District power supply capability evaluation method based on multivariate fuzzy membership function

Abstract

The invention provides a district power supply capability evaluation method based on a multivariate fuzzy membership function. The method specifically comprises the following steps: S1, calculating a district capacity-load ratio, a household average distribution transformer capacity, a line maximum load rate average value and a distribution transformer maximum load rate average value according to monitoring system data; s2, calculating the capacity-load ratio of the transformer area, the per household distribution transformer capacity, the average value of the maximum load rates of the lines, and the score of each single index in the average value of the maximum load rates of the distribution transformers; s3, constructing a multivariate fuzzy state membership function; s4, according to the scores of the four indexes, calculating the state score of the court; s5, constructing a transformer area power supply capability evaluation function based on the state score of the transformer area; and S6, calculating the closeness of the constructed power supply capability evaluation function of the power distribution area and each state membership function, and selecting the state corresponding to the state membership function with the maximum closeness as the power supply capability level of the power distribution area. According to the invention, the problems of inaccurate evaluation of the power supply capability of the existing distribution network area and unreasonable setting of the evaluation threshold can be effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of electric power distribution network, and in particular to a method for evaluating power supply capacity of a distribution station based on multivariate fuzzy membership functions. Background Art

[0002] With the development of my country's economy and society and the deepening of distribution network construction, the addition of a large number of distributed power sources, microgrids, and electric vehicles has made the distribution network structure more complex, and has put forward more stringent requirements and standards for the reliability, safety, economy, quality, and intelligence of distribution network operation. In order to improve the operation level of the distribution network, it is necessary to conduct a comprehensive evaluation of the power supply capacity of the distribution network area and improve the power supply reliability of the power system, which has a certain guiding role in power planning and design.

[0003] At present, the research on the evaluation of distribution network operation status is all based on the evaluation of a single indicator, and the emphasis and degree of the unilateral evaluation are different. There is a lack of evaluation and analysis of the overall power supply capacity, and the evaluation threshold is highly dependent on expert experience. There are situations where the threshold setting is simple and crude, and the threshold setting is unreasonable. Therefore, establishing a scientific and reasonable multi-indicator evaluation system to comprehensively reflect the power supply capacity of the distribution network substation is of great significance for locating the weak links in the distribution network operation and guiding future construction. Summary of the invention

[0004] The purpose of the present invention is to propose a method for evaluating the power supply capacity of a distribution network substation based on a multivariate fuzzy membership function, which can effectively solve the problems of inaccurate evaluation of the power supply capacity of a distribution network substation and unreasonable setting of evaluation thresholds involved in the above-mentioned background technology.

[0005] To achieve the above object, the technical solution of the present invention is: a method for evaluating the power supply capacity of a substation based on a multivariate fuzzy membership function, which specifically includes the following steps:

[0006] S1: Calculate the area capacity-load ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate based on the monitoring system data;

[0007] S2: Calculate the score of each single indicator among the area capacity-load ratio, average household distribution transformer capacity, average value of line maximum load factor, and average value of distribution transformer maximum load factor;

[0008] S3: construct multivariate fuzzy state membership function;

[0009] S4: Calculate the status score of the substation area based on the scores of the four indicators: the substation area capacity-load ratio, the average household distribution transformer capacity, the average value of the maximum load rate of the line, and the average value of the maximum load rate of the distribution transformer;

[0010] S5: Constructing the power supply capacity evaluation function of the substation based on the status score of the substation;

[0011] S6: Calculate the closeness between the constructed substation power supply capacity evaluation function and each state membership function, select the state corresponding to the state membership function with the largest closeness to the substation power supply capacity evaluation function as the power supply capacity level of the distribution station area, and realize the substation power supply capacity evaluation.

[0012] Preferably, the calculation formula of the capacity-load ratio is:

[0013]

[0014] The calculation formula for the average household distribution transformer capacity is:

[0015]

[0016] The calculation formula for the average value of the maximum load rate of the line is:

[0017]

[0018] The calculation formula for the average value of the maximum load factor of the distribution transformer is:

[0019]

[0020] Preferably, the calculation formula for the capacity ratio index score is:

[0021]

[0022] The calculation formula for the average household distribution and transformation capacity index score is:

[0023]

[0024] The calculation formula for the average value of the line maximum load factor index score is:

[0025]

[0026] The calculation formula for the average value index score of the maximum load factor of the distribution transformer is:

[0027]

[0028] In the formula, x rzb 、x hpr 、x xf 、x pf , respectively represent the parameter values ​​of capacity-load ratio, average household distribution transformer capacity, average value of line maximum load factor, and average value of distribution transformer maximum load factor, y rzb ,y hpr ,y xf ,y pf They respectively represent the indicator scores of capacity-load ratio, average household distribution transformer capacity, average maximum line load factor, and average maximum distribution transformer load factor.

[0029] Preferably, the construction of the multivariate fuzzy membership function is specifically:

[0030] The normal fuzzy membership function is used to make a more refined representation of the membership distribution change of the set, and the threshold y between the scores of the four status levels A, B, C, and D is defined through expert experience. yz1 ,y yz2 ,y yz3 The four status levels A, B, C, and D represent normal, caution, abnormal, and severe respectively; the threshold is fuzzy and will be y yz1 ,y yz2 ,y yz3 The midpoints of the four segmented intervals are taken as the mean values ​​u of the four piecewise normal functions. 1 、u 2 、u 3 、u 4 , according to the 3σ rule, the variance δ of the four piecewise normal functions is determined 1 , δ 2 , δ 3 , δ 4 , and using the mean u of the four piecewise normal functions 1 、u 2 、u 3 、u 4 and variance δ 1 , δ 2 , δ 3 , δ 4 Determine the normal membership function f of the four states 1 (y), f 2 (y), f 3 (y) and f 4 (y), y function independent variable;

[0031] The normal membership function f 1 (y), f 2 (y), f 3 (y) and f 4 (y) are as follows:

[0032] Membership function of normal state

[0033]

[0034] Note the membership function of the state

[0035]

[0036] Membership function of abnormal state

[0037]

[0038] Membership function of severe status

[0039]

[0040] Preferably, the mean u of the four piecewise normal functions is 1 、u 2 、u 3 、u 4 and variance δ 1 , δ 2 , δ 3 , δ 4 The calculation is as follows:

[0041]

[0042]

[0043] Preferably, the step S4 specifically includes the following steps:

[0044] S41: Map the domain U to the fuzzy set P:

[0045]

[0046] In the formula, u represents the sample used to construct the multivariate fuzzy membership function, f(u) represents the mapping value of the sample, A, B, C, and D are four status levels, representing normal, caution, abnormal, and severe respectively;

[0047] S42: obtaining multiple groups of sample data, each group of sample data includes four discriminant factors, the four discriminant factors refer to the scores of four indicators: area capacity-load ratio, household average distribution transformer capacity, average value of line maximum load rate, and average value of distribution transformer maximum load rate; comparing the four discriminant factors of each group of sample data with the corresponding status level obtained based on expert experience;

[0048] S43: Assume that the power supply capacity of each substation is a linear combination of four discriminant factors, and the linear model is expressed as:

[0049] y i =β 0 +β 1 x i1 +β 2 x i2 +β 3 x i3 +β 4 x i4 +ε i (10)

[0050] Where yi represents the status score of the area i, xi1, xi2, xi3, and xi4 represent the scores of the four indicators of the area capacity ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate of the area i, β0, β1, β2, β3, and β4 represent the linear coefficients of the four indicators of the area capacity ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate, respectively, and ε i is a normal random variable;

[0051] S44: Substitute the data of step S42 into the linear model of step S43 to obtain the matrix form of the linear model, and solve the undetermined parameter matrix B; the matrix form is:

[0052] Y=X×B+E (11)

[0053] Where Y is the distribution station area grade score matrix, and the value of each element in Y is determined by the state grade divided by the corresponding sample data in step S32 and the mapping function in step S31, n A 、n B 、n C 、n D Indicates the partitions corresponding to the elements in Y divided into four status levels: A, B, C, and D:

[0054]

[0055] X is the sample data matrix. Each row element in X represents a set of sample data and corresponds to the distribution station area level category matrix Y. i1 、x i2 、x i3 、x i4 They represent the scores of the four indicators of the area load ratio, average household distribution transformer capacity, average maximum line load rate, and average maximum distribution transformer load rate of area i:

[0056]

[0057] B is the unknown parameter matrix: B = [β 0 , β 1 , β 2 , β 3 , β 4 ] T ; E is the error matrix;

[0058] S45: Based on the scores of the four indicators of the substation capacity-load ratio, the average household distribution transformer capacity, the average value of the maximum load rate of the line, and the average value of the maximum load rate of the distribution transformer, the status score of the substation to be evaluated is obtained through formula (10).

[0059] Preferably, the solution of the undetermined parameter matrix B is specifically as follows: the solution of the undetermined parameter matrix B is converted into the solution of the minimum value of E=YX×B. According to the least squares principle, the solution is the least squares estimate of B:

[0060] B=(X T X) -1 X T Y (14).

[0061] Preferably, the power supply capacity evaluation function g(y) constructed based on the status score of the substation is specifically:

[0062]

[0063] Where y represents the function variable, t 1 =0.8y i , t 2 =1.2y i ,y i Indicates the status score of area i.

[0064] Preferably, the calculation of the closeness between the constructed power supply capacity evaluation function of the substation area and each state membership function is specifically as follows:

[0065]

[0066] Where f(y) represents a state membership function, g(y) is the constructed power supply capacity evaluation function of the substation, the symbol ∧ is a function or an operator, f(y)∧g(y) represents the maximum integral area of ​​the two, the symbol ∨ is a function and an operator, f(y)∧g(y) represents the minimum integral area of ​​the two functions.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] The power supply capacity evaluation method of the substation based on the multivariate fuzzy membership function of the present invention can realize the integration of multiple indicators, effectively solve the problems of inaccurate capacity evaluation and unreasonable evaluation threshold setting in the single threshold judgment in the distribution network indicator evaluation, and construct a scientific and reasonable multi-indicator evaluation system to realize the scientific and accurate evaluation of the power supply capacity of the distribution network substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0070] The following is combined with Figure 1 , the technical solution of the present invention is specifically described.

[0071] The present invention proposes a method for evaluating the power supply capacity of a substation based on a multivariate fuzzy membership function, which specifically includes the following steps:

[0072] S1: Calculate the area capacity-load ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate based on the monitoring system data;

[0073] S2: Calculate the score of each single indicator among the area capacity-load ratio, average household distribution transformer capacity, average value of line maximum load factor, and average value of distribution transformer maximum load factor;

[0074] S3: construct multivariate fuzzy state membership function;

[0075] S4: Calculate the status score of the substation area based on the scores of the four indicators: the substation area capacity-load ratio, the average household distribution transformer capacity, the average value of the maximum load rate of the line, and the average value of the maximum load rate of the distribution transformer;

[0076] S5: Constructing the power supply capacity evaluation function of the substation based on the status score of the substation;

[0077] S6: Calculate the closeness between the constructed substation power supply capacity evaluation function and each state membership function, select the state corresponding to the state membership function with the largest closeness to the substation power supply capacity evaluation function as the power supply capacity level of the distribution station area, and realize the substation power supply capacity evaluation.

[0078] In this embodiment, the area capacity-load ratio, household average distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate are calculated based on the monitoring system data. The indicators are defined as follows:

[0079] The capacity-load ratio reflects the relationship between the installed capacity and the actual operating capacity of the distribution transformer in the area, and reflects the power supply capacity of the distribution network in the area. The calculation formula of the capacity-load ratio is:

[0080]

[0081] The average household distribution transformer capacity is a moderate indicator, which reflects the reasonable allocation of distribution network resources and is also an important indicator of power supply capacity. The calculation formula of the average household distribution transformer capacity is:

[0082]

[0083] The average value of the maximum load rate of the line reflects the capacity usage and safety level of the line in the region, and is one of the important indicators to characterize the stability of the distribution network operation. The calculation formula of the average value of the maximum load rate of the line is:

[0084]

[0085] The average value of the maximum load rate of the distribution transformer reflects the capacity utilization and safety level of the distribution transformer in the region, and is one of the important technical and economic indicators that characterize the stability of the distribution network operation. The calculation formula for the average value of the maximum load rate of the distribution transformer is:

[0086]

[0087] In this embodiment, the definition of individual indicators involves operating guidelines and industry specifications. By integrating various guidelines and specifications, the calculation method and underlying supporting data of individual indicators are summarized on this basis. The indicator score calculation formula is as follows:

[0088] The calculation formula for the capacity ratio index score is:

[0089]

[0090] The calculation formula for the average household distribution and transformation capacity index score is:

[0091]

[0092] The calculation formula for the average value of the line maximum load factor index score is:

[0093]

[0094] The calculation formula for the average value index score of the maximum load factor of the distribution transformer is:

[0095]

[0096] In the formula, x rzb 、x hpr 、x xf 、x pf , respectively represent the parameter values ​​of capacity-load ratio, average household distribution transformer capacity, average value of line maximum load factor, and average value of distribution transformer maximum load factor, y rzb ,y hpr ,y xf ,y pf They respectively represent the indicator scores of capacity-load ratio, average household distribution transformer capacity, average maximum line load factor, and average maximum distribution transformer load factor.

[0097] In this embodiment, the construction of the multivariate fuzzy membership function is specifically as follows:

[0098] The normal fuzzy membership function is used to make a more refined representation of the membership distribution change of the set, and the threshold y between the scores of the four status levels A, B, C, and D is defined through expert experience. yz1 ,y yz2 ,y yz3 The four status levels A, B, C, and D represent normal, caution, abnormal, and severe respectively; the threshold is fuzzy and will be y yz1 ,y yz2 ,y yz3 The midpoints of the four segmented intervals are taken as the mean values ​​u of the four piecewise normal functions.1 、u 2 、u 3 、u 4 , according to the 3σ rule, the variance δ of the four piecewise normal functions is determined 1 , δ 2 , δ 3 , δ 4 , and using the mean u of the four piecewise normal functions 1 、u 2 、u 3 、u 4 and variance δ 1 , δ 2 , δ 3 , δ 4 Determine the normal membership function f of the four states 1 (y), f 2 (y), f 3 (y) and f 4 (y), y function independent variable;

[0099] The normal membership function f 1 (y), f 2 (y), f 3 (y) and f 4 (y) are as follows:

[0100] Membership function of normal state

[0101]

[0102] Note the membership function of the state

[0103]

[0104] Membership function of abnormal state

[0105]

[0106] Membership function of severe status

[0107]

[0108] Preferably, the mean u of the four piecewise normal functions is 1 、u 2 、u 3 、u 4 and variance δ 1 , δ 2 , δ 3 , δ 4 The calculation is as follows:

[0109]

[0110]

[0111] In this embodiment, step S4 specifically includes the following steps:

[0112] S41: Map the domain U to the fuzzy set P:

[0113]

[0114] In the formula, u represents the sample used to construct the multivariate fuzzy membership function, f(u) represents the mapping value of the sample, A, B, C, and D are four status levels, representing normal, caution, abnormal, and severe respectively;

[0115] S42: obtaining multiple groups of sample data, each group of sample data includes four discriminant factors, the four discriminant factors refer to the scores of four indicators: area capacity-load ratio, household average distribution transformer capacity, average value of line maximum load rate, and average value of distribution transformer maximum load rate; comparing the four discriminant factors of each group of sample data with the corresponding status level obtained based on expert experience;

[0116] S43: Assume that the power supply capacity of each substation is a linear combination of four discriminant factors, and the linear model is expressed as:

[0117] y i =β 0 +β 1 x i1 +β 2 x i2 +β 3 x i3 +β 4 x i4 +ε i (10)

[0118] Where yi represents the status score of the area i, xi1, xi2, xi3, and xi4 represent the scores of the four indicators of the area capacity ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate of the area i, β0, β1, β2, β3, and β4 represent the linear coefficients of the four indicators of the area capacity ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate, respectively, and ε i is a normal random variable;

[0119] S44: Substitute the data of step S42 into the linear model of step S43 to obtain the matrix form of the linear model, and solve the undetermined parameter matrix B; the matrix form is:

[0120] Y=X×B+E (11)

[0121] Where Y is the distribution station area grade score matrix, and the value of each element in Y is determined by the state grade divided by the corresponding sample data in step S32 and the mapping function in step S31, n A 、n B 、n C 、n D Indicates the partitions corresponding to the elements in Y divided into four status levels: A, B, C, and D:

[0122]

[0123] X is the sample data matrix. Each row element in X represents a set of sample data and corresponds to the distribution station area level category matrix Y. i1 、x i2 、x i3 、x i4 They represent the scores of the four indicators of the area load ratio, average household distribution transformer capacity, average maximum line load rate, and average maximum distribution transformer load rate of area i:

[0124]

[0125] B is the unknown parameter matrix: B = [β 0 , β 1 , β 2 , β 3 , β 4 ] T ; E is the error matrix; after solving β0, β1, β2, β3, β4, the construction of expression (10) is completed, so that the state score of the substation can be calculated through the sample constructed formula (10);

[0126] S45: Based on the scores of the four indicators of the substation capacity-load ratio, the average household distribution transformer capacity, the average value of the maximum load rate of the line, and the average value of the maximum load rate of the distribution transformer, the status score of the substation to be evaluated is obtained through formula (10).

[0127] In this embodiment, the solution of the undetermined parameter matrix B is specifically as follows: the solution of the undetermined parameter matrix B is converted into the solution of E=YX×B. According to the least squares principle, the solution is the least squares estimate of B:

[0128] B=(X T X) -1 X T Y (14).

[0129] In this embodiment, the power supply capacity evaluation function g(y) constructed based on the status score of the substation is specifically:

[0130]

[0131] Where y represents the function variable, t 1 =0.8y i , t 2 =1.2y i ,y i Indicates the status score of area i.

[0132] In this embodiment, the calculation of the closeness between the constructed power supply capacity evaluation function of the substation and each state membership function is specifically as follows:

[0133]

[0134] In the formula, f(y) represents a state membership function, g(y) is the constructed power supply capacity evaluation function of the substation, the symbol ∧ is a function or an operator, f(y)∧g(y) represents the maximum integral area of ​​the two, the symbol ∨ is a function and an operator, f(y)∧g(y) represents the minimum integral area of ​​the two functions. Here f(x) is f 1 (x), f 2 (x), f 3 (x) and f 4 (x) is used to substitute into f 1 (x) or f 2 (x) or f 3 (x) or f 4 (x).

[0135] The above are preferred embodiments of the present invention. Any changes made according to the technical solution of the present invention, as long as the resulting functions do not exceed the scope of the technical solution of the present invention, belong to the protection scope of the present invention.

Claims

1. A method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function, characterized in that: The specific steps include: S1: Calculate the area capacity-load ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate based on the monitoring system data; S2: Calculate the score of each single indicator among the area capacity-load ratio, average household distribution transformer capacity, average value of line maximum load factor, and average value of distribution transformer maximum load factor; S3: construct multivariate fuzzy state membership function; S4: Calculate the status score of the substation area based on the scores of the four indicators: the substation area capacity-load ratio, the average household distribution transformer capacity, the average value of the maximum load rate of the line, and the average value of the maximum load rate of the distribution transformer; S5: Constructing the power supply capacity evaluation function of the substation based on the status score of the substation; S6: Calculate the closeness between the constructed substation power supply capacity evaluation function and each state membership function, select the state corresponding to the state membership function with the largest closeness to the substation power supply capacity evaluation function as the power supply capacity level of the distribution station area, and realize the substation power supply capacity evaluation.

2. The method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function according to claim 1 is characterized in that: The calculation formula of the capacity-load ratio is: The calculation formula for the average household distribution transformer capacity is: The calculation formula for the average value of the maximum load rate of the line is: The calculation formula for the average value of the maximum load factor of the distribution transformer is:

3. The method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function according to claim 1 is characterized in that: The calculation formula for the capacity ratio index score is: The calculation formula for the average household distribution and transformation capacity index score is: The calculation formula for the average value of the line maximum load factor index score is: The calculation formula for the average value index score of the maximum load factor of the distribution transformer is: In the formula, x rzb 、x hpr 、x xf 、x pf , respectively represent the parameter values ​​of capacity-load ratio, average household distribution transformer capacity, average value of line maximum load factor, and average value of distribution transformer maximum load factor, y rzb ,y hpr ,y xf ,y pf They respectively represent the indicator scores of capacity-load ratio, average household distribution transformer capacity, average maximum line load factor, and average maximum distribution transformer load factor.

4. The method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function according to claim 1 is characterized in that: The construction of multivariate fuzzy membership function is specifically as follows: The normal fuzzy membership function is used to make a more refined representation of the membership distribution change of the set, and the threshold y between the scores of the four status levels A, B, C, and D is defined through expert experience. yz1 ,y yz2 ,y yz3 , the four status levels A, B, C, and D represent normal, caution, abnormal, and severe respectively; Fuzzy the threshold value, which will be yz1 ,y yz2 ,y yz3 The midpoints of the four divided intervals are used as the means u1, u2, u3, and u4 of the four piecewise normal functions. The variances δ1, δ2, δ3, and δ4 of the four piecewise normal functions are determined according to the 3σ rule. The means u1, u2, u3, and u4 and the variances δ1, δ2, δ3, and δ4 of the four piecewise normal functions are used to determine the normal membership functions f1(y), f2(y), f3(y), and f4(y) of the four states, and y is the independent variable of the function. The normal membership functions f1(y), f2(y), f3(y) and f4(y) are specifically as follows: Membership function of normal state Note the membership function of the state Membership function of abnormal state Membership function of severe status 5. The method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function according to claim 4 is characterized in that: The calculation of the means u1, u2, u3, u4 and variances δ1, δ2, δ3, δ4 of the four piecewise normal functions is as follows:

6. The method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function according to claim 1 is characterized in that: The step S4 specifically comprises the following steps: S41: Map the domain U to the fuzzy set P: In the formula, u represents the sample used to construct the multivariate fuzzy membership function, f(u) represents the mapping value of the sample, A, B, C, and D are four status levels, representing normal, caution, abnormal, and severe respectively; S42: obtaining multiple groups of sample data, each group of sample data includes four discriminant factors, the four discriminant factors refer to the scores of four indicators: area capacity-load ratio, household average distribution transformer capacity, average value of line maximum load rate, and average value of distribution transformer maximum load rate; comparing the four discriminant factors of each group of sample data with the corresponding status level obtained based on expert experience; S43: Assume that the power supply capacity of each substation is a linear combination of four discriminant factors, and the linear model is expressed as: y i =β0+β1x i1 +β2x i2 +β3x i3 +β4x i4 +e i (10) Where yi represents the status score of the area i, xi1, xi2, xi3, and xi4 represent the scores of the four indicators of the area capacity ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate of the area i, β0, β1, β2, β3, and β4 represent the linear coefficients of the four indicators of the area capacity ratio, average household distribution transformer capacity, average line maximum load rate, and average distribution transformer maximum load rate, respectively, and ε i is a normal random variable; S44: Substitute the data of step S42 into the linear model of step S43 to obtain the matrix form of the linear model, and solve the undetermined parameter matrix B; the matrix form is: Y=X×B+E (11) Where Y is the distribution station area grade score matrix, and the value of each element in Y is determined by the state grade divided by the corresponding sample data in step S32 and the mapping function in step S31, n A 、n B 、n C 、n D Indicates the partitions corresponding to the elements in Y divided into four status levels: A, B, C, and D: X is the sample data matrix. Each row element in X represents a set of sample data and corresponds to the distribution station area level category matrix Y. i1 、x i2 、x i3 、x i4 They represent the scores of the four indicators of the area load ratio, average household distribution transformer capacity, average maximum line load rate, and average maximum distribution transformer load rate of area i: B is the parameter matrix to be determined: B = [β0, β1, β2, β3, β4] T ; E is the error matrix; S45: Based on the scores of the four indicators of the substation capacity-load ratio, the average household distribution transformer capacity, the average value of the maximum load rate of the line, and the average value of the maximum load rate of the distribution transformer, the status score of the substation to be evaluated is obtained through formula (10).

7. The method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function according to claim 6 is characterized in that: The solution of the undetermined parameter matrix B is specifically as follows: the solution of the undetermined parameter matrix B is converted into the minimum value of E = YX × B. According to the least squares principle, the solution is the least squares estimate of B: B=(X T X) -1 X T Y (14)。 8. The method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function according to claim 7 is characterized in that: The power supply capacity evaluation function g(y) constructed based on the status score of the substation is specifically: Where y represents the function variable, t1=0.8y i , t2=1.2y i ,y i Indicates the status score of area i.

9. The method for evaluating the power supply capacity of a substation based on multivariate fuzzy membership function according to claim 1, characterized in that: The calculation of the closeness between the constructed power supply capacity evaluation function of the substation and each state membership function is as follows: Where f(y) represents a state membership function, g(y) is the constructed power supply capacity evaluation function of the substation, the symbol ∧ is a function or an operator, f(y)∧g(y) represents the maximum integral area of ​​the two, the symbol ∨ is a function and an operator, f(y)∧g(y) represents the minimum integral area of ​​the two functions.

Images