the power generation of the corresponding target string in the current time period based on the second power data.

[0061] The power generation can be determined by integrating the power data. For example, the power generation of the target string in the current time period can be determined by integrating the second power data of the target string over the current time period. Similarly, the power generation of target string 1 during the day can be determined by integrating the second power data of target string 2 during the day.

[0062] The solution in this application embodiment obtains the first power data of the standard string in the current time period, then inputs the first power data into a preset power relationship model, so that the power relationship model outputs the second power data of the corresponding target string in the current time period based on the first power data. Finally, the power generation of the corresponding target string in the current time period can be determined based on the second power data. In this application embodiment, the current and voltage data of the standard string can be directly obtained from the existing monitoring equipment in the photovoltaic power generation system. Therefore, there is no need to add other related data acquisition equipment, nor is it necessary to obtain other environmental, meteorological, or equipment parameters, thereby reducing costs. At the same time, it avoids the influence of deviations between actual construction and design parameters. Based on the power relationship model between the standard string and the corresponding target string, only the standard string needs to be maintained periodically to ensure the accurate determination of the power generation of the corresponding target string. In other words, in this application embodiment, only the current and voltage data of the standard string need to be obtained based on the existing monitoring equipment in the photovoltaic power generation system to determine the power generation of the corresponding target string. This not only reduces costs but also improves the accuracy of power generation calculation. The method is simple, efficient, and easy to implement.

[0063] In one exemplary embodiment, reference is made to Figure 2 The step S101 of obtaining the first power data of the standard string in the current time period may include the following steps S201~S202.

[0064] S201, Obtain the first current data and first voltage data of the standard string in the current time period.

[0065] Among them, the first current data and first voltage data of the standard string in the current time period can be obtained directly from the relevant monitoring equipment already in the photovoltaic power generation system.

[0066] S202, determine the first power data based on the product of the first current data and the first voltage data.

[0067] The first power data can be obtained by multiplying the first current data and the first voltage data.

[0068] In this embodiment, the first current data and first voltage data of the standard string can be directly obtained from the existing monitoring equipment in the photovoltaic power generation system. Therefore, there is no need to add other related data acquisition equipment, nor is it necessary to obtain other environmental, meteorological or equipment parameters, thereby reducing costs and avoiding the impact of deviations between actual construction and design parameters.

[0069] In an exemplary embodiment, step S103, determining the power generation of the corresponding target string in the current time period based on the second power data, may include: determining the power generation based on the integration of the second power data over time in the current time period. Specifically, the power generation of the target string can be obtained by integrating the second power data of the target string over time in the current time period.

[0070] In this embodiment, the power generation of the target string can be determined based on the second power data of the target string. The determined second power data of the target string is the theoretical power data of the target string, and the determined power generation of the target string is the theoretical power generation of the target string. The method of this embodiment is simple and easy to implement.

[0071] In one exemplary embodiment, reference is made to Figure 3 The method for determining theoretical power generation may also include the following steps S301~S303.

[0072] S301, Establish the initial model.

[0073] As an example, the mathematical form of the initial model is a univariate polynomial regression analysis model.

[0074] S302, acquire multiple third power data of the standard string and multiple fourth power data of the corresponding target string within the target historical time period.

[0075] The third power data is the power data for the target historical period of the standard string, and the fourth power data is the power data for the target historical period of the target string. As an example, the power data for the historical period of the string can be obtained by multiplying the current data and voltage data of the string during that period.

[0076] S303, based on the initial model, multiple third power data and multiple fourth power data, determines the model coefficients of the power relationship model.

[0077] The initial model can be trained based on the power data of the standard string and the target string during the historical period of the target, so as to finally obtain the model coefficients of the power relationship model.

[0078] In this embodiment, the data form of the initial model and the mathematical form of the power relationship model are both univariate polynomial regression analysis models. They have few parameters, low complexity, strong anti-interference ability, high tolerance to noisy data, simple training, simple deployment, and minimal resource consumption during operation, making them easy to implement on edge devices.

[0079] In one exemplary embodiment, reference is made to Figure 4 The step S303, which involves determining the model coefficients of the power relationship model based on the initial model, multiple third power data, and multiple fourth power data, may include the following steps S401 to S402.

[0080] S401, each time a third power data point and a fourth power data point are input into the initial model, an error is obtained.

[0081] S402 will use the model coefficients that minimize the sum of squared errors as the model coefficients for the power relationship model.

[0082] In one exemplary embodiment, the mathematical form of the initial model is:

[0083]

[0084] The matrix of model coefficients for the power relationship model can be obtained using the following formula:

[0085]

[0086] in, The expression represents the error, and m represents the degree of the polynomial. Represents model coefficients ( , … (All are model coefficients) The matrix representing the model coefficients of the power relationship model. This indicates the third power data. This represents a matrix composed of multiple third power data points. The superscript "T" indicates the transpose of the matrix, and the superscript "-1" indicates the inverse of the matrix. This indicates the fourth power data. This represents a matrix composed of multiple fourth power data.

[0087] Understandably, an excessively large value of m may lead to overfitting, while an excessively small value may result in insufficient learning of data patterns. Therefore, the specific value of m can be reasonably configured according to the actual application to ensure that data patterns are learned sufficiently without overfitting.

[0088] In this embodiment, the third and fourth power data are substituted into the initial model to train the initial model. Based on the least squares method, the sum of squared errors is calculated, and the model coefficients corresponding to the set with the smallest sum of squared errors are selected. … As the model coefficients of the power relationship model, the matrix of the model coefficients of the power relationship model is the set of model coefficients that minimizes the sum of squared errors. … This is the structure. Thus, the mathematical form of the power relationship model is based on a univariate polynomial regression analysis model with these model coefficients. The first power data of the standard string is input into the power relationship model, causing the model to output the second power data of the target string.

[0089] As an example, the matrix of model coefficients for solving the power relationship model is shown below. Example of the process:

[0090] The initial model is: .

[0091] The historical power data is: {(Pb1, Pt1), (Pb2, Pt2), ..., (Pbn, Ptn)}, then:

[0092] =[Pt1 Pt2 …Ptn], =[Pb1 Pb2 …Pbn], =[ … ];

[0093] =[ 1 2 … n].

[0094] '= ,in, ' is the predicted value, and These are measured values. This is also the measured value;

[0095] The error of the i-th sample is i= - '= - ,in, for The i-th row.

[0096] The goal of least squares is to find Make the sum of squared errors S( Minimum:

[0097] S( )= = Represent it in vector form (which makes differentiation easier):

[0098] S( )=

[0099] S( ) is about The minimum value of the quadratic function can be obtained by taking the partial derivative and setting the derivative to 0.

[0100] Step 1: For Find the partial derivative

[0101] According to the matrix differentiation rule:

[0102] = =-2 ( ).

[0103] Step 2: Set the partial derivatives to 0 to obtain the normal equation.

[0104] make =0, simplifying, we get:

[0105] =

[0106] This equation is called the least squares normal equation, and it is used to solve... The core equation.

[0107] Step 3: Solve ,in, It can also be understood as an estimate.

[0108] If design matrix Satisfying full rank (i.e. If the column vectors are linearly independent, then the matrix... Since it is an invertible matrix, it can be solved directly. The least squares estimate, i.e., the matrix of model coefficients for the power relationship model, can be obtained using the following formula:

[0109]

[0110] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0111] In one exemplary embodiment, this application also provides a photovoltaic power generation system, which includes:

[0112] A standard string and a target string that corresponds one-to-one with the standard string; the standard string is a maintained string, and the target string is an unmaintained string;

[0113] The server is pre-deployed with a power relationship model, the mathematical form of which is a univariate polynomial regression analysis model.

[0114] The server is configured to acquire the first power data of the standard string in the current time period, and input the first power data into a preset power relationship model, so that the power relationship model outputs the second power data of the target string in the current time period based on the first power data, and determines the power generation of the target string in the current time period based on the second power data.

[0115] The photovoltaic power generation system and the method for determining theoretical power generation provided in the embodiments of this application belong to the same inventive concept, can solve the same technical problems, and thus achieve the same technical effects. Repeated content will not be repeated here.

[0116] In one exemplary embodiment, the photovoltaic power generation system further includes:

[0117] Inverter, each inverter is connected to multiple photovoltaic strings, and each photovoltaic string is a target string;

[0118] The server is pre-deployed with multiple power relationship models that correspond one-to-one with the target string;

[0119] The server is used to determine the power generation of the corresponding target string based on each of the power relationship models, and to accumulate the power generation of the target strings connected to the same inverter to obtain the power generation of the inverter.

[0120] The solution in this application embodiment can determine not only the power generation of the string but also the power generation of the inverter level. It is understood that, based on the same inventive concept, the power generation of the combiner box level can also be determined.

[0121] Based on the same inventive concept, this application also provides a theoretical power generation determination device for implementing the power generation determination method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more power generation determination device embodiments provided below can be found in the limitations of the power generation determination method described above, and will not be repeated here.

[0122] In one exemplary embodiment, such as Figure 5 As shown, a theoretical power generation determination device is provided, which includes:

[0123] Data acquisition module 510 is used to acquire the first power data of the standard string in the current time period;

[0124] The power calculation module 520 is used to input the first power data into a preset power relationship model so that the power relationship model outputs the second power data of the target string in the current time period according to the first power data, wherein the mathematical form of the power relationship model is a univariate polynomial regression analysis model.

[0125] The power calculation module 530 is used to determine the power generation of the corresponding target string in the current time period based on the second power data.

[0126] The power generation determination device and power generation determination method provided in the embodiments of this application belong to the same inventive concept, can solve the same technical problem, and thus achieve the same technical effect. Repeated content will not be repeated here.

[0127] In one exemplary embodiment, such as Figure 6 As shown, the power generation determination device also includes a model building module 540, which is used for:

[0128] Establish an initial model;

[0129] Acquire multiple third power data of the standard string and multiple fourth power data of the corresponding target string within the target historical time period;

[0130] Based on the initial model, the plurality of third power data, and the plurality of fourth power data, the model coefficients of the power relationship model are determined.

[0131] In one exemplary embodiment, the model building module 540 is further configured to:

[0132] Each input of the third power data and the fourth power data into the initial model yields an error.

[0133] The model coefficients that minimize the sum of squared errors will be used as the model coefficients of the power relationship model.

[0134] In one exemplary embodiment, the data acquisition module 510 is further configured to:

[0135] Obtain the first current data and the first voltage data of the standard string during the current time period;

[0136] The first power data is determined by multiplying the first current data and the first voltage data.

[0137] In one exemplary embodiment, the power calculation module 530 is further configured to:

[0138] The power generation is determined by integrating the second power data over time during the current period.

[0139] Each module in the aforementioned power generation determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0140] In one exemplary embodiment, a server is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps in the above-described method embodiments.

[0141] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0142] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0143] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0144] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0145] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining theoretical power generation, applied to a photovoltaic power generation system, wherein the photovoltaic power generation system includes standard strings and target strings corresponding one-to-one with the standard strings, the standard strings being maintained strings and the target strings being unmaintained strings, characterized in that, The method includes: Obtain the first power data of the standard string in the current time period; The first power data is input into a preset power relationship model so that the power relationship model outputs the second power data of the target string in the current time period based on the first power data, wherein the mathematical form of the power relationship model is a univariate polynomial regression analysis model. The power generation of the corresponding target string in the current time period is determined based on the second power data.

2. The method for determining theoretical power generation according to claim 1, characterized in that, The method further includes: Establish an initial model; Acquire multiple third power data of the standard string and multiple fourth power data of the corresponding target string within the target historical time period; Based on the initial model, the plurality of third power data, and the plurality of fourth power data, the model coefficients of the power relationship model are determined.

3. The method for determining theoretical power generation according to claim 2, characterized in that, The step of determining the model coefficients of the power relationship model based on the initial model, the plurality of third power data, and the plurality of fourth power data includes: Each input of the third power data and the fourth power data into the initial model yields an error. The model coefficients that minimize the sum of squared errors will be used as the model coefficients of the power relationship model.

4. The method for determining theoretical power generation according to claim 2, characterized in that, The mathematical form of the initial model is: The matrix of model coefficients is as follows: in, The expression represents the error, and m represents the degree of the polynomial. Represents the model coefficients, The matrix representing the coefficients of the model. This refers to the third power data. This represents a matrix composed of the multiple third power data, where the superscript "T" indicates the transpose of the matrix and the superscript "-1" indicates the inverse of the matrix. This refers to the fourth power data. This represents a matrix composed of the plurality of fourth power data.

5. The method for determining theoretical power generation according to claim 1, characterized in that, The step of obtaining the first power data of the standard string in the current time period includes: Obtain the first current data and the first voltage data of the standard string during the current time period; The first power data is determined by multiplying the first current data and the first voltage data.

6. The method for determining theoretical power generation according to claim 1, characterized in that, Determining the power generation of the corresponding target string in the current time period based on the second power data includes: The power generation is determined by integrating the second power data over time during the current period.

7. A device for determining theoretical power generation, applied to a photovoltaic power generation system, the photovoltaic power generation system comprising standard strings and target strings corresponding one-to-one with the standard strings, wherein the standard strings are maintained strings and the target strings are unmaintained strings, characterized in that, The device includes: The data acquisition module is used to acquire the first power data of the standard string in the current time period; The power calculation module is used to input the first power data into a preset power relationship model, so that the power relationship model outputs the second power data of the target string in the current time period according to the first power data, wherein the mathematical form of the power relationship model is a univariate polynomial regression analysis model. The power calculation module is used to determine the power generation of the corresponding target string in the current time period based on the second power data.

8. A server comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A photovoltaic power generation system, characterized in that, The system includes: A standard string and a target string that corresponds one-to-one with the standard string; the standard string is a maintained string, and the target string is an unmaintained string; The server is pre-deployed with a power relationship model, the mathematical form of which is a univariate polynomial regression analysis model. The server is configured to acquire the first power data of the standard string in the current time period, and input the first power data into a preset power relationship model, so that the power relationship model outputs the second power data of the target string in the current time period based on the first power data, and determines the power generation of the target string in the current time period based on the second power data.

10. The photovoltaic power generation system according to claim 9, characterized in that, The system also includes: Inverter, each inverter is connected to multiple photovoltaic strings, and each photovoltaic string is a target string; The server is pre-deployed with multiple power relationship models that correspond one-to-one with the target string; The server is used to determine the power generation of the corresponding target string based on each of the power relationship models, and to accumulate the power generation of the target strings connected to the same inverter to obtain the power generation of the inverter.

Images