A method and system for predicting air gap discharge voltage of DC transmission line

Abstract

The present invention discloses a method and system for predicting the discharge voltage of the air gap of a DC transmission line, and belongs to the field of high voltage and insulation technology. The method of the present invention comprises: for a DC transmission line, obtaining basic information data of the DC transmission line, and conducting a discharge test of the gap at the tower head of the DC transmission line pole tower, obtaining characteristic data of the gap discharge, training the basic information data and the characteristic data, and obtaining a training model; obtaining basic information data of the DC transmission line to be tested, and inputting it into the training model to obtain output data, and the output data is the discharge voltage of the air gap of the DC transmission line. Compared with the traditional method for calculating the discharge voltage of the gap at the tower head of the pole tower, the present invention has higher prediction accuracy, does not require cumbersome calculation procedures, and only needs to input the size of the grading ring, meteorological parameters, tower width, and gap distance to achieve the prediction of the breakdown voltage.

Description

Technical Field

[0001] The present invention relates to the field of high voltage and insulation technology, and more specifically, to a method and system for predicting air gap discharge voltage of a direct current transmission line. Background Art

[0002] The current situation of extremely unbalanced energy distribution and economic development in my country has led to the need for my country to develop ultra-high voltage transmission projects to transport the power resources in the west to the economically developed eastern region. Ultra-high voltage transmission projects have the characteristics of large transmission capacity, long transmission lines, and high voltage levels, which brings major challenges to the insulation configuration of ultra-high voltage transmission projects. The air gap is the main form of external insulation for ultra-high voltage transmission lines. The discharge characteristics of the air gap at the head of the transmission line tower are an important basis for the external insulation design of ultra-high voltage transmission lines. The rationality of the external insulation design directly affects the economy and safety of the transmission and transformation project design.

[0003] The cross-regional interconnection transmission distance of ultra-high voltage overhead lines is long, and the climate change along the transmission project is complex. The size of the grading ring, the width of the tower body, the climate of the area where the tower is located, the altitude and other factors will affect the discharge of the tower head gap. Scientifically selecting the insulation level and reasonably determining the gap distance are the key issues in optimizing the external insulation design. At present, the breakdown voltage of the air gap of the tower head at home and abroad is mainly obtained through experimental methods, but the test cost is high and the cycle is long. Some scholars have proposed empirical formula fitting, physical model calculation and other methods to calculate the breakdown voltage of the air gap of the tower head based on a certain amount of discharge tests, but these methods currently have certain limitations.

[0004] The air gap discharge voltage of existing transmission line towers is generally obtained through experiments. For example, for ±800kV transmission lines, an operating impulse discharge test of a true-size tower head at an altitude of 55m was carried out, and the discharge characteristic curves of different gap distances were obtained. The discharge voltage under different gaps can be calculated through the curve.

[0005] The calculation of the discharge voltage under other meteorological conditions can be obtained by the meteorological or altitude correction method in the standard GB / T16927.1 or IEC60071-2, and by using the corresponding formula.

[0006] The existing technology mainly has the following disadvantages:

[0007] (1) Poor applicability. The voltage obtained is strictly dependent on parameters such as the size of the grading ring, the tower structure, and meteorological conditions. Changes in related parameters will cause large changes in voltage.

[0008] (2) The previous meteorological parameter correction method was a simple mathematical formula with poor calculation accuracy.

[0009] (3) The previous calculation method has poor altitude applicability and is only applicable to low-altitude areas. Summary of the invention

[0010] In view of the above problems, the present invention proposes a method for predicting the air gap discharge voltage of a DC transmission line, comprising:

[0011] For DC transmission lines, basic information data of DC transmission lines are obtained, and discharge tests of the gaps at the tower heads of DC transmission line towers are conducted to obtain characteristic data of gap discharges, and basic information data and characteristic data are trained to obtain training models;

[0012] The basic information data of the DC transmission line to be tested is obtained and input into the training model to obtain output data, where the output data is the discharge voltage of the air gap of the DC transmission line.

[0013] Optionally, different voltage levels and different meteorological conditions may be selected for the discharge test.

[0014] Optionally, obtain the training model, including:

[0015] The basic information data is used as training data, the characteristic data is used as output data, and the training data is normalized to obtain normalized data;

[0016] Input the normalized data into the SVR model, perform optimization processing, obtain the optimal parameters, and determine the optimal SVR model based on the optimal parameters

[0017] Perform integrated algorithm learning on the training data, output data and optimal SVR model to obtain the training model.

[0018] Optionally, training data, including: gap structure parameters and meteorological parameters;

[0019] The gap structure parameters include: the ring diameter and pipe diameter data of the high-pressure side equalizing ring, the gap distance and the tower width;

[0020] The meteorological parameters include: air pressure, air temperature and relative humidity of the air.

[0021] Optional, optimization processing, using the gray wolf algorithm to find the optimal solution. The specific process includes:

[0022] Initialize parameter positions, convergence factors, random vectors, and adaptation vectors, and use parameter positions to represent solutions;

[0023] Select the three sets of parameters with the smallest objective function value and save them as α, β, and δ in sequence;

[0024] The three sets of parameters are surrounded, hunted and attacked. After the processing is completed, the position of the gray wolf population, the convergence factor, the random vector and the adaptive vector are updated;

[0025] Update the positions of the three parameters α, β, and γ, and obtain the position of α through iteration, which is the optimal solution.

[0026] The present invention also proposes a prediction system for air gap discharge voltage of a DC transmission line, comprising:

[0027] The training module obtains basic information data of the DC transmission line, performs a discharge test on the gap at the tower head of the DC transmission line, obtains characteristic data of the gap discharge, trains the basic information data and characteristic data, and obtains a training model;

[0028] The prediction module obtains basic information data of the DC transmission line to be tested and inputs it into the training model to obtain output data, where the output data is the discharge voltage of the air gap of the DC transmission line.

[0029] Optionally, different voltage levels and different meteorological conditions may be selected for the discharge test.

[0030] Optionally, obtain the training model, including:

[0031] The basic information data is used as training data, the characteristic data is used as output data, and the training data is normalized to obtain normalized data;

[0032] Input the normalized data into the SVR model, perform optimization processing, obtain the optimal parameters, and determine the optimal SVR model based on the optimal parameters

[0033] Perform integrated algorithm learning on the training data, output data and optimal SVR model to obtain the training model.

[0034] Optionally, training data, including: gap structure parameters and meteorological parameters;

[0035] The gap structure parameters include: the ring diameter and pipe diameter data of the high-pressure side equalizing ring, the gap distance and the tower width;

[0036] The meteorological parameters include: air pressure, air temperature and relative humidity of the air.

[0037] Optional, optimization processing, using the gray wolf algorithm to find the optimal solution. The specific process includes:

[0038] Initialize parameter positions, convergence factors, random vectors, and adaptation vectors, and use parameter positions to represent solutions;

[0039] Select the three sets of parameters with the smallest objective function value and save them as α, β, and δ in sequence;

[0040] The three sets of parameters are surrounded, hunted and attacked. After the processing is completed, the position of the gray wolf population, the convergence factor, the random vector and the adaptive vector are updated;

[0041] Update the positions of the three parameters α, β, and γ, and obtain the position of α through iteration, which is the optimal solution.

[0042] Compared with the traditional tower head gap discharge voltage calculation method, the present invention has higher prediction accuracy and does not require complicated calculation procedures. It only needs to input the grading ring size, meteorological parameters, tower body width, and gap distance to realize the prediction of breakdown voltage. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flow chart of a method for predicting air gap discharge voltage of a DC transmission line according to the present invention;

[0044] Figure 2 This is a flow chart of an embodiment of a method for predicting air gap discharge voltage of a DC transmission line according to the present invention;

[0045] Figure 3 The present invention is a structural diagram of a prediction system for air gap discharge voltage of a DC transmission line. DETAILED DESCRIPTION

[0046] Now, exemplary embodiments of the present invention are described with reference to the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely and to fully convey the scope of the present invention to those skilled in the art. The terms used in the exemplary embodiments shown in the accompanying drawings are not intended to limit the present invention. In the accompanying drawings, the same units / elements are marked with the same reference numerals.

[0047] Unless otherwise specified, the terms (including technical terms) used herein have the commonly understood meanings to those skilled in the art. In addition, it is understood that the terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.

[0048] The present invention proposes a method for predicting the air gap discharge voltage of a DC transmission line. Figure 1 As shown, including:

[0049] For DC transmission lines, basic information data of DC transmission lines are obtained, and discharge tests of the gaps at the tower heads of DC transmission line towers are conducted to obtain characteristic data of gap discharges, and basic information data and characteristic data are trained to obtain training models;

[0050] The basic information data of the DC transmission line to be tested is obtained and input into the training model to obtain output data, where the output data is the discharge voltage of the air gap of the DC transmission line.

[0051] During the discharge test, different voltage levels and different meteorological conditions are selected.

[0052] Get the training model, including:

[0053] The basic information data is used as training data, the characteristic data is used as output data, and the training data is normalized to obtain normalized data;

[0054] Input the normalized data into the SVR model, perform optimization processing, obtain the optimal parameters, and determine the optimal SVR model based on the optimal parameters

[0055] Perform integrated algorithm learning on the training data, output data and optimal SVR model to obtain the training model.

[0056] Training data, including: gap structure parameters and meteorological parameters;

[0057] The gap structure parameters include: the ring diameter and pipe diameter data of the high-pressure side equalizing ring, the gap distance and the tower width;

[0058] The meteorological parameters include: air pressure, air temperature and relative humidity of the air.

[0059] Optimization process: using the gray wolf algorithm to optimize. The specific process includes:

[0060] Initialize parameter positions, convergence factors, random vectors, and adaptation vectors, and use parameter positions to represent solutions;

[0061] Select the three sets of parameters with the smallest objective function value and save them as α, β, and δ in sequence;

[0062] The three sets of parameters are surrounded, hunted and attacked. After the processing is completed, the position of the gray wolf population, the convergence factor, the random vector and the adaptive vector are updated;

[0063] Update the positions of the three parameters α, β, and γ, and obtain the position of α through iteration, which is the optimal solution.

[0064] The present invention will be further described below in conjunction with embodiments:

[0065] like Figure 2 As shown, including:

[0066] Step 1: Select the tower head gap operation impulse breakdown test data of ±1100kV, ±800kV, ±660kV, and ±500kV DC transmission line tower head gaps at different gap distances and under different meteorological conditions. In the process of selecting the training set, the training data is selected in a dispersed manner so that the training set contains as much meteorological conditions and tower head air gap structure information as possible.

[0067] Finally, the ring diameter of the grading ring at the high-voltage end of the tower, the tube diameter of the grading ring at the high-voltage end, the width of the tower body, the gap distance, air pressure, temperature, and relative humidity are used as input feature quantities, and the 50% discharge voltage of the gap at the tower head is used as the output feature quantity.

[0068] The input feature quantity and output feature quantity are normalized, and the expression is as follows:

[0069]

[0070] In the formula, x' i is the normalized value, x i is the value before normalization, x max and x min are the maximum and minimum values ​​of the feature data respectively.

[0071] Step 2: Establish optimization objective function;

[0072] Taking the mean square error of the output of the support vector regression (SVR) model as the optimization target, the following expression is established:

[0073]

[0074] Where n is the number of training data, y r is the output value of the rth training sample, y r* is the actual breakdown voltage of the rth training sample, f MSE is the objective function, and min. is the optimization for the minimum value of the objective function.

[0075] The process of optimizing support vector regression (SVR) by the Gray Wolf Algorithm is to find the parameters C and γ that minimize the mean square error value (objective function) of the SVR output and build the optimal SVR model.

[0076] Step 3, set the initial parameters of the gray wolf algorithm;

[0077] Initialize population X i (i=1, 2, 3...N) (N is the number of individuals in the population), where X i =(x i1 , x i2 , ..., x in)(n is the parameter to be optimized of the SVR model, and its value is 2), initialize the convergence factor a, the synergy coefficient vectors A and C, set the maximum number of iterations to 50, and the initial number of iterations t=1.

[0078] Step 4: Calculation of the initial objective function value;

[0079] The mean square error of the output of the support vector regression (SVR) model is used as the optimization target, and the initial objective function value corresponding to each gray wolf position is calculated. The initial objective function values ​​are compared, and the three sets of parameters with the smallest initial objective function values ​​are selected and saved as the three alpha wolves α, β, and δ in turn. The wolf with the highest level is α, which means that the parameter represented by the alpha wolf position has the smallest objective function value, followed by β, and then δ.

[0080] Step 5: Update the position of the gray wolf through three steps: encirclement, hunting and attack;

[0081] 1) Encirclement process;

[0082] The optimization process of the gray wolf algorithm is to simulate the process of gray wolves surrounding their prey. Its mathematical principle is shown in equations (1) and (2):

[0083] D=|C*X p (t)-X(t)| (1)

[0084] X(t+1)=X p (t)-A*D (2)

[0085] Where t is the current iteration number, X p represents the position vector of the prey, X(t) represents the position vector of the gray wolf in the tth iteration, D represents the distance between the gray wolf and the prey, A and C are the synergy coefficient vectors, calculated as shown in equations (3) and (4):

[0086] A=2a*r1-a (3)

[0087] C=2r2 (4)

[0088] In the formula, a is the convergence factor, and its value decreases linearly from 2 to 0 during the iteration process. r1 and r2 are random vectors in [0, 1]. When |A|>1, the gray wolf group expands the search range to find better prey, which corresponds to global search. When |A|<1, the gray wolf group narrows the encirclement, which corresponds to local search.

[0089] 2) Hunting process;

[0090] When the location of the prey is initially determined, the three gray wolves α, β, and δ guide the wolf pack ω to surround the prey, and then update the position of the search individual according to their position information, as shown in equations (5)-(11). Among them, equations (5)-(7) calculate the distance from wolf ω to the optimal three wolves α, β, and δ, equations (8)-(10) update the position of the gray wolf, and equation (11) calculates the position of the prey.

[0091] D α =|C1*X α -X| (5)

[0092] D β =|C2*X β -X| (6)

[0093] D δ =|C3*X δ -X| (7)

[0094] X1=X α -A1*D α (8)

[0095] X2=X β -A2*D β (9)

[0096] X3=X δ -A3*D δ (10)

[0097]

[0098] Among them, X α , X β , X δ Represent the current positions of the three gray wolves α, β, and δ respectively. C1, C2, and C3 represent a random vector. D α , D β , D δ They represent the distances between the current candidate gray wolf ω and the three best wolves α, β, and δ, respectively. X represents the gray wolf position vector. X1, X2, and X3 are the length and direction of the forward step of the ω wolf toward the three gray wolves α, β, and δ, respectively. X(t+1) is the final position of the ω wolf.

[0099] 3) Attack process;

[0100] When the prey stops moving, the wolf ends the hunt by attacking. It approaches the prey by reducing the value of the convergence factor a, and the value of A also decreases. So A is a random vector in the interval [-2a, 2a], where a gradually decreases linearly during the iteration process. When random A is in the interval [-1, 1], the next position of the search individual can be any position between the current position and the prey, that is, when |A| < 1, the wolf attacks the prey.

[0101] Step 6: Determine whether the maximum number of iterations has been reached;

[0102] Determine whether the number of iterations t has reached the maximum value. If not, return to step 5 to update the convergence factor a, the synergy coefficient vectors A and C and continue the iterative calculation until the maximum number of iterations is met or the convergence factor a is reduced to 0. If the maximum number of iterations is reached, output X α As the optimal parameter of SVR.

[0103] Step 7: Initialize the Adaboost-SVR model;

[0104] The SVR model with the optimal parameters obtained in step 6 is used as the base learner of the Adaboost algorithm. The final number of base learners is given as T = 20, and the weights of each sample are initialized as follows:

[0105]

[0106] Step 8: training the optimal Adaboost-SVR model;

[0107] The optimal SVR model is obtained by the gray wolf algorithm in step 6, and it is used as a base learner C1 in the Adaboost algorithm to calculate its training error, as shown in formula (12). The weight of the base learner C1 is calculated according to the training error value, and its calculation formula is shown in formula (13):

[0108]

[0109]

[0110] In the formula, ε1 is the training error, y j is the output feature quantity of the jth group of data in the training sample, is the weight of the j-th group of samples in the first round, is the predicted output of the j-th group of data obtained by the base learner C1, and α1 is the weight of the base learner C1.

[0111] Then update the second round sample weights, and the calculation formula is shown in formula (14):

[0112]

[0113] Where Z1 is the normalization coefficient, and the calculation formula is shown in formula (15):

[0114]

[0115] Repeat the above steps until T basis learners are trained, and then weighted combination is used to obtain the final Adaboost-SVR model.

[0116]

[0117] Step nine, encapsulate to obtain a visual window interface;

[0118] The final model and training data are displayed in a visual window through encapsulation and programming. The key influencing parameters such as the high-voltage end equalizing ring diameter, the high-voltage end equalizing ring pipe diameter, the tower body width, the gap distance, the air pressure, the temperature and the relative humidity in the prediction data are input to obtain the corresponding breakdown voltage, which is compared with the test values ​​under the same conditions. The maximum prediction error between the predicted value and the test value is only 5%, and the average relative error is 2.7%, both of which are within the engineering error, confirming the effectiveness of the calculation method.

[0119] The present invention also proposes a prediction system 200 for air gap discharge voltage of a DC transmission line, such as Figure 3 As shown, including:

[0120] The training module 201 obtains basic information data of the DC transmission line, performs a discharge test on the gap at the tower head of the DC transmission line, obtains characteristic data of the gap discharge, trains the basic information data and characteristic data, and obtains a training model;

[0121] The prediction module 202 obtains basic information data of the DC transmission line to be tested and inputs it into the training model to obtain output data, where the output data is the discharge voltage of the air gap of the DC transmission line.

[0122] During the discharge test, different voltage levels and different meteorological conditions are selected.

[0123] Get the training model, including:

[0124] The basic information data is used as training data, the characteristic data is used as output data, and the training data is normalized to obtain normalized data;

[0125] Input the normalized data into the SVR model, perform optimization processing, obtain the optimal parameters, and determine the optimal SVR model based on the optimal parameters

[0126] Perform integrated algorithm learning on the training data, output data and optimal SVR model to obtain the training model.

[0127] Training data, including: gap structure parameters and meteorological parameters;

[0128] The gap structure parameters include: the ring diameter and pipe diameter data of the high-pressure side equalizing ring, the gap distance and the tower width;

[0129] The meteorological parameters include: air pressure, air temperature and relative humidity of the air.

[0130] Optimization process: using the gray wolf algorithm to optimize. The specific process includes:

[0131] Initialize parameter positions, convergence factors, random vectors, and adaptation vectors, and use parameter positions to represent solutions;

[0132] Select the three sets of parameters with the smallest objective function value and save them as α, β, and δ in sequence;

[0133] The three sets of parameters are surrounded, hunted and attacked. After the processing is completed, the position of the gray wolf population, the convergence factor, the random vector and the adaptive vector are updated;

[0134] Update the positions of the three parameters α, β, and γ, and obtain the position of α through iteration, which is the optimal solution.

[0135] Compared with the traditional tower head gap discharge voltage calculation method, the present invention has higher prediction accuracy and does not require complicated calculation procedures. It only needs to input the grading ring size, meteorological parameters, tower body width, and gap distance to realize the prediction of breakdown voltage.

[0136] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0137] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0138] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0140] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0141] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting air gap discharge voltage of a DC transmission line, the method comprising: For DC transmission lines, basic information data of DC transmission lines are obtained, and discharge tests of the gaps at the tower heads of DC transmission line towers are conducted to obtain characteristic data of gap discharges, and basic information data and characteristic data are trained to obtain training models; Obtain basic information data of the DC transmission line to be tested, and input it into the training model to obtain output data, wherein the output data is the discharge voltage of the air gap of the DC transmission line; The obtaining of the training model specifically includes: The basic information data is used as training data, the characteristic data is used as output data, and the training data is normalized to obtain normalized data; Input the normalized data into the SVR model, perform optimization processing, obtain the optimal parameters, and determine the optimal SVR model based on the optimal parameters Perform integrated algorithm learning on the training data, output data and optimal SVR model to obtain the training model; The training data includes: gap structure parameters and meteorological parameters; The gap structure parameters include: the ring diameter and pipe diameter data of the high-pressure side equalizing ring, the gap distance and the tower width; The meteorological parameters include: air pressure, air temperature and relative humidity of the air; The optimization process uses the gray wolf algorithm to optimize, and the specific process includes: Initialize parameter positions, convergence factors, random vectors, and adaptation vectors, and use parameter positions to represent solutions; Select the three sets of parameters with the smallest objective function value and save them as α, β, and δ in sequence; The three sets of parameters are surrounded, hunted and attacked. After the processing is completed, the position of the gray wolf population, the convergence factor, the random vector and the adaptive vector are updated; Update the positions of the three parameters α, β, and γ, and obtain the position of α through iteration, which is the optimal solution.

2. According to the method of claim 1, during the discharge test, different voltage levels and different meteorological conditions are selected for the test.

3. A prediction system for air gap discharge voltage of a DC transmission line, the system comprising: The training module obtains basic information data of the DC transmission line, performs a discharge test on the gap at the tower head of the DC transmission line, obtains characteristic data of the gap discharge, trains the basic information data and characteristic data, and obtains a training model; The prediction module obtains basic information data of the DC transmission line to be tested, and inputs it into the training model to obtain output data, wherein the output data is the discharge voltage of the air gap of the DC transmission line; The obtaining of the training model specifically includes: The basic information data is used as training data, the characteristic data is used as output data, and the training data is normalized to obtain normalized data; Input the normalized data into the SVR model, perform optimization processing, obtain the optimal parameters, and determine the optimal SVR model based on the optimal parameters Perform integrated algorithm learning on the training data, output data and optimal SVR model to obtain the training model; The training data includes: gap structure parameters and meteorological parameters; The gap structure parameters include: the ring diameter and pipe diameter data of the high-pressure side equalizing ring, the gap distance and the tower width; The meteorological parameters include: air pressure, air temperature and relative humidity of the air; The optimization process uses the gray wolf algorithm to optimize, and the specific process includes: Initialize parameter positions, convergence factors, random vectors, and adaptation vectors, and use parameter positions to represent solutions; Select the three sets of parameters with the smallest objective function value and save them as α, β, and δ in sequence; The three sets of parameters are surrounded, hunted and attacked. After the processing is completed, the position of the gray wolf population, the convergence factor, the random vector and the adaptive vector are updated; Update the positions of the three parameters α, β, and γ, and obtain the position of α through iteration, which is the optimal solution.

4. The system according to claim 3, wherein different voltage levels and different meteorological conditions are selected for the discharge test.

Images