Transformer area treatment method and system based on network analytic hierarchy process

Abstract

The invention relates to a transformer area governance method and system based on a network analytic hierarchy process, electronic equipment and a storage medium, and the method comprises the steps: applying an ANP method to transformer area governance priority ranking through building a universal index system and a scoring method, and carrying out the priority ranking of transformer area governance through a universal scoring and judgment matrix generation method. Automation and standardization of treatment evaluation of the transformer area are realized; the efficiency is improved, and the stability and consistency of the evaluation result of the abnormal degree of the transformer area are ensured.

Description

Technical Field

[0001] The present application relates to the field of substation management, and in particular to a substation management method, system, computer device and computer-readable storage medium based on network hierarchy analysis method. Background Art

[0002] After obtaining information such as whether there are abnormalities in each substation and user, the type of abnormality, the number of abnormalities, abnormal meters, and the predicted amount of abnormal loss reduction, based on the results of intelligent line loss diagnosis, priority substations can be recommended for each power supply station and automatically updated.

[0003] In related technologies, the existing line loss anomaly diagnosis algorithm can identify whether there is an abnormality in the production area, and divide the anomalies into 5 major categories and 48 minor categories. The 5 major categories are metering anomalies, collection anomalies, archive anomalies, power consumption anomalies and technical factors, which can provide certain basic data for diagnostic analysis.

[0004] However, since manual on-site inspection and problem solving is time-consuming and labor-intensive, each time a plan is evaluated, it is necessary to make importance judgments based on expert assessments, resulting in low governance efficiency and high maintenance costs. Summary of the invention

[0005] The embodiments of the present application provide a method, system, computer device and computer-readable storage medium for substation management based on network hierarchy analysis method, so as to at least solve the problems of low management efficiency and high maintenance cost in related technologies.

[0006] In a first aspect, the present application embodiment provides a method for managing a substation area based on a network analysis hierarchy process, including:

[0007] Based on the abnormal monitoring data of each substation in the target area, the ANP model is constructed according to the pre-established indicator system table and indicator impact relationship table;

[0008] Based on the ANP model, by comparing the relative advantages between model elements with the same affiliation and relative influencing factors, a pairwise judgment matrix between each model element is constructed;

[0009] Obtaining a weighted supermatrix according to the pairwise discriminant matrices between the elements of each low-level model and the pairwise discriminant matrices between the element sets to which the low-level model elements belong;

[0010] By solving the weighted supermatrix, the global weight of each model element in the ANP model is obtained, and the substation management priority information is generated based on the global weight.

[0011] In some of the embodiments, based on the abnormal monitoring data processing of each substation in the target area, according to the pre-established indicator system table and indicator influence relationship table, constructing the ANP model includes:

[0012] By calculating the abnormal monitoring data, the level of the corresponding indicator in the indicator system table is obtained to obtain the model element;

[0013] According to the indicator influence relationship table, the model elements and the correlation information between the model elements are obtained, and the ANP model is constructed based on the model elements and the correlation.

[0014] In some embodiments, the indicator system table includes multiple primary indicators and secondary indicators subordinate to the primary indicators.

[0015] Among them, the first-level indicators include: basic conditions of the substation, abnormal conditions and line loss conditions; the second-level indicators under the basic conditions of the substation include: power supply level, user quantity level, substation governance difficulty, and substation management pressure level;

[0016] The secondary indicators of the abnormal situation include: abnormal category type, abnormal source, and abnormal table count level;

[0017] The secondary indicators under the line loss situation include: line loss abnormal days level and line loss abnormal status.

[0018] In some embodiments, based on the ANP model, by comparing the relative importance weights between elements with the same membership, constructing a pairwise judgment matrix between each model element includes:

[0019] Any model element with a downward subordinate relationship is used as the criterion model element;

[0020] The criterion model element is set at the initial item of the matrix, and the matrix framework is constructed by sequentially setting the subordinate elements belonging to the criterion model element at the rows and columns after the initial item;

[0021] Combined with expert knowledge in this field, the relative advantage between any two indicators in the framework matrix is ​​obtained, and the relative advantage information is filled into the corresponding rows and columns in the matrix framework as matrix elements to obtain the pairwise discriminant matrix, wherein the relative advantage is dynamically optimized by the power supply management personnel according to actual conditions.

[0022] In some embodiments, in the process of constructing the pairwise discriminant matrix, the method includes:

[0023] For the model elements corresponding to the first-level indicators:

[0024] Based on the primary model elements belonging to the same substation, constructing a pairwise judgment matrix between the primary model elements;

[0025] For the model elements corresponding to the secondary indicators:

[0026] Under the same area, obtain the secondary model elements belonging to the same model element as any secondary element index, and obtain the model elements of the same element set;

[0027] Obtain secondary element indicators that are not subordinate to any secondary element indicator and are mutually related in the indicator influence relationship table, obtain model elements between element sets, and construct a pairwise discriminant matrix between the secondary model elements based on the model elements of the same element set and the model elements between the element sets;

[0028] For the mentioned areas:

[0029] According to the historical data of the substation area and the expert knowledge in this field, the corresponding index score of each model element is obtained;

[0030] When the model elements are compared pairwise, the score ratio is obtained according to the indicator scores of the two model elements, and the relative superiority between the model elements is obtained by comparing the score ratio with the preset superiority relationship table, and a judgment matrix between the station areas and the model elements is constructed according to the relative superiority between the model elements.

[0031] In some embodiments, based on the pairwise discriminant matrix between the element indicators and the pairwise discriminant matrix between the element sets to which the lower-level model elements belong, a weighted supermatrix is ​​obtained, which includes:

[0032] Based on the pairwise judgment matrix between the elements of the secondary model, the corresponding normalized eigenvectors are obtained using the eigenvector method, and an unweighted supermatrix is ​​obtained according to the normalized eigenvectors;

[0033] Based on the pairwise judgment matrix of the second-level elements, the relative importance weights of each element and are obtained, and according to the relative importance weights, the weight matrix between the element sets is obtained;

[0034] A weighted supermatrix is ​​obtained by multiplying the unweighted supermatrix and the weight matrix.

[0035] In some embodiments, solving the weighted supermatrix to obtain the global weights of each model element in the ANP model includes:

[0036] Solving the Nth power of the weighted supermatrix by the power method until the column vector of the weighted supermatrix remains unchanged, thereby obtaining a limit supermatrix;

[0037] According to the extreme super-true column vector, the global weight corresponding to each substation is obtained, and based on the global weight corresponding to each substation, the governance priority information of the substation is output.

[0038] In a second aspect, the embodiment of the present application provides a system for managing a substation area based on the network analytic hierarchy process, including: a model building module, a matrix building module and an operation module, wherein:

[0039] The model building module is used to build an ANP model based on the abnormal monitoring data of each substation in the target area and according to a pre-established indicator system table and an indicator influence relationship table;

[0040] The matrix construction module is used to construct a pairwise judgment matrix between each model element based on the ANP model by comparing the relative advantages between model elements with the same affiliation and relative influencing factors.

[0041] and obtaining a weighted supermatrix according to the pairwise discriminant matrices between the lower-level model elements and the pairwise discriminant matrices between the element sets to which the lower-level model elements belong;

[0042] The operation module is used to obtain the global weight of each model element in the ANP model by solving the weighted super matrix, and generate the substation management priority information based on the global weight.

[0043] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect above when executing the computer program.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect above.

[0045] Compared with the related technologies, the embodiment of the present application provides a substation management method and system based on network analysis method, which applies the ANP method to the substation management priority ranking by establishing a common indicator system and scoring method, and realizes the automation and standardization of substation management evaluation through a common scoring and judgment matrix generation method; it not only improves the efficiency, but also ensures the stability and consistency of the substation abnormality evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0047] Figure 1 It is a flow chart of a method for managing a substation area based on the network analysis hierarchy process according to an embodiment of the present application;

[0048] Figure 2 is a schematic diagram of the indicator influence relationship according to an embodiment of the present application;

[0049] Figure 3 is a schematic diagram of an ANP model according to an embodiment of the present application;

[0050] Figure 4 is a schematic diagram of the 1-9 scaling method according to an embodiment of the present application;

[0051] Figure 5 is a schematic diagram of an unweighted supermatrix according to an embodiment of the present application;

[0052] Figure 6 is a schematic diagram of a weighted supermatrix according to an embodiment of the present application;

[0053] Figure 7 is a schematic diagram of a limit supermatrix according to an embodiment of the present application;

[0054] Figure 8 It is a structural diagram of a substation management system based on network analytic hierarchy process according to an embodiment of the present application;

[0055] Fig. 9 It is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0057] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0058] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0059] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0060] Based on the results of intelligent diagnosis of line losses, after obtaining information such as whether there are abnormalities in each substation and user, the type of abnormality, the number of abnormalities, abnormal meters, and the predicted amount of abnormal loss reduction, the system recommends priority substations for treatment and automatically updates them.

[0061] The existing line loss anomaly diagnosis algorithm can identify whether there are abnormalities in the substation area, and divide the anomalies into five major categories and 48 subcategories. The five major categories are metering anomalies, collection anomalies, archive anomalies, power consumption anomalies and technical factors. Since manual on-site inspection and problem handling are time-consuming and laborious, if the abnormal substation areas can be prioritized, it can provide effective guidance for the line loss management work of the power supply station and save the power company's operation and maintenance costs and labor costs.

[0062] In view of this, the embodiment of the present application provides a method for substation management based on the network hierarchy analysis method, which sorts the priority of substation management, and can effectively guide the power supply station to give priority to managing substations that have a greater impact on users and power grids and are easier to manage when operation and maintenance resources are limited;

[0063] Figure 1 is a flow chart of a method for managing a substation area based on the network analytic hierarchy process according to an embodiment of the present application, such as Figure 1 As shown, the process includes the following steps:

[0064] S101, based on the abnormal monitoring data of each substation in the target area, according to the pre-established indicator system table and indicator influence relationship table, construct an ANP model;

[0065] Among them, a substation refers to a relatively independent distribution unit in the power supply system, usually consisting of a distribution transformer and the users it supplies. In China, the power distribution network of the power system usually divides a larger area into multiple substations. Each substation is powered by a distribution transformer (usually called a substation transformer or a public transformer). Users in the substation obtain electricity through this transformer. Users in the substation can be residents, commercial users, or small industrial users.

[0066] Furthermore, the index system table is formulated by combining the expert knowledge in this field with the data analysis results of the specific area. The following table is an index system table according to an embodiment of the present application:

[0067]

[0068]

[0069] It can be learned that the indicator system table includes multiple first-level indicators and second-level indicators subordinate to the first-level indicators. Among them, the first-level indicators include: basic situation of the substation, abnormal situation and line loss situation; the second-level indicators under the basic situation of the substation include: power supply level, user quantity level, substation governance difficulty, substation management pressure level; the second-level indicators under abnormal situation include: abnormal category type, abnormal source, abnormal table count level; the second-level indicators under line loss situation include: line loss abnormal day level and line loss abnormal status.

[0070] In addition, for each substation, the value of the corresponding indicator of the substation can be calculated based on the collection system and archive data, that is, the level of each indicator corresponding to the abnormal monitoring data, and each level is scored according to 1-9. The higher the level, the greater the score. In this embodiment, the indicators corresponding to the data in the substation and their corresponding scores constitute the model elements in this embodiment;

[0071] In addition, the indicator impact relationship table reflects the existing and feedback relationships between various indicators, which can also be constructed based on the expert knowledge in this field. Figure 2 It is a schematic diagram of the indicator influence relationship according to an embodiment of the present application.

[0072] It can be understood that by establishing a network structure influence relationship table of indicators, the dependency and feedback relationship between different indicators can be analyzed. This relationship table can help understand the mutual influence of each indicator in the entire system, as well as the performance of each substation under multiple indicators.

[0073] Finally, assuming that the intelligent diagnosis system in a certain region reports that there are three abnormalities in a power supply station, namely, Q1, Q2, and Q3. Combining the indicator system and the mutual influence relationship between indicators, an ANP (Analytic Network Process) model is constructed to lay a foundation for subsequent weight calculation.

[0074] Figure 3 is a schematic diagram of an ANP model according to an embodiment of the present application, such as Figure 3 As shown in the figure, the key to this model is to combine the indicator system and the mutual influence relationship between indicators. The ANP model replaces the hierarchical structure by constructing a network structure so that the various elements in the decision-making problem can influence each other. In the ANP model, the decision-making problem is transformed into a directed network, which consists of nodes and edges. The nodes represent the various elements of the decision-making problem (such as goals, criteria, plans, etc.), and the edges represent the dependencies between these elements, ultimately realizing the governance priority ranking of the three substations.

[0075] S102, based on the ANP model, by comparing the relative advantages between model elements with the same affiliation and relative influencing factors, a pairwise judgment matrix between each model element is constructed;

[0076] Specifically, the judgment matrix is ​​based on the interaction between the elements in the ANP network model, and is mainly used to compare the dominance between elements. The judgment matrix represents the comparison of the relative importance of the factors in the previous layer and the factors related to the current layer. All factors that have interdependent and feedback relationships should be compared pairwise. Methods for constructing judgment matrices

[0077] This step includes the following sub-steps:

[0078] Step 1, take any model element with downward subordinate relationship as the criterion model element;

[0079] First, you need to identify a model element with a subordinate relationship as the current criterion model element. This element will serve as a basis for comparison to evaluate the relative importance of its subordinate elements.

[0080] Step 2, set the criterion model element to the initial item of the matrix, and set the subordinate elements belonging to the criterion model element to the rows and columns after the initial item in sequence to build a matrix framework;

[0081] Specific:

[0082] S1, set initial item: place the selected criterion model element in the upper left corner of the matrix (usually the first row and first column), and this position serves as the initial item or reference point of the matrix.

[0083] S2, add subordinate elements: add all subordinate elements belonging to the criterion model element to the rows and columns of the matrix in turn; these elements will be arranged in the rest of the matrix in a certain order (such as alphabetical order, order of importance, etc.).

[0084] S3, forming a framework: Through the above steps, a square matrix is ​​formed, where the dimension of the matrix is ​​determined by the number of subordinate elements; each row and column of the matrix represents an element, and the intersection of the row and column represents the relative importance comparison between the two elements.

[0085] Step 3, combining the expert knowledge in this field, obtain the relative advantage between any two indicators in the framework matrix, and fill in the relative advantage information as the matrix element to obtain a pairwise discriminant matrix, in which the relative advantage can be dynamically optimized by the power supply management personnel according to the actual situation;

[0086] In this embodiment, the relative importance of each pair of elements in the framework matrix is ​​compared in combination with the knowledge and experience of experts in this field, which is usually accomplished through expert scoring or discussion.

[0087] Furthermore, the relative importance information given by the experts is converted into specific numerical values, which are usually expressed using Saaty's scale (such as the 1-9 scale). It can be understood that a scale of 1 indicates that two elements are equally important, a scale of 9 indicates that one element is extremely more important than the other, and the intermediate scale values ​​represent different degrees of relative importance.

[0088] Finally, the quantified relative advantage is filled into the corresponding position of the matrix, and the weight parameters of each column are calculated.

[0089] In addition, it should be noted that after filling in the judgment matrix, a consistency check is usually required to ensure that the expert's judgment is logically consistent. If the consistency check fails, it may be necessary to re-consult the expert or adjust the judgment matrix.

[0090] In an exemplary embodiment:

[0091] 1. For the model elements corresponding to the first-level indicators: Based on the first-level model elements belonging to the same substation, a pairwise judgment matrix between the first-level model elements is constructed, specifically, including the following steps:

[0092] The judgment matrix between the first-level indicators (including the solution layer, i.e., the abnormal area layer): the judgment matrix between the area Q, the area situation T, the abnormal situation Y, and the line loss situation X is generated according to the evaluation of the business experts, and the judgment matrix is ​​constructed. For example, taking the area Q as the criterion, the judgment matrix shown in the following table is constructed:

[0093] Taiwan Area Q Taiwan Area Q Taiwan area situation Abnormal situation Y Line loss X Weight Taiwan Area Q 1 1 / 2 3 3 0.278 Taiwan area situation 2 1 6 5 0.532 Abnormal situation Y 1 / 3 1 / 6 1 1 0.093 Line loss X 1 / 3 1 / 5 1 1 0.097

[0094] Note: CR = 0.002 ≤ 0.1;

[0095] It can be learned that the substation Q is the criterion, the substation situation T, the abnormal situation Y, and the line loss situation X are four first-level indicators;

[0096] Each element of the judgment matrix represents the comparison of the importance between the two indicators, for example:

[0097] The first position (1,1) represents the comparison between "Area Q" and "Area Q", and the value is 1, which means that they are equal to each other.

[0098] At position (1,2), the value is 1 / 2, which means that "station area Q" is less important than "station area situation T" and the weight is 1 / 2.

[0099] At position (1,3), the value is 3, which means that "station area Q" is 3 times more important than "abnormal situation Y".

[0100] The entire matrix is ​​filled in a similar comparison method, and the weight of each indicator is further calculated, which is the eigenvector calculated based on the judgment matrix;

[0101] For example, the weight of "substation condition T" is 0.532, which means that it is the most important among all the first-level indicators and accounts for the largest proportion; "abnormal condition Y" and "line loss condition X" are 0.093 and 0.097 respectively, indicating that they are relatively minor.

[0102] Finally, the judgment matrix needs to pass the consistency test to ensure that the expert's judgment is reasonable and logically self-consistent; the CR (consistency ratio) in the table is 0.002, which is much smaller than 0.1, indicating that the consistency of the matrix is ​​very good and the judgment result is reliable.

[0103] In the above example of the first-level indicators, the comparison of the first-level indicators with expert knowledge, the judgment matrix and weights concluded that "area situation T" is the most important for the overall goal and has the largest weight (0.532). In contrast, "abnormal situation Y" and "line loss situation X" have less impact; these weights can help to reasonably allocate resources in actual operations and give priority to more important indicators.

[0104] 2. For the model elements corresponding to the secondary indicators: in the same area, obtain the secondary model elements belonging to the same model element as any secondary element indicator, and obtain the model elements of the same element set;

[0105] Furthermore, the secondary element indicators that are not subordinate to any secondary element indicator and have mutual training in the indicator influence relationship table are obtained to obtain the model elements between element sets, and the pairwise discriminant matrix between the secondary model elements is constructed based on the model elements of the same element set and the model elements between element sets;

[0106] Specifically, the judgment matrix between the secondary indicators is also obtained by combining the analysis of experts. This matrix is ​​universal in each power supply station, but it should be noted that each power supply station can adjust the advantage degree according to its own situation. After it is determined, it can be used for a long time and adjusted regularly.

[0107] It can be seen that according to the indicator impact relationship diagram, when analyzing the impact of a certain indicator on the overall goal, we cannot only consider the weight of the indicator itself, but also consider all other factors that affect the indicator. Therefore, the matrix constructed for each secondary indicator contains the relative importance comparison of all other factors related to the indicator, including indicators in the same element set and indicators that are related between other different element sets;

[0108] Taking indicator T3 as an example, within the element set, the indicators that affect T3 are T1 and T2. Between element sets, Y1, Y2, Y3, X1, and X2 will all affect T3. For example, the following judgment matrix is ​​the judgment matrix of T3 and Y1, Y2, and Y3:

[0109] The judgment matrix between different element sets is shown in the following table:

[0110] T3 Y1 Y2 Y3 Weight Y1 1 2 3 0.540 Y2 1 / 2 1 2 0.297 Y3 1 / 3 1 / 2 2 0.163

[0111] Note: CR=0.0091<0.1

[0112] It can be seen that the judgment matrix shown in the above table shows the relative importance of the secondary indicators Y1, Y2, and Y3, as well as their weights to the overall goal, specifically:

[0113] First, T3 is used as a reference criterion to compare the relative importance of the three secondary indicators Y1, Y2, and Y3;

[0114] For example:

[0115] At position (1,2), the value is 2, which means that Y1 is twice as important as Y2.

[0116] At position (1,3), the value is 3, which means that Y1 is three times more important than Y3.

[0117] At position (2,3), the value is 2, which means that Y2 is twice as important as Y3.

[0118] Secondly, the weight of each indicator is calculated based on the eigenvector of the judgment matrix (calculated by the eigenvector method).

[0119] The weight of Y1 is 0.540, indicating that it is the most important among the three indicators.

[0120] The weight of Y2 is 0.297, indicating that it is less important than Y1.

[0121] The weight of Y3 is 0.163, indicating that it is relatively the least important among the three indicators.

[0122] Finally, the judgment matrix needs to be tested for consistency to ensure that the expert's judgment is logically consistent. Here, the CR (consistency ratio) is 0.0091, which is much smaller than 0.1, indicating that the consistency of the matrix is ​​very good and the judgment result is reliable.

[0123] Based on the expert evaluation, this judgment matrix shows the importance weights between the secondary indicators Y1, Y2, and Y3 under the reference criterion T3. Y1 has the greatest impact on T3, so it has the highest weight (0.540). Through these weights, it can be further applied to the weighted super matrix to analyze the impact of each secondary indicator on the overall goal. Judgment matrices between different element sets can help establish cross-level and cross-dimensional comparisons, thereby providing more comprehensive information support for the final decision.

[0124] 3. For the substation: according to the historical data of the substation and the expert knowledge in this field, obtain the corresponding index score of each model element;

[0125] When comparing model elements pairwise, the score ratio is obtained according to the indicator scores of the two model elements, and the relative advantage between the model elements is obtained by comparing the score ratio with the preset advantage relationship table, and a judgment matrix between the substation and the model elements is constructed according to the relative advantage between the model elements.

[0126] Specifically, taking the substation Q as an example, since the substations contained in the substation Q are dynamically changing, different power supply stations and different dates will have different abnormal substations. In order to automatically complete the recommended governance priority ranking of abnormal substations for different power supply stations and different dates;

[0127] In this embodiment, the index value of the abnormal area is calculated based on the data of the collection system and the archive data. The value of each index is assigned points according to certain rules, ranging from 1 to 9 points. The higher the score, the higher the governance priority for the index. (This step is automatically completed by the program and updated daily) The index scores of the three areas are shown in the following table:

[0128]

[0129]

[0130] Furthermore, pairwise comparisons are performed, first comparing the scores, and then according to the ratio of the scores, corresponding to the matching dominance relationship. Figure 4 is a schematic diagram of the 1-9 scaling method according to an embodiment of the present application;

[0131] For details, refer to the above Figure 4 As shown, when performing pairwise comparison, the dominance relationship between the indicators is determined by comparing the scores of the two indicators. The specific steps are as follows:

[0132] Calculate the score ratio K: First, calculate the ratio of the scores of the two indicators K = larger score smaller score K = \frac{\text{larger score}}{\text{smaller score}}K = smaller score larger score.

[0133] Suppose that based on a certain abnormal area, index i and index j are compared, the score of index i is recorded as a, the score of index j is recorded as b, and the score ratio K = max(a,b) / min(a,b), that is, the larger score divided by the smaller score. In the set {1,2,3,4,5,6,7,8,9}, find the value closest to K, recorded as M, and determine the dominance according to the method shown in the following table:

[0134]

[0135] For example, if the score of station Q1 on indicator X1 is 5, and the score of station Q2 on indicator X2 is 6, then the score ratio K = 65 = 1.2K = \frac{6}{5} = 1.2K = 56 = 1.2;

[0136] Determine the dominance relationship M: Next, find the integer closest to the ratio K on the 1-9 scale as the dominance relationship M. In this example, 1.2 is close to 1, so M=1.

[0137] Finally, establish a judgment matrix: fill in the judgment matrix according to the dominance relationship M. For example, for the comparison of indicator X1 of area Q1 and indicator X2 of area Q2, the relationship in the judgment matrix can be written as follows: if the scores are equal, the weights of both are 1; if one side has a larger score, the weight is allocated according to the M value.

[0138] For station Q1, X1=5, X2=6, then the judgment matrix of Q1 for X1 and X2 is as follows:

[0139]

[0140] In the above way, the mapping relationship between the score ratio and the 1-9 scaling method is used to ensure that the judgment matrix after each calculation reflects the actual weight relationship between the indicators. This method relies on the comparison of the scores of the substation indicators, and the generated substation has a certain size relationship with the judgment matrix between the model elements. Since the judgment matrix obtained based on the scores is automatically generated by the program, the size relationship between the scores has been determined, so there is no need for consistency check.

[0141] S103, obtaining a weighted supermatrix according to the pairwise discriminant matrices between the lower-level elements and the pairwise discriminant matrices between the higher-level element sets to which the lower-level elements belong;

[0142] The specific steps include:

[0143] Step 1, based on the pairwise judgment matrix between the elements of the secondary model, the corresponding normalized eigenvectors are obtained using the eigenvector method, and the unweighted supermatrix is ​​obtained according to the normalized eigenvectors;

[0144] Among them, the unweighted supermatrix is ​​obtained by comparing the mutual influence of all elements by considering the relationship between all elements. Its significance lies in that it can analyze the influence degree of elements in a certain element set on the sub-criteria. Each column in the matrix is ​​the ranking weight of a certain element as a sub-criteria, that is, the unweighted matrix is ​​composed of the influence weights of the elements in each element set on the sub-criteria. Based on the pairwise judgment matrix, the eigenvector method is used to obtain the normalized eigenvector value and fill in the supermatrix column vector; the unweighted supermatrix provides basic data for further weighted supermatrix calculation and final decision;

[0145] Figure 5 is a schematic diagram of an unweighted supermatrix according to an embodiment of the present application.

[0146] Step 2, based on the pairwise judgment matrix of the second-level elements, obtain the relative importance weights of each element and, according to the relative importance weights, obtain the weight matrix between the element sets;

[0147] It should be noted that in order to achieve comparison across element sets, a weight matrix needs to be constructed, which reflects the relative importance weights between each element set.

[0148] S1, through expert scoring or data analysis, the importance of different element sets is compared pairwise. For example, the two indicator sets of "power supply reliability" and "user satisfaction" are evaluated to see which one is more important for the priority of substation governance. The results will be expressed in the form of relative weights.

[0149] S2, further, constructs a judgment matrix based on the results of the pairwise comparison. The elements in the matrix represent the relative importance of each element set. This matrix is ​​similar to the judgment matrix in the unweighted supermatrix, except that this time the entire element set is compared instead of a single element.

[0150] S3, using the eigenvector method to calculate the eigenvector of the element set judgment matrix, this eigenvector represents the relative weight between each element set, and normalizes it so that the sum of the weights is 1.

[0151] Step 3, obtain the weighted super matrix by multiplying the unweighted super matrix and the weight matrix;

[0152] In this embodiment, the weighted supermatrix is ​​obtained by multiplying the unweighted supermatrix with the weight matrix. This process combines the relationship between elements within the element set and the relative importance between different element sets. The weighted supermatrix represents the degree of influence of each element on the overall goal (such as the priority of substation governance) after considering the relative importance between all element sets. This matrix can help decision makers conduct a more comprehensive analysis across different element sets, so as to more accurately determine which factors have a greater impact on the final goal.

[0153] Through the weighted super matrix, the ultimate impact of each indicator, substation or other element on the overall goal (such as substation governance priority) can be analyzed, thereby helping to formulate more effective governance strategies; it can reflect the global weight across element sets and help analyze the impact of each element on the overall goal.

[0154] Figure 6 is a schematic diagram of a weighted supermatrix according to an embodiment of the present application.

[0155] S104, by solving the weighted super matrix, the global weight of each model element in the ANP model is obtained, and the substation governance priority is generated based on the global weight.

[0156] In this embodiment, the Nth power of the weighted supermatrix is ​​solved by the power method until the column vector of the weighted supermatrix remains unchanged, thereby obtaining a limit supermatrix; Figure 7 is a schematic diagram of an extreme supermatrix according to an embodiment of the present application.

[0157] Finally, according to the column vector of the extreme supermatrix, the global weight corresponding to each substation is obtained, and based on the global weight corresponding to each substation, the governance priority information of the substation is output.

[0158] Combining the global weights obtained from the above super-limit matrix, it can be seen that in substations Q1, Q2, and Q3, the priority of recommended governance is Q2>Q1>Q3, and the power supply station and other power operation and maintenance units can formulate governance strategies in this order.

[0159] In step S104, the ultimate supermatrix obtained by continuously multiplying the weighted supermatrix by itself reflects the comprehensive impact of each element on the overall goal. This process automatically considers the complex relationship between the elements in the system, and the final output provides decision makers with global weight information for optimizing decisions.

[0160] Through the above steps S101 to S104, compared with the traditional method of providing substation governance information by manual collection and manual analysis, the method provided in the embodiment of the present application establishes a general indicator system and scoring method, applies the ANP method to the priority sorting of substation governance, and realizes the automation and standardization of substation governance evaluation through a general scoring and judgment matrix generation method. It not only improves efficiency and reduces operation and maintenance costs, but also ensures the stability and consistency of the evaluation process.

[0161] This embodiment also provides a substation management system based on network analytic hierarchy process, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module", "unit", "subunit", etc. can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0162] Figure 8 is a structural diagram of a substation management system based on the network analytic hierarchy process according to an embodiment of the present application, such as Figure 8 As shown, the system includes a model building module 80, a matrix building module 81 and an operation module 82, wherein:

[0163] The model building module 80 is used to build an ANP model based on the abnormal monitoring data of each substation in the target area and according to the pre-established indicator system table and indicator influence relationship table;

[0164] The matrix construction module 81 is used to construct a pairwise judgment matrix between each model element by comparing the relative advantages between model elements with the same affiliation and relative influencing factors based on the ANP model, and to obtain a weighted supermatrix according to the pairwise judgment matrix between each lower-level model element and the pairwise judgment matrix between the element sets to which the lower-level model elements belong;

[0165] The operation module 82 is used to obtain the global weight of each model element in the ANP model by solving the weighted super matrix, and generate the substation management priority information based on the global weight.

[0166] Through the above system, compared with the traditional solution of providing substation governance information by manual collection and manual analysis, the system provided by the embodiment of the present application establishes a general indicator system and scoring method, applies the ANP method to the priority sorting of substation governance, and realizes the automation and standardization of substation governance evaluation through a general scoring and judgment matrix generation method. It not only improves efficiency and reduces operation and maintenance costs, but also ensures the stability and consistency of the evaluation process.

[0167] In one embodiment, Fig. 9 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, such as Fig. 9 As shown, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in Fig. 9 As shown. The electronic device includes a processor, a network interface, an internal memory and a non-volatile memory connected through an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used to provide computing and control capabilities, the network interface is used to communicate with an external terminal through a network connection, the internal memory is used to provide an environment for the operation of the operating system and the computer program, the computer program is executed by the processor to implement a method for managing a substation based on the network hierarchical analysis method, and the database is used to store data.

[0168] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0169] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0170] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for managing a substation area based on analytic network hierarchy process, characterized in that: include: Based on the abnormal monitoring data of each substation in the target area, the ANP model is constructed according to the pre-established indicator system table and indicator impact relationship table; Based on the ANP model, by comparing the relative advantages between model elements with the same affiliation and relative influencing factors, a pairwise judgment matrix between each model element is constructed; Obtaining a weighted supermatrix according to the pairwise discriminant matrices between the elements of each low-level model and the pairwise discriminant matrices between the element sets to which the low-level model elements belong; By solving the weighted supermatrix, the global weight of each model element in the ANP model is obtained, and the substation management priority information is generated based on the global weight.

2. The method according to claim 1, characterized in that Based on the abnormal monitoring data processing of each substation in the target area, according to the pre-established indicator system table and indicator impact relationship table, the ANP model is constructed including: By calculating the abnormal monitoring data, the level of the corresponding indicator in the indicator system table is obtained to obtain the model element; According to the indicator influence relationship table, the model elements and the correlation information between the model elements are obtained, and the ANP model is constructed based on the model elements and the correlation.

3. The method according to any one of claims 1 to 2, characterized in that The indicator system table includes multiple first-level indicators and second-level indicators subordinate to the first-level indicators. Among them, the first-level indicators include: basic conditions of the substation, abnormal conditions and line loss conditions; the second-level indicators under the basic conditions of the substation include: power supply level, user quantity level, substation governance difficulty, and substation management pressure level; The secondary indicators of the abnormal situation include: abnormal category type, abnormal source, and abnormal table count level; The secondary indicators under the line loss situation include: line loss abnormal days level and line loss abnormal status.

4. The method according to claim 1, characterized in that: Based on the ANP model, by comparing the relative importance weights between elements with the same affiliation, a pairwise judgment matrix between each model element is constructed, including: Any model element with a downward subordinate relationship is used as the criterion model element; The criterion model element is set at the initial item of the matrix, and the matrix framework is constructed by sequentially setting the subordinate elements belonging to the criterion model element at the rows and columns after the initial item; Combined with expert knowledge in this field, the relative advantage between any two indicators in the framework matrix is ​​obtained, and the relative advantage information is filled into the corresponding rows and columns in the matrix framework as matrix elements to obtain the pairwise discriminant matrix, wherein the relative advantage is dynamically optimized by the power supply management personnel according to actual conditions.

5. The method according to claim 4, characterized in that In the process of constructing the pairwise discriminant matrix, the method includes: For the model elements corresponding to the first-level indicators: Based on the primary model elements belonging to the same substation, constructing a pairwise judgment matrix between the primary model elements; For the model elements corresponding to the secondary indicators: Under the same area, obtain the secondary model elements belonging to the same model element as any secondary element index, and obtain the model elements of the same element set; Obtain secondary element indicators that are not subordinate to any secondary element indicator and are mutually related in the indicator influence relationship table, obtain model elements between element sets, and construct a pairwise discriminant matrix between the secondary model elements based on the model elements of the same element set and the model elements between the element sets; For the mentioned areas: According to the historical data of the substation area and the expert knowledge in this field, the corresponding index score of each model element is obtained; When the model elements are compared pairwise, the score ratio is obtained according to the indicator scores of the two model elements, and the relative superiority between the model elements is obtained by comparing the score ratio with the preset superiority relationship table, and a judgment matrix between the station areas and the model elements is constructed according to the relative superiority between the model elements.

6. The method according to claim 3, characterized in that Based on the pairwise discriminant matrix between the indexes of each element and the pairwise discriminant matrix between the element sets to which the elements of the lower-level model belong, the weighted supermatrix is ​​obtained, including: Based on the pairwise judgment matrix between the elements of the secondary model, the corresponding normalized eigenvectors are obtained using the eigenvector method, and an unweighted supermatrix is ​​obtained according to the normalized eigenvectors; Based on the pairwise judgment matrix of the second-level elements, the relative importance weights of each element and are obtained, and according to the relative importance weights, the weight matrix between the element sets is obtained; A weighted super-matrix is ​​obtained by multiplying the unweighted super-matrix and the weight matrix.

7. The method according to claim 6, characterized in that By solving the weighted supermatrix, the global weights of each model element in the ANP model are obtained, including: Solving the Nth power of the weighted supermatrix by the power method until the column vector of the weighted supermatrix remains unchanged, thereby obtaining a limit supermatrix; According to the extreme super-true column vector, the global weight corresponding to each substation is obtained, and based on the global weight corresponding to each substation, the governance priority information of the substation is output.

8. A substation management system based on analytic network hierarchy process, characterized in that: include: Model building blocks, matrix building blocks, and operation blocks, where: The model building module is used to build an ANP model based on the abnormal monitoring data of each substation in the target area and according to a pre-established indicator system table and an indicator influence relationship table; The matrix construction module is used to construct a pairwise judgment matrix between each model element based on the ANP model by comparing the relative advantages between model elements with the same affiliation and relative influencing factors. and obtaining a weighted supermatrix according to the pairwise discriminant matrices between the lower-level model elements and the pairwise discriminant matrices between the element sets to which the lower-level model elements belong; The operation module is used to obtain the global weight of each model element in the ANP model by solving the weighted supermatrix, and generate the substation management priority information based on the global weight.

9. A computer 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 computer program, the method according to 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 method according to any one of claims 1 to 7 is implemented.

Images