Active power distribution network line loss rate threshold determination method based on photovoltaic and load uncertainty modeling

Abstract

The invention provides an active power distribution network line loss rate threshold determination method based on photovoltaic and load uncertainty modeling, and the method considers the characteristic that photovoltaic output and load have changes along with seasons and moments, and also considers the uncertainty of the photovoltaic output and load. A BP neural network is trained according to historical electricity sales data, historical photovoltaic output data and historical load data of a certain season and a certain moment, line loss is predicted according to the historical electricity sales data, photovoltaic output sampling data and load sampling data, the line loss rate of a certain season and a certain moment is calculated, and the frequency distribution curve of the line loss rate of the time period is drawn. And determining a threshold interval of the normal line loss rate. The threshold interval of the line loss rate has the reasonability of statistical significance.

Description

Technical Field

[0001] This invention belongs to the field of new energy grid connection management, and in particular relates to a method for determining the line loss rate threshold of active distribution networks based on photovoltaic and load uncertainty modeling. Background Technology

[0002] The acceptable range for line loss rate in a traditional distribution network (excluding distributed photovoltaic distribution networks) is no more than 6%. If the line loss rate of a traditional distribution network exceeds 6%, it is necessary to investigate whether there are faults in power equipment, lines, and metering equipment, and to investigate whether users are engaging in illegal electricity use or electricity theft. When distributed photovoltaics are connected to the distribution network, the power flow direction of the distribution network changes from unidirectional to bidirectional. Using the 6% threshold of the traditional distribution network for abnormal line loss rate judgment will result in missed detections.

[0003] In their paper "Evaluation of Line Loss Threshold for Distribution Networks Considering Photovoltaic Volatility," Zhou Qun et al. calculated a probability density distribution model of the weather type index and used Monte Carlo sampling to obtain weather type index samples. The randomness of the weather type index samples replaced the photovoltaic volatility and was used to evaluate the acceptable fluctuation range of the line loss rate of distribution networks containing distributed photovoltaics. The disadvantages of this method are: (1) The weather type index is composed of ambient temperature, atmospheric pressure, and humidity. Using ambient temperature, atmospheric pressure, and humidity to reflect the volatility of photovoltaic output is not accurate enough, as photovoltaic volatility is mainly determined by the solar irradiance; (2) The load volatility within a daily time range is not considered. Summary of the Invention

[0004] In view of this, the present invention aims to overcome the deficiencies in the prior art and proposes a method for determining the line loss rate threshold of active distribution networks based on photovoltaic and load uncertainty modeling. This invention considers the seasonal and temporal variations in photovoltaic output and load, as well as the uncertainties in photovoltaic output and load. It trains a BP neural network based on historical electricity sales data, historical photovoltaic output data, and historical load data for a specific season and time. Line losses are predicted based on historical electricity sales data, sampled photovoltaic output data, and sampled load data, and the line loss rate for a specific season and time is calculated. By plotting the frequency distribution curve of the line loss rate for that time period, a threshold range for the normal line loss rate is determined. This threshold range for the line loss rate is statistically significant and reasonable.

[0005] To achieve the above objectives, the technical solution of the present invention is implemented as follows:

[0006] In a first aspect, the present invention provides a method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling, the method comprising the following steps:

[0007] Step S1: Collect historical solar irradiance data for the area where the distribution network is located, classify it according to the four seasons, sample the solar irradiance of the current season to obtain N1 solar irradiance samples, and calculate N1 photovoltaic outputs based on the N1 solar irradiance samples.

[0008] Step S2: Collect historical load data of the distribution network, classify it according to the four seasons, and sample the load of the current season to obtain N2 load samples;

[0009] Step S3: Use the historical electricity sales, photovoltaic output, and load of each time period in the current season as input features of the BP neural network to train the BP neural network model.

[0010] Step S4: Input the electricity sales data for each time period of the current season, the N1 photovoltaic output sampling data generated in step S1, and the N2 load sampling data generated in step S2 into the trained BP neural network to calculate the N1×N2 predicted line loss results for each time period of the current season, and calculate the line loss rate.

[0011] S5: Plot the frequency distribution curves of line loss rate for each time period in the current season, and determine the minimum and maximum values ​​of line loss rate, which are the loss rate thresholds for active distribution network line loss rate for each time period in the previous season.

[0012] Furthermore, the classification method for the historical solar intensity data of the distribution network area collected in step S1 is as follows: spring is from March to May; summer is from June to August; autumn is from September to November; and winter is from December to February, and it is assumed that the solar intensity at each time point in the four seasons follows a Beta distribution.

[0013] Furthermore, in step S1, it is assumed that the mean of the solar radiation intensity at each time point in the four seasons is μ, and the variance of the solar radiation intensity is σ. 2 Calculate the α and β parameters of the Beta distribution.

[0014] Furthermore, the sampling method in step S1 is Monte Carlo sampling, which includes the following steps:

[0015] (a) Discretize the Beta probability density distribution for the current season and calculate the cumulative probability distribution function F(r);

[0016] (b) Generate N1 random numbers y1, y2, ... y1 in the value space [0, 1] of the cumulative probability distribution function F(r). N1 ;

[0017] (c) Generate N1 random numbers y1, y2, ... y N1 Substituting the inverse function F of the cumulative probability distribution function -1(r), to obtain N1 solar radiation intensities r k1 =F -1 (y k1 ), k1=1,2,…N1, and calculate the photovoltaic output at each time point of the current season based on the solar radiation intensity.

[0018] Furthermore, the photovoltaic output is denoted as P. V,k1 The calculation formula is:

[0019]

[0020] Where k1 = 1, 2, ..., N1, P Vm For photovoltaic installed capacity, r b This represents the saturation value of photovoltaic solar irradiance.

[0021] Furthermore, the classification method for the historical load data of the distribution network collected in step S2 is as follows: spring is from March to May; summer is from June to August; autumn is from September to November; and winter is from December to February, and it is assumed that the load at each time point in the four seasons follows a normal distribution.

[0022] Furthermore, the sampling method in step S2 is Monte Carlo sampling, which includes the following steps:

[0023] (a) Discretize the normal probability density distribution of the current season and calculate the cumulative probability distribution function F(P). L );

[0024] (b) In the cumulative probability distribution function F(P) L Generate N2 random numbers y1, y2, ... y from the value space [0, 1]. N2 ;

[0025] (c) Generate N2 random numbers y1, y2, ... y N2 Substituting the inverse function F of the cumulative probability distribution function -1 (P L ), thus obtaining N2 loads P L,k2 =F -1 (y k2 ), k2=1,2,…N2.

[0026] Furthermore, in the training process of the BP neural network model in step S3, the line loss of each time period of the current season is used as the output result, and the input features and output results are used as the dataset. The dataset is divided into a training set and a test set. The training set accounts for 90% of the dataset, and the test set accounts for 10% of the dataset. The training set is used to train the parameters of the BP neural network, and the test set is used to test the prediction accuracy of the BP neural network.

[0027] Furthermore, the line loss rate in step S4 is denoted as P. Loss,j,m The calculation formula is:

[0028]

[0029] Among them, G j Let j = 1, 2, ... 24, m = 1, 2, ... N1 × N2.

[0030] In a second aspect, the present invention provides a computer terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling as described in the first aspect of the present invention.

[0031] Thirdly, the present invention provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the active distribution network line loss rate threshold determination method based on photovoltaic and load uncertainty modeling as described in the first aspect of the present invention.

[0032] Compared with the prior art, the present invention has the following advantages:

[0033] (1) The method of the present invention takes into account the characteristics of photovoltaic output and load changing with the season and time, and predicts the line loss rate at each time for the current season. The characteristics of photovoltaic output and load changing with the season and time are specifically reflected in: (a) at the same time, the photovoltaic output and load are different in spring, summer, autumn and winter; (b) in a certain season, the photovoltaic output and load are also different at different times;

[0034] (2) The method of the present invention takes into account the uncertainty of photovoltaic output and load at the same time, and corrects the unreasonableness of predicting photovoltaic output based on weather index, such as the method of “evaluation of distribution network line loss threshold considering photovoltaic volatility” in the paper.

[0035] (3) The method of the present invention selects electricity sales, photovoltaic output, and load as input features of the BP neural network, and selects line loss instead of line loss rate as output feature of the BP neural network. Since electricity sales, photovoltaic output, load, and line loss have the same dimensions, and electricity sales, photovoltaic output, and load are directly related to line loss, the method has high prediction accuracy;

[0036] (4) The method of the present invention determines the minimum and maximum values ​​of the line loss rate, i.e. the threshold range of the normal line loss rate, based on the frequency distribution curve of the line loss rate in the current season and time period. The threshold has statistical significance and rationality. Attached Figure Description

[0037] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0038] Figure 1 This is a flowchart of the distribution network line loss rate threshold determination method based on photovoltaic and load uncertainty modeling of the present invention.

[0039] Figure 2 This is a historical solar radiation intensity data chart for the present invention;

[0040] Figure 3 This is a sampling result diagram of the photovoltaic output of the present invention;

[0041] Figure 4 This is a historical load data graph for the present invention;

[0042] Figure 5 This is a load sampling data graph of the present invention;

[0043] Figure 6 This is a frequency distribution curve of the predicted line loss rate of the present invention. Detailed Implementation

[0044] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0045] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0046] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0047] A method for determining the line loss rate threshold of a distribution network based on photovoltaic and load uncertainty modeling, the process is as follows: Figure 1 As shown, the specific steps include the following:

[0048] (1) Collect historical solar radiation intensity data for the area where the power distribution network is located, and categorize them according to the four seasons: spring (March to May); summer (June to August); autumn (September to November); and winter (December to February). Assume that the solar radiation intensity at each time point (every hour, a total of 24 time points) in the four seasons follows a Beta distribution, i.e.:

[0049]

[0050] Where r is the solar radiation intensity, rmax Let Γ be the maximum solar radiation intensity, Γ be the gamma function, and α and β be shape parameters. The mean solar radiation intensity at each time point in the four seasons is μ, and the variance of the solar radiation intensity is σ. 2 Then the formulas for calculating α and β are:

[0051]

[0052] (2) Conduct Monte Carlo sampling of the solar radiation intensity for the current season. The sampling method is as follows:

[0053] (a) Discretize the Beta probability density distribution for the current season and calculate the cumulative probability distribution function F(r);

[0054] (b) Generate N1 random numbers y1, y2, ... y1 in the value space [0, 1] of the cumulative probability distribution function F(r). N1 ;

[0055] (c) Generate N1 random numbers y1, y2, ... y N1 Substituting the inverse function F of the cumulative probability distribution function -1 (r), to obtain N1 solar radiation intensities r k1 =F -1 (y k1 ), k1=1,2,…N1.

[0056] (3) Calculate the photovoltaic output at each time point in the current season. Photovoltaic output P V,k1 The formula for calculating (k1 = 1, 2, ..., N1) is:

[0057]

[0058] Where P Vm For photovoltaic installed capacity, r b This represents the saturation value of photovoltaic solar irradiance.

[0059] (4) Collect historical load data of the distribution network and categorize it according to the four seasons. Assume the load P at each time point (every hour, a total of 24 time points) in the four seasons. L Follows a normal distribution:

[0060]

[0061] Where μ L σ is the load average. L 2 denoted as μ, representing the variance of the load. L and σ L 2 The calculation formula is:

[0062]

[0063] Where N is the number of load data points at each time point in the current season.

[0064] (5) Conduct Monte Carlo sampling of the current season's load. The sampling method is as follows:

[0065] (a) Discretize the normal probability density distribution of the current season and calculate the cumulative probability distribution function F(P). L );

[0066] (b) In the cumulative probability distribution function F(P) L Generate N2 random numbers y1, y2, ... y from the value space [0, 1]. N2 ;

[0067] (c) Generate N2 random numbers y1, y2, ... y N2 Substituting the inverse function F of the cumulative probability distribution function -1 (P L ), thus obtaining N2 loads P L,k2 =F -1 (y k2 ), k2=1,2,…N2.

[0068] (6) Based on the historical electricity sales volume G for each time period of the current season j (j=1, 2, …24), historical photovoltaic output P for each time period of the current season V,j Historical load P for each time period in the current season L,j As input features to the BP neural network, a BP neural network model is built, and the basic parameters of the model are input. The line loss of each time period in the current season is used as the output result. The dataset = {input features, line loss results} is divided into a training set and a test set. The training set accounts for 90% of the dataset, and the test set accounts for 10% of the dataset. The training set is used to train the parameters of the BP neural network, and the test set is used to test the prediction accuracy of the BP neural network.

[0069] (7) The electricity sales volume G for each time period of the current season in history j (j=1, 2, …24), N1 photovoltaic power output sampling data P generated in step (3) V,j,k1 The N2 load sampling data P generated in step (5) L,j,k2 Using the input features of the BP neural network, N1×N2 predicted line loss results P are calculated for each time period of the current season. Loss,j,m (j=1, 2,...24, m=1, 2,...N1×N2).

[0070] (8) Calculate the line loss rate for this time period. The formula for calculating the line loss rate is:

[0071]

[0072] (9) Plot the frequency distribution curve of the line loss rate for this period, and determine the minimum and maximum values ​​of the line loss rate, which are the threshold range of the normal line loss rate for this period. If the actual line loss rate is less than the predicted minimum line loss rate or exceeds the predicted maximum line loss rate, it is determined that the actual line loss rate is abnormal, and an investigation of abnormal line loss rates should be carried out.

[0073] Example 1

[0074] (1) Collect historical solar irradiance data for a certain year from a power distribution network in Baoding. The historical solar irradiance is as follows: Figure 2 As shown.

[0075] (2) Taking autumn as an example, the values ​​of α and β at each time point of the Beta distribution are calculated as shown in Table 1.

[0076] Table 1. α and β values ​​at each time point

[0077]

[0078] (3) Monte Carlo sampling was conducted on the solar radiation intensity of the current season. When the number of samples was 500, the photovoltaic output sampling data was as follows: Figure 3 As shown.

[0079] (4) Collect historical load data of the distribution network, such as historical load data. Figure 4 As shown.

[0080] (5) Calculate μ at each time point in autumn L and σ L The values ​​are shown in Table 2.

[0081] Table 2 μ at various times L and σ L value

[0082]

[0083] (6) Conduct Monte Carlo sampling of the current season's load. When the sample size is 500, the load sampling data is as follows: Figure 5 As shown.

[0084] (7) Taking 10:00 AM as an example, the historical autumn electricity sales volume G from 9:30 AM to 10:30 AM. 10 Historical autumn solar power output P from 9:30 to 10:30 V,10 Historical autumn load P from 9:30 to 10:30 L,10 Using the input features of the BP neural network, a BP neural network model was built, and the line loss of historical autumn hours from 9:30 to 10:30 was used as the output result to train the BP neural network.

[0085] (8) Based on historical autumn sales volume G from 9:30 to 10:30 10 The photovoltaic output sampling data from step (3) and the load sampling data from step (6) are used as input features and input into the BP neural network trained in step (7) to calculate 500×500 predicted line loss results P for 9:30-10:30 in autumn. Loss,10,m (m=1, 2, …500×500), calculate the predicted line loss rate P according to formula (8). Loss,10,m %(m=1,2,…500×500);

[0086] (9) Plot the frequency distribution curve of the predicted line loss rate from 9:30 to 10:30 in autumn, as shown below. Figure 6 As shown. By Figure 6 It can be seen that the predicted line loss rate during the autumn period from 9:30 to 10:30 is concentrated at 3.75%, and the fluctuation range of the line loss rate caused by the uncertainty of photovoltaic output and load is [3.30%, 4.20%]. A line loss rate less than 3.30% or more than 4.20% can be identified as an abnormal line loss rate, and an investigation into the abnormal line loss should be carried out.

[0087] Example 2

[0088] A computer terminal device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling as described in Embodiment 1.

[0089] Example 3

[0090] A computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the active distribution network line loss rate threshold determination method based on photovoltaic and load uncertainty modeling as described in Example 1.

[0091] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this disclosure all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0092] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0093] This disclosure is intended to provide implementation schemes for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0094] The acquisition, transmission, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of national laws and regulations.

[0095] It should be noted that in the embodiments disclosed herein, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary and are intended only to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used such solutions.

[0096] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0097] Furthermore, 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. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0098] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0099] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0100] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0101] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0102] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0103] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling, characterized in that: The method includes the following steps: Step S1: Collect historical solar irradiance data for the area where the distribution network is located, classify it according to the four seasons, sample the solar irradiance of the current season to obtain N1 solar irradiance samples, and calculate N1 photovoltaic outputs based on the N1 solar irradiance samples. Step S2: Collect historical load data of the distribution network, classify it according to the four seasons, and sample the load of the current season to obtain N2 load samples; Step S3: Use the historical electricity sales, photovoltaic output, and load of each time period in the current season as input features of the BP neural network to train the BP neural network model. Step S4: Input the electricity sales data for each time period of the current season, the N1 photovoltaic output sampling data generated in step S1, and the N2 load sampling data generated in step S2 into the trained BP neural network to calculate the N1×N2 predicted line loss results for each time period of the current season, and calculate the line loss rate. S5: Plot the frequency distribution curves of line loss rate for each time period in the current season, and determine the minimum and maximum values ​​of line loss rate, which are the loss rate thresholds for active distribution network line loss rate for each time period in the previous season.

2. The method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling as described in claim 1, characterized in that: The classification method for the historical solar intensity data of the distribution network area collected in step S1 is as follows: spring is from March to May; summer is from June to August; autumn is from September to November; and winter is from December to February. It is assumed that the solar intensity at each time point in the four seasons follows a Beta distribution.

3. The method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling according to claim 2, characterized in that: In step S1, it is assumed that the mean of solar radiation intensity at each time point in the four seasons is μ, and the variance of solar radiation intensity is σ. 2 Calculate the α and β parameters of the Beta distribution.

4. The method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling as described in claim 3, characterized in that: The sampling method in step S1 is Monte Carlo sampling, which includes the following steps: (a) Discretize the Beta probability density distribution for the current season and calculate the cumulative probability distribution function F(r); (b) Generate N1 random numbers y1, y2, ... y1 in the value space [0, 1] of the cumulative probability distribution function F(r). N1 ; (c) Generate N1 random numbers y1, y2, ... y N1 Substituting the inverse function F of the cumulative probability distribution function -1 (r), to obtain N1 solar radiation intensities r k1 =F -1 (y k1 ), k1=1,2,…N1, and calculate the photovoltaic output at each time point of the current season based on the solar radiation intensity.

5. The method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling according to claim 4, characterized in that: The photovoltaic output is denoted as P. V,k1 The calculation formula is: Where k1 = 1, 2, ..., N1, P Vm For photovoltaic installed capacity, r b This represents the saturation value of photovoltaic solar irradiance.

6. The method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling according to claim 1, characterized in that: The classification method for the historical load data of the distribution network collected in step S2 is as follows: spring is from March to May; summer is from June to August; autumn is from September to November; and winter is from December to February, and it is assumed that the load at each time point in the four seasons follows a normal distribution.

7. The method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling according to claim 6, characterized in that: The sampling method in step S2 is Monte Carlo sampling, which includes the following steps: (a) Discretize the normal probability density distribution of the current season and calculate the cumulative probability distribution function F(P). L ); (b) In the cumulative probability distribution function F(P) L Generate N2 random numbers y1, y2, ... y from the value space [0, 1]. N2 ; (c) Generate N2 random numbers y1, y2, ... y N2 Substituting the inverse function F of the cumulative probability distribution function -1 (P L ), thus obtaining N2 loads P L,k2 =F -1 (y k2 ), k2=1,2,…N2.

8. The method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling according to claim 1, characterized in that: In the training process of the BP neural network model in step S3, the line loss of each time period of the current season is used as the output result. The input features and the output result are used as the dataset. The dataset is divided into a training set and a test set. The training set accounts for 90% of the dataset, and the test set accounts for 10% of the dataset. The training set is used to train the parameters of the BP neural network, and the test set is used to test the prediction accuracy of the BP neural network.

9. The method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling according to claim 1, characterized in that: In step S4, the line loss rate is denoted as P. Loss,j,m The calculation formula is: Among them, G j Let j = 1, 2, ... 24, m = 1, 2, ... N1 × N2.

10. A computer terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the method for determining the line loss rate threshold of an active distribution network based on photovoltaic and load uncertainty modeling as described in any one of claims 1-9.

Images