A method for evaluating line losses in power enterprise substations based on improved fuzzy decision theory

Abstract

The present invention relates to the technical field of power systems, and specifically to a method for evaluating line losses in power enterprise substations based on improved fuzzy decision theory. The present invention constructs a substation line loss evaluation system, which includes a target layer, a criterion layer, and an indicator layer. The period difference is calculated based on the evaluation indicator data of the previous cycle, and an adaptive membership function is generated to obtain a first membership matrix. A basic weight matrix is ​​constructed and calculated with the first membership matrix to obtain a basic substation line loss evaluation value. The basic weight matrix is ​​input into the substation line loss evaluation model, and the basic weight matrix is ​​optimized using a particle swarm algorithm using the weight optimization layer of the model to obtain a first line loss weight matrix. The comprehensive evaluation coefficient calculation layer of the model is used to calculate the comprehensive substation line loss evaluation value based on the first line loss weight matrix and the first membership matrix. The substation line loss level is determined based on the comprehensive line loss evaluation value and a preset threshold value, and an early warning is issued. The present invention improves the accuracy of substation line loss evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method for evaluating line losses in power enterprise substations based on improved fuzzy decision theory. Background Art

[0002] A substation refers to the power supply range or area of ​​one or more transformers in the power system. End users are connected through low-voltage lines within the area to form a power supply network radiating to the surrounding areas. As a terminal connecting users, the line loss problem becomes more prominent; therefore, reasonable substation line loss management is directly related to the economic operation and energy utilization efficiency of the power grid.

[0003] Currently, existing methods for evaluating line losses in substations often rely on a single evaluation metric, failing to comprehensively assess the overall line losses in a substation. Consequently, this can lead to insufficient evaluation of line losses in substations by power companies, directly impacting substation efficiency optimization and the overall operational quality of the power grid.

[0004] Therefore, a line loss evaluation method for power enterprises based on improved fuzzy decision theory is proposed. Summary of the Invention

[0005] The present invention aims to provide a method for evaluating line losses in power substations based on improved fuzzy decision theory. This method constructs a substation line loss evaluation system, comprising a target layer, a criterion layer, and an indicator layer. The system calculates periodic differences based on the evaluation indicator data from the previous cycle and generates an adaptive membership function to obtain a first membership matrix. A basic weight matrix is ​​constructed and combined with the first membership matrix to obtain a basic substation line loss evaluation value. This value is then input into a substation line loss evaluation model. The model's weight optimization layer optimizes the basic weight matrix using a particle swarm algorithm to obtain a first line loss weight matrix. The model's comprehensive evaluation coefficient calculation layer calculates a comprehensive substation line loss evaluation value based on the first line loss weight matrix and the first membership matrix. Based on the comprehensive line loss evaluation value and a preset threshold, the substation line loss level is determined and an early warning is issued. This invention improves the accuracy of substation line loss evaluation.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for evaluating line losses in power enterprise substations based on improved fuzzy decision theory, comprising:

[0008] S1. Constructing a line loss evaluation system for the substation area, the evaluation system includes a target layer, a criterion layer, and an indicator layer; the criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria, and user attribute criteria;

[0009] S2. Comparing the evaluation indicator data of the previous cycle obtained under each indicator layer with the standard reference data to obtain the period difference of each indicator, and obtaining an adaptive membership function based on the difference according to the period difference and the traditional triangular membership function; and obtaining a first membership matrix according to the adaptive membership function;

[0010] S3. Construct a basic weight matrix, obtain a basic substation line loss evaluation value based on the first membership matrix and the basic weight matrix, and input the value into a substation line loss evaluation model. The substation line loss evaluation model includes a preprocessing layer, a weight optimization layer, and a comprehensive evaluation coefficient calculation layer. The weight optimization layer optimizes the basic weight matrix using a particle swarm optimization algorithm to obtain a first line loss weight matrix.

[0011] S4. Analyze the first line loss weight matrix and the first membership matrix according to the comprehensive evaluation coefficient calculation layer of the model to calculate the comprehensive area line loss evaluation value;

[0012] S5. Determine the line loss level of the substation based on the comprehensive substation line loss evaluation value and the preset threshold, and issue a warning in a timely manner based on the warning level.

[0013] Preferably, the indicator layer under the equipment attribute criteria includes equipment update frequency, equipment fault response time and equipment cost; the indicator layer under the management attribute criteria includes the average educational level of managers, the number of managers and the experience index of managers; the indicator layer under the line attribute criteria includes line quality, line design and line wear coefficient; the indicator layer under the load attribute criteria includes average load, maximum load and load fluctuation rate; the indicator layer under the user attribute criteria includes user scale, user type and frequency of illegal electricity use.

[0014] Preferably, managers are divided into levels according to their years of work experience, and experience level weights of each manager are generated to obtain the manager experience index; the user types include residential users, commercial users and industrial users.

[0015] Preferably, the adaptive membership function based on difference is:

[0016]

[0017] Among them, u(i) represents the adaptive membership value of the i-th evaluation index; a new 、b new and c new is a set of adjustment parameters for constructing the adaptive membership function; a0, b0 and c0 are a set of initial parameters for constructing the traditional triangular membership function; α i , β i and γi are three adjustment parameters; x i Indicates the i-th evaluation index data of the previous cycle; x i,ref The standard reference data representing the i-th evaluation index.

[0018] Preferably, the generation process of the first membership matrix is:

[0019] Obtaining adaptive membership values ​​of various evaluation indicators according to the adaptive membership function based on the degree of difference, generating a matrix of M rows and N columns of the adaptive membership values ​​of various evaluation indicators to obtain the first membership matrix; wherein M represents the number of principle layers; and N represents the number of evaluation indicators in the indicator layer;

[0020] The first membership matrix is:

[0021]

[0022] Among them, R M*N Represented as the first membership matrix.

[0023] Preferably, the line loss evaluation value of the basic substation area is:

[0024] E base =R M*N T *W base ;

[0025] Among them, E base Expressed as the line loss evaluation value of the basic substation area; R M*N T W is the transposed matrix of the first membership matrix; base Represented as the basic weight matrix.

[0026] Preferably, the weight optimization layer uses a particle swarm optimization algorithm to optimize the basic weight matrix to obtain a first line loss weight matrix. The specific process includes: initializing a particle swarm, including the position and velocity of the particles, each particle represents a set of weight combinations, and calculating a fitness function based on weight optimization according to the basic substation line loss evaluation value and the actual substation line loss data. By continuously iteratively updating the position and velocity of the particles, a global optimal weight combination is obtained, and based on the global optimal weight combination, the first line loss weight matrix is ​​obtained.

[0027] Preferably, the fitness function based on weight optimization is obtained by taking the absolute value of the error between the basic substation line loss evaluation value and the actual line loss value, and the actual line loss value is obtained according to the line loss report of the previous period of the substation.

[0028] Preferably, the comprehensive area line loss evaluation value is:

[0029] E com =R M*N T *W opt ;

[0030] Among them, E com It is expressed as the comprehensive area line loss evaluation value; R M*N T The device matrix represented as the first membership matrix; W opt Represented as the first line loss weight matrix.

[0031] Preferably, the line loss level of the substation is compared with a preset threshold value based on the comprehensive substation line loss evaluation value. The line loss level includes light line loss, medium line loss, and heavy line loss. The preset threshold value includes a first line loss level discrimination threshold value and a second line loss level discrimination threshold value. The specific calculation process of the line loss level is as follows:

[0032]

[0033] Wherein, ALo represents the comprehensive line loss level; LineLoss low Indicates light line loss; LineLoss intermediate Indicates intermediate line loss; LineLoss high Indicates heavy line loss; E com It represents the comprehensive substation line loss evaluation value; Thres1 represents the first line loss level judgment threshold; Thres2 represents the second line loss level judgment threshold.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] 1. The present invention constructs a substation line loss evaluation system, which includes a target layer, a criterion layer and an indicator layer; the criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria and user attribute criteria; each criterion layer includes setting various evaluation indicators, and by analyzing the difference between each evaluation indicator data and the standard reference data in the previous cycle, and based on the traditional triangular membership function, the membership value of each evaluation indicator to the substation line loss evaluation target is obtained, and the complex and changeable substation line loss evaluation indicators are converted into fuzzy quantities, thereby quantifying the membership of each evaluation indicator, improving the comprehensiveness and flexibility of the substation line loss evaluation, and further improving the accuracy of the substation line loss evaluation.

[0036] 2. The present invention obtains the first membership matrix of the substation based on the adaptive membership function, and constructs a basic weight matrix to obtain the basic substation line loss evaluation value of the substation, and obtains the optimization objective function based on the basic substation line loss evaluation value and the actual substation line loss value, and uses the particle swarm optimization algorithm to optimize the optimization objective function to obtain the first line loss weight matrix. Through the first line loss evaluation matrix, a good foundation is laid for realizing the evaluation of substation line loss, and the accuracy of substation line loss evaluation is further improved.

[0037] 3. The present invention calculates the first line loss weight matrix and the first membership matrix through optimization to obtain a comprehensive substation line loss evaluation value, thereby improving the comprehensiveness of the substation line loss evaluation. The comprehensive evaluation value is compared with the preset threshold to obtain the line loss level of the substation, and timely warnings are issued according to the line loss level, thereby improving the management efficiency of the substation line loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flow chart of a method for evaluating line loss in a power enterprise substation based on improved fuzzy decision theory provided by an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of a substation line loss evaluation system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 making creative efforts are within the scope of protection of the present invention.

[0041] Example 1

[0042] In order to improve the accuracy of line loss evaluation, A substation applied a line loss evaluation method based on improved fuzzy decision theory.

[0043] Reference Figure 1 , which is a flow chart of a line loss evaluation method for power enterprises based on improved fuzzy decision theory, including:

[0044] S1. Constructing a line loss evaluation system for the substation area, the evaluation system includes a target layer, a criterion layer, and an indicator layer; the criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria, and user attribute criteria;

[0045] Reference Figure 2, which is a schematic diagram of a substation line loss evaluation system, including a target layer, a criterion layer and an indicator layer. The target layer is the substation line loss evaluation; the criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria and user attribute criteria; the indicator layer under the equipment attribute criteria includes equipment update frequency, equipment failure response time and equipment cost; the indicator layer under the management attribute criteria includes the average education level of managers, the number of managers and the experience index of managers; the indicator layer under the line attribute criteria includes line quality, line design and line wear coefficient; the indicator layer under the load attribute criteria includes average load, maximum load and load fluctuation rate; the indicator layer under the user attribute criteria includes user scale, user type and frequency of illegal electricity use.

[0046] Furthermore, the equipment update frequency is obtained by providing the equipment update record report of the A substation; the equipment fault response time automatically collects the start and end time of each fault in the A substation and calculates the response time. The equipment cost is obtained through the equipment procurement record of the A substation; the average educational level of the managers is obtained by dividing the different educational levels into grades, and the quotient of the sum of the grades and the number of people; the managers are divided into grades according to their years of work, and the experience level weight of each manager is generated to obtain the manager experience index; the line quality can detect the corrosion of the line through the remote monitoring equipment installed on the line, and obtain the non The corroded line segment is obtained by dividing the non-corroded line segment by the total line segment to obtain the line quality; the line design is analyzed by the line design experts of the power company to obtain the qualified rate of the substation line design; the line wear coefficient is obtained by subtracting the line quality value from 1; the average load, maximum load and load fluctuation rate are obtained from the power load report of substation A; the user scale is obtained by the number of power users in substation A; the user types include residential users, commercial users and industrial users; different type weight values ​​are assigned to each type; the frequency of illegal electricity use behavior is obtained by dividing the number of illegal electricity use behaviors of users during the monitoring period by the period time;

[0047] S2. Comparing the evaluation indicator data of the previous cycle obtained under each indicator layer with the standard reference data to obtain the period difference of each indicator, and obtaining an adaptive membership function based on the difference according to the period difference and the traditional triangular membership function; and obtaining a first membership matrix according to the adaptive membership function;

[0048] S3. Construct a basic weight matrix, obtain a basic substation line loss evaluation value based on the first membership matrix and the basic weight matrix, and input the value into a substation line loss evaluation model. The substation line loss evaluation model includes a preprocessing layer, a weight optimization layer, and a comprehensive evaluation coefficient calculation layer. The weight optimization layer optimizes the basic weight matrix using a particle swarm optimization algorithm to obtain a first line loss weight matrix.

[0049] S4. Analyze the first line loss weight matrix and the first membership matrix according to the comprehensive evaluation coefficient calculation layer of the model to calculate the comprehensive area line loss evaluation value;

[0050] S5. Determine the comprehensive line loss level of the substation based on the comprehensive substation line loss evaluation value and the preset threshold, and issue a warning in a timely manner based on the warning level.

[0051] The traditional triangular membership function is:

[0052]

[0053] Wherein, u(x) represents the traditional triangular membership function; a, b and c are a set of initial parameters for constructing the traditional triangular membership function; α i , β i and γ i There are three adjustment parameters;

[0054] Furthermore, the adaptive membership function based on the difference is:

[0055]

[0056] Among them, u(i) represents the adaptive membership value of the i-th evaluation index; a new 、b new and c new is a set of adjustment parameters for constructing the adaptive membership function; a0, b0 and c0 are a set of initial parameters for constructing the traditional triangular membership function; α i , β i and γ i are three adjustment parameters; x i Indicates the i-th evaluation index data of the previous cycle; x i,ref The standard reference data representing the i-th evaluation index.

[0057] Furthermore, the generation process of the first membership matrix is:

[0058] Obtaining adaptive membership values ​​of various evaluation indicators according to the adaptive membership function based on the degree of difference, generating a matrix of M rows and N columns of the adaptive membership values ​​of various evaluation indicators to obtain the first membership matrix; wherein M represents the number of principle layers; and N represents the number of evaluation indicators in the indicator layer;

[0059] The first membership matrix is:

[0060]

[0061] Among them, R M*N Expressed as the first membership matrix;

[0062] This embodiment constructs a substation line loss evaluation system, including a target layer, a criterion layer and an indicator layer; the criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria and user attribute criteria; each criterion layer includes setting various evaluation indicators, and by analyzing the difference between each evaluation indicator data and the standard reference data in the previous cycle, and based on the traditional triangular membership function, the membership value of each evaluation indicator to the substation line loss evaluation target is obtained, and the complex and changeable substation line loss evaluation indicators are converted into fuzzy quantities, thereby quantifying the membership of each evaluation indicator, improving the comprehensiveness and flexibility of the substation line loss evaluation, and further improving the accuracy of the substation line loss evaluation.

[0063] Furthermore, the line loss evaluation value of the basic substation area is:

[0064] E base =R M*N T *W base ;

[0065] Among them, E base Expressed as the line loss evaluation value of the basic substation area; R M*N T W is the transposed matrix of the first membership matrix; base Represented as the basic weight matrix;

[0066] The basic weight matrix is:

[0067]

[0068] Among them, W base It is represented as the basic weight matrix; w1, w2, w3, w4 and w5 are five weight parameters for constructing the basic weight matrix;

[0069] Furthermore, the weight optimization layer optimizes the basic weight matrix using a particle swarm optimization algorithm to obtain a first line loss weight matrix. The specific process includes: initializing a particle swarm, including the position and velocity of the particles, each particle representing a set of weight combinations; calculating a fitness function based on weight optimization according to the basic substation line loss evaluation value and the actual substation line loss data; obtaining a global optimal weight combination by continuously iteratively updating the position and velocity of the particles; and obtaining the first line loss weight matrix based on the global optimal weight combination;

[0070] The fitness function is:

[0071] F=|E base -E actual |;

[0072] Among them, F represents the fitness function; E base It is expressed as the line loss evaluation value of the basic substation area; E actual Expressed as actual line loss value;

[0073] Furthermore, the fitness function based on weight optimization is obtained by taking the absolute value of the error between the basic substation line loss evaluation value and the actual line loss value, and the actual line loss value is obtained according to the line loss report of the previous period of the A substation.

[0074] This embodiment obtains the first membership matrix of the substation based on the adaptive membership function, and constructs a basic weight matrix to obtain the basic substation line loss evaluation value of the substation, and obtains the optimization objective function based on the basic substation line loss evaluation value and the actual substation line loss value, and uses the particle swarm optimization algorithm to optimize the optimization objective function to obtain the first line loss weight matrix. Through the first line loss evaluation matrix, a good foundation is laid for realizing the evaluation of substation line loss, and the accuracy of substation line loss evaluation is further improved.

[0075] Furthermore, the comprehensive area line loss evaluation value is:

[0076] E com =R M*N T *W opt ;

[0077] Among them, E com It is expressed as the comprehensive area line loss evaluation value; R M*N T The device matrix represented as the first membership matrix; W opt Expressed as the first line loss weight matrix;

[0078] Furthermore, the line loss level of the substation is compared with a preset threshold value based on the comprehensive substation line loss evaluation value. The line loss level includes light line loss, medium line loss, and heavy line loss. The preset threshold value includes a first line loss level discrimination threshold value and a second line loss level discrimination threshold value. The specific calculation process of the line loss level is as follows:

[0079]

[0080] Wherein, ALo represents the comprehensive line loss level; LineLoss low Indicates light line loss; LineLoss intermediate Indicates intermediate line loss; LineLoss high Indicates heavy line loss; E com It represents the comprehensive area line loss evaluation value; Thres1 represents the first line loss level judgment threshold; Thres2 represents the second line loss level judgment threshold;

[0081] In this embodiment, when the comprehensive line loss level of the A substation is severe, an early warning is issued.

[0082] This embodiment calculates the optimized first line loss weight matrix and the first membership matrix to obtain a comprehensive substation line loss evaluation value, thereby improving the comprehensiveness of the substation line loss evaluation. The comprehensive evaluation value is compared with the preset threshold to obtain the substation line loss level, and timely warnings are issued based on the line loss level, thereby improving the management efficiency of the substation line loss.

[0083] Example 2

[0084] In order to improve the accuracy of line loss evaluation, a line loss evaluation method for power enterprise substations based on improved fuzzy decision theory was applied in Substation B.

[0085] Reference Figure 1 , which is a flow chart of a line loss evaluation method for power enterprises based on improved fuzzy decision theory, including:

[0086] S1. Constructing a line loss evaluation system for the substation area, the evaluation system includes a target layer, a criterion layer, and an indicator layer; the criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria, and user attribute criteria;

[0087] Reference Figure 2, which is a schematic diagram of a substation line loss evaluation system, including a target layer, a criterion layer and an indicator layer. The target layer is the substation line loss evaluation; the criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria and user attribute criteria; the indicator layer under the equipment attribute criteria includes equipment update frequency, equipment failure response time and equipment cost; the indicator layer under the management attribute criteria includes the average education level of managers, the number of managers and the experience index of managers; the indicator layer under the line attribute criteria includes line quality, line design and line wear coefficient; the indicator layer under the load attribute criteria includes average load, maximum load and load fluctuation rate; the indicator layer under the user attribute criteria includes user scale, user type and frequency of illegal electricity use.

[0088] Furthermore, the equipment update frequency is obtained by providing the equipment update record report of the B station area; the equipment fault response time automatically collects the start and end time of each fault in the B station area and calculates the response time, and the equipment cost is obtained through the equipment procurement record of the B station area; the average educational level of the managers is divided into grades according to different educational levels, and obtained according to the sum of the grades and the quotient of the number of people; the managers are divided into grades according to their years of work, and the experience grade weight of each manager is generated to obtain the manager experience index; the line quality can detect the corrosion of the line through the remote monitoring equipment installed on the line, and obtain the non The corroded line segment is obtained by dividing the non-corroded line segment by the total line segment to obtain the line quality; the line design is analyzed by the line design experts of the power company to obtain the qualified rate of the substation line design; the line wear coefficient is obtained by subtracting the line quality value from 1; the average load, maximum load and load fluctuation rate are obtained from the power load report of the B substation; the user scale is obtained by the number of power users in the B substation; the user types include residential users, commercial users and industrial users; different type weight values ​​are assigned to each type; the frequency of illegal electricity use behavior is obtained by dividing the number of illegal electricity use behaviors of users during the monitoring period by the period time;

[0089] S2. Comparing the evaluation indicator data of the previous cycle obtained under each indicator layer with the standard reference data to obtain the period difference of each indicator, and obtaining an adaptive membership function based on the difference according to the period difference and the traditional triangular membership function; and obtaining a first membership matrix according to the adaptive membership function;

[0090] S3. Construct a basic weight matrix, obtain a basic substation line loss evaluation value based on the first membership matrix and the basic weight matrix, and input the value into a substation line loss evaluation model. The substation line loss evaluation model includes a preprocessing layer, a weight optimization layer, and a comprehensive evaluation coefficient calculation layer. The weight optimization layer optimizes the basic weight matrix using a particle swarm optimization algorithm to obtain a first line loss weight matrix.

[0091] S4. Analyze the first line loss weight matrix and the first membership matrix according to the comprehensive evaluation coefficient calculation layer of the model to calculate the comprehensive area line loss evaluation value;

[0092] S5. Determine the comprehensive line loss level of the substation based on the comprehensive substation line loss evaluation value and the preset threshold, and issue a warning in a timely manner based on the warning level.

[0093] The traditional triangular membership function is:

[0094]

[0095] Wherein, u(x) represents the traditional triangular membership function; a, b and c are a set of initial parameters for constructing the traditional triangular membership function; α i , β i and γ i There are three adjustment parameters;

[0096] Furthermore, the adaptive membership function based on the difference is:

[0097]

[0098] Among them, u(i) represents the adaptive membership value of the i-th evaluation index; a new 、b new and c new is a set of adjustment parameters for constructing the adaptive membership function; a0, b0 and c0 are a set of initial parameters for constructing the traditional triangular membership function; α i , β i and γ i are three adjustment parameters; x i Indicates the i-th evaluation index data of the previous cycle; x i,ref The standard reference data representing the i-th evaluation index.

[0099] Furthermore, the generation process of the first membership matrix is:

[0100] Obtaining adaptive membership values ​​of various evaluation indicators according to the adaptive membership function based on the degree of difference, generating a matrix of M rows and N columns of the adaptive membership values ​​of various evaluation indicators to obtain the first membership matrix; wherein M represents the number of principle layers; and N represents the number of evaluation indicators in the indicator layer;

[0101] The first membership matrix is:

[0102]

[0103] Among them, R M*N Expressed as the first membership matrix;

[0104] This embodiment constructs a substation line loss evaluation system, including a target layer, a criterion layer and an indicator layer; the criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria and user attribute criteria; each criterion layer includes setting various evaluation indicators, and by analyzing the difference between each evaluation indicator data and the standard reference data in the previous cycle, and based on the traditional triangular membership function, the membership value of each evaluation indicator to the substation line loss evaluation target is obtained, and the complex and changeable substation line loss evaluation indicators are converted into fuzzy quantities, thereby quantifying the membership of each evaluation indicator, improving the comprehensiveness and flexibility of the substation line loss evaluation, and further improving the accuracy of the substation line loss evaluation.

[0105] Furthermore, the line loss evaluation value of the basic substation area is:

[0106] E base =R M*N T *W base ;

[0107] Among them, E base Expressed as the line loss evaluation value of the basic substation area; R M*N T W is the transposed matrix of the first membership matrix; base Represented as the basic weight matrix;

[0108] The basic weight matrix is:

[0109]

[0110] Among them, W base It is represented as the basic weight matrix; w1, w2, w3, w4 and w5 are five weight parameters for constructing the basic weight matrix;

[0111] Furthermore, the weight optimization layer optimizes the basic weight matrix using a particle swarm optimization algorithm to obtain a first line loss weight matrix. The specific process includes: initializing a particle swarm, including the position and velocity of the particles, each particle representing a set of weight combinations; calculating a fitness function based on weight optimization according to the basic substation line loss evaluation value and the actual substation line loss data; obtaining a global optimal weight combination by continuously iteratively updating the position and velocity of the particles; and obtaining the first line loss weight matrix based on the global optimal weight combination;

[0112] The fitness function is:

[0113] F=|E base -E actual |;

[0114] Among them, F represents the fitness function; E base It is expressed as the line loss evaluation value of the basic substation area; E actual Expressed as actual line loss value;

[0115] Furthermore, the fitness function based on weight optimization is obtained by taking the absolute value of the error between the basic substation line loss evaluation value and the actual line loss value, and the actual line loss value is obtained according to the line loss report of the previous period in the B substation.

[0116] This embodiment obtains the first membership matrix of the substation based on the adaptive membership function, and constructs a basic weight matrix to obtain the basic substation line loss evaluation value of the substation, and obtains the optimization objective function based on the basic substation line loss evaluation value and the actual substation line loss value, and uses the particle swarm optimization algorithm to optimize the optimization objective function to obtain the first line loss weight matrix. Through the first line loss evaluation matrix, a good foundation is laid for realizing the evaluation of substation line loss, and the accuracy of substation line loss evaluation is further improved.

[0117] Furthermore, the comprehensive area line loss evaluation value is:

[0118] E com =R M*N T *W opt ;

[0119] Among them, E com It is expressed as the comprehensive area line loss evaluation value; R M*N T The device matrix represented as the first membership matrix; W opt Expressed as the first line loss weight matrix;

[0120] Furthermore, the line loss level of the substation is compared with a preset threshold value based on the comprehensive substation line loss evaluation value. The line loss level includes light line loss, medium line loss, and heavy line loss. The preset threshold value includes a first line loss level discrimination threshold value and a second line loss level discrimination threshold value. The specific calculation process of the line loss level is as follows:

[0121]

[0122] Wherein, ALo represents the comprehensive line loss level; LineLoss low Indicates light line loss; LineLoss intermediate Indicates intermediate line loss; LineLoss high Indicates heavy line loss; E com It represents the comprehensive area line loss evaluation value; Thres1 represents the first line loss level judgment threshold; Thres2 represents the second line loss level judgment threshold;

[0123] In this embodiment, when the comprehensive line loss level of the B substation area is severe, an early warning is issued.

[0124] This embodiment calculates the optimized first line loss weight matrix and the first membership matrix to obtain a comprehensive substation line loss evaluation value, thereby improving the comprehensiveness of the substation line loss evaluation. The comprehensive evaluation value is compared with the preset threshold to obtain the substation line loss level, and timely warnings are issued based on the line loss level, thereby improving the management efficiency of the substation line loss.

[0125] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory, characterized in that: The power enterprise substation line loss evaluation method based on improved fuzzy decision theory includes: S1. Construct a substation line loss evaluation system, comprising a target layer, a criterion layer, and an indicator layer. The criterion layer includes equipment attribute criteria, management attribute criteria, line attribute criteria, load attribute criteria, and user attribute criteria. The indicator layer under the equipment attribute criteria includes equipment update frequency, equipment failure response time, and equipment cost. The indicator layer under the management attribute criteria includes the average education level of management personnel, the number of management personnel, and the management personnel experience index. The indicator layer under the line attribute criteria includes line quality, line design, and line wear coefficient. The indicator layer under the load attribute criteria includes average load, maximum load, and load fluctuation rate. The indicator layer under the user attribute criteria includes user scale, user type, and the frequency of illegal electricity use. S2. Comparing the evaluation indicator data of the previous cycle obtained under each indicator layer with the standard reference data to obtain the period difference of each indicator, and obtaining an adaptive membership function based on the difference according to the period difference and the traditional triangular membership function; and obtaining a first membership matrix according to the adaptive membership function; S3. Construct a basic weight matrix, obtain a basic substation line loss evaluation value based on the first membership matrix and the basic weight matrix, and input the value into a substation line loss evaluation model. The substation line loss evaluation model includes a preprocessing layer, a weight optimization layer, and a comprehensive evaluation coefficient calculation layer. The weight optimization layer optimizes the basic weight matrix using a particle swarm optimization algorithm to obtain a first line loss weight matrix. S4. Analyze the first line loss weight matrix and the first membership matrix according to the comprehensive evaluation coefficient calculation layer of the model to calculate the comprehensive area line loss evaluation value; S5. Determine the comprehensive line loss level of the substation based on the comprehensive substation line loss evaluation value and the preset threshold, and issue a warning in a timely manner based on the warning level.

2. The method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory according to claim 1, characterized in that: The managers are divided into different levels according to their years of work experience, and the experience level weight of each manager is generated to obtain the manager experience index; the user types include residential users, commercial users and industrial users.

3. The method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory according to claim 1, characterized in that: The adaptive membership function based on difference is: ； ； ； ； in, Indicates the Adaptive membership value of each evaluation index; 、 and is a set of adjustment parameters for constructing the adaptive membership function; 、 and is a set of initial parameters for constructing the traditional triangular membership function; 、 and There are three adjustment parameters; Indicates the last cycle Evaluation index data; Indicates the The standard reference data of the evaluation indicators.

4. The method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory according to claim 1, characterized in that: The generation process of the first membership matrix is: According to the adaptive membership function based on the difference, the adaptive membership value of each evaluation index is obtained, and the adaptive membership value of each evaluation index is converted into the adaptive membership value of each evaluation index according to the difference. OK Column generation matrix, to obtain the first membership matrix; wherein, Indicates the number of principle layers; Represents the number of evaluation indicators of the indicator layer; The first membership matrix is: ； in, Represented as the first membership matrix.

5. The method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory according to claim 1, characterized in that: The line loss evaluation value of the basic substation area is: ； in, It is represented by the line loss evaluation value of the basic substation area; is represented as the transposed matrix of the first membership matrix; Represented as the basic weight matrix.

6. The method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory according to claim 1, characterized in that: The weight optimization layer uses a particle swarm optimization algorithm to optimize the basic weight matrix to obtain a first line loss weight matrix. The specific process includes: initializing a particle swarm, including the position and velocity of the particles, each particle represents a set of weight combinations, and calculating a fitness function based on weight optimization according to the basic substation line loss evaluation value and the actual substation line loss data. By continuously iteratively updating the position and velocity of the particles, the global optimal weight combination is obtained, and based on the global optimal weight combination, the first line loss weight matrix is ​​obtained.

7. The method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory according to claim 6, characterized in that: The fitness function based on weight optimization is obtained by taking the absolute value of the error between the basic substation line loss evaluation value and the actual line loss value, and the actual line loss value is obtained according to the line loss report of the previous period of the substation.

8. The method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory according to claim 1, characterized in that: The comprehensive area line loss evaluation value is: ； in, It is represented by the comprehensive area line loss evaluation value; a device matrix represented as the first membership matrix; Represented as the first line loss weight matrix.

9. The method for evaluating line loss in power enterprise substations based on improved fuzzy decision theory according to claim 1, characterized in that: The comprehensive line loss level of the substation is compared with a preset threshold value based on the comprehensive substation line loss evaluation value. The line loss levels include light line loss, medium line loss, and heavy line loss. The preset threshold values ​​include a first line loss level discrimination threshold value and a second line loss level discrimination threshold value. The specific calculation process of the line loss level is as follows: ； in, Indicates the comprehensive line loss level; Indicates light line loss; Indicates intermediate line loss; Indicates heavy line loss; It is represented by the comprehensive area line loss evaluation value; Indicates the first line loss level judgment threshold; Indicates the second line loss level judgment threshold.

Images