Distribution line equivalent impedance parameter optimization method based on large model and PSO

By combining large models and PSO algorithms, the impedance parameters of distribution lines are optimized, and the problems of complex calculations, large errors and limited equipment configuration in the existing technology are solved, and efficient and applicable equivalent impedance parameters are achieved, which is suitable for multiple networks distribution lines with frame structure.

CN118940618APending Publication Date: 2024-11-12GUANGZHOU YOUTONG ENERGY TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410964653.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The prior art has problems such as complex calculation, large error, high cost and limited equipment configuration in the acquisition of power distribution line impedance parameters, and is especially suitable for power transmission networks but not for power distribution networks.

Method used

Using a simulation model based on large model and particle swarm optimization algorithm (PSO) combined with simulation model, data preprocessing is performed by obtaining the topological structure and operation data of the target distribution line, using the large model to extract the wire table to adjust, and using the PSO algorithm to perform simulation model The impedance parameters are optimized to obtain equivalent impedance parameters.

Benefits of technology

It simplifies data acquisition and processing, improves computing efficiency, reduces errors, and is suitable for distribution lines of multiple grid structures, reducing operational complexity and cost.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940618A_ABST
    Figure CN118940618A_ABST
Patent Text Reader

Abstract

The invention discloses a distribution line equivalent impedance parameter optimization method based on a large model and PSO. The method comprises the following steps: obtaining a first topological structure, first operation data and a report document of a target distribution line; performing data preprocessing on the first topological structure and the first operation data of the target distribution line to obtain a second topological structure and second operation data; reading the report document by using the large model to obtain a to-be-adjusted lead table; constructing a simulation model of the target distribution line based on the second topological structure; optimizing the impedance parameter of the simulation model by using a PSO algorithm to obtain an equivalent impedance parameter; according to the method, the obtained information of the target distribution line is utilized to construct the large model and the simulation model, the to-be-adjusted wire table is obtained, the to-be-adjusted wire table and the simulation model are combined, the PSO algorithm is utilized, the impedance parameters are continuously optimized to obtain the equivalent impedance parameters, and the method is suitable for target distribution lines of various grid structures.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power system operation control, and in particular to a distribution line equivalent impedance parameter optimization method based on a large model and PSO. Background Art

[0002] Particle Swarm Optimization (PSO) is an optimization tool based on swarm intelligence.

[0003] Big models are currently cutting-edge application technologies. They simulate human understanding, reasoning, and creativity by learning massive data sets, and are widely used in natural language processing, image recognition, decision support, and other fields.

[0004] The distribution network, as a key link to ensure the transmission of electricity to end users, faces challenges such as natural wear and tear and urban construction interference, which lead to aging of lines and reduced efficiency. These problems not only increase maintenance costs, but also affect the reliability of power supply and the stability of the entire power system.

[0005] The four main methods for obtaining line parameters include precise calculation method, approximate calculation method, impedance online measurement method and equivalent circuit calculation method. The precise calculation method is comprehensive but cumbersome and slow; the approximate calculation method is easy to operate but has large errors; the impedance online measurement method has high accuracy but high cost and complex operation; the equivalent circuit calculation method relies on a large amount of data and is suitable for transmission networks but is limited by the limited configuration of distribution network measurement equipment.

[0006] The invention patent with application number 201210442529.X discloses an online virtual measurement method for distribution line impedance. This method only uses the voltage and current information at the beginning and end of the line, but fails to make full use of the active power, reactive power, power factor and other information that can be collected at both ends of the line. It also uses complex numbers for calculation, and the calculation process is relatively complicated. The invention patent with application number 201410222105.1 discloses an online identification method for distribution line impedance. This method is different from 201210442529.X in that it uses the least squares method for calculation, but it also uses complex numbers for calculation, and it still needs to collect data at the beginning and end of each wire segment, which is difficult to implement. Summary of the invention

[0007] In order to overcome the shortcomings of the above-mentioned prior art, the present invention proposes a distribution line equivalent impedance parameter optimization method based on a large model and PSO. The present invention uses the information of the target distribution line obtained to construct a large model and a simulation model to obtain a table of conductors that need to be adjusted. The impedance parameters are continuously optimized by combining the table of conductors that need to be adjusted and the simulation model using the PSO algorithm to obtain equivalent impedance parameters, which is suitable for target distribution lines with various grid structures.

[0008] In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical scheme:

[0009] A distribution line equivalent impedance parameter optimization method based on a large model and PSO, the method comprising the following steps:

[0010] S1. Obtaining a first topology structure, a first operation data and a report document of a target distribution line;

[0011] S2. Preprocess the first topology and the first operation data of the target distribution line to obtain a second topology and a second operation data;

[0012] S3. Use the large model to read the report document and obtain the wire table that needs to be adjusted;

[0013] S4. Constructing a simulation model of the target distribution line based on the second topology;

[0014] S5. Use the PSO algorithm to optimize the impedance parameters of the simulation model and obtain equivalent impedance parameters.

[0015] In a further preferred embodiment of the technical solution of the present invention, the first topological structure is used to describe the connection relationship between the devices of the target distribution line, the devices of the target distribution line include substations, conductors, switches, and distribution transformers, the first topological structure includes parameters and user information of the devices of the target distribution line, and the user information includes user number information;

[0016] The first operation data includes five types of data at the head end of the target distribution line and multiple time sections of each node: current, voltage, active power, reactive power and power factor.

[0017] Each node is a target power distribution line device installed with a measurement device;

[0018] The report documents include fault analysis report, problem analysis report, technical improvement plan report, engineering design report and engineering completion report of the target distribution line.

[0019] In a further preferred embodiment of the technical solution of the present invention, in step S2, preprocessing the first topology structure of the target distribution line to obtain a second topology structure comprises the following steps:

[0020] AS1. Check the length and model information of each wire and whether the user number information of each transformer is missing;

[0021] AS2. For wires with missing length information, the length information is calculated using the longitude and latitude coordinates of the wire's first and last endpoints;

[0022] AS3. For the wire without model information, search for the previous wire. If the previous wire has model information, fill the model information of the previous wire into the wire. If not, continue to search for the previous wire of the previous wire until the model information of the wire is found and filled into the wire.

[0023] AS4. For transformers that are missing user numbers, find the corresponding user in the first operation data according to the transformer name, and fill the user number of the user into the transformer.

[0024] In a further preferred embodiment of the technical solution of the present invention, in step S2, preprocessing the first operation data of the target distribution line to obtain the second operation data comprises the following steps:

[0025] BS1. Convert the reading values ​​in the first operation data to the real values;

[0026] BS2. For the five data of the time section of each node, if one of the data is missing, use the missing data to estimate, otherwise execute S3;

[0027] BS3. Fill in the missing data of the same type at different time sections of each node, as follows:

[0028] The same type of missing data at different time sections of each node are arranged in chronological order, and the proportion of missing values ​​is calculated. If the proportion of missing values ​​is less than the first threshold, linear interpolation is used to fill the missing values. Otherwise, the mean of the non-missing data is used to fill the missing values.

[0029] In a further preferred embodiment of the technical solution of the present invention, in step S3, the report document is read by using a large model to obtain a list of conductors to be adjusted, specifically as follows: the report document includes multiple texts, the multiple texts are filled into a first prompt, the first prompt is submitted to the first large model to obtain the output of the first large model, and the table output by the first large model is a total list of conductor repair and test records;

[0030] The conductor repair and testing record summary table is filled into the second prompt, and the second prompt is submitted to the second largest model to obtain the output of the second largest model; the output of the second largest model is the conductor list that needs to be adjusted, which includes the conductor name information, modification record information and positive and negative information.

[0031] Further optimization of the technical solution of the present invention is as follows: the PSO algorithm described in step S5 optimizes the impedance parameters of the simulation model:

[0032] Generate a particle swarm containing N particles, and the position of particle i is represented by a D-dimensional vector x i =(x i1 , x i2 , ..., xiD )=(resistance i1 , reactance i1 ,resistance i2 , reactance i2 ,…,resistance iN , reactance iN ), and give each particle a random speed v i =(v i1 , v i2 , ..., v iD ),resistance in , reactance in is the resistance and reactance of wire n corresponding to particle i, and D is twice the number of wires N;

[0033] During each iteration, the fitness function value corresponding to the current position of each particle in the particle swarm is evaluated. The fitness function value is the average voltage error rate of all nodes obtained after substituting the current position of each particle into the simulation model;

[0034] Determine whether the current particle swarm meets the convergence condition. If it does, output the current position of each particle. If not, continue to update the speed and position of each particle.

[0035] The convergence condition is: the proportion of benign particles in the current particle swarm exceeds the third threshold, and benign particles are particles whose fitness function value is lower than the second threshold;

[0036] Speed ​​update formula:

[0037]

[0038] Position update formula:

[0039]

[0040] is the velocity of particle i in the dth dimension when it performs t iterations;

[0041] is the velocity of particle i in the dth dimension when it performs t+1 iterations;

[0042] is the position of particle i in the dth dimension when it performs t iterations;

[0043] is the position of particle i in the dth dimension when it performs t+1 iterations;

[0044] gbest id is the historical optimal position of particle i in the dth dimension, d = 1, 2, …, D;

[0045] gbest dis the historical optimal position of the particle swarm in the dth dimension, d = 1, 2, ..., D;

[0046] w is the inertia weight, which is used to control the influence of the previous iteration speed on the current speed;

[0047] c1, c2 are acceleration constants;

[0048] rand() and Rand() generate random numbers in the interval [0, 1] respectively;

[0049] h d is the directional coefficient of the dth dimension.

[0050] In a further preferred embodiment of the technical solution of the present invention, the average voltage error rate is obtained by substituting the position of particle i into the simulation model, performing simulation calculations, and obtaining the simulated voltage value of each node, and further calculating,

[0051] m is the number of nodes.

[0052] In a further embodiment of the technical solution of the present invention, the method further includes adjusting the simulation parameters of the simulation model by using the copper loss of the transformer winding, the iron loss of the transformer core and the transformer transformation ratio.

[0053] The distribution line equivalent impedance parameter optimization system based on a large model and PSO is characterized in that: the system includes a data acquisition module, a data processing module, a large model module, a simulation module and a PSO module;

[0054] The data acquisition module is used to acquire the first topological structure and the first operation data;

[0055] The data processing module is used to pre-process the first topological structure and the first operating data to obtain a second topological structure and second operating data;

[0056] The large model module is used to obtain the wire list that needs to be adjusted based on the report document;

[0057] The simulation module is used to establish a simulation model of the target distribution line based on the second topology structure to perform simulation and obtain corresponding simulation parameters;

[0058] The PSO module is used to optimize the impedance parameters of the simulation model using the PSO algorithm to obtain equivalent impedance parameters.

[0059] An electronic device comprises a processor and a memory, wherein the memory stores a computer program that can be run on the processor, and the processor executes the steps of the above method when running the computer program.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] 1. In the present invention, the first topological structure, the first operating data and the report document of the target distribution line can be directly derived from the existing system, and the data acquisition is simple.

[0062] 2. The present invention uses the powerful semantic understanding ability of the large model to replace human work, extract the repair and test records of the conductors from numerous line report documents, automatically determine the impact of the repair and test records on the conductor impedance, determine the directional coefficient, guide the update direction of the PSO algorithm, and accelerate the convergence speed.

[0063] 3. The present invention uses the equivalent impedance of the conductor of the target distribution line as the particle position of the PSO algorithm for iterative optimization, and the process is easy to implement and has good practicality.

[0064] 4. The present invention converts equivalent impedance parameters into vector quantization without being restricted by grid structure, and is applicable to target distribution lines with various structures such as single radiation, ring, star, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flow chart of the method for optimizing equivalent impedance parameters of power distribution lines based on a large model and PSO of the present invention;

[0066] Figure 2 It is a first topology structure preprocessing flow chart of the power distribution line equivalent impedance parameter optimization method based on a large model and PSO of the present invention;

[0067] Figure 3 It is a first operation data preprocessing flow chart of the distribution line equivalent impedance parameter optimization method based on a large model and PSO of the present invention;

[0068] Figure 4 It is a PSO algorithm iteration flow chart of the distribution line equivalent impedance parameter optimization method based on a large model and PSO of the present invention;

[0069] Figure 5 This is an example diagram of a target distribution line of the distribution line equivalent impedance parameter optimization method based on a large model and PSO of the present invention. DETAILED DESCRIPTION

[0070] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the specific embodiments of the present invention are further described in detail below with reference to the accompanying drawings.

[0071] The four main methods for obtaining line parameters include precise calculation method, approximate calculation method, impedance online measurement method and equivalent circuit calculation method. The precise calculation method is comprehensive but cumbersome and slow; the approximate calculation method is easy to operate but has large errors; the impedance online measurement method has high accuracy but high cost and complex operation; the equivalent circuit calculation method relies on a large amount of data and is suitable for transmission networks but is limited by the limited configuration of distribution network measurement equipment.

[0072] Based on the above considerations, the present invention provides a distribution line equivalent impedance parameter optimization method based on a large model and PSO, such as Figure 1 As shown, the method comprises the following steps:

[0073] S1. Obtaining a first topology structure, a first operation data and a report document of a target distribution line;

[0074] S2. Preprocess the first topology and the first operation data of the target distribution line to obtain a second topology and a second operation data;

[0075] S3. Use the large model to read the report document and obtain the wire table that needs to be adjusted;

[0076] S4. Constructing a simulation model of the target distribution line based on the second topology;

[0077] S5. Use the PSO algorithm to optimize the impedance parameters of the simulation model and obtain equivalent impedance parameters.

[0078] The first topological structure in step S1 is used to describe the connection relationship between the various devices of the target distribution line. The various devices of the target distribution line include substations, conductors, switches, and distribution transformers; the conductors include overhead conductors and cables, and the switches include load switches, knife switches, circuit breakers, and other devices used to disconnect distribution lines.

[0079] The carrier of the first topology structure is generally an image file or a text file; the image file is generally called a line single-line diagram, and common file formats include PDF, SVG, JPG or PNG; the text file is generally called a line CIM file, and a common file format is XML.

[0080] The first topology structure includes parameters of each device of the target distribution line and user information, and the user information includes user number information.

[0081] The first operation data in step S1 includes the current, voltage, active power, reactive power and power factor of the head end and each node of the target distribution line for a total of 96 time sections in one day; that is, it is recorded every 15 minutes starting from 00:00.

[0082] Each node is a target power distribution line device installed with a measurement device.

[0083] The report documents in step S1 include a fault analysis report, a problem analysis report, a technical improvement plan report, an engineering design report, a project completion report, etc. of the target distribution line.

[0084] The report document is in text format.

[0085] like Figure 2 As shown, in step S2, preprocessing the first topology structure of the target distribution line to obtain a second topology structure includes the following steps:

[0086] AS1. Check the length and model information of each wire and whether the user number information of each transformer is missing;

[0087] AS2. For wires with missing length information, the length information is calculated using the longitude and latitude coordinates of the wire's first and last endpoints;

[0088] AS3. For the wire without model information, search for the previous wire. If the previous wire has model information, fill the model information of the previous wire into the wire. If not, continue to search for the previous wire of the previous wire until the model information of the wire is found and filled into the wire.

[0089] AS4. For transformers that are missing user numbers, find the corresponding user in the first operation data according to the transformer name, and fill the user number of the user into the transformer.

[0090] For example, in the first topology structure, the name of a transformer with a missing user number is "Hebian Public Transformer". In the first operation data, a user's user name is "Hebian Public Transformer". The two names are different but have been manually confirmed to belong to the same transformer. The user name of "Hebian Public Transformer" in the first operation data can be filled in the "Hebian Public Transformer" transformer in the first topology structure.

[0091] like Figure 3 As shown, in step S2, data preprocessing is performed on the first operation data of the target distribution line to obtain second operation data, including the following steps:

[0092] BS1. Convert the reading values ​​in the first operation data to the real values;

[0093] BS2. For the five data of the time section of each node, if one of the data is missing, use the missing data for estimation, otherwise execute S3;

[0094] BS3. Fill in the missing data of the same type in different time sections of each node;

[0095] Step BS1 is converted into a real value by the following calculation formula:

[0096] The actual value of current = current reading value × CT ratio. The CT ratio is the ratio of the current on the primary side to the secondary side of the current transformer.

[0097] The actual value of voltage = voltage reading value × PT ratio, where PT is the ratio of the primary side voltage to the secondary side voltage of the voltage transformer;

[0098] The actual value of active power = active power reading value × CT ratio × PT ratio;

[0099] The actual value of five-phase reactive power = reactive power reading value × CT ratio × PT ratio.

[0100] Step BS2 fills in the missing data of the same type in different time sections of each node; the details are as follows:

[0101] The five data of the simultaneous cross section of each node are current, voltage, active power, reactive power and power factor.

[0102] Among the five data of current, voltage, active power, reactive power and power factor, voltage, active power and reactive power are necessary data for simulation calculation. They can be estimated from each other through formulas according to the missing data of the five data in the same time section. The formula is as follows:

[0103] Active power = current × voltage × power factor,

[0104]

[0105] That is, if active power or reactive power is missing, but current, voltage, and power factor are known, the corresponding active power or reactive power value can be estimated by calculation through the formula; if voltage is missing, but current, active power, power factor or current, reactive power, and power factor are known, the corresponding voltage can be estimated by calculation through the formula; if current or power factor is missing, but active power, reactive power, and voltage are known, the corresponding current or power factor can be estimated by calculation through the formula.

[0106] Step BS3 fills in the missing data of the same type in different time sections of each node, as follows:

[0107] Data of the same data type in each node, such as current data of all time sections of a node, voltage data of all time sections of a certain electromechanical device, etc.

[0108] The missing data of the same data type at different time sections of each node are arranged in chronological order, and the missing value ratio is calculated. If the missing value ratio is less than the first threshold, linear interpolation is used to fill the missing value. Otherwise, the mean of the non-missing data is used to fill the missing value. The missing value ratio calculation formula is:

[0109]

[0110] The total number of time points refers to the number of time sections included in the first operating data, and the first threshold is set to 10%.

[0111] In step S3, the report document is read using the large model to obtain the wire table that needs to be adjusted, as follows:

[0112] Fill the text of the report document into the first prompt, submit the first prompt to the first large model and obtain the output of the first large model. According to the different capabilities of different large models, the amount of text that can be filled in at one time is different. Therefore, multiple first prompt submissions may be made to obtain multiple first large model outputs. The tables of multiple first large model outputs are sorted and merged to obtain the wire repair and test record summary table, which includes the wire name and repair and test record.

[0113] Fill the second prompt with the conductor repair and testing record summary table, submit the second prompt to the second largest model and obtain the second largest model output; the second largest model output is the conductor list that needs to be adjusted, which includes the conductor name that needs to be adjusted, the repair and testing record, and the positive and negative properties.

[0114] After the information in the conductor repair and test summary table is obtained by the large model and the second large model output, the conductor name in the conductor repair and test summary table is renamed as the conductor name to be adjusted, and positive and negative information is added. The positive and negative information is judged based on the conductor name and the repair and test record corresponding to the conductor name to determine whether the impedance of the conductor is larger, smaller or normal compared to the normal situation. If it is larger, it is "True", and if it is smaller, it is "False".

[0115] The simulation model in step S4 may be a target distribution line simulation model constructed by various simulation software.

[0116] The method also includes adjusting simulation parameters of the simulation model using the copper loss of the transformer winding, the iron loss of the transformer core and the transformer ratio.

[0117] The PSO algorithm described in step S5 optimizes the impedance parameters of the simulation model as follows:

[0118] Generate a particle swarm containing N particles, and the position of particle i is represented by a D-dimensional vector x i =(x i1 , x i2 , ..., x iD )=(resistance i1 , reactance i1 ,resistance i2 , reactance i2 ,…,resistance iN , reactance iN ), and give each particle a random speed vi =(v i1 , v i2 , ..., v iD ),resistance in , reactance in is the resistance and reactance of wire n corresponding to particle i, and D is twice the number of wires N.

[0119] During each iteration, the fitness function value corresponding to the current position of each particle is evaluated. The fitness function value is the average voltage error rate of all nodes obtained after substituting the current position of each particle into the simulation model;

[0120] The average voltage error rate is obtained by substituting the position of particle i into the simulation model, performing simulation calculations, and obtaining the simulated voltage value of each node.

[0121]

[0122]

[0123] m is the number of nodes.

[0124] Determine whether the current particle swarm and the particles in the particle swarm meet the convergence conditions. If they do, output the current position of each particle in the particle swarm, which is the equivalent impedance parameter of the wire corresponding to the particle in the particle swarm. If not, iteratively update the particles in the particle swarm.

[0125] The convergence condition is: the proportion of benign particles in the particle group exceeds the third threshold, and the benign particles are particles whose fitness function value is lower than the second threshold; generally, the second threshold is set to 1% and the third threshold is set to 90%.

[0126] The particle iterative update process is as follows:

[0127] The speed update formula and position update formula are used to iteratively update the position of the particle. The speed update formula is:

[0128]

[0129] Position update formula:

[0130]

[0131] is the velocity of particle i in the dth dimension when it performs t iterations;

[0132] is the velocity of particle i in the dth dimension when it performs t+1 iterations;

[0133] is the position of particle i in the dth dimension when it performs t iterations;

[0134] is the position of particle i in the dth dimension when it performs t+1 iterations;

[0135] pbest id is the historical optimal position of particle i in the dth dimension, that is, the position of particle i when the fitness function value of particle i is the lowest after multiple iterations, d = 1, 2, ..., D;

[0136] gbest d is the historical optimal position of the particle swarm in the dth dimension, that is, the position of the particle with the lowest fitness function value in the particle swarm after multiple iterations, d = 1, 2, ..., D;

[0137] w is the inertia weight, which is used to control the influence of the previous iteration speed on the current speed;

[0138] c1, c2 are acceleration constants, usually c1 = c2 = 2.0;

[0139] rand() and Rand() generate random numbers in the interval [0, 1] respectively;

[0140] h d It is the directional coefficient of the dth dimension. The value is randomly generated between [0.001, 0.1]. The positive and negative signs are determined according to the positive and negative information of the wire table to be adjusted.

[0141] like Figure 5 A target distribution line is shown, in which the nodes are automatic switches K1, K2; distribution transformers T1, T2, T3; and the wires are as follows: [line head end-K1, K1-F1, F1-F2, F2-T1, F2-F3, F3-F4, F4-T3, F3-K2, K2-F5, F5-F6, F6-T2], with a total of 11 sections of wires.

[0142] Therefore, the 22-dimensional vector x i Corresponding to an equivalent impedance parameter of the target distribution line.

[0143] x i =(x i1 , x i2 , ..., x i21 , x i22 );

[0144] According to the list of conductors that need to be adjusted, the following information can be found: Name of conductor that needs to be adjusted: [F1-F2, F4-F3]; Repair and test record: [The conductor insulation was broken and then repaired by wrapping, and a new conductor of the same line type was replaced]; Positive and negative: [False, True].

[0145] Then, for the wire F1-F2, the corresponding vector x iThe 5th and 6th dimensions, that is, h5 and h6, are negative; for wire F4-T3, the corresponding vector x i The 13th and 14th dimensions in h 13 and h 14 The sign of is positive.

[0146] A distribution line equivalent impedance parameter optimization system based on a large model and PSO, the system comprising a data acquisition module, a data processing module, a large model module, a simulation module and a PSO module;

[0147] The data acquisition module is used to acquire the first topological structure and the first operation data;

[0148] The data processing module is used to pre-process the first topological structure and the first operating data to obtain a second topological structure and second operating data;

[0149] The large model module is used to obtain the wire list that needs to be adjusted based on the report document;

[0150] The simulation module is used to establish a simulation model of the target distribution line based on the second topology structure to perform simulation and obtain corresponding simulation parameters;

[0151] The PSO module is used to optimize the impedance parameters of the simulation model using the PSO algorithm to obtain equivalent impedance parameters;

[0152] like Figure 4 As shown in Figure 2, the iterative process of the PSO algorithm is as follows:

[0153] DS1, execution initialization unit;

[0154] DS2, executive assessment unit;

[0155] DS3, execution update unit;

[0156] DS4, execute the termination unit. If the convergence conditions are met, obtain the output and the equivalent impedance parameters. Otherwise, continue with DS2.

[0157] The parts not involved in the present invention are the same as the prior art or can be implemented by using the prior art.

[0158] As described above, although the present invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the present invention itself. Various changes in form and details may be made without departing from the spirit and scope of the present invention as defined in the appended claims.

Claims

1. A distribution line equivalent impedance parameter optimization method based on a large model and PSO, characterized by: The method comprises the following steps: S1. Obtaining a first topology structure, a first operation data and a report document of a target distribution line; S2. Preprocess the first topology and the first operation data of the target distribution line to obtain a second topology and a second operation data; S3. Use the large model to read the report document and obtain the wire table that needs to be adjusted; S4. Constructing a simulation model of the target distribution line based on the second topology; S5. Use the PSO algorithm to optimize the impedance parameters of the simulation model and obtain equivalent impedance parameters.

2. The method for optimizing equivalent impedance parameters of distribution lines based on a large model and PSO according to claim 1 is characterized in that: The first topology structure is used to describe the connection relationship between the devices of the target distribution line. The devices of the target distribution line include substations, conductors, switches, and distribution transformers. The first topology structure includes parameters and user information of the devices of the target distribution line. The user information includes user number information. The first operation data includes five types of data at the head end of the target distribution line and multiple time sections of each node: current, voltage, active power, reactive power and power factor. Each node is a target power distribution line device installed with a measurement device; The report documents include fault analysis report, problem analysis report, technical improvement plan report, engineering design report and engineering completion report of the target distribution line.

3. The method for optimizing equivalent impedance parameters of distribution lines based on a large model and PSO according to claim 2 is characterized in that: In step S2, preprocessing the first topology structure of the target distribution line to obtain a second topology structure includes the following steps: AS1. Check the length and model information of each wire and whether the user number information of each transformer is missing; AS2. For wires with missing length information, the length information is calculated using the longitude and latitude coordinates of the wire's first and last endpoints; AS3. For the wire without model information, search for the previous wire. If the previous wire has model information, fill the model information of the previous wire into the wire. If not, continue to search for the previous wire of the previous wire until the model information of the wire is found and filled into the wire. AS4. For transformers that are missing user ID information, find the corresponding user in the first operation data according to the transformer name, and fill the user ID information of the user into the transformer.

4. The method for optimizing equivalent impedance parameters of distribution lines based on a large model and PSO according to claim 3 is characterized in that: In step S2, data preprocessing is performed on the first operation data of the target distribution line to obtain second operation data, which includes the following steps: BS1. Convert the reading values ​​in the first operation data to the real values; BS2. For the five data of the time section of each node, if one of the data is missing, use the missing data for estimation, otherwise execute BS3; BS3. Fill in the missing data of the same type at different time sections of each node, as follows: The same type of missing data at different time sections of each node are arranged in chronological order, and the proportion of missing values ​​is calculated. If the proportion of missing values ​​is less than the first threshold, linear interpolation is used to fill the missing values. Otherwise, the mean of the non-missing data is used to fill the missing values.

5. The method for optimizing equivalent impedance parameters of distribution lines based on a large model and PSO according to claim 4 is characterized in that: In step S3, the report document is read by the large model to obtain a list of conductors to be adjusted, which is as follows: the report document includes multiple texts, the multiple texts are filled into the first prompt, the first prompt is submitted to the first large model to obtain the output of the first large model, and the table output by the first large model is a total list of conductor repair and test records; The conductor repair and test record summary table is filled into the second prompt, and the second prompt is submitted to the second largest model to obtain the output of the second largest model; the output of the second largest model is the conductor list that needs to be adjusted, which includes the name information of the conductor that needs to be adjusted, the modification record information and the positive and negative information.

6. The method for optimizing equivalent impedance parameters of distribution lines based on a large model and PSO according to claim 5 is characterized in that: The PSO algorithm described in step S5 optimizes the impedance parameters of the simulation model as follows: Generate a particle swarm containing N particles, and the position of particle i is represented by a D-dimensional vector x i =(x i1 , x i2 , ..., x iD )=(resistance i1 , reactance i1 ,resistance i2 , reactance i2 ,…,resistance iN , reactance iN ), and give each particle a random speed v i =(v i1 , v i2 , ..., v iD ),resistance in , reactance in is the resistance and reactance of wire n corresponding to particle i, and D is twice the number of wires N; During each iteration, the fitness function value corresponding to the current position of each particle in the particle swarm is evaluated. The fitness function value is the average voltage error rate of all nodes obtained after substituting the current position of each particle into the simulation model. Determine whether the current particle swarm meets the convergence condition. If it does, output the current position of each particle. If not, continue to update the speed and position of each particle. The convergence condition is: the proportion of benign particles in the current particle swarm exceeds the third threshold, and benign particles are particles whose fitness function value is lower than the second threshold; Speed ​​update formula: Position update formula: is the velocity of particle i in the dth dimension when it performs t iterations; is the velocity of particle i in the dth dimension when it performs t+1 iterations; is the position of particle i in the dth dimension when it performs t iterations; is the position of particle i in the dth dimension when it performs t+1 iterations; pbest id is the historical optimal position of particle i in the dth dimension, d = 1, 2, …, D; gbest d is the historical optimal position of the particle swarm in the dth dimension, d = 1, 2, ..., D; w is the inertia weight, which is used to control the influence of the previous iteration speed on the current speed; c1, c2 are acceleration constants; rand() and Rand() generate random numbers in the interval [0, 1] respectively; h d is the directional coefficient of the dth dimension.

7. The method for optimizing equivalent impedance parameters of distribution lines based on a large model and PSO according to claim 6 is characterized in that: The average voltage error rate is obtained by substituting the position of particle i into the simulation model, performing simulation calculations, and obtaining the simulated voltage value of each node. m is the number of nodes.

8. The method for optimizing equivalent impedance parameters of distribution lines based on a large model and PSO according to claim 7 is characterized in that: The method also includes adjusting simulation parameters of the simulation model using the copper loss of the transformer winding, the iron loss of the transformer core and the transformer ratio.

9. The distribution line equivalent impedance parameter optimization system based on large model and PSO is characterized by: The system includes a data acquisition module, a data processing module, a large model module, a simulation module and a PSO module; The data acquisition module is used to acquire the first topological structure and the first operation data; The data processing module is used to pre-process the first topological structure and the first operating data to obtain a second topological structure and second operating data; The large model module is used to obtain the wire list that needs to be adjusted based on the report document; The simulation module is used to establish a simulation model of the target distribution line based on the second topology structure to perform simulation and obtain corresponding simulation parameters; The PSO module is used to optimize the impedance parameters of the simulation model using the PSO algorithm to obtain equivalent impedance parameters.

10. An electronic device comprising a processor and a memory, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor runs the computer program, the steps of the method according to any one of claims 1 to 8 are performed.