A photovoltaic power generation loss evaluation method and device, electronic equipment and storage medium

Abstract

This application provides a method, apparatus, electronic device, and storage medium for assessing photovoltaic power generation losses. The method includes: determining the loss value of each loss item of the photovoltaic system in each monitoring period based on the collected parameters of the photovoltaic system during multiple monitoring periods; merging the column vectors corresponding to all loss items to obtain an original matrix; wherein the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods; standardizing the original matrix and calculating the covariance to determine the target loss matrix corresponding to the photovoltaic system; and determining the power generation loss information of the photovoltaic system based on all elements in the target loss matrix. This embodiment can determine the power generation loss information of the photovoltaic system under the influence of multiple factors, thereby accurately assessing photovoltaic power generation losses.

Description

Technical Field

[0001] This application relates to the field of photovoltaic power generation technology, and in particular to a photovoltaic power generation loss assessment method, apparatus, electronic device, and storage medium. Background Technology

[0002] With increasing emphasis on energy, photovoltaic (PV) power generation has developed rapidly and become a mainstream power generation method. To ensure efficient and safe PV power generation, it is necessary to assess PV power generation losses, thereby achieving efficient operation and maintenance of PV systems.

[0003] In related technologies, based on the collected parameters of the photovoltaic system, it is determined whether there are any abnormalities in photovoltaic power generation, thereby realizing the monitoring of power generation losses.

[0004] However, the above method monitors each collected parameter individually. Since the power generation loss of a photovoltaic system is affected by a variety of factors, the above method is difficult to accurately assess the power generation loss of a photovoltaic system. Summary of the Invention

[0005] This application provides a photovoltaic power generation loss assessment method, apparatus, electronic device, and storage medium for accurately assessing photovoltaic power generation losses.

[0006] In a first aspect, embodiments of this application provide a method for assessing photovoltaic power generation losses, the method comprising:

[0007] Based on the parameters collected by the photovoltaic system during multiple monitoring periods, the loss value of each loss item of the photovoltaic system in each monitoring period is determined;

[0008] The column vectors corresponding to all loss items are merged to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the photovoltaic system in the multiple monitoring periods;

[0009] The original matrix is ​​standardized and its covariance is calculated to determine the target loss matrix corresponding to the photovoltaic system.

[0010] Based on all elements in the target loss matrix, the power generation loss information of the photovoltaic system is determined.

[0011] The above scheme, based on the collected parameters from multiple monitoring periods, determines the loss value of each loss item in multiple monitoring periods. Different loss items characterize different loss dimensions of the photovoltaic system. Considering the various factors affecting the power generation loss of the photovoltaic system, after assembling these loss values ​​into an original matrix, the original matrix is ​​standardized and covariance is calculated to reduce noise in the original matrix, and a target loss matrix reflecting the main information of the original matrix is ​​determined (i.e., principal component analysis is performed on the original matrix). Therefore, based on all elements in the target loss matrix, the power generation loss information of the photovoltaic system under the influence of multiple factors can be determined, thereby accurately assessing the photovoltaic power generation loss.

[0012] In some optional implementations, the original matrix is ​​standardized and its covariance is calculated to determine the target loss matrix corresponding to the photovoltaic system, including:

[0013] The original matrix is ​​standardized to obtain a standardized matrix; then the covariance of the standardized matrix is ​​calculated to determine the feature matrix.

[0014] The target loss matrix is ​​determined by multiplying the transpose of the standardized matrix with the transpose of the feature matrix.

[0015] The above scheme standardizes the original matrix to prevent the numerical distribution in the standardized matrix from being too sparse or too dense, transforming large differences into comparable values. It then calculates the covariance of the standardized matrix to determine the feature matrix used to adjust the loss values ​​of each loss term. By multiplying the transpose of the standardized matrix with the transpose of the feature matrix, the loss values ​​of each loss term are adjusted based on different coefficients in the feature matrix. Different loss terms will have different effects, thus revealing the characteristics of random variables in the original matrix and reducing the influence of noise in the original matrix.

[0016] In some optional implementations, the original matrix is ​​standardized to obtain a standardized matrix, including:

[0017] The standardized matrix is ​​obtained by standardizing each column vector in the original matrix.

[0018] The above scheme standardizes each column vector in the original matrix, transforming different loss values ​​of the same loss term into comparable values ​​that reflect the differences between the loss terms.

[0019] In some optional implementations, covariance calculation is performed on the standardized matrix to determine the characteristic matrix, including:

[0020] The covariance of the standardized matrix is ​​calculated to obtain the covariance matrix;

[0021] From a plurality of eigenvalues ​​of the covariance matrix, a predetermined number of target eigenvalues ​​are selected; wherein each target eigenvalue is greater than any non-target eigenvalue among the plurality of eigenvalues.

[0022] The feature column vectors corresponding to the target feature values ​​are merged to obtain the feature matrix.

[0023] The above scheme calculates the covariance of the standardized matrix to obtain a covariance matrix that represents the correlation between each loss term. From the multiple eigenvalues ​​of the covariance matrix, the largest m (preset number) target eigenvalues ​​are selected. Since the target eigenvalues ​​have a large contribution, the loss values ​​of each loss term are adjusted by combining the feature column vectors corresponding to the target eigenvalues ​​to obtain a feature matrix, so that important loss terms have a greater impact.

[0024] In some optional implementations, the loss value of each loss item of the photovoltaic system in each monitoring period is determined based on the collected parameters of the photovoltaic system during multiple monitoring periods, including:

[0025] For any given monitoring period, based on the acquisition parameters corresponding to any loss item and the preset parameters corresponding to the loss item, the loss value of the photovoltaic system for the loss item during the monitoring period is determined.

[0026] The above scheme, because each loss item is affected by different factors and different parameters need to be considered, can accurately determine the loss value of each loss item based on the collection parameters and the corresponding preset parameters.

[0027] In some optional implementations, the power generation loss information of the photovoltaic system is determined based on all elements in the target loss matrix, including:

[0028] The power generation loss information is obtained by weighting and summing all the elements according to the preset weighting coefficients.

[0029] In some optional implementations, before determining the loss value of each loss item of the photovoltaic system in each monitoring period, the method further includes:

[0030] Missing values ​​in the collected parameters are filled in; and / or outliers in the collected parameters are removed.

[0031] The above scheme, since missing values ​​are missing information in the collected parameters, fills in the missing values ​​to obtain more complete collected parameters; since outliers deviate from the other normal values ​​in the collected parameters and will affect the subsequent calculation of the loss value, the outliers are removed to reduce the interference with the loss value.

[0032] In some optional implementations, the loss term includes some or all of the following:

[0033] The loss items characterizing power generation attenuation loss, shading loss, fault loss, temperature rise loss, component mismatch loss, line loss, power curtailment loss, and transformer loss.

[0034] Secondly, embodiments of this application also provide a photovoltaic power generation loss assessment device, comprising:

[0035] The loss value determination module is used to determine the loss value of each loss item of the photovoltaic system in each monitoring period based on the collected parameters of the photovoltaic system in multiple monitoring periods.

[0036] The matrix processing module is used to merge the column vectors corresponding to all loss items to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods;

[0037] The matrix processing module is also used to standardize the original matrix and calculate the covariance to determine the target loss matrix corresponding to the photovoltaic system.

[0038] The loss assessment module is used to determine the power generation loss information of the photovoltaic system based on all elements in the target loss matrix.

[0039] In some optional implementations, the matrix processing module is specifically used for:

[0040] The original matrix is ​​standardized to obtain a standardized matrix; then the covariance of the standardized matrix is ​​calculated to determine the feature matrix.

[0041] The target loss matrix is ​​determined by multiplying the transpose of the standardized matrix with the transpose of the feature matrix.

[0042] In some optional implementations, the matrix processing module is specifically used for:

[0043] The standardized matrix is ​​obtained by standardizing each column vector in the original matrix.

[0044] In some optional implementations, the matrix processing module is specifically used for:

[0045] The covariance of the standardized matrix is ​​calculated to obtain the covariance matrix;

[0046] From a plurality of eigenvalues ​​of the covariance matrix, a predetermined number of target eigenvalues ​​are selected; wherein each target eigenvalue is greater than any non-target eigenvalue among the plurality of eigenvalues.

[0047] The feature column vectors corresponding to the target feature values ​​are merged to obtain the feature matrix.

[0048] In some optional implementations, the loss value determination module is specifically used for:

[0049] For any given monitoring period, based on the acquisition parameters corresponding to any loss item and the preset parameters corresponding to the loss item, the loss value of the photovoltaic system for the loss item during the monitoring period is determined.

[0050] In some optional implementations, the loss assessment module is specifically used for:

[0051] The power generation loss information is obtained by weighting and summing all the elements according to the preset weighting coefficients.

[0052] In some optional implementations, before determining the loss value of each loss item of the photovoltaic system in each monitoring period, the loss value determination module is further configured to:

[0053] Missing values ​​in the collected parameters are filled in; and / or outliers in the collected parameters are removed.

[0054] In some optional implementations, the loss term includes some or all of the following:

[0055] The loss items characterizing power generation attenuation loss, shading loss, fault loss, temperature rise loss, component mismatch loss, line loss, power curtailment loss, and transformer loss.

[0056] Thirdly, embodiments of this application provide an electronic device, including at least one processor and at least one memory, wherein the memory stores a computer program, and when the program is executed by the processor, the processor performs the photovoltaic power generation loss assessment method described in any of the first aspects above.

[0057] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the photovoltaic power generation loss assessment method described in any of the first aspects above.

[0058] Furthermore, the technical effects of any of the implementation methods in aspects two to four can be found in the technical effects of different implementation methods in aspect one, and will not be repeated here. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0060] Figure 1 This is a schematic diagram illustrating an application scenario provided in the embodiments of this application;

[0061] Figure 2 A flowchart illustrating the first photovoltaic power generation loss assessment method provided in this application embodiment;

[0062] Figure 3 A flowchart illustrating the target loss matrix determination method provided in this application embodiment;

[0063] Figure 4 A flowchart illustrating the second photovoltaic power generation loss assessment method provided in this application embodiment;

[0064] Figure 5 A flowchart illustrating the third photovoltaic power generation loss assessment method provided in this application embodiment;

[0065] Figure 6 A flowchart illustrating the fourth photovoltaic power generation loss assessment method provided in this application embodiment;

[0066] Figure 7 This is a schematic diagram of the structure of the photovoltaic power generation loss assessment device provided in the embodiments of this application;

[0067] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0069] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0070] In this embodiment of the invention, the term "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following associated objects have an "or" relationship.

[0071] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the term "connection" should be interpreted broadly. For example, it can refer to a direct connection, an indirect connection through an intermediate medium, or a connection within two devices. Those skilled in the art can understand the specific meaning of the above term in this application based on the specific circumstances.

[0072] To ensure efficient and safe photovoltaic power generation, it is necessary to assess photovoltaic power generation losses in order to achieve efficient operation and maintenance of photovoltaic systems.

[0073] In related technologies, based on the collected parameters of the photovoltaic system, it is possible to determine whether there are any abnormalities in photovoltaic power generation, thereby achieving monitoring of power generation losses. For example, whether the current and temperature in the photovoltaic system are normal.

[0074] However, the above method monitors each collected parameter individually. Since the power generation loss of a photovoltaic system is affected by a variety of factors, the above method is difficult to accurately assess the power generation loss of a photovoltaic system.

[0075] In view of this, embodiments of this application propose a photovoltaic power generation loss assessment method, apparatus, electronic device and storage medium for accurately assessing photovoltaic power generation losses.

[0076] See Figure 1 As shown, this is an application scenario provided by an embodiment of the present application. This application scenario includes an electronic device 100 and multiple acquisition devices ( Figure 1 Taking data acquisition devices 201, 202, and 203 as examples, more or fewer data acquisition devices can be set up in actual applications.

[0077] The aforementioned data acquisition device is installed at the photovoltaic system to acquire the photovoltaic system's acquisition parameters and send the acquired parameters to the electronic device 100.

[0078] The electronic device 100 is used to: determine the loss value of each loss item of the photovoltaic system in each monitoring period based on the collected parameters of the photovoltaic system in multiple monitoring periods; merge the column vectors corresponding to all loss items to obtain an original matrix; wherein the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods; perform standardization processing and covariance calculation on the original matrix to determine the target loss matrix corresponding to the photovoltaic system; and determine the power generation loss information of the photovoltaic system based on all elements in the target loss matrix.

[0079] The above scheme, based on the collected parameters from multiple monitoring periods, determines the loss value of each loss item in multiple monitoring periods. Different loss items characterize different loss dimensions of the photovoltaic system. Considering the various factors affecting the power generation loss of the photovoltaic system, after assembling these loss values ​​into an original matrix, the original matrix is ​​standardized and covariance is calculated to reduce noise in the original matrix, and a target loss matrix reflecting the main information of the original matrix is ​​determined (i.e., principal component analysis is performed on the original matrix). Therefore, based on all elements in the target loss matrix, the power generation loss information of the photovoltaic system under the influence of multiple factors can be determined, thereby accurately assessing the photovoltaic power generation loss.

[0080] This embodiment does not specifically limit the above-mentioned data acquisition equipment. For example, it may include some or all of the following: grid-connected measurement equipment, inverter control equipment, solar irradiance sensors, photovoltaic module temperature sensors, wind speed sensors, environmental sensors, humidity sensors, and electricity meter devices, etc. The specific implementation method of the acquired parameters is related to the type of data acquisition equipment.

[0081] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with reference to the accompanying drawings and specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0082] This application provides a first method for assessing photovoltaic power generation losses, applied to the aforementioned electronic equipment, such as... Figure 2 As shown, it includes the following steps:

[0083] Step S201: Based on the collected parameters of the photovoltaic system during multiple monitoring periods, determine the loss value of each loss item of the photovoltaic system during each monitoring period.

[0084] In practice, due to the numerous factors affecting photovoltaic power generation, it is difficult to assess power generation loss through a single acquisition parameter or a single dimension. However, the acquisition parameters of various types characterize the working status of the photovoltaic system. Therefore, based on the acquisition parameters of multiple monitoring periods, it is possible to determine the loss value of each loss item in multiple monitoring periods. Different loss items characterize different loss dimensions of the photovoltaic system, taking into account the various factors affecting the power generation loss of the photovoltaic system.

[0085] Step S202: Merge the column vectors corresponding to all loss items to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods.

[0086] For example, the loss values ​​of a loss item form a column vector for that loss item. For instance, the loss value of loss item 1 during monitoring period 1 is x. 11 The loss value of loss item 1 during monitoring period 2 is x. 21 The loss value of loss item 1 during monitoring period n is x. n1 The column vector corresponding to loss term 1 is denoted as x1.

[0087] The same method is used to determine the column vectors corresponding to other loss terms;

[0088] In this embodiment, there are p loss terms, and the original matrix x = (x1, x2, ..., xp). p ); where x1 is the column vector corresponding to loss term 1, x2 is the column vector corresponding to loss term 2, ..., x p Let p be the column vector corresponding to the loss term.

[0089] The loss terms and their corresponding column vectors described above are merely illustrative examples and are not intended to limit this application.

[0090] Step S203: Standardize the original matrix and calculate the covariance to determine the target loss matrix corresponding to the photovoltaic system.

[0091] For example, because the original matrix composed of these loss values ​​is quite noisy, it cannot directly reflect the main impact information;

[0092] Based on this, after assembling these loss values ​​into an original matrix, the original matrix is ​​standardized and its covariance is calculated to reduce noise in the original matrix, and the target loss matrix that reflects the main information of the original matrix is ​​determined, i.e., principal component analysis (PCA) is performed on the original matrix.

[0093] Step S204: Based on all elements in the target loss matrix, determine the power generation loss information of the photovoltaic system.

[0094] The above scheme, based on the collected parameters from multiple monitoring periods, determines the loss value of each loss item in multiple monitoring periods. Different loss items characterize different loss dimensions of the photovoltaic system. Considering the various factors affecting the power generation loss of the photovoltaic system, after assembling these loss values ​​into an original matrix, the original matrix is ​​standardized and covariance is calculated to reduce noise in the original matrix, and a target loss matrix reflecting the main information of the original matrix is ​​determined (i.e., principal component analysis is performed on the original matrix). Therefore, based on all elements in the target loss matrix, the power generation loss information of the photovoltaic system under the influence of multiple factors can be determined, thereby accurately assessing the photovoltaic power generation loss.

[0095] See Figure 3 As shown, in some optional embodiments, step S203 above can be implemented in, but is not limited to, the following ways:

[0096] Step S301: Standardize the original matrix to obtain a standardized matrix; and calculate the covariance of the standardized matrix to determine the characteristic matrix.

[0097] In practice, since there may be large differences between loss values, it is difficult to directly compare the loss values. Based on this, this embodiment performs standardization processing on the original matrix so that the numerical distribution in the standardized matrix is ​​not too sparse or too dense, and transforms the large differences into comparable values.

[0098] Furthermore, different loss terms have different impacts on the power generation loss of the photovoltaic system. Based on this, this embodiment calculates the covariance of the standardized matrix to determine the characteristic matrix that adjusts the loss value of each loss term, thereby revealing the characteristics of the random variables in the original matrix and reducing the noise influence in the original matrix.

[0099] Step S302: The product of the transpose of the normalized matrix and the transpose of the feature matrix is ​​determined as the target loss matrix.

[0100] For example, the target loss matrix F = X T *A T ; where X T Let A be the transpose of the above standardized matrix. T This is the transpose of the aforementioned characteristic matrix.

[0101] The above scheme standardizes the original matrix to prevent the numerical distribution in the standardized matrix from being too sparse or too dense, transforming large differences into comparable values. It then calculates the covariance of the standardized matrix to determine the feature matrix used to adjust the loss values ​​of each loss term. By multiplying the transpose of the standardized matrix with the transpose of the feature matrix, the loss values ​​of each loss term are adjusted based on different coefficients in the feature matrix. Different loss terms will have different effects, thus revealing the characteristics of random variables in the original matrix and reducing the influence of noise in the original matrix.

[0102] In some optional implementations, the original matrix is ​​standardized to obtain a standardized matrix, including:

[0103] The standardized matrix is ​​obtained by standardizing each column vector in the original matrix.

[0104] For example, any column vector in the original matrix consists of loss values ​​of the same loss term. In order to convert different loss values ​​of the same loss term into comparable values, it is necessary to standardize each column vector in the original matrix.

[0105] Using the original matrix x = (x1, x2, ..., x...) as described above... p Taking x1 as an example, we can standardize all elements in x1 to obtain...

[0106] The other column vectors in the normalized matrix are obtained in the same way;

[0107] Standardized matrix

[0108] Among them, the elements in the above standardized matrix X Let be the mean of the elements in column vector j. S j Let j be the standard deviation of the elements in column vector j.

[0109] It is understood that the number of loss items and the number of loss values ​​in the loss items are merely illustrative examples and are not intended to limit this application.

[0110] The above scheme standardizes each column vector in the original matrix, transforming different loss values ​​of the same loss term into comparable values ​​that reflect the differences between the loss terms.

[0111] In some optional implementations, covariance calculation is performed on the standardized matrix to determine the characteristic matrix, including:

[0112] The covariance of the standardized matrix is ​​calculated to obtain the covariance matrix;

[0113] From a plurality of eigenvalues ​​of the covariance matrix, a predetermined number of target eigenvalues ​​are selected; wherein each target eigenvalue is greater than any non-target eigenvalue among the plurality of eigenvalues.

[0114] The feature column vectors corresponding to the target feature values ​​are merged to obtain the feature matrix.

[0115] For example, by calculating the covariance of the standardized matrix X, a covariance matrix R representing the correlation between the loss terms is obtained; the covariance matrix R has p eigenvalues, namely λ1, λ2, ..., λp; where the feature column vector corresponding to λ1 is a1, the feature column vector corresponding to λ2 is a2, ..., and the feature column vector corresponding to λp is a... p Select the m largest eigenvalues ​​from these p eigenvalues ​​as target eigenvalues, and merge the feature column vectors corresponding to the m target eigenvalues ​​to obtain the feature matrix A.

[0116] The above scheme calculates the covariance of the standardized matrix to obtain a covariance matrix that represents the correlation between each loss term. From the multiple eigenvalues ​​of the covariance matrix, the largest m (preset number) target eigenvalues ​​are selected. Since the target eigenvalues ​​have a large contribution, the loss values ​​of each loss term are adjusted by combining the feature column vectors corresponding to the target eigenvalues ​​to obtain a feature matrix, so that important loss terms have a greater impact.

[0117] This application provides a second method for assessing photovoltaic power generation losses, applied to the aforementioned electronic equipment, such as... Figure 4 As shown, it includes the following steps:

[0118] Step S401: For any monitoring period, based on the acquisition parameters corresponding to any loss item and the preset parameters corresponding to the loss item, determine the loss value of the photovoltaic system for the loss item during the monitoring period.

[0119] During implementation, each loss item is affected by different factors, and different parameters need to be considered. Based on this, this embodiment can accurately determine the loss value of each loss item according to the collection parameters and the corresponding preset parameters.

[0120] The following are some specific examples to illustrate this:

[0121] 1) Regarding the loss term characterizing power generation attenuation:

[0122] The loss value Q1 is the amount of electricity lost corresponding to the degradation ratio of the photovoltaic system; where the degradation ratio is the difference between the overall degradation rate of the photovoltaic system and the average degradation rate of all strings.

[0123] Where p0 is the initial power, P x The actual power during the detection period; P x =V x *I x P0 = V0 * I0, where V0 is the preset voltage (voltage under standard conditions) and I0 is the preset current (current under standard conditions).

[0124] I x =I0*S x *[1+a*△T] / S0, V x =V0*(1+c*△T)*ln[e+b(S x / S0-1)];where S x Photovoltaics

[0125] The system measures the light intensity (irradiance) during the monitoring period, where 'a' is the first preset coefficient and 'S0' is the preset light intensity (e.g., 1000 W / m²). 2 c is the second preset coefficient (e.g., 0.00288℃); b is the third preset coefficient (e.g., 0.5);

[0126] The above △T=T x +K*S x -T0; where T x The ambient temperature corresponding to the monitoring period; K is the fourth preset coefficient (e.g., 0.03 (℃·m)). 2 / W)), T0 is the first preset temperature (e.g., 25℃).

[0127] 2) Regarding the loss term characterizing shadow occlusion loss:

[0128] The loss value Q2 is obtained by multiplying the power generation duration of the shading loss by the inverter capacity;

[0129] The duration of power generation loss due to shading can be determined in the following ways:

[0130] After determining the current and voltage during the monitoring period, the actual current-voltage curve is compared with the preset current-voltage curve to identify the shaded string inverters (string inverters with shadows have multiple peaks in their IU curve); the preset current-voltage curve is the curve when there is no shading, such as the curve obtained based on the current and voltage data of string inverters during winter from 9:00 to 15:00.

[0131] The difference between the preset equivalent hours (such as the average equivalent hours of an unshaded string inverter) and the average equivalent hours of a shaded string inverter is determined as the power generation duration lost due to shading.

[0132] 3) Regarding the loss term characterizing failure loss:

[0133] If there is a period of zero current during the working hours of the monitoring period (e.g., 6:00-18:00), the period of zero current is determined as the fault period in the monitoring period, and the missing power generation corresponding to the fault period is determined as the loss value Q3 of the third loss item.

[0134] In practice, the actual power generation in historical periods with similar external environments to the monitoring period can be used as the missing power generation.

[0135] 4) Regarding the loss term characterizing temperature rise loss:

[0136] When the module operates at high temperatures, it will generate power loss. The module's operating temperature is affected by solar radiation; therefore, the loss value is Q4 = K. T *S x *PAZ*0.83; where K T =P STC *[1+γ*(T N -25)];

[0137] K T S is the temperature loss coefficient. x The above irradiance is given by PAZ, where P is the system installed capacity; P STC The component output power is under standard conditions, γ is the fifth preset coefficient, and T is the output power of the component under standard conditions. N The second preset temperature (backsheet temperature of the photovoltaic system, such as 45°C);

[0138] 5) Regarding the loss term characterizing component mismatch loss:

[0139] Loss value Q5 = (P1 - P2) / P1 * Q0 * 100%; where Q0 = S x *PAZ* 83%;

[0140] P1 is the sum of the corrected maximum power of all components in the photovoltaic system, P2 is the corrected maximum power of the string, Q0 is the theoretical power generation, and S x The above refers to the irradiance; PAZ represents the installed capacity of the above system.

[0141] Component mismatch loss occurs when components in the same array have individual differences, resulting in the output voltage being the sum of the values ​​of all components, while the output current is the minimum value among all components, causing the total output power to be less than the sum of the nominal power of each component.

[0142] 6) Regarding the loss items characterizing the line losses of a photovoltaic system:

[0143] Loss value Q6 = P 损失 / P 总功率 *S x*PAZ* 83%; P 损失 =3*I 交流 2 *R 交流 +3*I 直流 2 *R 直流 ;

[0144] I 交流 For AC line current, R 交流 For AC line resistance, I 直流 R is the DC line current. 直流 P is the resistance of the DC line. 容量 S represents the total power of the photovoltaic system. x The above refers to the irradiance; PAZ represents the installed capacity of the above system.

[0145] 7) Regarding the loss term characterizing power curtailment losses:

[0146] When a photovoltaic system is subject to power curtailment due to overcapacity or other reasons, a power curtailment loss will occur; the loss value Q7 = equivalent curtailment hours * curtailment time.

[0147] 8) Regarding the loss term characterizing transformer losses:

[0148] Q8 = P T *S x *PAZ*83%; where P T =P F *t+P K *t*Y*λ;

[0149] P F For rated iron loss, P K Rated copper loss, t is the working time, Y is the sixth preset coefficient, λ is the seventh preset coefficient, S x The above refers to the irradiance; PAZ represents the installed capacity of the above system.

[0150] The above-mentioned loss items are only illustrative examples. In practice, some of these loss items may be selected, or other loss items may be selected.

[0151] Step S402: Merge the column vectors corresponding to all loss items to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods.

[0152] Step S403: Standardize the original matrix and calculate the covariance to determine the target loss matrix corresponding to the photovoltaic system.

[0153] Step S404: Based on all elements in the target loss matrix, determine the power generation loss information of the photovoltaic system.

[0154] The specific implementation of steps S402 to S404 can be found in the above embodiments, and will not be repeated here.

[0155] The above scheme, because each loss item is affected by different factors and different parameters need to be considered, can accurately determine the loss value of each loss item based on the collection parameters and the corresponding preset parameters.

[0156] This application provides a third method for assessing photovoltaic power generation losses, applied to the aforementioned electronic equipment, such as... Figure 5 As shown, it includes the following steps:

[0157] Step S501: Based on the collected parameters of the photovoltaic system during multiple monitoring periods, determine the loss value of each loss item of the photovoltaic system during each monitoring period.

[0158] Step S502: Merge the column vectors corresponding to all loss items to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods.

[0159] Step S503: Standardize the original matrix and calculate the covariance to determine the target loss matrix corresponding to the photovoltaic system.

[0160] The specific implementation of steps S501 to S503 can be referred to the above embodiments, and will not be repeated here.

[0161] Step S504: According to the preset weighting coefficients, perform a weighted summation on all the elements to obtain the power generation loss information.

[0162] For example, the target loss matrix has multiple elements, each of which corresponds to a weight coefficient. Each element is multiplied by its corresponding weight coefficient, and all the products are added together to determine the power generation loss information that characterizes the power generation loss of the photovoltaic system.

[0163] This application provides a fourth method for assessing photovoltaic power generation losses, applied to the aforementioned electronic equipment, such as... Figure 6 As shown, it includes the following steps:

[0164] Step S601: Fill in missing values ​​in the collected parameters; and / or remove outliers in the collected parameters.

[0165] During implementation, data acquisition equipment may be subject to interference, or communication between the acquisition equipment and electronic equipment may fail, which may result in data loss or data anomalies.

[0166] Since missing values ​​represent missing information in the collected parameters, filling in the missing values ​​yields more complete collected parameters.

[0167] The above-mentioned filling process is performed on the same type of collected parameters. This embodiment does not limit the specific implementation method of the filling process, such as using the average value of a certain type of valid values ​​to fill the missing values ​​of that type; or inputting a certain type of valid values ​​into the prediction model for prediction, and predicting the missing values ​​of that type through the prediction model, etc.

[0168] Since outliers deviate from the other normal values ​​in the collected parameters, they can affect the subsequent calculation of the loss value. By removing outliers, the interference with subsequent calculations can be reduced.

[0169] The above outliers are determined for the same type of acquisition parameters, such as by using the Raida criterion (3σ) or the Grubbs criterion to identify outliers in the acquisition parameters.

[0170] Step S602: Based on the collected parameters of the photovoltaic system during multiple monitoring periods, determine the loss value of each loss item of the photovoltaic system during each monitoring period.

[0171] Step S603: Merge the column vectors corresponding to all loss items to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods.

[0172] Step S604: Standardize the original matrix and calculate the covariance to determine the target loss matrix corresponding to the photovoltaic system.

[0173] Step S605: Based on all elements in the target loss matrix, determine the power generation loss information of the photovoltaic system.

[0174] The specific implementation of steps S602 to S605 can be referred to the above embodiments, and will not be repeated here.

[0175] The above scheme fills in missing values ​​to obtain more complete data collection parameters, since missing values ​​are missing information in the collected parameters. Outliers deviate from the other normal values ​​in the collected parameters and will affect the subsequent calculation of loss values. By removing outliers, interference with subsequent calculations is reduced.

[0176] In some optional implementations, after determining the power generation loss information through the above embodiments, this power generation loss information can be compared with historical power generation loss information, or compared with a power generation loss threshold, to determine whether the photovoltaic system has significant power generation loss, and then relevant personnel can be notified. For example:

[0177] If the power generation loss information is greater than the power generation loss threshold, the loss value of each loss item will be notified through a preset notification method; or

[0178] If the increase in the power generation loss information compared to the historical power generation loss information of the photovoltaic system is greater than a preset increase, then the loss value of each loss item will be notified through a preset notification method.

[0179] Based on the same inventive concept, this application provides a photovoltaic power generation loss assessment device, see reference. Figure 7 As shown, the photovoltaic power generation loss assessment device 700 includes:

[0180] The loss value determination module 701 is used to determine the loss value of each loss item of the photovoltaic system in each monitoring period based on the collected parameters of the photovoltaic system in multiple monitoring periods;

[0181] The matrix processing module 702 is used to merge the column vectors corresponding to all loss items to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods;

[0182] The matrix processing module 702 is also used to perform standardization processing and covariance calculation on the original matrix to determine the target loss matrix corresponding to the photovoltaic system.

[0183] The loss assessment module 703 is used to determine the power generation loss information of the photovoltaic system based on all elements in the target loss matrix.

[0184] In some optional implementations, the matrix processing module 702 is specifically used for:

[0185] The original matrix is ​​standardized to obtain a standardized matrix; then the covariance of the standardized matrix is ​​calculated to determine the feature matrix.

[0186] The target loss matrix is ​​determined by multiplying the transpose of the standardized matrix with the transpose of the feature matrix.

[0187] In some optional implementations, the matrix processing module 702 is specifically used for:

[0188] The standardized matrix is ​​obtained by standardizing each column vector in the original matrix.

[0189] In some optional implementations, the matrix processing module 702 is specifically used for:

[0190] The covariance of the standardized matrix is ​​calculated to obtain the covariance matrix;

[0191] From a plurality of eigenvalues ​​of the covariance matrix, a predetermined number of target eigenvalues ​​are selected; wherein each target eigenvalue is greater than any non-target eigenvalue among the plurality of eigenvalues.

[0192] The feature column vectors corresponding to the target feature values ​​are merged to obtain the feature matrix.

[0193] In some optional implementations, the loss value determination module 701 is specifically used for:

[0194] For any given monitoring period, based on the acquisition parameters corresponding to any loss item and the preset parameters corresponding to the loss item, the loss value of the photovoltaic system for the loss item during the monitoring period is determined.

[0195] In some optional implementations, the loss assessment module 703 is specifically used for:

[0196] The power generation loss information is obtained by weighting and summing all the elements according to the preset weighting coefficients.

[0197] In some optional implementations, before determining the loss value of each loss item of the photovoltaic system in each monitoring period, the loss value determination module 701 is further configured to:

[0198] Missing values ​​in the collected parameters are filled in; and / or outliers in the collected parameters are removed.

[0199] In some optional implementations, the loss term includes some or all of the following:

[0200] The loss items characterizing power generation attenuation loss, shading loss, fault loss, temperature rise loss, component mismatch loss, line loss, power curtailment loss, and transformer loss.

[0201] Since this device is the same as the device in the method of this application embodiment, and the principle of the device in solving the problem is similar to that of the method, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described again.

[0202] Based on the same technical concept, this application also provides an electronic device 800, such as... Figure 8 As shown, it includes at least one processor 801 and a memory 802 connected to at least one processor. In this embodiment, the specific connection medium between the processor 801 and the memory 802 is not limited. Figure 8Taking the connection between the processor 801 and the memory 802 via bus 803 as an example, the bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0203] The processor 801 is the control center of the electronic device. It can connect to various parts of the electronic device through various interfaces and lines, and performs data processing by running or executing instructions stored in the memory 802 and calling data stored in the memory 802. Optionally, the processor 801 may include one or more processing units. The processor 801 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and application programs, while the modem processor mainly handles issuing instructions. It is understood that the modem processor may not be integrated into the processor 801. In some embodiments, the processor 801 and the memory 802 may be implemented on the same chip; in some embodiments, they may also be implemented on separate chips.

[0204] The processor 801 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of the photovoltaic power generation loss assessment method can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0205] Memory 802, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 802 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. Memory 802 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 802 can also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0206] In this embodiment, the memory 802 stores a computer program, which, when executed by the processor 801, causes the processor 801 to perform the following:

[0207] Based on the parameters collected by the photovoltaic system during multiple monitoring periods, the loss value of each loss item of the photovoltaic system in each monitoring period is determined;

[0208] The column vectors corresponding to all loss items are merged to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the photovoltaic system in the multiple monitoring periods;

[0209] The original matrix is ​​standardized and its covariance is calculated to determine the target loss matrix corresponding to the photovoltaic system.

[0210] Based on all elements in the target loss matrix, the power generation loss information of the photovoltaic system is determined.

[0211] In some alternative implementations, processor 801 specifically performs:

[0212] The original matrix is ​​standardized to obtain a standardized matrix; then the covariance of the standardized matrix is ​​calculated to determine the feature matrix.

[0213] The target loss matrix is ​​determined by multiplying the transpose of the standardized matrix with the transpose of the feature matrix.

[0214] In some alternative implementations, processor 801 specifically performs:

[0215] The standardized matrix is ​​obtained by standardizing each column vector in the original matrix.

[0216] In some alternative implementations, processor 801 specifically performs:

[0217] The covariance of the standardized matrix is ​​calculated to obtain the covariance matrix;

[0218] From a plurality of eigenvalues ​​of the covariance matrix, a predetermined number of target eigenvalues ​​are selected; wherein each target eigenvalue is greater than any non-target eigenvalue among the plurality of eigenvalues.

[0219] The feature column vectors corresponding to the target feature values ​​are merged to obtain the feature matrix.

[0220] In some alternative implementations, processor 801 specifically performs:

[0221] For any given monitoring period, based on the acquisition parameters corresponding to any loss item and the preset parameters corresponding to the loss item, the loss value of the photovoltaic system for the loss item during the monitoring period is determined.

[0222] In some alternative implementations, processor 801 specifically performs:

[0223] The power generation loss information is obtained by weighting and summing all the elements according to the preset weighting coefficients.

[0224] In some optional implementations, before determining the loss value of each loss item of the photovoltaic system in each monitoring period, the processor 801 further performs:

[0225] Missing values ​​in the collected parameters are filled in; and / or outliers in the collected parameters are removed.

[0226] In some optional implementations, the loss term includes some or all of the following:

[0227] The loss items characterizing power generation attenuation loss, shading loss, fault loss, temperature rise loss, component mismatch loss, line loss, power curtailment loss, and transformer loss.

[0228] Since the electronic device is the same as the electronic device in the method of this application embodiment, and the principle of the electronic device in solving the problem is similar to that of the method, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be described again.

[0229] Based on the same technical concept, embodiments of this application also provide a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the photovoltaic power generation loss assessment method described above.

[0230] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0231] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0232] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0233] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0234] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0235] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for assessing photovoltaic power generation losses, characterized in that, The method includes: Based on the parameters collected by the photovoltaic system during multiple monitoring periods, the loss values ​​corresponding to multiple loss items of the photovoltaic system in each monitoring period are determined; wherein, different loss items characterize different loss dimensions of the photovoltaic system. The column vectors corresponding to all loss items are merged to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the photovoltaic system in the multiple monitoring periods; The original matrix is ​​standardized to obtain a standardized matrix; then the covariance of the standardized matrix is ​​calculated to determine the feature matrix. The product of the transpose of the standardized matrix and the transpose of the characteristic matrix is ​​determined as the target loss matrix corresponding to the photovoltaic system. Based on all elements in the target loss matrix, the power generation loss information of the photovoltaic system is determined; The step of calculating the covariance of the standardized matrix to determine the feature matrix includes: The covariance of the standardized matrix is ​​calculated to obtain the covariance matrix; From a plurality of eigenvalues ​​of the covariance matrix, a predetermined number of target eigenvalues ​​are selected; wherein each target eigenvalue is greater than any non-target eigenvalue among the plurality of eigenvalues. The feature column vectors corresponding to the target feature values ​​are merged to obtain the feature matrix.

2. The method as described in claim 1, characterized in that, The standardization process of the original matrix to obtain the standardized matrix includes: The standardized matrix is ​​obtained by standardizing each column vector in the original matrix.

3. The method as described in claim 1, characterized in that, The step of determining the loss value of each loss item of the photovoltaic system in each monitoring period based on the collected parameters of the photovoltaic system in multiple monitoring periods includes: For any given monitoring period, based on the acquisition parameters corresponding to any loss item and the preset parameters corresponding to the loss item, the loss value of the photovoltaic system for the loss item during the monitoring period is determined.

4. The method as described in claim 1, characterized in that, The process of determining the power generation loss information of the photovoltaic system based on all elements in the target loss matrix includes: The power generation loss information is obtained by weighting and summing all the elements according to the preset weighting coefficients.

5. The method as described in claim 1, characterized in that, Before determining the loss value of each loss item of the photovoltaic system in each monitoring period, the method further includes: Missing values ​​in the collected parameters are filled in; and / or outliers in the collected parameters are removed.

6. The method according to any one of claims 1 to 5, characterized in that, The loss item includes some or all of the following: The loss items characterizing power generation attenuation loss, shading loss, fault loss, temperature rise loss, component mismatch loss, line loss, power curtailment loss, and transformer loss.

7. A photovoltaic power generation loss assessment device, characterized in that, include: The loss value determination module is used to determine the loss value corresponding to each of the multiple loss items of the photovoltaic system in each monitoring period based on the collected parameters of the photovoltaic system in multiple monitoring periods; wherein, different loss items represent different loss dimensions of the photovoltaic system; The matrix processing module is used to merge the column vectors corresponding to all loss items to obtain the original matrix; wherein, the column vectors corresponding to the loss items are composed of the loss values ​​of the loss items of the photovoltaic system in the multiple monitoring periods; The matrix processing module is further configured to standardize the original matrix to obtain a standardized matrix; calculate the covariance of the standardized matrix to determine the feature matrix; and determine the target loss matrix corresponding to the photovoltaic system by multiplying the transpose of the standardized matrix and the transpose of the feature matrix. The loss assessment module is used to determine the power generation loss information of the photovoltaic system based on all elements in the target loss matrix. The matrix processing module is specifically used for: The covariance of the standardized matrix is ​​calculated to obtain the covariance matrix; From a plurality of eigenvalues ​​of the covariance matrix, a predetermined number of target eigenvalues ​​are selected; wherein each target eigenvalue is greater than any non-target eigenvalue among the plurality of eigenvalues. The feature column vectors corresponding to the target feature values ​​are merged to obtain the feature matrix.

8. An electronic device, characterized in that, It includes at least one processor and at least one memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the method as described in any one of claims 1 to 6.

Images