Distribution network line optimization operation method and system

Abstract

The invention relates to the technical field of line optimization, and discloses a distribution network line optimization operation method and system, and the method comprises the steps: obtaining the historical operation data of all distribution transformers in a distribution network line in a preset period; calculating a load rate of each distribution transformer according to the historical operation data, and calculating a characteristic statistical index of the distribution transformer according to the load rate; performing classification evaluation on the operation state of the distribution transformer according to the characteristic statistical index of the distribution transformer to obtain a classification evaluation result of the operation state of the distribution transformer; screening out the distribution transformers which do not meet a preset economic benefit threshold in the classification evaluation result, constructing an optimization coefficient matrix of the distribution transformers, and establishing a position adjustment assignment problem model of the distribution transformers; and solving the position adjustment assignment problem model by using a Hungary method to obtain a distribution transformer position adjustment scheme. According to the method, the positions of the heavy-overload and light-load distribution transformers are optimized, so that the distribution line optimization is better achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of line optimization, and in particular to a distribution network line optimization operation method and system. Background Art

[0002] With the acceleration of urbanization and the improvement of people's living standards, the demand for electricity continues to grow. In order to meet the demand for electricity, the proportion of distribution network investment continues to increase, becoming one of the key areas of power grid construction investment. This shows that the position of distribution network in the power system is becoming increasingly important, and the demand for optimized operation of distribution network lines is becoming increasingly urgent.

[0003] Although the existing line optimization can optimize the distribution transformer line operation mode by adjusting the position of the distribution transformer, the distribution transformer operation status is rarely evaluated during the distribution transformer position adjustment process. Although there are studies that evaluate the operation status of the distribution transformer and then adjust the position of the distribution transformer based on the evaluation results, most of the evaluations only consider the heavy overload evaluation of the distribution transformer and ignore the light load evaluation of the distribution transformer, resulting in insufficient line optimization. Summary of the invention

[0004] In view of the problem that the existing technology considers the heavy overload evaluation of the distribution transformer and ignores the light load evaluation of the distribution transformer, resulting in insufficient line optimization, the present invention provides a distribution network line optimization operation method and system, which can optimize the position of heavy overload and light load distribution transformers, improve the economic efficiency of distribution transformer operation, reduce distribution transformer losses, and achieve the purpose of better optimizing distribution line operation. The specific technical solution is as follows:

[0005] A distribution network line optimization operation method, comprising:

[0006] Obtain the historical operating data of all distribution transformers in the distribution network in a preset period;

[0007] Calculating the load rate of each distribution transformer according to the historical operation data, and calculating the characteristic statistical index of each distribution transformer according to the load rate;

[0008] Classify and evaluate the operating status of the distribution transformer according to the characteristic statistical indicators of each distribution transformer, and obtain the classification evaluation results of the operating status of each distribution transformer;

[0009] Screen out the distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, construct the optimization coefficient matrix of the screened distribution transformers, and establish a distribution transformer location adjustment assignment problem model with the goal of minimizing cost;

[0010] The Hungarian method is used to solve the position adjustment assignment problem model, and the distribution transformer position adjustment plan is obtained based on the solution results.

[0011] Preferably, the characteristic statistical index of each distribution transformer calculated according to the load rate includes:

[0012] According to the load factor of each distribution transformer, characteristic statistical indicators reflecting the dynamic load factor trend, dispersion degree and distribution form are calculated;

[0013] Characteristic statistical indicators of trends include mean, minimum, median and maximum;

[0014] Characteristic statistical indicators of dispersion include lower quartile, standard deviation and upper quartile;

[0015] The characteristic statistical indicators of the distribution pattern include overload duration, heavy load duration, economic duration and light load duration.

[0016] Preferably, the classification evaluation of the operating status of the distribution transformers is performed according to the characteristic statistical indicators of each distribution transformer, and the classification evaluation results of the operating status of each distribution transformer are obtained, including:

[0017] Preprocess the characteristic statistical indicators of each distribution transformer;

[0018] The operating status of each distribution transformer is categorized and marked according to the processed characteristic statistical indicators of each distribution transformer;

[0019] The processed and marked characteristic statistical index data of the distribution transformer is used as the input feature and the corresponding operating status category label is used as the output label, which is input into the SVM model for learning and training, and a classification prediction result model with output distribution transformer operating status is obtained;

[0020] According to the trained classification prediction result model with output distribution transformer operating status, the classification evaluation result of the distribution transformer operating status is obtained.

[0021] Preferably, the step of classifying the operating status of each distribution transformer according to the processed characteristic statistical indicators of each distribution transformer comprises:

[0022] According to the processed characteristic statistical indicators of each distribution transformer, the operating state of each distribution transformer is marked as a light-load operating state, a heavy-load operating state, an overload operating state or an economic operating state.

[0023] Preferably, the screening out of the distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, constructing the optimization coefficient matrix of the screened distribution transformers, and establishing the location adjustment assignment problem model of the distribution transformer with the goal of minimizing the cost includes:

[0024] Filter out distribution transformers with classification evaluation results of light-load operation state, heavy-load operation state, and overload operation state labels, and count the number of distribution transformers;

[0025] Assigning points to the operating states of the screened distribution transformers, and constructing an optimization coefficient matrix of the screened distribution transformers according to the scoring results and the number of the distribution transformers;

[0026] According to the optimization coefficient matrix, preset decision variables and assignment rules, a distribution transformer location adjustment assignment problem model with the goal of minimizing cost is established.

[0027] Preferably, the step of assigning points to the operating states of the screened distribution transformers and constructing an optimization coefficient matrix of the screened distribution transformers according to the scoring results and the number of the distribution transformers comprises:

[0028] Obtain scores from multiple experts on the operating status of the screened distribution transformers under preset scoring rules to obtain direct scoring results for each distribution transformer;

[0029] Obtain the weights of multiple experts and obtain the expert weight results;

[0030] According to the direct scoring result and expert weight result of each distribution transformer, the comprehensive scoring result of each distribution transformer is obtained;

[0031] According to the comprehensive scoring results and quantity of distribution transformers, the optimization coefficient matrix of the screened distribution transformers is constructed.

[0032] Preferably, the step of obtaining the weights of multiple experts to obtain the expert weight results includes:

[0033] Obtain the mutual trust between experts and calculate the comprehensive trust level of each expert in the expert group;

[0034] The weight of each expert is calculated according to the comprehensive trust level of each expert, and the expert weight result is obtained.

[0035] A distribution network line optimization operation system, applied to the above-mentioned distribution network line optimization operation method, comprises:

[0036] A data acquisition unit, used to acquire historical operation data of all distribution transformers in the distribution network line in a preset period;

[0037] An index calculation unit, used to calculate the load rate of each distribution transformer according to the historical operation data, and calculate the characteristic statistical index of each distribution transformer according to the load rate;

[0038] A classification evaluation unit, used to classify and evaluate the operating status of the distribution transformer according to the characteristic statistical indicators of each distribution transformer, and obtain a classification evaluation result of the operating status of each distribution transformer;

[0039] A model building unit is used to screen out distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, construct an optimization coefficient matrix of the screened distribution transformers, and establish a distribution transformer location adjustment assignment problem model with the goal of minimizing cost;

[0040] The model solving unit is used to solve the position adjustment assignment problem model by using the Hungarian method, and obtain the distribution transformer position adjustment plan according to the solution result.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] A distribution network line optimization operation method of the present invention obtains the historical operation data of all distribution transformers in the distribution network line in a preset period; calculates the load rate of each distribution transformer according to the historical operation data, and calculates the characteristic statistical index of each distribution transformer according to the load rate; classifies and evaluates the operation status of the distribution transformer according to the characteristic statistical index of each distribution transformer, and obtains the classification evaluation result of the operation status of each distribution transformer; screens out the distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, constructs the optimization coefficient matrix of the distribution transformers after screening, and establishes a distribution transformer position adjustment assignment problem model with the minimum cost as the goal; solves the position adjustment assignment problem model by using the Hungarian method, and obtains the distribution transformer position adjustment plan according to the solution result. The present invention extracts the representative characteristic statistical index of the distribution transformer, evaluates the distribution transformer, optimizes the position of the heavily overloaded and lightly loaded distribution transformers according to the evaluation results, improves the economic efficiency of the distribution transformer operation, reduces the loss of the distribution transformer, and achieves the purpose of better optimizing the operation of the distribution line. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0044] Figure 1 The present invention is a flow chart of a distribution network line optimization operation method.

[0045] Figure 2 The present invention is a flow chart of an embodiment of a method for optimizing operation of distribution network lines.

[0046] Figure 3 The present invention is a flow chart of another embodiment of a method for optimizing operation of distribution network lines.

[0047] Figure 4 The present invention is a schematic diagram of a distribution network line optimization operation system. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0050] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0051] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] The present application optimizes the line of the distribution network based on the position adjustment of the distribution transformer, and optimizes the line based on the position optimization adjustment of the distribution transformer to minimize the total loss of the distribution transformer in the distribution network.

[0053] See the following examples Figure 1 , Figure 2 , Figure 3 and Figure 4 .

[0054] The present application provides a method for optimizing the operation of a distribution network line, including:

[0055] Step S1, obtaining historical operation data of all distribution transformers in the distribution network in a preset period;

[0056] The historical operation data of distribution transformers can be selected according to the established requirements to select all distribution transformers under one or more distribution lines as data collection objects. The preset period can be set according to the actual distribution network line management requirements and past experience, for example, it can be set to the past year, half a year, one month or one day.

[0057] Historical operation data can be typical daily operation data, or daily operation data, monthly operation data, quarterly operation data, and annual operation data. If you choose typical daily operation data, you need to select data from typical dates that can represent different seasons and different peak and trough characteristic periods of electricity consumption based on past electricity consumption patterns; if you choose daily, monthly, quarterly, or annual operation data, you need to collect and organize the corresponding voltage, current, power, and other related operation parameter records according to the corresponding time span.

[0058] By comprehensively and targetedly collecting historical operating data, reliable basic information is provided for the subsequent accurate analysis of the operating status of distribution transformers, so that subsequent calculations and evaluations based on these data can be in line with actual operating scenarios.

[0059] Step S2, calculating the load rate of each distribution transformer according to the historical operation data, and calculating the characteristic statistical index of each distribution transformer according to the load rate;

[0060] The load rate of each distribution transformer at each time point or time period is calculated by the ratio of the actual output power of the distribution transformer to the rated power. For example, if the data is recorded daily, the daily load rate can be calculated, and then the load rate values ​​of different dimensions such as the average load rate can be comprehensively counted.

[0061] Based on the load rate, the characteristic statistical indicators are calculated using appropriate statistical methods. Among them, the characteristic statistical indicators of the distribution transformer include characteristic statistical indicators that reflect the dynamic load rate trend, discrete degree and distribution form;

[0062] The characteristic statistical indicators of trends include average, minimum, median and maximum values; these indicators can fully reflect the degree of convergence or aggregation of data;

[0063] The characteristic statistical indicators of dispersion include the lower quartile, standard deviation and upper quartile; these indicators reflect the distance and distribution of the data from the center;

[0064] The characteristic statistical indicators of the distribution pattern include overload duration, heavy load duration, economic duration and light load duration; these indicators characterize the distribution of the data.

[0065] By calculating the load rate and its characteristic statistical indicators, the working intensity and load change characteristics of the distribution transformer can be quantitatively displayed, providing a key numerical basis for further accurate judgment of its operating status, and helping to grasp the operating status of each distribution transformer more finely.

[0066] Step S3, classifying and evaluating the operating status of the distribution transformers according to the characteristic statistical indicators of each distribution transformer, and obtaining the classification evaluation results of the operating status of each distribution transformer;

[0067] By classifying and evaluating the operating status of distribution transformers, we can intuitively understand the overall operating health level of each distribution transformer. Here, the SVM model is used for learning classification evaluation, and the random forest decision tree model can also be used for classification evaluation.

[0068] Specifically, the classification evaluation of the operating status of the distribution transformers is performed according to the characteristic statistical indicators of each distribution transformer, and the classification evaluation results of the operating status of each distribution transformer are obtained, including:

[0069] Step S31, preprocessing the characteristic statistical indicators of each distribution transformer;

[0070] Preprocessing requires standardization or normalization of the data to prevent the different data dimensions of different feature statistical indicators from affecting model training.

[0071] Step S32: classify the operating status of each distribution transformer according to the processed characteristic statistical indicators of each distribution transformer;

[0072] The category boundary conditions of different operating states are determined by comprehensively considering the performance of distribution transformers. For example, for the characteristic statistical indicator of the mean load rate, the load rate can be set to mark the operating state of each distribution transformer as a light load operating state, a heavy load operating state, an overload operating state, or an economic operating state.

[0073] Step S33, the processed and marked characteristic statistical index data of the distribution transformer is used as input features and the corresponding operating status category label is used as output label, and is input into the SVM model for learning and training, so as to obtain a trained classification prediction result model capable of outputting the operating status of the distribution transformer;

[0074] The characteristic statistical indicator data of all distribution transformers that have been marked with operating status categories and preprocessed are randomly divided into training data sets and test data sets according to a certain ratio (such as 80% for training and 20% for testing) to ensure the randomness and representativeness of data division, so that the trained model has good generalization ability.

[0075] Using the divided training data set, the input features and corresponding output labels are input into the SVM model with the selected kernel function and parameter configuration for training. During the training process, the SVM model will determine the optimal decision boundary between different operating status categories by optimizing the objective function based on the relationship between the input and output data, and continuously adjust the key elements such as the support vector inside the model until the set training stop condition is reached. At this time, a trained classification prediction result model with output distribution transformer operating status is obtained.

[0076] Step S34: Obtain a classification evaluation result of the operating state of the distribution transformer according to the trained classification prediction result model capable of outputting the operating state of the distribution transformer.

[0077] The trained model will output the corresponding operating status classification prediction results of each distribution transformer based on its learned decision boundary. These results are the final classification evaluation results of the distribution transformer operating status, such as outputting corresponding operating status categories such as light load operating status, heavy load operating status, overload operating status or economic operating status.

[0078] Step S4, screening out the distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, constructing the optimization coefficient matrix of the screened distribution transformers, and establishing a distribution transformer location adjustment assignment problem model with the goal of minimizing cost;

[0079] Through a series of operations such as screening, matrix construction and model establishment, the actual problem of optimizing the position of distribution transformers is transformed into a model problem that can be solved by mathematical methods, which provides an effective analysis framework for the scientific and reasonable formulation of position adjustment plans and helps to achieve improved economic benefits.

[0080] Step S5: solve the position adjustment assignment problem model using the Hungarian method, and obtain a distribution transformer position adjustment plan based on the solution result.

[0081] The established distribution transformer position adjustment assignment problem model is sorted and formatted according to the requirements of the Hungarian method. The calculation steps of the Hungarian method are strictly followed. Through operations such as row and column transformation and ticking, the optimal solution is gradually found, that is, the corresponding assignment plan for the most economical (minimum loss of distribution transformer) distribution transformer position adjustment is found to achieve the final distribution network line optimization plan.

[0082] A distribution network line optimization operation method of the present invention evaluates the distribution transformer by extracting representative characteristic statistical indicators of the distribution transformer, and optimizes the positions of heavily overloaded and lightly loaded distribution transformers based on the evaluation results, thereby improving the operating economy of the distribution transformer and reducing the loss of the distribution transformer, thereby achieving the purpose of better optimizing the operation of the distribution line.

[0083] Specifically, in a preferred embodiment of the present application, the screening out of the distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, constructing the optimization coefficient matrix of the screened distribution transformers, and establishing the location adjustment assignment problem model of the distribution transformer with the goal of minimizing the cost includes:

[0084] Step S41, screening out distribution transformers with classification evaluation results of light-load operation state, heavy-load operation state and overload operation state labels, and counting the number of distribution transformers, recorded as n;

[0085] Step S42, scoring the operating states of the screened distribution transformers, and constructing an optimization coefficient matrix of the screened distribution transformers according to the scoring results and the number of the distribution transformers;

[0086] Specifically, the operation status of the screened distribution transformers is scored, and the optimization coefficient matrix of the screened distribution transformers is constructed according to the scoring results and the number of the distribution transformers, including:

[0087] Obtain scores from multiple experts on the operating status of the screened distribution transformers under the preset scoring rules, and obtain direct scoring results for each distribution transformer based on the scoring results; assuming that there are r experts scoring, the direct scoring results are calculated as follows:

[0088]

[0089] Where, M1 is the direct scoring result; m i is the scoring result of the i-th expert, i=1, 2, ..., r;

[0090] Get the weights of multiple experts and get the expert weight result ω i ;

[0091] Expert scoring is somewhat subjective, so it is necessary to determine the expert weights and establish a trust propagation equation between experts through the social trust propagation relationship between experts.

[0092]

[0093] In the formula, α ab represents the trust of expert a in expert b, α ba is the trust of expert b in expert a; α ab ,α ba ∈[0,1].

[0094] Among them, the trust degree α ab It can be expressed as,

[0095]

[0096] Where c is the trust propagation path between expert a and expert b, d = {d1, d2, ..., d c}.

[0097] Based on this, the comprehensive trust level of expert a in the expert group OT a Then:

[0098]

[0099] In the formula, OT a The larger the value is, the higher the comprehensive trust of expert a in the expert group is, which means that its weight in the expert group is higher. The weight of expert a can be expressed as:

[0100]

[0101] In the formula, ω a is the weight of expert a, satisfying

[0102] According to the direct scoring result M1 of each distribution transformer and the expert weight result ω i , the comprehensive scoring result M2 of each distribution transformer is obtained, that is, the scoring result M2 of the operating status of each distribution transformer; the comprehensive scoring result is calculated as follows:

[0103]

[0104] The M2 value indicates the severity of the uneconomical operation of the distribution transformer, specifically, whether it is in a light load operation state, a heavy load operation state, or an overload operation state.

[0105] According to the scoring result M2 and the number of distribution transformers (assuming that the number of distribution transformers is n), the optimization coefficient matrix K of the distribution transformer after screening is constructed. The optimization coefficient matrix K is a matrix composed of the operating state coefficients of n distribution transformers at n different positions, which represents the operating state of n distribution transformers at n different positions. The formula of the optimization coefficient matrix is ​​as follows:

[0106]

[0107] In the formula, k ij It represents the M2 value of the operating status evaluation result of the i-th distribution transformer when it is operating at the j-th location.

[0108] Step S43: Establish a distribution transformer location adjustment assignment problem model with the goal of minimizing cost based on the optimization coefficient matrix, preset decision variables and assignment rules.

[0109] First, the default assignment rules are as follows:

[0110] In the assignment problem of distribution transformer location adjustment, the installation locations of i distribution transformers are as follows:

[0111]

[0112] Among them, 1 means that the i-th distribution transformer is installed at position j; 0 means that the i-th distribution transformer is installed or not installed at position j.

[0113] Second, the preset decision variables are as follows:

[0114] The n×n decision variables x ij Arranged into an n×n matrix, called decision variables, as follows:

[0115]

[0116] Third, the model of the assignment problem in the position adjustment of distribution transformers is constructed as follows:

[0117]

[0118] In formula (1), it means that the uneconomic degree of n distribution transformers at n locations is the smallest, that is, the economic benefit is the largest;

[0119] In formula (2), it means that each distribution transformer can only have one position;

[0120] In formula (3), it means that there can only be one distribution transformer at each location;

[0121] In formula (4), the decision variable can only take two integer values ​​0 or 1.

[0122] The specific solution process of the model is as follows:

[0123] To find the model that satisfies the assignment problem in the position adjustment of the distribution transformer, we need to find n elements located in different rows and columns on the optimization coefficient matrix so that they satisfy equations (1) to (4). For the positions of these n elements on the optimization coefficient matrix K, let the corresponding element x in the decision matrix X be ij =1, and the other elements are 0, then an optimal solution for the distribution transformer position adjustment is obtained.

[0124] Assume that the optimization coefficient matrix of the distribution transformer position adjustment model is K = (k ij ) n×n , subtract the same constant a from each element of a row or column of the K matrix to obtain a new optimization coefficient matrix Then The optimal solution of the distribution transformer position adjustment model with the optimized coefficient matrix is ​​the same as the optimal solution of the original model, and its optimal value is a less than the original optimal value. The optimized coefficient matrix is ​​continuously transformed until the transformed K matrix contains n "0" elements located in different rows and columns. Suppose the final optimized coefficient matrix (k′ ij ) n×n , then (k ij ) n×n The solution of the distribution transformer location adjustment model with the optimized coefficient matrix is ​​the same as that of the original model. ij ) n×n In the solution matrix of the corresponding problem, there are n independent variables x with zero elements. ij The value is 1, and the other variables are 0, then the objective function value reaches the minimum, and (k ij ) n×n The optimal solution of the distribution transformer location adjustment model with the optimized coefficient matrix is ​​also the optimal solution to the original problem.

[0125] By solving the distribution transformer location adjustment assignment problem model with the goal of minimizing cost, the optimal position of each transformer is obtained. Finally, the changes in voltage and loss at each node of the entire distribution network line before and after the distribution transformer location optimization are calculated to verify the line optimization effect.

[0126] In this embodiment, based on the optimization coefficient matrix, combined with the preset decision variables and the assignment rules that conform to the actual distribution network operation logic, the complex distribution transformer position adjustment problem in reality can be converted into an assignment problem model that can be solved by mathematical methods. In this way, the problem of formulating a position adjustment plan that was originally difficult to accurately grasp by relying on experience and qualitative judgment can be solved through rigorous mathematical calculations and model optimization to find the optimal solution, that is, the adjustment plan with the lowest cost. The model takes the minimum cost as the goal, fully considers many factors such as the operating status of the distribution transformer and the cost of position adjustment. By solving the model, it helps to improve the economic benefits of the distribution network line, thereby optimizing the overall operation of the distribution network line.

[0127] The present application also provides a distribution network line optimization operation system, including:

[0128] A data acquisition unit, used to acquire historical operation data of all distribution transformers in the distribution network line in a preset period;

[0129] An index calculation unit, used to calculate the load rate of each distribution transformer according to the historical operation data, and calculate the characteristic statistical index of each distribution transformer according to the load rate;

[0130] A classification evaluation unit, used to classify and evaluate the operating status of the distribution transformer according to the characteristic statistical indicators of each distribution transformer, and obtain a classification evaluation result of the operating status of each distribution transformer;

[0131] A model building unit is used to screen out distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, construct an optimization coefficient matrix of the screened distribution transformers, and establish a distribution transformer location adjustment assignment problem model with the goal of minimizing cost;

[0132] The model solving unit is used to solve the position adjustment assignment problem model by using the Hungarian method, and obtain the distribution transformer position adjustment plan according to the solution result.

[0133] The technical effect of this embodiment is the same as that of the embodiment of a distribution network line optimization operation method, and will not be repeated here. In this embodiment, the functional explanation of each unit is also the same as that of the embodiment of a distribution network line optimization operation method of the embodiment.

[0134] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0135] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0136] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0137] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A distribution network line optimization operation method, characterized in that: include: Obtain the historical operating data of all distribution transformers in the distribution network in a preset period; Calculating the load rate of each distribution transformer according to the historical operation data, and calculating the characteristic statistical index of each distribution transformer according to the load rate; Classify and evaluate the operating status of the distribution transformer according to the characteristic statistical indicators of each distribution transformer, and obtain the classification evaluation results of the operating status of each distribution transformer; Screen out the distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, construct the optimization coefficient matrix of the screened distribution transformers, and establish a distribution transformer location adjustment assignment problem model with the goal of minimizing cost; The Hungarian method is used to solve the position adjustment assignment problem model, and the distribution transformer position adjustment plan is obtained based on the solution results.

2. A distribution network line optimization operation method according to claim 1, characterized in that: The characteristic statistical index of each distribution transformer calculated according to the load rate includes: According to the load factor of each distribution transformer, characteristic statistical indicators reflecting the dynamic load factor trend, dispersion degree and distribution form are calculated; Characteristic statistical indicators of trends include mean, minimum, median and maximum; Characteristic statistical indicators of dispersion include lower quartile, standard deviation and upper quartile; The characteristic statistical indicators of the distribution pattern include overload duration, heavy load duration, economic duration and light load duration.

3. A distribution network line optimization operation method according to claim 2, characterized in that: The classification evaluation of the operating status of the distribution transformers is performed according to the characteristic statistical indicators of each distribution transformer, and the classification evaluation results of the operating status of each distribution transformer are obtained, including: Preprocess the characteristic statistical indicators of each distribution transformer; The operating status of each distribution transformer is categorized according to the processed characteristic statistical indicators of each distribution transformer; the processed and labeled characteristic statistical indicator data of the distribution transformer is used as input features and the corresponding operating status category label is used as output label, which is input into the SVM model for learning and training, and a trained classification prediction result model capable of outputting the operating status of the distribution transformer is obtained; According to the trained classification prediction result model with output distribution transformer operating status, the classification evaluation result of the distribution transformer operating status is obtained.

4. A distribution network line optimization operation method according to claim 3, characterized in that: The step of classifying the operating status of each distribution transformer according to the processed characteristic statistical indicators of each distribution transformer includes: According to the processed characteristic statistical indicators of each distribution transformer, the operating state of each distribution transformer is marked as a light-load operating state, a heavy-load operating state, an overload operating state or an economic operating state.

5. A distribution network line optimization operation method according to claim 4, characterized in that: The method of screening out the distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, constructing the optimization coefficient matrix of the distribution transformers after screening, and establishing the location adjustment assignment problem model of the distribution transformers with the goal of minimizing the cost includes: Filter out distribution transformers with classification evaluation results of light-load operation state, heavy-load operation state, and overload operation state labels, and count the number of distribution transformers; Assigning points to the operating states of the screened distribution transformers, and constructing an optimization coefficient matrix of the screened distribution transformers according to the scoring results and the number of the distribution transformers; According to the optimization coefficient matrix, preset decision variables and assignment rules, a distribution transformer location adjustment assignment problem model with the goal of minimizing cost is established.

6. A distribution network line optimization operation method according to claim 5, characterized in that: The step of assigning points to the operating status of the screened distribution transformers and constructing an optimization coefficient matrix of the screened distribution transformers according to the scoring results and the number of the distribution transformers includes: Obtain scores from multiple experts on the operating status of the screened distribution transformers under preset scoring rules to obtain direct scoring results for each distribution transformer; Obtain the weights of multiple experts and obtain the expert weight results; According to the direct scoring results and expert weight results of each distribution transformer, the comprehensive scoring results of each distribution transformer are obtained; according to the comprehensive scoring results and the number of distribution transformers, the optimization coefficient matrix of the screened distribution transformers is constructed.

7. A distribution network line optimization operation method according to claim 6, characterized in that: The step of obtaining the weights of multiple experts to obtain the expert weight results includes: Obtain the mutual trust between experts and calculate the comprehensive trust level of each expert in the expert group; The weight of each expert is calculated according to the comprehensive trust level of each expert, and the expert weight result is obtained.

8. A distribution network line optimization operation system, characterized in that: A distribution network line optimization operation method applied to any one of claims 1 to 7, comprising: A data acquisition unit, used to acquire the historical operation data of all distribution transformers in the distribution network line in a preset period; an index calculation unit, used to calculate the load rate of each distribution transformer according to the historical operation data, and calculate the characteristic statistical index of each distribution transformer according to the load rate; A classification evaluation unit, used to classify and evaluate the operating status of the distribution transformer according to the characteristic statistical indicators of each distribution transformer, and obtain a classification evaluation result of the operating status of each distribution transformer; A model building unit is used to screen out distribution transformers that do not meet the preset economic benefit threshold in the classification evaluation results, construct an optimization coefficient matrix of the screened distribution transformers, and establish a distribution transformer location adjustment assignment problem model with the goal of minimizing cost; The model solving unit is used to solve the position adjustment assignment problem model by using the Hungarian method, and obtain the distribution transformer position adjustment plan according to the solution result.

Images