Area line loss anomaly multi-dimensional evaluation method and system

Abstract

The invention relates to a transformer area line loss abnormity multi-dimensional evaluation method and system, and the method comprises the following steps: obtaining the measurement data of a power supply side general meter of a target transformer area and all electric meters at the transformer area side, and carrying out the preprocessing, and obtaining the measurement data of the target transformer area; constructing a split-phase electric quantity balance model of the target transformer area based on the transformer area topological structure and the energy conservation law, and calculating balance electric quantity data based on the electric quantity balance model of the target transformer area and the measurement data of the target transformer area; a multi-dimensional evaluation index system of the line loss of the multi-dimensional transformer area is constructed; wherein the five evaluation indexes comprise a non-technical line loss ratio, a determination coefficient of the transformer subdivision phase electric quantity balance model, a mean absolute error ratio of the transformer subdivision phase electric quantity balance model, a median of a regression coefficient of the transformer subdivision phase electric quantity balance model and a fixed loss ratio of the transformer subdivision phase electric quantity balance model; and index values of the five evaluation indexes are calculated through the balanced electric quantity data, and line loss abnormity evaluation of the target transformer area is carried out according to a pre-constructed evaluation rule.

Description

Technical Field

[0001] The present invention relates to a multi-dimensional evaluation method and system for abnormal line loss in a transformer area, and belongs to the technical field of line loss management in a transformer area. Background Art

[0002] For power supply companies, deepening line loss management can effectively protect the legitimate rights and interests of both power supply and demand parties and promote fair transactions. As the last link in the distribution network, the substation has many complex line loss problems, which makes the management of line loss extremely difficult. Reasonable evaluation of the line loss level of the substation is the premise for power supply companies to carry out line loss diagnosis and management, and plays a vital role in ensuring the safe and stable operation of the power grid, improving energy utilization efficiency, and safeguarding the rights and interests of users.

[0003] With the development of HPLC technology, it is now possible to freeze the indication of electricity data for 15 minutes. High-frequency electricity data collection enables the calculation and analysis of line loss to be based on a more detailed time granularity, which provides the possibility for refined evaluation of line loss. The widely used line loss evaluation method is to compare and analyze the theoretical line loss with the statistical line loss rate index of the substation, that is, the "one substation one index" line loss evaluation method. Although this method has achieved the control of line loss to a certain extent, it has also exposed its shortcomings in practical applications. For example, some substations with electricity theft have a relatively small amount of electricity theft, resulting in the overall line loss rate not exceeding the standard range, so that these substations are mistakenly identified as qualified, and negative errors may also lead to misjudgment of qualified substations. These problems not only affect the economic benefits of power companies, but may also lead to safety hazards and reduced service quality. Therefore, the accuracy and effectiveness of the "one substation one index" management model are limited in the face of complex real-world environments. Summary of the invention

[0004] In order to solve the problems existing in the above-mentioned prior art, the present invention proposes a multi-dimensional evaluation method and system for line loss anomaly in a substation, which constructs a variety of line loss anomaly evaluation indicators and establishes corresponding judgment rules to achieve a reasonable evaluation of line loss in the substation.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention proposes a multi-dimensional evaluation method for abnormal line loss in a transformer area, comprising the following steps:

[0007] Obtain the metering data of the total meter on the power supply side of the target substation and all the meters on the substation side, and perform preprocessing to obtain the metering data of the target substation;

[0008] Based on the substation topology and the law of conservation of energy, a phase-by-phase power balance model of the target substation is constructed, and the balance power data is calculated based on the power balance model of the target substation and the metering data of the target substation;

[0009] Construct a multi-dimensional evaluation index system for substation line loss, which includes five evaluation indicators: the proportion of non-technical line loss, the coefficient of determination of the substation phase power balance model, the average absolute error proportion of the substation phase power balance model, the median of the regression coefficient of the substation phase power balance model, and the proportion of fixed loss of the substation phase power balance model;

[0010] The index values ​​of five evaluation indicators are calculated by balancing the power data, and the line loss anomaly evaluation of the target substation is carried out according to the index values ​​and pre-built evaluation rules.

[0011] As a preferred implementation, the metering data of the target substation power supply side total meter and all the electric meters on the substation side include the voltage and power indication curve data of the substation power supply side total meter and all the electric meters on the substation user side, as well as the phase sequence information of the substation power supply side total meter and all the electric meters on the substation user side.

[0012] As a preferred embodiment, the pretreatment comprises the following steps:

[0013] For the electric quantity indication curve data, the length of the metering cycle is selected as L, and the electric quantity consumption data of a metering cycle is obtained by differential operation, as shown in the following formula:

[0014] h i,t =F·(e i,t+L -e i,t );

[0015] Among them, h i,t represents the amount of electricity measured by the tth metering cycle of the ith meter; e i,t+L 、e i,t are the electric quantity indications of the ith electric meter at the t+Lth moment and the tth moment respectively; F represents the comprehensive multiplier of the ith electric meter;

[0016] For the voltage indication curve data, the length of the metering cycle is selected as L, and the voltage data of a metering cycle is obtained by calculating the average value of the voltage of all sampling points in a metering cycle, as shown in the following formula:

[0017]

[0018] Among them, u i,t represents the voltage of the tth metering cycle of the ith meter; u i,t,j It represents the voltage value of the jth sampling point in the tth metering cycle of the ith meter.

[0019] As a preferred implementation, the steps of constructing a phase-separated power balance model of the target area based on the area topology and the law of conservation of energy, and calculating the balanced power data based on the power balance model of the target area and the metering data of the target area include:

[0020] Based on the topological structure of the substation and the law of conservation of energy, the energy balance relationship of the target substation is: "Total meter power" = "sum of power of each user's meter" + "fixed loss power" + "variable loss power" + "non-technical loss power", as shown in the following formula:

[0021]

[0022] Among them, h 0,t,α 、h i,t,α 、h chloss,t,α 、h imloss,t,α and h nonloss,t,α Respectively represent the total meter power, the i-th meter power, the variable loss power, the fixed loss power and the non-technical loss power of the α-phase area in the t-th metering cycle; α represents the phase difference, α∈{A,B,C}; N α Indicates the number of electric meters of phase α on the user side of the substation;

[0023] Introduce an electricity correction coefficient β before the electricity quantity of each user's electricity meter in phase α i,α , establish the phase electricity balance model of the substation as follows:

[0024]

[0025] Among them, β 0,α represents the intercept term of the regression equation, i.e., the fixed power loss of phase α in the substation; ε represents the error term;

[0026] Among them, the variable loss power of phase α h chloss,t,α The voltage loss rate method is used for calculation, as shown below:

[0027]

[0028] Among them, Δu i,t,α represents the voltage loss rate of the ith meter in phase α of the tth metering cycle, Δu i,t,α The calculation method is as follows:

[0029]

[0030] Among them, u 0,t,α represents the α-phase voltage of the total meter of the substation in the tth metering cycle; u i,t,α represents the α-phase voltage of the ith meter in the tth metering cycle;

[0031] Select the length of the metering cycle L, select NA +N B +N B Substitute the sample data of the group into the calculation formula of the phase electricity balance model of the substation for regression analysis, and obtain the regression coefficient β of the phase α electricity balance model of the substation i,α , the intercept term β of the phase α electricity balance model in the substation 0,α , the determination coefficient of the phase α power balance model in the substation And the mean absolute error MAE of the phase α power balance model in the substation α ; and MAE α The calculation formula is as follows:

[0032]

[0033] in, It represents the total meter power forecast value given by the α-phase power balance model of the substation; Indicates the average value of the total α phase charge.

[0034] As a preferred implementation, the non-technical line loss ratio is the maximum value of the 95% probability value of the non-technical line loss ratio of the three phases A, B, and C, and is calculated as follows:

[0035] C1=max(F A ,F B ,F C );

[0036] Among them, max(·) represents the maximum value operation; F A 、F B 、F C They are the 95% probability values ​​of the proportion of non-technical line losses of phases A, B, and C respectively;

[0037]

[0038] Among them, cp95(·) represents the 95% probability value of the sequence;

[0039] The determination coefficient of the phase-by-phase electricity balance model of the substation is the minimum value of the determination coefficients of the three phase-by-phase electricity balance models, specifically:

[0040]

[0041] Among them, min(·) represents the minimum value operation;

[0042] The mean absolute error ratio of the phase power balance model of the substation is defined as the maximum value of the mean absolute error ratio of the three phase power balance models, as shown below:

[0043] C3=max(M A ,MB ,M C );

[0044] Among them, max(·) represents the maximum value operation, M A ,M B ,M C They represent the average absolute error percentages of the phase A power balance model, the phase B power balance model, and the phase C power balance model in the substation area, respectively;

[0045] The average absolute error ratio of each phase is M α The calculation formula is as follows:

[0046]

[0047] Among them, MAE α It represents the mean absolute error of the phase α power balance model in the substation; It indicates the average value of the total α phase electricity;

[0048] The median of the regression coefficient of the phase electricity balance model of the substation is calculated as follows:

[0049]

[0050] Among them, median(·) represents the median operation; Indicates the electricity consumption of the users

[0051] Quantity correction coefficient sequence; The method for determining is: traverse all users in the area, if the user's power consumption curve is not all 0, then add the regression coefficient corresponding to this user to middle;

[0052] The fixed loss ratio of the phase-by-phase power balance model of the substation is defined as the maximum fixed loss ratio of the three phase-by-phase power balance models, as shown below:

[0053] C5=max(G A ,G B ,G C );

[0054] Among them, max(·) represents the maximum value operation, G A ,G B ,G C They represent the fixed loss proportions of the phase A power balance model, the phase B power balance model, and the phase C power balance model in the substation area respectively;

[0055] Fixed loss ratio of each phase G α The calculation formula is as follows:

[0056]

[0057] β 0,α It represents the intercept term of the α-phase power balance model in the substation; Indicates the average value of the total α phase charge.

[0058] As a preferred implementation, the step of calculating the index values ​​of five evaluation indexes by balancing the power data and evaluating the line loss anomaly of the target substation according to the index values ​​and the pre-built evaluation rules includes:

[0059] According to the index values ​​and empirical rules of the five evaluation indicators, the target area line loss is evaluated to see whether it is abnormal;

[0060] For the substations whose line losses are not evaluated as abnormal, an evaluation model based on the sequential relationship analysis method is used to evaluate whether the line losses in the substations are suspected to be abnormal or normal.

[0061] As a preferred implementation, the step of evaluating whether the line loss in the target area is abnormal based on the index values ​​of the five evaluation indexes and the empirical rules is specifically as follows:

[0062] Set the following rules of thumb:

[0063] If the index value of the non-technical line loss ratio is greater than the preset allowable upper limit of the non-technical line loss ratio, it is determined that the line loss in the target area is abnormal;

[0064] If the determination coefficient index value of the phase-to-phase electricity balance model of the substation is less than the allowable lower limit of the determination coefficient of the phase-to-phase electricity balance model of the substation, it is determined that the line loss in the target substation is abnormal;

[0065] If the average absolute error ratio index value of the phase-to-phase power balance model of the substation is greater than the allowable upper limit of the average absolute error ratio of the phase-to-phase power balance model of the substation, it is determined that the line loss in the target substation is abnormal;

[0066] If the median index value of the regression coefficient of the phase power balance model of the substation is greater than the allowable upper limit of the median or the index value is less than the allowable lower limit of the median, it is determined that the line loss in the target substation is abnormal;

[0067] If the fixed loss ratio index value of the phase power balance model of the substation is greater than the allowable upper limit of the fixed loss ratio, it is determined that the line loss in the target substation is abnormal;

[0068] The steps of using a multi-dimensional evaluation model for abnormal line loss in a substation area based on a sequence relationship analysis method to evaluate whether the line loss in the substation area is suspected to be abnormal or normal for the substation area whose line loss is not evaluated as abnormal include:

[0069] The subjective weight of the evaluation model is calculated using the ordinal relationship analysis method, specifically:

[0070] Establishing ordinal relationship: Experts rank the relative importance of the five evaluation indicators according to the criteria and work experience;

[0071] According to engineering experience and standards, the relative importance ratio of adjacent indicators is assigned:

[0072]

[0073] Among them, R k is the ratio of the relative importance of adjacent indicators, a k is the relative importance of the evaluation index ranked by importance k;

[0074] Find the subjective weight of the last-ranked evaluation indicator, specifically:

[0075]

[0076] Among them, ω σ5 is the subjective weight of the last-ranked evaluation index, and m is one of the five status indicators;

[0077] The subjective weights of other evaluation indicators are calculated based on the subjective weight of the evaluation indicator with the lowest importance:

[0078] ω σ(i－1) =ω σi R k (i=(5,4,3,2));

[0079] Among them, ω σi is the subjective weight of the evaluation index ranked i;

[0080] Establishing the evaluation model:

[0081] S=ω σ1 C1+ω σ2 C2+ω σ3 C3+ω σ4 C4+ω σ5 C5;

[0082] Among them, S represents the evaluation score, which is between 0 and 1;

[0083] For each indicator C i (i=1,2,3,4,5) is activated to obtain the activated indicators C i '(i=1,2,3,4,5), as shown below:

[0084]

[0085] Among them, δ i,max (i=1,2,3,4,5),δ i,min(i=1,2,3,4,5) represents the permissible upper and lower limits of the i-th evaluation index;

[0086] After activation, each indicator C i '(i=1,2,3,4,5) is substituted into the evaluation model to obtain the scoring result. If the scoring result is greater than the set threshold, the line loss in the substation area is evaluated as normal, otherwise it is suspected to be abnormal.

[0087] On the other hand, the present invention also proposes a multi-dimensional evaluation system for abnormal line loss in a transformer area, comprising:

[0088] The data acquisition module is used to obtain the metering data of the total meter on the power supply side of the target substation and all the meters on the substation side, and perform preprocessing to obtain the metering data of the target substation;

[0089] The balancing data construction module constructs a phase-by-phase power balance model of the target area based on the area topology and the law of conservation of energy, and calculates the balancing power data based on the power balance model of the target area and the metering data of the target area;

[0090] The indicator system construction module is used to construct a multi-dimensional evaluation indicator system for substation line losses, which includes five evaluation indicators: the proportion of non-technical line losses, the determination coefficient of the substation phase power balance model, the average absolute error proportion of the substation phase power balance model, the median of the regression coefficient of the substation phase power balance model, and the fixed loss proportion of the substation phase power balance model;

[0091] The abnormality evaluation module is used to calculate the index values ​​of five evaluation indicators through balanced electricity data, and to evaluate the line loss abnormality of the target substation according to the index values ​​and pre-built evaluation rules.

[0092] On the other hand, the present invention further proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the multi-dimensional evaluation method for line loss anomalies in a substation area as described in any embodiment of the present invention is implemented.

[0093] On the other hand, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the multi-dimensional evaluation method for line loss anomalies in a substation area as described in any embodiment of the present invention.

[0094] Additional aspects and advantages of the present invention will be set forth in the following description, and some of them will be apparent from the description, or may be understood by practicing the present invention. In addition, the various aspects and advantages of the present invention may be realized and obtained by the method steps and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] Figure 1This is a schematic diagram of a method flow chart of Embodiment 1 of the present invention;

[0096] Figure 2 Schematic diagram of the evaluation index system of an embodiment of the present invention. DETAILED DESCRIPTION

[0097] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0098] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0099] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0100] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0101] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0102] Embodiment 1:

[0103] In order to solve the problems existing in the prior art, this embodiment deeply explores the advantages of the 15-minute electricity indication curve data, constructs a variety of line loss abnormality evaluation indicators, and establishes corresponding judgment rules to achieve a reasonable evaluation of the line loss in the substation area.

[0104] See also Figure 1 This embodiment provides a multi-dimensional evaluation method for abnormal line loss in a transformer area, comprising the following steps:

[0105] S100, obtaining metering data of the total meter on the power supply side of the target substation and all the meters on the substation side from the power consumption information collection system, and performing preprocessing to obtain the metering data of the target substation.

[0106] S200, based on the substation topology and the law of conservation of energy, construct a phase-by-phase electricity balance model for the target substation, and obtain balanced electricity data based on the target substation electricity balance model and the time-by-phase electricity data solution model in the target substation metering data.

[0107] S300, see Figure 2 , a multi-dimensional evaluation index system for substation line losses is constructed, which includes five evaluation indicators: the proportion of non-technical line losses, the determination coefficient of the substation phase electricity balance model, the average absolute error proportion of the substation phase electricity balance model, the median of the regression coefficient of the substation phase electricity balance model and the proportion of fixed losses in the substation phase electricity balance model.

[0108] S400, calculating the index values ​​of five evaluation indexes by balancing the power data, and performing line loss anomaly evaluation of the target substation according to the index values ​​and pre-built evaluation rules.

[0109] As a preferred implementation of this embodiment, in step S100, the metering data of the target area power supply side total meter and all the area side electric meters include:

[0110] 1) The voltage and power indication curve data of the total meter on the power supply side of the substation and all the meters on the user side of the substation, with a data granularity of 15 minutes.

[0111] 2) Phase sequence information of the main meter on the power supply side of the substation and all meters on the user side of the substation.

[0112] As a preferred implementation of this embodiment, in step S100, the preprocessing includes the following steps:

[0113] Generally speaking, the power data collection accuracy of smart meters without transformers is 0.01kWh. When the power indication of the meter changes little within 15 minutes, the power consumption data of 15 minutes obtained by differential operation with 15 minutes as the metering period has a certain quantization error. Therefore, according to actual needs, the length of the metering period can be increased, sacrificing some accuracy and detailed information to enhance the stability of the data and reduce the impact of errors. For the convenience of representation, in this patent, L is defined as the length of the metering period, with 15 minutes as its scale. Under this standard, L=1 means the metering period is 15 minutes, and L=4 means the metering period is 1 hour.

[0114] S101. For the obtained electric quantity indication curve data, the length of the metering cycle is selected as L, and the electric quantity consumption data of a metering cycle can be obtained by differential operation, as shown in the following formula:

[0115] h i,t =F·(e i,t+L -e i,t ) (1)

[0116] Among them, h i,t represents the amount of electricity measured by the tth metering cycle of the ith meter; e i,t+L 、e i,t are the electric quantity indications of the ith electric meter at the t+Lth moment and the tth moment respectively; F represents the comprehensive multiplier of the ith electric meter;

[0117] S102. For the voltage indication curve data, the missing values ​​are filled based on the linear interpolation method. The voltage data is an instantaneous value. In this embodiment, the average value of the voltages of all sampling points in a metering cycle is considered as the voltage value of the metering cycle. Therefore, the length of the metering cycle is selected as L. The voltage data of a metering cycle can be calculated by the following formula:

[0118]

[0119] Among them, u i,t represents the voltage of the tth metering cycle of the ith meter; u i,t,j It represents the voltage value of the jth sampling point in the tth metering cycle of the ith meter.

[0120] As a preferred implementation of this embodiment, in step S200, the phase-separated power balance model of the target area is constructed based on the area topology and the law of conservation of energy, and the step of calculating the balanced power data based on the power balance model of the target area and the metering data of the target area includes:

[0121] S201. Based on the topological structure of the substation and the law of conservation of energy, the energy balance relationship of the target substation is obtained as follows: "total meter power" = "sum of power of each user's meter" + "fixed loss power" + "variable loss power" + "non-technical loss power". By expanding the balance relationship in phases, the following formula can be obtained:

[0122]

[0123] Among them, h 0,t,α 、h i,t,α 、h chloss,t,α 、h imloss,t,α and h nonloss,t,α Respectively represent the total meter power, the i-th meter power, the variable loss power, the fixed loss power and the non-technical loss power of the α-phase area in the t-th metering cycle; α represents the phase difference, α∈{A,B,C}; N α Indicates the number of electric meters of phase α on the user side of the substation;

[0124] S202, introduce an electric quantity correction coefficient β before the electric quantity of each user's electric meter in phase α i,α , establish the phase electricity balance model of the substation as follows:

[0125]

[0126] Among them, β i,α Represents the regression coefficient of the regression equation, that is, the power correction coefficient of the α phase meter; β 0,α It represents the intercept term of the regression equation, that is, the fixed power loss of phase α in the substation. This part of the loss generally refers to the meter loss; ε represents the error term.

[0127] Among them, the variable loss power of phase α h chloss,t,α Generally refers to line loss, which can be calculated using the voltage loss rate method, as shown below:

[0128]

[0129] Among them, Δu i,t,α represents the voltage loss rate of the ith meter in phase α of the tth metering cycle, Δu i,t,α The calculation method is as follows:

[0130]

[0131] Among them, u 0,t,α represents the α-phase voltage of the total meter of the substation in the tth metering cycle; u i,t,α It represents the α-phase voltage of the ith meter in the t-th metering cycle; α is one of the three phases A, B, and C.

[0132] S203, select the metering cycle length L, select N A +N B +N B Substitute the sample data of the group into formula (4) for regression analysis and obtain the regression coefficient β of the phase α power balance model of the substation area i,α , the intercept term β of the phase α electricity balance model in the substation 0,α , the determination coefficient of the phase α power balance model in the substation And the mean absolute error MAE of the phase α power balance model in the substation α ; and MAE α The calculation formula is as follows:

[0133]

[0134]

[0135] in, It represents the total meter power forecast value given by the α-phase power balance model of the substation; Indicates the average value of the total α phase charge.

[0136] As a preferred implementation of this embodiment, in step S300:

[0137] Non-technical power loss h nonloss,t,α It is the loss caused by metering equipment failure, malicious electricity theft by users, etc. The non-technical line loss ratio C1 is defined as the maximum value of the 95% probability value of the non-technical line loss ratio of phases A, B, and C, which can well reflect the line loss situation in the substation area. The calculation method is shown in the following formula:

[0138] C1=max(F A ,F B ,F C );

[0139]

[0140] Among them, max(·) represents the maximum value operation; F A 、F B 、F C are the 95% probability values ​​of the proportion of non-technical line losses of phases A, B, and C respectively; cp95(·) represents the 95% probability value of the sequence.

[0141] In formula (9), based on the energy balance relationship constructed in formula (6), h nonloss,t,α It can be calculated by the following formula:

[0142]

[0143] In formula (10), h imloss,t,α There are two ways to calculate it. One is to use regression analysis through formula (7), that is, h imloss,t,α =β 0,α , and the second is calculated according to the following empirical formula:

[0144]

[0145] Where: n 1,α and n2 represent the number of α-phase single-phase meters and three-phase meters in the substation respectively; L represents the length of the metering cycle.

[0146] The phase-to-phase electricity balance model constructed by formula (4) can be expanded according to the phases and can be divided into: phase A electricity balance model, phase B electricity balance model and phase C electricity balance model. In the multivariate linear regression, R 2 It is an important statistical indicator. 2 The closer it is to 1, the better the model fits the data; conversely, the closer it is to 0, the worse the model's explanation effect. This patent focuses on determining whether there is abnormal line loss in the platform area, and R 2The smaller the value, the worse the model fitting effect is, indicating that there is a greater possibility of line loss problems. Therefore, in this embodiment, the determination coefficient C2 of the phase-by-phase power balance model of the substation is defined as the minimum value of the determination coefficients of the three phase-by-phase power balance models, specifically:

[0147]

[0148] Among them, min(·) represents the minimum value operation.

[0149] In multiple linear regression, the mean absolute error directly reflects the difference between the predicted value and the actual value. The larger the mean absolute error, the more random and unexplainable information there is in the sample, which makes the model less effective. In the scenario of this embodiment, the larger the mean absolute error of the phase-by-phase power balance model of the substation, the greater the non-technical loss of the substation. Based on the above analysis and the purpose of this embodiment to determine whether there is abnormal line loss in the substation, the mean absolute error proportion C3 of the phase-by-phase power balance model of the substation is defined as the maximum value of the mean absolute error proportion of the three phase-by-phase power balance models, as shown below:

[0150] C3=max(M A ,M B ,M C )(13)

[0151] Among them, max(·) represents the maximum value operation, M A ,M B ,M C They respectively represent the average absolute error percentages of the phase A power balance model, the phase B power balance model and the phase C power balance model in the substation.

[0152] The average absolute error ratio of each phase is M α The calculation formula is as follows:

[0153]

[0154] Among them, MAE α It represents the mean absolute error of the phase α power balance model in the substation; Indicates the average value of the total α phase charge.

[0155] The regression coefficient of the phase-phase power balance model of the substation represents the power correction coefficient. When the substation does not have a normal situation, the power correction coefficient of the users who use electricity should be around 1. In statistics, the median can well reflect the overall trend of a set of data. The calculation method of the median C4 of the regression coefficient of the phase-phase power balance model of the substation constructed in this embodiment is as follows:

[0156]

[0157] Among them, median(·) represents the median operation; It represents the electricity consumption correction coefficient sequence of the electricity users; The method for determining is: traverse all users in the area, if the user's power consumption curve is not all 0, then add the regression coefficient corresponding to this user to middle.

[0158] The fixed loss in the substation is generally not large. When the fixed loss is too large, the substation may have abnormal line loss. Therefore, in this embodiment, the fixed loss proportion C5 of the substation phase power balance model is defined as the maximum value of the fixed loss proportions of the three phase power balance models, as shown below:

[0159] C5=max(G A ,G B ,G C )(16)

[0160] Among them, max(·) represents the maximum value operation, G A ,G B ,G C They represent the fixed loss proportions of the phase A power balance model, the phase B power balance model, and the phase C power balance model in the substation area respectively;

[0161] Fixed loss ratio of each phase G α The calculation formula is as follows:

[0162]

[0163] β 0,α It represents the intercept term of the α-phase power balance model in the substation; Indicates the average value of the total α phase charge.

[0164] As a preferred implementation of this embodiment, in step S400, the step of calculating the index values ​​of the five evaluation indexes by balancing the power data, and performing line loss abnormality evaluation of the target substation according to the index values ​​and the pre-built evaluation rules includes:

[0165] S401. Classify the status level of the substation line loss into three levels: abnormal, suspected abnormal, and normal.

[0166] S402. Evaluate whether the line loss in the substation area belongs to the "abnormal" status level based on the index values ​​of the five evaluation indexes and empirical rules.

[0167] S403. For the substations whose line losses are not evaluated as abnormal, an evaluation model based on the sequence relationship analysis method is used to evaluate whether the line losses in the substations belong to the "suspected abnormal" or "normal" state level.

[0168] As a preferred implementation of this embodiment, in step S402, the step of evaluating whether the target area line loss is abnormal based on the index values ​​of the five evaluation indexes and the empirical rules is specifically as follows:

[0169] Set the following rules of thumb:

[0170] (1) If the non-technical line loss ratio C1 is greater than δ 1,max , then the line loss in the substation area is judged to be in the "abnormal" state level. 1,max It indicates the permissible upper limit of the proportion of non-technical line loss, which needs to be formulated according to specific project requirements.

[0171] (2) If the determination coefficient C2 of the phase-to-phase power balance model is less than δ 2,min , then the line loss in the substation area is judged to be in the "abnormal" state level. 2,min It indicates the allowable lower limit of the determination coefficient of the phase electricity balance model of the substation, which needs to be formulated according to specific engineering requirements.

[0172] (3) If the average absolute error ratio C3 of the phase power balance model in the substation is greater than δ 3,max , then the line loss in the substation area is judged to be in the "abnormal" state level. 3,max It represents the allowable upper limit of the mean absolute error ratio of the phase power balance model in the substation, which needs to be formulated according to specific engineering requirements.

[0173] (4) If the median C4 of the regression coefficients of the phase-phase electricity balance model is greater than δ 4,max Or C4 is less than δ 4,min , then the line loss in the substation area is judged to be in the "abnormal" state level. 4,max , δ 4,min They represent the allowable upper and lower limits of the median, respectively, and need to be formulated according to specific project requirements.

[0174] (5) If the fixed loss ratio C5 of the phase power balance model of the substation is greater than δ 5,max , then the line loss in the substation area is judged to be in the "abnormal" state level. 5,max It represents the allowable upper limit of the fixed loss ratio in the phase power balance model of the substation, which needs to be formulated according to specific engineering requirements.

[0175] As a preferred implementation of this embodiment, in step S403, for a substation whose line loss is not evaluated as abnormal, the step of using a multi-dimensional evaluation model for line loss abnormality in the substation based on the sequence relationship analysis method to evaluate whether the line loss in the substation is suspected abnormal or normal includes:

[0176] S4031. Use the ordinal relationship analysis method to calculate the subjective weight of the evaluation model, specifically:

[0177] 1) Establishing an ordinal relationship: Experts ranked the relative importance of the five evaluation indicators according to the criteria and work experience, and obtained the ordinal relationship of a1>a2>a3>a4>a5.

[0178] 2) R k is the relative importance ratio of adjacent indicators. k Assignment:

[0179]

[0180] Among them, a k is the relative importance of the evaluation index ranked by importance k;

[0181] 3) Find the subjective weight of the last ranking evaluation index, specifically:

[0182]

[0183] Among them, ω σ5 is the subjective weight of the last evaluation index, m is one of the five status indicators; Part of the specific expression: take the initial value of m as 2, perform multiplication and then accumulation operations, and finally get the calculated value of R2R3R4R5+R3R4R5+R4R5+R5.

[0184] 4) Calculate the subjective weights of other evaluation indicators based on the subjective weight of the evaluation indicator with the lowest importance:

[0185] ω σ(i－1) =ω σi R k (i=(5,4,3,2))(20)

[0186] Among them, ω σi is the subjective weight of the evaluation index ranked i;

[0187] S4032. Establish an evaluation model:

[0188] S=ω σ1 C1+ω σ2 C2+ω σ3 C3+ω σ4 C4+ω σ5 C5(21)

[0189] Among them, S represents the evaluation score, which is between 0 and 1;

[0190] S4033, for each evaluation index C i (i=1,2,3,4,5) is activated to obtain the evaluation index C after activation i'(i=1,2,3,4,5), as shown below:

[0191]

[0192] Among them, δ i,max (i=1,2,3,4,5),δ i,min (i=1, 2, 3, 4, 5) represents the allowable upper and lower limits of the i-th evaluation index.

[0193] S4034, activate each indicator C i '(i=1,2,3,4,5) is substituted into the evaluation model to obtain the scoring result. If the scoring result is greater than the set threshold δ S , the line loss in the substation area is evaluated as a "normal" state, otherwise it is a "suspected abnormal" state.

[0194] Embodiment 2:

[0195] This embodiment proposes a multi-dimensional evaluation system for abnormal line loss in a transformer area, including:

[0196] A data acquisition module is used to obtain metering data of the total meter on the power supply side of the target area and all electric meters on the area side, and perform preprocessing to obtain metering data of the target area; this module is used to implement the function of step S100 in the first embodiment, and will not be repeated here;

[0197] A balancing data construction module, based on the substation topology and the law of conservation of energy, constructs a phase-by-phase power balance model of the target substation, and calculates the balancing power data based on the power balance model of the target substation and the metering data of the target substation; this module is used to implement the function of step S200 in the first embodiment, which will not be described in detail here;

[0198] An indicator system construction module is used to construct a multi-dimensional evaluation indicator system for substation line losses, including five evaluation indicators: non-technical line loss ratio, determination coefficient of substation phase power balance model, average absolute error ratio of substation phase power balance model, median of regression coefficient of substation phase power balance model and fixed loss ratio of substation phase power balance model; this module is used to implement the function of step S300 in embodiment 1, which will not be repeated here;

[0199] The abnormality evaluation module is used to calculate the index values ​​of five evaluation indicators by balancing the power data, and to perform line loss abnormality evaluation of the target substation according to the index values ​​and pre-built evaluation rules; this module is used to implement the function of step S400 in embodiment 1, which will not be repeated here.

[0200] Embodiment three:

[0201] This embodiment proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a multi-dimensional evaluation method for abnormal line loss in a substation area as described in any embodiment of the present invention is implemented.

[0202] Embodiment 4:

[0203] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the multi-dimensional evaluation method for abnormal line loss in a substation area as described in any embodiment of the present invention is implemented.

[0204] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0205] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0206] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0207] In several embodiments provided in the present application, if any 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 application, 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, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0208] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-dimensional evaluation method for abnormal line loss in a transformer area, characterized in that: The following steps are involved: Obtain the metering data of the total meter on the power supply side of the target substation and all the meters on the substation side, and perform preprocessing to obtain the metering data of the target substation; Based on the substation topology and the law of conservation of energy, a phase-by-phase power balance model of the target substation is constructed, and the balance power data is calculated based on the power balance model of the target substation and the metering data of the target substation; Construct a multi-dimensional evaluation index system for substation line loss, which includes five evaluation indicators: the proportion of non-technical line loss, the coefficient of determination of the substation phase power balance model, the average absolute error proportion of the substation phase power balance model, the median of the regression coefficient of the substation phase power balance model, and the proportion of fixed loss of the substation phase power balance model; The index values ​​of five evaluation indicators are calculated by balancing the power data, and the line loss anomaly evaluation of the target substation is carried out according to the index values ​​and pre-built evaluation rules.

2. According to claim 1, a multi-dimensional evaluation method for abnormal line loss in a transformer area is characterized by: The metering data of the target substation power supply side total meter and all the electric meters on the substation side include the voltage and power indication curve data of the substation power supply side total meter and all the electric meters on the substation user side, as well as the phase sequence information of the substation power supply side total meter and all the electric meters on the substation user side.

3. A multi-dimensional evaluation method for abnormal line loss in a transformer area according to claim 2, characterized in that: The pre-processing comprises the following steps: For the electric quantity indication curve data, the length of the metering cycle is selected as L, and the electric quantity consumption data of a metering cycle is obtained by differential operation, as shown in the following formula: h i,t =F·(e i,t+L -e i,t ); Among them, h i,t represents the amount of electricity measured by the tth metering cycle of the ith meter; e i,t+L 、e i,t are the electric quantity indications of the ith electric meter at the t+Lth moment and the tth moment respectively; F represents the comprehensive multiplier of the ith electric meter; For the voltage indication curve data, the length of the metering cycle is selected as L, and the voltage data of a metering cycle is obtained by calculating the average value of the voltage of all sampling points in a metering cycle, as shown in the following formula: Among them, u i,t represents the voltage of the tth metering cycle of the ith meter; u i,t,j It represents the voltage value of the jth sampling point in the tth metering cycle of the ith meter.

4. The multi-dimensional evaluation method for abnormal line loss in a transformer area according to claim 1 is characterized in that: The steps of constructing a phase-by-phase power balance model of the target area based on the area topology structure and the law of conservation of energy, and calculating the balance power data based on the power balance model of the target area and the metering data of the target area include: Based on the topological structure of the substation and the law of conservation of energy, the energy balance relationship of the target substation is: "total meter power" = "sum of each user's meter power" + "fixed loss power" + "variable loss power" + "non-technical loss power", as shown in the following formula: Among them, h 0,t,α 、h i,t,α 、h chloss,t,α 、h imloss,t,α and h nonloss,t,α Respectively represent the total meter power, the i-th meter power, the variable loss power, the fixed loss power and the non-technical loss power of the α-phase area in the t-th metering cycle; α represents the phase difference, α∈{A,B,C}; N α Indicates the number of electric meters of phase α on the user side of the substation; Introduce an electricity correction coefficient β before the electricity quantity of each user's electricity meter in phase α i,α , establish the phase electricity balance model of the substation as follows: Among them, β 0,α represents the intercept term of the regression equation, i.e., the fixed power loss of phase α in the substation; ε represents the error term; Among them, the variable power loss of phase α h chloss,t,α The voltage loss rate method is used for calculation, as shown below: Among them, Δu i,t,α represents the voltage loss rate of the ith meter in phase α of the tth metering cycle, Δu i,t,α The calculation method is as follows: Among them, u 0,t,α represents the α-phase voltage of the total meter of the substation in the tth metering cycle; u i,t,α represents the α-phase voltage of the ith meter in the tth metering cycle; Select the length of the metering cycle L, select N A +N B +N B Substitute the sample data of the group into the calculation formula of the phase electricity balance model of the substation for regression analysis, and obtain the regression coefficient β of the phase α electricity balance model of the substation i,α , the intercept term β of the phase α electricity balance model in the substation 0,α , the determination coefficient of the phase α power balance model in the substation And the mean absolute error MAE of the phase α power balance model in the substation α ; and MAE α The calculation formula is as follows: in, It represents the total meter power forecast value given by the α-phase power balance model of the substation; Indicates the average value of the total α phase charge.

5. The multi-dimensional evaluation method for abnormal line loss in a transformer area according to claim 4 is characterized in that: The non-technical line loss ratio is the maximum value of the 95% probability value of the non-technical line loss ratio of phases A, B, and C, and is calculated as follows: C1=max(F A ,F B ,F C ); Among them, max(·) represents the maximum value operation; F A 、F B 、F C They are the 95% probability values ​​of the proportion of non-technical line losses of phases A, B, and C respectively; 95% probability value F of the proportion of non-technical line loss in each phase α The calculation formula is as follows: Among them, cp95(·) represents the 95% probability value of the sequence; The determination coefficient of the phase-by-phase electricity balance model of the substation is the minimum value of the determination coefficients of the three phase-by-phase electricity balance models, specifically: Among them, min(·) represents the minimum value operation; The mean absolute error ratio of the phase power balance model of the substation is defined as the maximum value of the mean absolute error ratio of the three phase power balance models, as shown below: C3=max(M A ,M B ,M C ); Among them, max(·) represents the maximum value operation, M A ,M B ,M C They represent the average absolute error percentages of the phase A power balance model, the phase B power balance model, and the phase C power balance model in the substation area, respectively; The average absolute error ratio of each phase is M α The calculation formula is as follows: Among them, MAE α It represents the mean absolute error of the phase α power balance model in the substation; It indicates the average value of the total α phase electricity; The median of the regression coefficient of the phase electricity balance model of the substation is calculated as follows: Among them, median(·) represents the median operation; It represents the electricity consumption correction coefficient sequence of the electricity users; The method for determining is: traverse all users in the area, if the user's power consumption curve is not all 0, then add the regression coefficient corresponding to this user to middle; The fixed loss ratio of the phase-by-phase power balance model of the substation is defined as the maximum fixed loss ratio of the three phase-by-phase power balance models, as shown below: C5=max(G A ,G B ,G C ); Among them, max(·) represents the maximum value operation, G A ,G B ,G C They represent the fixed loss proportions of the phase A power balance model, the phase B power balance model, and the phase C power balance model in the substation area respectively; Fixed loss ratio of each phase G α The calculation formula is as follows: β 0,α It represents the intercept term of the α-phase power balance model in the substation; Indicates the average value of the total α phase charge.

6. The multi-dimensional evaluation method for abnormal line loss in a transformer area according to claim 1, characterized in that: The step of calculating the index values ​​of five evaluation indexes by balancing the power data and evaluating the line loss anomaly of the target substation according to the index values ​​and the pre-built evaluation rules includes: According to the index values ​​and empirical rules of the five evaluation indicators, the target area line loss is evaluated to see whether it is abnormal; For the substations whose line losses are not evaluated as abnormal, an evaluation model based on the sequential relationship analysis method is used to evaluate whether the line losses in the substations are suspected to be abnormal or normal.

7. A multi-dimensional evaluation method for abnormal line loss in a transformer area according to claim 6, characterized in that: The steps of evaluating whether the line loss in the target area is abnormal based on the index values ​​of the five evaluation indexes and the empirical rules are specifically as follows: Set the following rules of thumb: If the index value of the non-technical line loss ratio is greater than the preset allowable upper limit of the non-technical line loss ratio, the line loss in the target area is judged to be abnormal; If the determination coefficient index value of the phase-to-phase electricity balance model of the substation is less than the allowable lower limit of the determination coefficient of the phase-to-phase electricity balance model of the substation, it is determined that the line loss in the target substation is abnormal; If the average absolute error ratio index value of the phase-to-phase power balance model of the substation is greater than the allowable upper limit of the average absolute error ratio of the phase-to-phase power balance model of the substation, it is determined that the line loss in the target substation is abnormal; If the median index value of the regression coefficient of the phase power balance model of the substation is greater than the allowable upper limit of the median or the index value is less than the allowable lower limit of the median, it is determined that the line loss in the target substation is abnormal; If the fixed loss ratio index value of the phase power balance model of the substation is greater than the allowable upper limit of the fixed loss ratio, it is determined that the line loss in the target substation is abnormal; The steps of using a multi-dimensional evaluation model for abnormal line loss in a substation area based on a sequence relationship analysis method to evaluate whether the line loss in the substation area is suspected to be abnormal or normal for the substation area whose line loss is not evaluated as abnormal include: The subjective weight of the evaluation model is calculated using the ordinal relationship analysis method, specifically: Establishing ordinal relationship: Experts rank the relative importance of the five evaluation indicators according to the criteria and work experience; According to engineering experience and standards, the relative importance ratio of adjacent indicators is assigned: Among them, R k is the ratio of the relative importance of adjacent indicators, a k is the relative importance of the evaluation index ranked by importance k; Find the subjective weight of the last-ranked evaluation indicator, specifically: Among them, ω σ5 is the subjective weight of the last evaluation index; m is one of the five status indicators; The subjective weights of other evaluation indicators are calculated based on the subjective weight of the evaluation indicator with the lowest importance: oh σ(i－1) =ω σi R k (i=(5,4,3,2)); Among them, ω σi is the subjective weight of the evaluation index ranked i; Establishing the evaluation model: S=ω σ1 C1+ω σ2 C2+ω σ3 C3+ω σ4 C4+ω σ5 C5; Among them, S represents the evaluation score, which is between 0 and 1; For each indicator C i (i=1,2,3,4,5) is activated to obtain the activated indicators C i '(i=1,2,3,4,5), as shown below: Among them, δ i,max (i=1,2,3,4,5),δ i,min (i=1,2,3,4,5) represents the permissible upper and lower limits of the i-th evaluation index; After activation, each indicator C i '(i=1,2,3,4,5) is substituted into the evaluation model to obtain the scoring result. If the scoring result is greater than the set threshold, the line loss in the substation area is evaluated as normal, otherwise it is suspected to be abnormal.

8. A multi-dimensional evaluation system for abnormal line loss in a transformer area, characterized in that: include: The data acquisition module is used to obtain the metering data of the total meter on the power supply side of the target substation and all the meters on the substation side, and perform preprocessing to obtain the metering data of the target substation; The balancing data construction module constructs a phase-by-phase power balance model of the target area based on the area topology and the law of conservation of energy, and calculates the balancing power data based on the power balance model of the target area and the metering data of the target area; The indicator system construction module is used to construct a multi-dimensional evaluation indicator system for substation line losses, which includes five evaluation indicators: the proportion of non-technical line losses, the determination coefficient of the substation phase power balance model, the average absolute error proportion of the substation phase power balance model, the median of the regression coefficient of the substation phase power balance model, and the fixed loss proportion of the substation phase power balance model; The abnormality evaluation module is used to calculate the index values ​​of five evaluation indicators through balanced electricity data, and to evaluate the line loss abnormality of the target substation according to the index values ​​and pre-built evaluation rules.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the multi-dimensional evaluation method for abnormal line loss in a substation area as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the multi-dimensional evaluation method for abnormal line loss in a substation area as described in any one of claims 1 to 7 is implemented.

Images