Power distribution network fault distance measurement scheme recommendation method and system based on combined empowerment

Abstract

The invention relates to the technical field of power distribution networks, in particular to a power distribution network fault distance measurement scheme recommendation method and system based on combined empowerment. Obtaining range finding scheme evaluation data in the first target power distribution network area, and performing first preprocessing on the range finding scheme evaluation data to obtain second evaluation data; presetting a first scheme evaluation model and inputting the second evaluation data into the first scheme evaluation model; and recommending a fault location scheme according to the output of the first scheme evaluation model. The first combined weighting algorithm comprises subjective weight analysis, objective weight analysis and combined weight generation; the evaluation factors comprise the power supply reliability improvement degree, the distributed energy access capability, the social and economic benefits, the enterprise operation benefits, the scheme implementation difficulty and the maintenance cost. By introducing a multi-dimensional evaluation data acquisition mechanism and combining dual preprocessing and a combined weighting algorithm, all-around evaluation coverage of a ranging scheme is realized, the problem that traditional single data source evaluation is not comprehensive is solved, and the evaluation accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network, and in particular to a method and system for recommending a distribution network fault distance measurement scheme based on combined weighting. Background Art

[0002] Since distribution lines are complex and diverse and directly face users, the recommendation of fault distance measurement schemes needs to be combined with specific lines, that is, the type of distance measurement scheme to be adopted needs to be determined according to the specific line type and should not be generalized. Because the recommendation and evaluation of fault distance measurement schemes belongs to multi-factor decision-making problems, there are many mathematical methods to solve such problems. According to the way of determining weights, they can be divided into subjective methods and objective methods. Among them, the hierarchical analysis method is a more widely used subjective method. The subjective method is easily affected by the preferences of the evaluator. If there is a large deviation in the weights between the core elements, it will lead to unsatisfactory evaluation results. The objective method is completely dependent on the attributes of the elements themselves, has poor flexibility, and it is difficult to fully reflect the full picture of the problem when the amount of data is insufficient. Summary of the invention

[0003] In view of the problems existing in the prior art, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is how to solve the problem that the weights of the core elements of the fault location solution in the distribution network have large deviations, which will lead to unsatisfactory evaluation results. The objective method completely relies on the attributes of the elements themselves, has poor flexibility, and is difficult to fully reflect the full picture of the problem when the amount of data is insufficient.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a method for recommending a distribution network fault distance measurement scheme based on combined weighting, which includes taking distance measurement scheme evaluation data within a first target distribution network area, and performing a first preprocessing on the distance measurement scheme evaluation data to obtain second evaluation data;

[0007] Presetting a first solution evaluation model, and inputting the second evaluation data into the first solution evaluation model;

[0008] A fault location solution is recommended based on the output of the first solution evaluation model.

[0009] As a preferred scheme of the distribution network fault ranging scheme recommendation method based on combined weighting described in the present invention, wherein: the ranging scheme evaluation data includes: first category evaluation data, second category evaluation data, third category evaluation data and fourth category evaluation data; the ranging scheme evaluation data is all evaluation data obtained when performing evaluation and analysis through a preset first combined weighting algorithm.

[0010] As a preferred scheme of the distribution network fault distance measurement scheme recommendation method based on combined weighting described in the present invention, wherein: the first preprocessing includes at least a first manual evaluation and a first data increment processing; the first manual evaluation includes a first evaluation verification operation and a second evaluation verification operation; the first data increment processing is used to expand the distance measurement scheme evaluation data after the first manual evaluation.

[0011] As a preferred solution of the distribution network fault distance measurement scheme recommendation method based on combined weighting described in the present invention, wherein: the first combined weighting algorithm includes: subjective weight analysis, used to analyze and determine the subjective importance of each evaluation factor; objective weight analysis, used to calculate the objective weight of each evaluation factor based on the distance measurement scheme evaluation data; combined weight generation, used to optimize the combination of subjective weight and objective weight.

[0012] As a preferred scheme of the distribution network fault distance measurement scheme recommendation method based on combined weighting described in the present invention, the evaluation factors include: the degree of improvement of power supply reliability, distributed energy access capability, social and economic benefits, enterprise operation benefits, scheme implementation difficulty and maintenance cost; the subjective weights of the evaluation factors are obtained by expert scoring method, and the objective weights of the evaluation factors are obtained by data statistical analysis.

[0013] As a preferred scheme of the distribution network fault distance measurement scheme recommendation method based on combined weighting described in the present invention, the evaluation process of the first scheme evaluation model includes: preliminary screening of each alternative distance measurement scheme; comprehensive scoring of the screened alternative distance measurement schemes according to the combined weights; and ranking and recommending the alternative distance measurement schemes based on the comprehensive scoring results.

[0014] As a preferred solution of the distribution network fault distance measurement scheme recommendation method based on combined weighting described in the present invention, wherein: the first scheme evaluation model includes: the input is the second evaluation data, the output is the distance measurement scheme recommendation result, the evaluation index is a combined evaluation index, and the combined evaluation index includes at least a power supply reliability index, an economic index and a technical feasibility index.

[0015] In a second aspect, an embodiment of the present invention provides a distribution network fault distance measurement scheme recommendation system based on combined weighting, which includes an evaluation data acquisition module, which acquires distance measurement scheme evaluation data in a first target distribution network area, and performs a first preprocessing on the distance measurement scheme evaluation data to obtain second evaluation data;

[0016] A model operation module presets a first solution evaluation model and inputs the second evaluation data into the first solution evaluation model;

[0017] The recommendation result acquisition module recommends a fault distance measurement scheme according to the output of the first scheme evaluation model.

[0018] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the method for recommending a distribution network fault location scheme based on combined weighting as described in the first aspect of the present invention are implemented.

[0019] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the method for recommending a distribution network fault location scheme based on combined weighting as described in the first aspect of the present invention are implemented.

[0020] The beneficial effects of the present invention are as follows: the present invention adopts a multi-dimensional evaluation data collection mechanism, combined with dual preprocessing and combined weighting algorithms, to construct a complete distribution network fault ranging scheme recommendation system. Through multi-source data collection and fusion processing, the problem of incomplete evaluation of traditional single data source is solved, and a comprehensive evaluation of ranging schemes from multiple dimensions such as technical, economic and social benefits is achieved. The first manual evaluation and the first data increment processing mechanism set up effectively guarantee the quality and adequacy of the evaluation data, and overcome the defects of unstable data quality and insufficient sample size in traditional evaluation. The innovatively introduced combined weighting algorithm organically combines subjective weights and objective weights to avoid the problem of unreasonable weight distribution in traditional single weight methods, making the evaluation results more scientific and reliable. The model design based on the multi-layer evaluation structure realizes the intelligence and automation of ranging scheme evaluation, and significantly improves the evaluation efficiency. At the same time, the system's interpretability analysis module and dynamic adjustment mechanism make the evaluation results more convincing and adaptable, effectively solving the problem that the evaluation results in traditional methods are difficult to explain and adjust. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flowchart of a proposed method for fault location scheme in distribution network based on combined weighting;

[0023] Figure 2 Computer equipment diagram for recommending a method for fault location scheme in distribution network based on combined weighting;

[0024] Figure 3A hierarchical diagram of the recommended distribution network fault location scheme for the distribution network fault location scheme recommendation method based on combined weighting. DETAILED DESCRIPTION

[0025] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0027] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0028] Example 1

[0029] Reference Figure 1-2 , which is the first embodiment of the present invention, and provides a method for recommending a distribution network fault location solution based on combined weighting, comprising:

[0030] S100: taking distance measurement scheme evaluation data within a first target distribution network area, and performing a first preprocessing on the distance measurement scheme evaluation data to obtain second evaluation data;

[0031] S101: the ranging scheme evaluation data includes: first-category evaluation data, second-category evaluation data, third-category evaluation data and fourth-category evaluation data; the ranging scheme evaluation data is all evaluation data obtained when performing evaluation and analysis through a preset first combination weighting algorithm.

[0032] In the embodiment of the present application, the ranging scheme evaluation data includes: first category evaluation data, second category evaluation data, third category evaluation data and fourth category evaluation data; the ranging scheme evaluation data is all evaluation data obtained when performing evaluation and analysis through a preset first combination weighting algorithm.

[0033] Specifically, the first type of evaluation data may be data related to power supply reliability, including reliability indicator data such as the system average outage time index (SAIDI) and the system average outage frequency index (SAIFI); the second type of evaluation data may be data related to distributed energy access capability, including technical parameters such as distributed power source installed capacity and grid carrying capacity; the third type of evaluation data may be data related to social and economic benefits, such as the degree to which the accuracy of fault location improves the quality of power supply services and the impact on user satisfaction; the fourth type of evaluation data may be data on the technical implementation difficulty of the ranging solution, including indicators such as communication dependence and timing accuracy requirements.

[0034] In an optional embodiment, the first type of evaluation data, the second type of evaluation data, the third type of evaluation data, and the fourth type of evaluation data may be a combination of multiple data sources from a distribution automation system, a distribution management system (DMS), a fault indicator, an intelligent terminal, etc. For example, when the first type of evaluation data is a reliability index from a distribution automation system, the fourth type of evaluation data may be technical parameter data from an intelligent terminal.

[0035] In an optional embodiment, the first type of evaluation data, the second type of evaluation data, the third type of evaluation data, and the fourth type of evaluation data can also add or reduce other data according to different target effects. For example, when a more refined evaluation is required, maintenance cost-related data (i.e., the fifth type of cost data) can be added to capture the economic characteristics of the ranging solution, thereby further improving the comprehensiveness and accuracy of the evaluation. In addition, considering the impact of differences in distribution network architectures in different regions on the quality of the evaluation, an adaptive data calibration algorithm can also be introduced to dynamically adjust the collected evaluation data to ensure that high-quality evaluation data can be obtained under various network topologies.

[0036] In an optional embodiment, if the technical implementation difficulty does not need to be considered, the fourth type of evaluation data can be omitted, thereby reducing the workload of data collection and processing. However, in this application, in order to ensure the comprehensiveness of the evaluation, such data is still retained.

[0037] It should be noted that the acquisition of the above-mentioned evaluation data can fully cover all evaluation dimensions of the ranging scheme, including but not limited to technical feasibility, economic rationality, social benefits, etc., so as to ensure the accuracy and comprehensiveness of the evaluation results. At the same time, by introducing multiple data sources and evaluation dimensions, such as distribution automation systems, distribution management systems, etc., we can make full use of the advantages of various types of data, complement each other, and improve the efficiency and accuracy of the evaluation. In addition, according to the needs of different target effects, the type and quantity of data can be flexibly adjusted to meet the needs of actual evaluation work. This multi-source data fusion strategy not only improves the flexibility and adaptability of the evaluation system, but also provides rich data support for subsequent intelligent analysis.

[0038] S102: The first preprocessing includes at least a first manual evaluation and a first data increment processing; the first manual evaluation includes a first evaluation verification operation and a second evaluation verification operation; the first data increment processing is used to expand the ranging scheme evaluation data after the first manual evaluation.

[0039] In an embodiment of the present application, the first preprocessing includes at least a first manual evaluation and a first data increment processing; the first manual evaluation includes a first evaluation verification operation and a second evaluation verification operation; the first data increment processing is used to expand the ranging scheme evaluation data after the first manual preprocessing.

[0040] In a preferred embodiment, different preprocessing strategies are adopted according to different evaluation data types. For example, for the first type of evaluation data related to reliability, it is necessary to perform power outage time statistical verification, fault frequency analysis and other processing; for the second type of evaluation data related to distributed energy access, it is necessary to perform power flow analysis, voltage stability evaluation and other processing; for the third type of evaluation data related to social and economic benefits, it is necessary to perform cost-benefit analysis, user satisfaction survey and other processing; for the fourth type of evaluation data related to the difficulty of technical implementation, it is necessary to perform communication bandwidth evaluation, clock synchronization accuracy verification and other processing. After these preprocessing steps, the quality and availability of various types of evaluation data are significantly improved, laying a solid foundation for the subsequent solution recommendation analysis.

[0041] In an embodiment of the present application, the first evaluation and verification operation is a verification operation for technical indicators, and the second evaluation and verification operation is a verification operation for economic benefits. For example, the first evaluation and verification operation can specifically be a comprehensive review of the technical indicators of the ranging solution, including verification of indicators such as fault location accuracy and response time, to ensure the accuracy of technical parameters. The second evaluation and verification operation is a manual check of economic benefit indicators, including evaluation of economic indicators such as investment cost, operation and maintenance cost, and benefit recovery period. Although this manual verification operation is time-consuming, it can significantly improve the accuracy of the evaluation results and ensure the reliability of subsequent analysis.

[0042] In the embodiment of the present application, the first data increment processing is a data expansion operation, the purpose of which is to enrich and improve the evaluation data set. The present application is implemented by multi-dimensionally expanding the ranging scheme evaluation data after the first manual preprocessing. Specifically, it includes collecting historical fault data, building a typical fault scenario model, integrating expert evaluation opinions, etc., to generate a more complete data set to ensure that the model can adapt to different fault types and network topologies.

[0043] In an optional embodiment, the first data increment processing can also be implemented in other ways, such as introducing machine learning technology to generate more diverse evaluation data samples by learning the features of existing data. This method can not only save data collection time, but also improve the integrity of the data by utilizing the correlation between data. In addition, in order to further improve the effect of data expansion, multiple data processing methods can be combined, such as combining data enhancement with data verification, or mixing simulated data with measured data to achieve better preprocessing effects.

[0044] It should be noted that the above data increment processing method can not only expand the amount of evaluation data, but also improve the quality and representativeness of the data. At the same time, special attention should be paid to key links such as data quality control, consistency maintenance and security assurance to ensure that the expanded data can truly reflect the various characteristics of the distribution network fault location solution and provide reliable data support for subsequent solution recommendations.

[0045] S103: The first combined weighting algorithm includes: subjective weight analysis, which is used to analyze and determine the subjective importance of each evaluation factor; objective weight analysis, which is used to calculate the objective weight of each evaluation factor based on the ranging scheme evaluation data; combined weight generation, which is used to optimize the combination of subjective weight and objective weight.

[0046] In a preferred embodiment, the subjective weight analysis adopts an improved analytic hierarchy process (AHP), which mainly includes the following steps: first, the importance of each evaluation factor is scored through an expert questionnaire survey; second, a judgment matrix is ​​constructed and a consistency test is performed; finally, the subjective weight value of each evaluation factor is calculated. For example, in a certain actual case, the subjective weight of the degree of improvement in power supply reliability is 0.35, the subjective weight of distributed energy access capability is 0.25, the subjective weight of social and economic benefits is 0.20, and the subjective weight of enterprise operation benefits is 0.20.

[0047] In the embodiment of the present application, the objective weight analysis adopts the information entropy method, and the objective weight is determined by calculating the information entropy value of each evaluation factor. Specifically, the greater the data difference of a certain evaluation factor, the greater the amount of effective information provided by the factor, and the greater its weight. For example, after calculation by the information entropy method, the objective weight of the power supply reliability index in a certain case is 0.30, the objective weight of the distributed energy access capability is 0.28, the objective weight of the social and economic benefits is 0.22, and the objective weight of the enterprise operation efficiency is 0.20.

[0048] In an optional embodiment, the combination weight is generated by a linear weighted combination method, and an adjustment coefficient α (0≤α≤1) is introduced to balance the subjective weight and the objective weight. When α=0.5, it means that the influence of both subjective and objective weights is considered; when α is close to 1, the subjective weight is more emphasized; when α is close to 0, the objective weight is more emphasized. By adjusting the α value, the weight combination strategy can be flexibly adjusted according to actual needs.

[0049] S104: Evaluation factors include: degree of improvement in power supply reliability, distributed energy access capability, social and economic benefits, enterprise operation benefits, difficulty of program implementation and maintenance costs; the subjective weights of the evaluation factors are obtained through expert scoring method, and the objective weights of the evaluation factors are obtained through data statistical analysis.

[0050] In the embodiment of the present application, the degree of improvement in power supply reliability mainly examines the effect of the ranging scheme on improving system reliability indicators, including key indicators such as fault location accuracy and fault isolation time. For example, a certain ranging scheme can improve the fault location accuracy from 85% to 95%, and shorten the fault isolation time from an average of 30 minutes to 15 minutes.

[0051] In an optional embodiment, the distributed energy access capability assessment mainly focuses on the degree of support of the distance measurement scheme for the distribution network to accept distributed energy. For example, whether the distance measurement scheme has the ability to adapt to the access of high-penetration distributed power sources, whether it can accurately identify the fault characteristics of the branch containing distributed power sources, etc.

[0052] It should be noted that social and economic benefits and business operation benefits need to be evaluated from multiple dimensions. Social and economic benefits include reduced user reliability costs and improved social impact, while business operation benefits include reduced operation and maintenance costs and extended equipment life. By comprehensively evaluating these factors, the actual application value of the ranging solution can be fully reflected.

[0053] S200: Preset a first solution evaluation model, and input the second evaluation data into the first solution evaluation model;

[0054] In the embodiment of the present application, the first scheme evaluation model adopts a multi-layer evaluation structure based on BP neural network, including an input layer, a hidden layer and an output layer. The input layer receives the pre-processed second evaluation data, the hidden layer performs feature extraction and nonlinear mapping through multiple neurons, and the output layer gives the final evaluation result.

[0055] In a preferred embodiment, the training process of the model adopts an improved back propagation algorithm, introduces a momentum term and an adaptive learning rate to improve training efficiency and model performance. For example, a parameter configuration of a batch size of 64 and a learning rate of 0.01 is used, and a good model effect is obtained through 3000 rounds of iterative training.

[0056] S201: The evaluation process of the first scheme evaluation model includes: preliminary screening of the candidate distance measurement schemes; comprehensive scoring of the screened candidate distance measurement schemes according to the combined weights; and ranking and recommending the candidate distance measurement schemes based on the comprehensive scoring results.

[0057] S203: The first scheme evaluation model includes: input is the second evaluation data, output is the distance measurement scheme recommendation result, the evaluation index is a combined evaluation index, and the combined evaluation index at least includes a power supply reliability index, an economic index and a technical feasibility index.

[0058] S300: Recommending a fault location solution according to the output of the first solution evaluation model.

[0059] In the embodiment of the present application, the system ranks the alternative solutions according to the comprehensive score output by the model, and recommends the most suitable ranging solution in combination with the actual constraints. For example, the recommended solution results of a certain distribution area show that the ranging solution based on transient characteristic analysis has the highest comprehensive score of 0.92, which is better than the solution based on impedance measurement (score 0.85) and the solution based on traveling wave ranging (score 0.78).

[0060] In an optional embodiment, the system also provides an explainable analysis module for the recommendation results, which intuitively displays the performance of each solution in different evaluation dimensions through visualization methods such as radar charts and weighted contribution, helping decision makers to better understand the basis for the recommendation.

[0061] It should be noted that the special requirements of the actual application scenario need to be considered during the solution recommendation process. For example, for power-intensive areas, more attention may be paid to the solution's anti-interference ability; for load-intensive areas, more attention may be paid to the solution's response speed. By flexibly adjusting the evaluation weights, we can ensure that the recommendation results are more in line with actual needs.

[0062] Furthermore, this embodiment also provides a distribution network fault location solution recommendation system based on combined weighting, comprising:

[0063] An evaluation data acquisition module is used to acquire the distance measurement scheme evaluation data in the first target distribution network area, and to perform a first preprocessing on the distance measurement scheme evaluation data to obtain second evaluation data;

[0064] A model operation module presets a first solution evaluation model and inputs the second evaluation data into the first solution evaluation model;

[0065] The recommendation result acquisition module recommends a fault distance measurement scheme according to the output of the first scheme evaluation model.

[0066] In summary, by introducing a multi-dimensional evaluation data collection mechanism (first-category evaluation data, second-category evaluation data, third-category evaluation data, and fourth-category evaluation data), a comprehensive evaluation coverage of the ranging scheme is achieved, solving the problem of incomplete evaluation of traditional single data sources, making the scheme evaluation results more objective and accurate. This multi-dimensional data collection mechanism can comprehensively evaluate the ranging scheme from multiple perspectives such as technical feasibility, economic rationality, and social benefits, significantly improving the integrity and reliability of the evaluation.

[0067] By setting up a dual preprocessing mechanism of first manual evaluation and first data incremental processing, the quality control and data expansion of the evaluation data are achieved, solving the problems of uneven data quality and insufficient sample size in traditional methods. This preprocessing mechanism not only ensures data quality, but also improves the generalization ability of the evaluation model through data expansion, making the evaluation results more stable and reliable.

[0068] By innovatively introducing a combined weighting algorithm, the subjective weight analysis and objective weight analysis are organically combined to achieve the optimal allocation of evaluation factor weights, solving the problem that the traditional single weight method is easily affected by subjective factors or lacks flexibility. This combined weighting method takes into account both expert experience and objective data characteristics, making the weight allocation more reasonable and scientific.

[0069] By building an evaluation model based on a multi-layer evaluation structure, intelligent evaluation and recommendation of ranging solutions are achieved, solving the problems of low efficiency and poor consistency of traditional manual evaluation. The model can automatically extract features and perform nonlinear mapping, improving evaluation efficiency and accuracy.

[0070] By designing an interpretable analysis module, the evaluation results can be intuitively displayed and explained, solving the problem that the results of traditional black box models are difficult to explain. This visual display method enables decision makers to clearly understand the basis for recommendations and improves the scientific nature of solution selection.

[0071] By introducing a dynamic adjustment mechanism, the system can flexibly adjust the evaluation weights according to the special requirements of different application scenarios, solving the problem that traditional fixed weight solutions are difficult to adapt to the needs of different scenarios. This flexible adjustment mechanism significantly improves the adaptability and practicality of the system.

[0072] Example 2

[0073] Reference Figure 2 - Figure 3 , which is the second embodiment of the present invention, and this embodiment provides a distribution network fault location scheme recommendation method based on combined weighting. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0074] S1: Determine the alternative schemes for fault location and form a scheme layer, determine the evaluation factors for the alternative schemes and form a criterion layer.

[0075] That is to establish Figure 3 The hierarchical structure diagram shown in the figure has the target layer, criterion layer and scheme layer from top to bottom. Among them, the target layer is the recommended ranging scheme; the evaluation factors of the alternative schemes in the criterion layer include improved power supply reliability, improved distributed energy consumption rate, social and economic benefits, benefits of power supply enterprises, communication dependence and time dependence; the scheme layer contains alternative schemes for fault ranging.

[0076] S2: The Saaty1-9 scaling method improved by triangular fuzzy numbers is used to compare each evaluation factor pairwise to obtain a fuzzy judgment matrix. Among them, the traditional Saaty1-9 scaling method and its reciprocal scaling method are improved by introducing triangular fuzzy numbers, and the improved Saaty1-9 scaling method is used to compare each factor of the criterion layer pairwise to obtain a fuzzy judgment matrix; the scaling principle of the improved Saaty1-9 scaling method is shown in Table 1 below:

[0077] Table 1 Scaling principles of the improved Saaty 1-9 scaling method

[0078]

[0079] Furthermore, the fuzzy judgment matrix is ​​obtained as follows:

[0080]

[0081] In the above formula, a ij =(p ij ,q ij ,r ij ) is the result of comparing the evaluation factor i with the evaluation factor j expressed as a triangular fuzzy number; p ij 、r ij They represent the upper and lower limits of triangular fuzzy numbers respectively; q ij Indicates the most likely value of a triangular fuzzy number.

[0082] S3: Perform consistency check on the fuzzy judgment matrix. If it passes the check, proceed to the next step S4. If it fails, return to the previous step S2 and perform pairwise comparison again.

[0083] Furthermore, the consistency check of the fuzzy judgment matrix refers to whether the random consistency ratio CR < 0.1 is satisfied. Furthermore, the calculation formula of CR is as follows:

[0084]

[0085] Furthermore, the calculation method of the consistency index CI is:

[0086]

[0087] In the above formula, λ max is the maximum eigenvalue of the fuzzy judgment matrix.

[0088] Furthermore, due to the maximum eigenvalue λ of the fuzzy judgment matrix max The solution process is rather complicated, so this solution is simplified as follows: the value q with the highest probability of the triangular fuzzy number in step S2 is used. ij Construct a simplified matrix, and use the maximum eigenvalue of the simplified matrix to approximately replace the maximum eigenvalue of the fuzzy judgment matrix, that is, use the maximum eigenvalue of the simplified matrix as the maximum eigenvalue λ of the fuzzy judgment matrix max .

[0089] Further, the value q with the maximum probability of the triangular fuzzy number in step S2 is ij Construct a simplified matrix and get the simplified matrix as follows:

[0090]

[0091] S4: Apply the logarithmic least squares method to the fuzzy judgment matrix to solve the fuzzy weight of each evaluation factor, and fuzzify and normalize the fuzzy weight to obtain the subjective weight of each evaluation factor.

[0092] Furthermore, the fuzzy judgment matrix is ​​solved by the logarithmic least square method to obtain the fuzzy weight of each evaluation factor. The formula is as follows:

[0093]

[0094] That is, the fuzzy weight ω of each evaluation factor 11 ,ω 12 ,ω 13 ,ω 14 ,ω 15 ,ω 16 as follows: Get the fuzzy weight dataset: {ω 1i} i＝1,2,3,...,6 Furthermore, defuzzification of the fuzzy weights is performed by taking the most likely value qij among the triangular fuzzy numbers to calculate {ω 1i} i＝1,2,3,...,6 Do defuzzification.

[0095] Furthermore, normalization is performed (so that the sum of the elements of the vector is 1) to obtain the subjective weight ranking of each evaluation factor as follows:

[0096] ω′ 1i=[ω′ 11 ,ω′ 12 ,ω′ 13 ,…,ω′ 16 ].(6)

[0097] S5: construct an original factor data matrix with the numerical values ​​of the evaluation factors of the alternative solutions; standardize the original factor data matrix, and solve the standard deviation and correlation coefficient of each evaluation factor data.

[0098] Furthermore, assuming that the number of device selection options is c, the original factor data matrix is ​​constructed as follows:

[0099]

[0100] In the above formula, x ci It is expressed as the value of the i-th evaluation factor in the c-th alternative plan, which is the value of the six evaluation factors in each row of the original factor data matrix for one alternative plan.

[0101] Furthermore, the standardization of the original factor data matrix refers to standardizing the evaluation factor values ​​of each alternative (i.e., the elements of each column of the original factor data matrix) to obtain a factor standardized data matrix. If the value of the evaluation factor after the standardization is as large as possible, the evaluation factor is a positive factor; if the value of the evaluation factor after the standardization is as small as possible, the evaluation factor is a negative factor.

[0102] Furthermore, the normalization processing method of the positive evaluation factors is as follows: formula (8); the normalization processing method of the negative evaluation factors is as follows: formula (9).

[0103]

[0104] In the above formula, x′ ci is the evaluation factor value after standardization. i-min The minimum value in the i-th evaluation factor (i.e., the i-th column of the original factor data matrix); x i-max The maximum value in the i-th evaluation factor (i.e. the i-th column of the original factor data matrix).

[0105] Furthermore, the standard deviation S of each evaluation factor data is solved i , refers to solving the standard deviation of each evaluation factor based on the standardized evaluation factor values, that is, based on the obtained factor standardized data matrix. For example, based on the value of the i-th column of the obtained factor standardized data matrix, the standard deviation S of the i-th evaluation factor is obtained. i The calculation formula is already available and will not be repeated here.

[0106] Furthermore, the formula for solving the correlation coefficient is as follows:

[0107]

[0108] In the formula, r ij represents the correlation coefficient between evaluation factors i and j, R i is the correlation coefficient of evaluation factor i.

[0109] S6: Calculate the information content and objective weight of each evaluation factor based on the correlation coefficient.

[0110] Furthermore, the formula for solving the information amount of each evaluation factor is as follows:

[0111] ω 2i =S i R i ;

[0112] In the above formula, S i is the standard deviation of evaluation factor i; R i is the correlation coefficient of evaluation factor i; ω 2i is the amount of information of evaluation factor i.

[0113] Furthermore, to solve the objective weight of each evaluation factor, the information amount of each evaluation factor {ω 2i} i-1,2,3,6 After normalization, objective weight ranking can be obtained

[0114] S7: Calculate the score of each alternative plan using subjective weight and objective weight, and determine the recommended plan.

[0115] Further, the comprehensive weight of each evaluation factor {ω i} i＝1，2,3，...，6 The equation with inequality constraints is the variable, and the comprehensive weight of each evaluation factor ω is obtained. i , the formula is as follows:

[0116]

[0117] stω i ≥0

[0118] Furthermore, the scores of the alternatives are calculated, and the alternative with the highest score is selected as the recommended solution. The score calculation formula of each alternative is as follows:

[0119]

[0120] In the above formula, f c Score the cth alternative; x ci Represented as the value of the i-th evaluation factor in the c-th alternative; ω i is the comprehensive weight of the ith evaluation factor.

[0121] Example 3

[0122] This embodiment also provides a computer device, which is applicable to a method for recommending a distribution network fault distance measurement scheme based on combined weighting, and includes a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a forced oscillation detection and positioning method for a distribution network as proposed in the above embodiment.

[0123] This embodiment further provides a storage medium on which a computer program is stored. When the program is executed by a processor, a forced oscillation detection and positioning method for a distribution network is implemented as proposed in the above embodiment.

[0124] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0125] If the function 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, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0126] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0127] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0128] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0129] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A distribution network fault location scheme recommendation method based on combined weighting, characterized by: The method comprises taking distance measurement scheme evaluation data within a first target distribution network area, and performing a first preprocessing on the distance measurement scheme evaluation data to obtain second evaluation data; Presetting a first solution evaluation model, and inputting the second evaluation data into the first solution evaluation model; A fault location solution is recommended based on the output of the first solution evaluation model.

2. The method for recommending a distribution network fault location solution based on combined weighting according to claim 1, characterized in that: The ranging scheme evaluation data includes: first-category evaluation data, second-category evaluation data, third-category evaluation data and fourth-category evaluation data; the ranging scheme evaluation data is all evaluation data obtained when performing evaluation and analysis through a preset first combination weighting algorithm.

3. The method for recommending a distribution network fault location solution based on combined weighting according to claim 2, characterized in that: The first preprocessing includes at least a first manual evaluation and a first data increment processing; The first manual evaluation includes a first evaluation verification operation and a second evaluation verification operation; the first data increment processing is used to expand the ranging scheme evaluation data after the first manual evaluation.

4. The method for recommending a distribution network fault location solution based on combined weighting according to claim 3, characterized in that: The first combined weighting algorithm includes: subjective weight analysis, which is used to analyze and determine the subjective importance of each evaluation factor; objective weight analysis, which is used to calculate the objective weight of each evaluation factor based on the ranging scheme evaluation data; and combined weight generation, which is used to optimize the combination of subjective weight and objective weight.

5. The method for recommending a distribution network fault location solution based on combined weighting according to claim 4, characterized in that: The evaluation factors include: the degree of improvement in power supply reliability, distributed energy access capabilities, social and economic benefits, enterprise operating benefits, difficulty of program implementation and maintenance costs; the subjective weights of the evaluation factors are obtained through expert scoring method, and the objective weights of the evaluation factors are obtained through data statistical analysis.

6. The method for recommending a distribution network fault location solution based on combined weighting according to claim 5, characterized in that: The evaluation process of the first scheme evaluation model includes: preliminary screening of the alternative ranging schemes; comprehensive scoring of the screened alternative ranging schemes according to the combined weights; and ranking and recommending the alternative ranging schemes based on the comprehensive scoring results.

7. The method for recommending a distribution network fault location solution based on combined weighting according to claim 6, characterized in that: The first scheme evaluation model includes: input is the second evaluation data, output is the ranging scheme recommendation result, the evaluation index is a combined evaluation index, and the combined evaluation index at least includes a power supply reliability index, an economic index and a technical feasibility index.

8. A distribution network fault distance solution recommendation system based on combined weighting, based on the distribution network fault distance solution recommendation method based on combined weighting according to any one of claims 1 to 7, characterized in that: It also includes an evaluation data acquisition module, which acquires the distance measurement scheme evaluation data in the first target distribution network area, and performs a first preprocessing on the distance measurement scheme evaluation data to obtain second evaluation data; A model operation module presets a first solution evaluation model and inputs the second evaluation data into the first solution evaluation model; The recommendation result acquisition module recommends a fault distance measurement solution according to the output of the first solution evaluation model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for recommending a distribution network fault location solution based on combined weighting according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for recommending a distribution network fault location solution based on combined weighting according to any one of claims 1 to 7 are implemented.

Images