Identification method and device for key nodes in oil field power grid and storage medium

Abstract

The invention discloses an identification method and device for key nodes in an oil field power grid and a storage medium, and belongs to the field of oil and gas development. The method comprises the following steps: constructing a directed topological graph of an oil field power grid; based on the electrical characteristics between two nodes with a connection relationship in the directed topological graph, determining the weight of an edge used for connecting the two nodes, and obtaining the weight of each edge in the directed topological graph; based on the directed topological graph and the weight of each edge in the directed topological graph, determining kernel values respectively corresponding to the plurality of nodes; dividing the target kernel value range into a plurality of kernel value intervals; and screening the plurality of nodes according to the plurality of kernel value intervals so as to determine the node of which the kernel value is located in the maximum kernel value interval in the plurality of kernel value intervals, and taking the node located in the maximum kernel value interval as the key node in the oilfield power grid. According to the method, the node kernel value is determined by combining the electrical characteristics and diversified indexes, and then the nodes are screened, so that the key node set in the oil field power grid can be accurately identified.

Description

Technical Field

[0001] The present application relates to the field of oil and gas development, and in particular to a method, device and storage medium for identifying key nodes in an oilfield power grid. Background Art

[0002] In the process of oil and gas production, the power grid is required to provide power in the links of oil and gas lifting, water injection, gathering and transportation, power supply and distribution, etc. In domestic oil fields, there is a common situation where the oil field power grid is adjacent to villages and towns, and the phenomenon of power theft is relatively serious, which affects the safe operation of the oil field power grid, and then affects the normal oil and gas production process of the oil field, resulting in damage to economic benefits.

[0003] Therefore, how to ensure the safety of oilfield power systems and enhance the robustness of power systems is a key issue that needs to be studied in depth, and identifying and protecting key nodes in oilfield power grids is an effective way. However, in related technologies, the methods for identifying key nodes in oilfield power grids have certain limitations, and the accuracy of identification is not high. Summary of the invention

[0004] The present application provides a method, device and storage medium for identifying key nodes in an oilfield power grid, which can accurately identify key nodes in an oilfield power grid. The technical solution is as follows:

[0005] In one aspect, a method for identifying key nodes in an oilfield power grid is provided, the method comprising:

[0006] Constructing a directed topological graph of the oilfield power grid, wherein the directed topological graph indicates the connection relationship of a plurality of nodes included in the oilfield power grid and the electrical direction between the plurality of nodes, wherein the plurality of nodes include generators, substations, and power supply line buses in the oilfield power grid;

[0007] Determine the weight of an edge connecting two nodes based on electrical characteristics between two nodes having a connection relationship in the directed topological graph, and obtain the weight of each edge in the directed topological graph;

[0008] Based on the directed topological graph and the weight of each edge in the directed topological graph, determining the core values ​​corresponding to the plurality of nodes respectively, the core values ​​indicating the degree of influence of the nodes on the oilfield power grid;

[0009] Divide the target core value range into multiple core value intervals, wherein the minimum value of the target core value range is the minimum value among the core values ​​corresponding to the multiple nodes, and the maximum value of the target core value range is the maximum value among the core values ​​corresponding to the multiple nodes;

[0010] According to the multiple core value intervals, the multiple nodes are screened to determine the nodes whose core values ​​are within the maximum core value interval among the multiple core value intervals, and the nodes within the maximum core value interval are used as key nodes in the oilfield power grid.

[0011] On the other hand, a device for identifying key nodes in an oilfield power grid is provided, the device comprising:

[0012] A construction module, used to construct a directed topological graph of the oilfield power grid, wherein the directed topological graph indicates the connection relationship of multiple nodes included in the oilfield power grid and the electrical direction between the multiple nodes, wherein the multiple nodes include generators, substations, and power supply line buses in the oilfield power grid;

[0013] A first determination module, configured to determine the weight of an edge connecting two nodes having a connection relationship in the directed topological graph based on electrical characteristics between the two nodes, and obtain the weight of each edge in the directed topological graph;

[0014] A second determination module is used to determine the core values ​​corresponding to the multiple nodes respectively based on the directed topological graph and the weight of each edge in the directed topological graph, wherein the core values ​​indicate the influence degree of the nodes on the oilfield power grid;

[0015] An interval division module, used to divide the target core value range into a plurality of core value intervals, wherein the minimum value of the target core value range is the minimum value among the core values ​​corresponding to the plurality of nodes, and the maximum value of the target core value range is the maximum value among the core values ​​corresponding to the plurality of nodes;

[0016] A screening module is used to screen the multiple nodes according to the multiple core value intervals to determine the nodes whose core values ​​are within the maximum core value interval among the multiple core value intervals, and to use the nodes within the maximum core value interval as key nodes in the oilfield power grid.

[0017] On the other hand, a computer device is provided, which includes a memory and a processor, wherein the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to implement the steps of the above-mentioned method for identifying key nodes in the oil field power grid.

[0018] On the other hand, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for identifying key nodes in the oilfield power grid are implemented.

[0019] On the other hand, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the steps of the above-mentioned method for identifying key nodes in an oilfield power grid.

[0020] The technical solution provided by this application can at least bring the following beneficial effects:

[0021] By constructing a directed topology graph of the oilfield power grid and combining the electrical characteristics of the oilfield power grid to determine the node core value, the determined node core value can accurately reflect the characteristics of the oilfield power grid and the importance of each node in the actual oilfield power grid. By iteratively screening nodes layer by layer based on the node core value, the key node set in the oilfield power grid can be found rigorously and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 It is a flow chart of a method for identifying key nodes in an oilfield power grid provided in an embodiment of the present application;

[0024] Figure 2 It is a structural diagram of an IEEE-39 system provided in an embodiment of the present application;

[0025] Figure 3 It is a schematic diagram of the result of iterative node screening of an IEEE-39 system provided by an embodiment of the present application;

[0026] Figure 4 It is a schematic diagram of the load loss rate after removing individual nodes of the top 10 nodes in terms of importance under three methods provided in an embodiment of the present application;

[0027] Figure 5 It is a schematic diagram of the network performance loss rate after removing individual nodes of the top 10 nodes in terms of importance under three methods provided in an embodiment of the present application;

[0028] Figure 6 It is a schematic diagram of network connectivity after cumulatively removing the top 10 nodes in terms of importance under three methods provided in an embodiment of the present application;

[0029] Figure 7 It is a schematic diagram of the total load loss rate and the total efficiency loss rate after all the top 10 nodes of importance are removed under three methods provided in an embodiment of the present application;

[0030] Figure 8 It is a structural schematic diagram of a device for identifying key nodes in an oil field power grid provided in an embodiment of the present application;

[0031] Fig. 9 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0033] Before explaining in detail the method for identifying key nodes in an oilfield power grid provided in an embodiment of the present application, the application scenarios and implementation environments involved in the embodiment of the present application are first introduced.

[0034] In the process of oil and gas production, the power grid is required to provide power in the links of oil and gas lifting, water injection, gathering and transportation, power supply and distribution. In domestic oil fields, there is a common situation where the oil field power grid is adjacent to villages and towns, and the phenomenon of power theft is relatively serious, which affects the safe operation of the oil field power grid, and then affects the normal oil and gas production process of the oil field, resulting in damage to economic benefits. Therefore, ensuring the safety of the oil field power system and enhancing the robustness of the power system are key issues that need to be studied in depth. Among them, identifying the key nodes of the power grid and protecting them is an effective way. A key node refers to a node that, compared with other nodes in the entire power grid system, if the node fails or is removed, it will have a greater impact on the entire system. When a key node in the power system fails, it usually triggers a series of chain failures in the system, resulting in a large-scale power outage.

[0035] In the related technology, there are two main methods for identifying the key nodes of the oilfield power grid: one is to directly identify the key nodes based on the structure and operation characteristics of the power system, and the other is to establish a number of evaluation indicators based on complex network theory to identify the key nodes. However, both methods have their limitations. The first method is prone to miss very important nodes, and most of the second methods do not combine indicators with electrical characteristics. They only verify that the nodes play a key role in the network in terms of spatial structure, or the indicators are single and cannot accurately reflect the characteristics of the power grid.

[0036] Based on this, this application constructs a directed topological graph of the oilfield power grid, combines the electrical characteristics, newly defines the three evaluation indicators of node degree, clustering coefficient and betweenness, and weights the three average indicators to further define new node core values. The key node set is found by iteratively screening the node core values ​​layer by layer. In this way, the key nodes in the power grid can be accurately identified, which helps to ensure the safe operation of the oilfield power grid.

[0037] The executor of the method for identifying key nodes in the oil field power grid provided in the embodiment of the present application is a computer device, such as a PC (Personal Computer), a mobile phone, a smart phone, a PDA (Personal Digital Assistant), a Pocket PC (PPC), a tablet computer, a smart car machine, etc.

[0038] Those skilled in the art should understand that the above-mentioned computer devices are only examples, and other existing or future computer devices, if applicable to the embodiments of the present application, should also be included in the protection scope of the embodiments of the present application and are included here by reference.

[0039] It should be noted that the application scenarios and implementation environments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of application scenarios and implementation environments, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0040] Next, the method for identifying key nodes in the oil field power grid provided in the embodiment of the present application is explained in detail.

[0041] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for identifying key nodes in an oilfield power grid provided in an embodiment of the present application. The method includes the following steps.

[0042] Step 101: construct a directed topology graph of the oilfield power grid, which indicates the connection relationship of multiple nodes included in the oilfield power grid and the electrical direction between the multiple nodes, and the multiple nodes include generators, substations, and power supply line buses in the oilfield power grid.

[0043] In some embodiments, when constructing a directed topology graph of an oilfield power grid, the generators, substations, and power supply line buses in the oilfield power grid are abstracted as nodes of the directed topology graph; the transmission lines between the substations and the transmission lines from the power supply line bus to the load are abstracted as edges of the directed topology graph. Then, based on the connection relationship between each node and the nodes, a directed topology graph of the oilfield power grid is constructed. The direction of the edge in the directed topology graph is the direction of the current or power in the corresponding transmission line.

[0044] Since in the oil field power grid, the power supply line bus is not directly connected to the load, but is connected to the corresponding load through multiple transmission lines, the power supply line bus is equivalent to the source of current of multiple transmission lines, so the power supply line bus can be abstracted as a node of a directed topological graph.

[0045] In some embodiments, when constructing a directed topology graph of an oilfield power grid, unused generators, substations, and power supply line buses in the oilfield power grid may not be abstracted or may be abstracted as zero-demand nodes.

[0046] Since there are many devices and complex circuit wiring in the oilfield power grid, the number of nodes in the corresponding directed topology graph is huge and the connection relationship is complex. In order to reduce the scale of the directed topology graph, the topology structure needs to be appropriately simplified. Optionally, after constructing the directed topology graph of the oilfield power grid in the above manner, two nodes without switches in the connecting line can be merged, the load is accumulated, and if there is a zero demand node, the zero demand node is merged into its parent node.

[0047] Step 102: Based on the electrical characteristics between two nodes having a connection relationship in the directed topological graph, the weight of the edge used to connect the two nodes is determined to obtain the weight of each edge in the directed topological graph.

[0048] The electrical characteristic is any one of the following: rated current, rated power, rated voltage, and actual current, actual power, and actual voltage during actual operation.

[0049] When the electrical characteristics are rated current, rated power and rated voltage, the corresponding directed topology diagram is recorded as a functional layer topology diagram; when the electrical characteristics are actual current, actual power and actual voltage during actual operation, the corresponding directed topology diagram is recorded as an operation layer topology diagram.

[0050] Regardless of whether the electrical characteristic is any parameter among rated current, rated power, rated voltage, actual current, actual power and actual voltage, the values ​​of these parameters may be greater than 1, and the weight is usually between 0 and 1. Therefore, the actual value of the electrical characteristic between each two nodes with a connection relationship in the directed topology graph can be obtained, and the maximum value of these actual values ​​can be determined. Then, for any two nodes with a connection relationship, the ratio of the actual value of the electrical characteristic between the two nodes to the maximum value is used as the weight of the edge between the two nodes, that is, the normalized result of the actual value of the electrical characteristic is used as the weight of each edge in the directed topology graph.

[0051] Step 103: Based on the directed topology graph and the weight of each edge in the directed topology graph, determine the core values ​​corresponding to the multiple nodes respectively, and the core values ​​indicate the influence degree of the nodes on the oilfield power grid.

[0052] In some embodiments, based on the directed topological graph and the weight of each edge in the directed topological graph, the core values ​​corresponding to the multiple nodes are determined according to the following steps (1)-(2).

[0053] (1) Based on the directed topological graph and the weight of each edge in the directed topological graph, the degrees, clustering coefficients and betweenness corresponding to the multiple nodes are determined respectively; wherein the degree indicates the number of edges connected to the node, the clustering coefficient indicates the degree of clustering of the node, and the betweenness indicates the number of shortest paths passing through the node.

[0054] In some embodiments, based on the directed topological graph and the weight of each edge in the directed topological graph, the degrees, clustering coefficients and betweenness corresponding to the plurality of nodes are determined according to the following steps (11)-(14).

[0055] (11) Based on the directed topological graph, an adjacency matrix is ​​constructed. The adjacency matrix is ​​used to describe the connection relationship between every two nodes in the directed topological graph.

[0056] Based on the above description, the electrical characteristic used in determining the weight can be any of the following: rated current, rated power, rated voltage, and actual current, actual power, and actual voltage during actual operation. Next, assuming that the electrical characteristic used in determining the weight is rated current, taking this case as an example, the process of determining the degree, clustering coefficient, and betweenness corresponding to multiple nodes based on a directed topological graph and the weight of each edge in the directed topological graph is described.

[0057] When constructing an adjacency matrix based on a directed topological graph, an n-order matrix can be constructed, in which the matrix element corresponding to the i-th row and the j-th column indicates the connection relationship between node i and node j, and the matrix element corresponding to the j-th row and the i-th column indicates the connection relationship between node j and node i. If there is an edge connecting two nodes in the directed topological graph, the corresponding matrix element is 1, if there is no edge connecting the two nodes, the corresponding matrix element is 0, and when i=j, the corresponding matrix element is 0. Wherein, i and j are integers less than or equal to n, and n is the total number of nodes in the directed topological graph.

[0058] (12) Based on the adjacency matrix and the weight of each edge in the directed topological graph, the in-degree and out-degree corresponding to multiple nodes are determined respectively, and the sum of the in-degree and out-degree of the same node is taken as the degree of the node.

[0059] In some embodiments, based on the adjacency matrix and the weight of each edge in the directed topological graph, the degrees corresponding to the multiple nodes are determined by the following formula (1):

[0060]

[0061] Among them, S i represents the degree of node i, n represents the total number of nodes in the directed topology graph, and a ij represents the matrix element corresponding to the i-th row and j-th column in the above-constructed adjacency matrix, I ij represents the weight of the edge from node i to node j, represents the out-degree of node i, a ji represents the matrix element corresponding to the jth row and the ith column in the above adjacency matrix, I ji represents the weight of the edge from node j to node i, Represents the out-degree of node i.

[0062] (13) Based on the in-degree and out-degree corresponding to the multiple nodes and the weight of each edge in the directed topological graph, the in-clustering coefficient and out-clustering coefficient corresponding to the multiple nodes are determined, and the sum of the in-clustering coefficient and the out-clustering coefficient of the same node is taken as the clustering coefficient of the node.

[0063] In some embodiments, based on the in-degree and out-degree corresponding to the multiple nodes and the weight of each edge in the directed topological graph, the clustering coefficients corresponding to the multiple nodes are determined by the following formula (2):

[0064]

[0065] Among them, C i represents the clustering coefficient of node i, represents the in-degree of node i, represents the normalized weight of the edge from node j to node i, represents the normalized weight of the edge between node j and node k, represents the normalized weight of the edge from node k to node i, represents the in-clustering coefficient of node i; represents the out-degree of node i, represents the normalized weight of the edge from node i to node j, represents the normalized weight of the edge from node i to node k, represents the outbound clustering coefficient of node i.

[0066] Among them, both node j and node k are connected to node i. At the same time, there is no restriction on the direction of the edge between node j and node k. It can be from node j to node k or from node k to node j.

[0067] in, It can be determined by the following formula (3):

[0068]

[0069] Among them, I ji represents the weight of the edge between node j and node k, max(I ji ) represents the maximum value of the path weight among all paths from node j to node k and from node k to node j. The path weight is the sum of the weights of all edges included in the path. and It can also be determined in the same way.

[0070] (14) Based on the directed topological graph, determine the betweenness corresponding to multiple nodes.

[0071] In some embodiments, based on the directed topology graph, the betweennesses corresponding to the multiple nodes are determined by the following formula (4):

[0072]

[0073] Among them, B i represents the betweenness of node i, Indicates that i, j, and k are all nodes in the directed topology graph. i≠j≠k indicates that the three nodes are different nodes. n indicates the total number of nodes in the directed topology graph. N jk represents the number of shortest paths from node j to node k, N jk(i) It indicates the number of shortest paths from node j to node k that pass through node i. The shortest path refers to the path with the smallest sum of the reciprocals of the weights of all edges included in all paths from node j to node k. The shortest path may be one or more.

[0074] The weight of an edge can be divided into dissimilarity weight and similarity weight according to its meaning. If the weight of an edge is dissimilarity weight, the larger the weight, the greater the distance between the two nodes and the more distant the relationship; if the weight of an edge is similarity weight, the larger the weight, the smaller the distance between the two nodes and the closer the relationship. When the normalized current value is used as the weight of an edge, the weight of the edge is similarity weight, so when determining the shortest path, the inverse of the weight of the edge can be used to determine it.

[0075] When the electrical characteristic used to determine the weight is rated power or actual power, the edge weight is also similarity weight. In this case, the shortest path can be determined in the same way as above. When the electrical characteristic used to determine the weight is rated voltage or actual voltage, the edge weight is dissimilarity weight. In this case, the path with the smallest sum of weights of all edges is the shortest path.

[0076] (2) Based on the degrees, clustering coefficients and betweenness corresponding to the multiple nodes, the kernel values ​​corresponding to the multiple nodes are determined.

[0077] In some embodiments, based on the degrees, clustering coefficients and betweennesses corresponding to the multiple nodes, the kernel values ​​corresponding to the multiple nodes are determined according to the following steps (21)-(24).

[0078] (21) Based on the degrees, clustering coefficients and betweenness corresponding to multiple nodes, a first evaluation data matrix is ​​constructed.

[0079] In some embodiments, based on the degrees, clustering coefficients, and betweennesses corresponding to a plurality of nodes, a first evaluation data matrix shown in the following matrix X is constructed:

[0080]

[0081] Where n represents the total number of nodes in the directed topology graph, x i1 represents the first evaluation index corresponding to node i, x i2 represents the second evaluation index corresponding to node i, x i3 It represents the third evaluation index corresponding to node i. The first evaluation index, the second evaluation index and the third evaluation index correspond to one of degree, clustering coefficient and betweenness respectively.

[0082] (22) Normalize the first evaluation data matrix.

[0083] In some embodiments, after constructing the first evaluation data matrix as shown in the matrix X, the first evaluation data matrix is ​​normalized by the following formula (5):

[0084]

[0085] Among them, W ij represents the jth evaluation index of node i in the normalized first evaluation data matrix, x ij represents the jth evaluation index of node i in the first evaluation data matrix before normalization, max(x j ) and min(x j ) respectively represent the maximum and minimum values ​​of the j-th evaluation index corresponding to all nodes in the first evaluation data matrix before normalization.

[0086] (23) Based on the normalized first evaluation data matrix, the weights corresponding to the degrees, clustering coefficients and betweenness of the multiple nodes are determined.

[0087] In some embodiments, based on the normalized first evaluation data matrix, the weights corresponding to the degrees, clustering coefficients, and betweenness of the multiple nodes are determined in the following manner:

[0088] First, the feature weight of each node under the three evaluation indicators can be determined by the following formula (6):

[0089]

[0090] Among them, P ij represents the feature weight of node i under the jth evaluation index, W ij Represents the j-th evaluation index of node i in the normalized first evaluation data matrix.

[0091] Next, the entropy values ​​corresponding to the three evaluation indicators can be determined by the following formula (7):

[0092]

[0093] Among them, e j represents the entropy value corresponding to the jth evaluation index, n represents the total number of nodes, P ij Represents the feature weight of node i under the jth evaluation index.

[0094] Then, the difference coefficients corresponding to the three evaluation indicators can be determined by the following formula (8):

[0095] d j =1-e j (8)

[0096] Among them, d j represents the coefficient of difference of the j-th evaluation index, e j Represents the entropy value corresponding to the j-th evaluation index.

[0097] The above j The larger the value is, the greater the amount of information provided by the jth evaluation indicator, and the greater the weight should be given to this evaluation indicator. Based on this, the weights corresponding to the three evaluation indicators can be determined by the following formula (9):

[0098]

[0099] in, represents the weight of the jth evaluation index, d j Represents the coefficient of difference of the j-th evaluation index.

[0100] (24) Based on the degrees, clustering coefficients and betweennesses corresponding to the multiple nodes, and the weights corresponding to the degrees, clustering coefficients and betweennesses of the multiple nodes, the kernel values ​​corresponding to the multiple nodes are determined.

[0101] In some embodiments, based on the degrees, clustering coefficients, and betweennesses corresponding to the multiple nodes, and the weights corresponding to the degrees, clustering coefficients, and betweennesses of the multiple nodes, the kernel values ​​corresponding to the multiple nodes are determined by the following formula (10):

[0102]

[0103] Among them, K(i) represents the core value of node i, and represents the weights corresponding to degree, clustering coefficient and betweenness respectively, S i , C i and B iThey represent the degree, clustering coefficient and betweenness corresponding to node i respectively.

[0104] Based on the above description, the electrical characteristics used to determine the weight of each edge in the directed topological graph are any of the following: rated current, rated power, rated voltage, and actual current, actual power and actual voltage during actual operation. Of course, in practical applications, the electrical characteristics used to determine the weight of each edge in the directed topological graph can also be at least two of the above electrical characteristics. For example, when all the above electrical characteristics are used to determine the weight of each edge in the directed topological graph, and then determine the core value of the node, the core value of the node is obtained by the first core value, the second core value, the third core value, the fourth core value, the fifth core value, the sixth core value and the seventh core value; wherein the first core value is determined according to the rated current, the second core value is determined according to the rated power, the third core value is determined according to the rated voltage, the fourth core value is determined according to the actual current, the fifth core value is determined according to the actual power, the sixth core value is determined according to the actual voltage, and the seventh core value is determined according to the undirected topological graph of the oil field power grid.

[0105] Among them, the method for determining the first core value has been explained as an example above. The method for determining the second to sixth core values ​​is similar to the method for determining the first core value. The difference is that the electrical characteristics used to determine the weight of each edge in the directed topological graph are different, which will not be elaborated here.

[0106] The seventh core value can be determined by: constructing an undirected topological graph of the oilfield power grid; based on the undirected topological graph, determining the number of edges connected to each node in the undirected topological graph; the obtained number is the seventh core value of each node.

[0107] The process of constructing an undirected topological graph of an oilfield power grid is similar to that of constructing a directed topological graph. That is, the generators, substations, and power supply line buses in the oilfield power grid can be abstracted as nodes of an undirected topological graph; the transmission lines between substations and the transmission lines from the power supply line bus to the load are abstracted as edges of the undirected topological graph. The undirected topological graph is consistent with the connection relationship between nodes in the above-mentioned directed topological graph, but the edges in the undirected topological graph have no direction. Corresponding to the functional layer topological graph and the operation layer topological graph described above, the undirected topological graph is recorded as a physical layer topological graph.

[0108] After determining the first to seventh core values ​​of multiple nodes, the method for obtaining the core values ​​of the multiple nodes through multiple first core values, second core values, third core values, fourth core values, fifth core values, sixth core values ​​and seventh core values ​​can be: determining the functional layer core values ​​of the multiple nodes in the functional layer topology map based on the first core values, second core values ​​and third core values ​​of the multiple nodes; determining the operating layer core values ​​of the multiple nodes in the operating layer topology map based on the fourth core values, fifth core values ​​and sixth core values ​​of the multiple nodes; determining the physical layer core values ​​of the multiple nodes in the physical layer topology map based on the seventh core values ​​of the multiple nodes; determining the core values ​​of the multiple nodes based on the functional layer core values, operating layer core values ​​and physical layer core values ​​respectively corresponding to the multiple nodes.

[0109] Among them, when determining the functional layer core values ​​of multiple nodes in the functional layer topology map based on the first core values, second core values ​​and third core values ​​of multiple nodes, the following method can be used: construct a second evaluation data matrix based on the first core values, second core values ​​and third core values ​​corresponding to the multiple nodes respectively; normalize the second evaluation data matrix; determine the weights corresponding to the first core values, second core values ​​and third core values ​​of the multiple nodes respectively based on the normalized second evaluation data matrix; determine the functional layer core values ​​corresponding to the multiple nodes respectively based on the first core values, second core values ​​and third core values ​​corresponding to the multiple nodes respectively, and the weights corresponding to the first core values, second core values ​​and third core values ​​of the multiple nodes respectively. The same method can also be used when determining the operating layer core values ​​of multiple nodes in the operating layer topology map based on the fourth core values, fifth core values ​​and sixth core values ​​of multiple nodes.

[0110] This process is similar to the process described above of determining the core values ​​corresponding to multiple nodes based on the degrees, clustering coefficients, and betweennesses corresponding to the multiple nodes, except that the degrees, clustering coefficients, and betweennesses are replaced by the first core value, the second core value, and the third core value, or the fourth core value, the fifth core value, and the sixth core value. The specific process is not described here.

[0111] When determining the physical layer core values ​​of multiple nodes in the physical layer topology graph based on the seventh core values ​​of the multiple nodes, the seventh core value of each node may be directly used as the physical layer core value of the node.

[0112] Finally, when determining the core values ​​of multiple nodes based on the functional layer core values, operating layer core values ​​and physical layer core values ​​respectively corresponding to the multiple nodes, the following method can be used: construct a third evaluation data matrix based on the functional layer core values, operating layer core values ​​and physical layer core values ​​respectively corresponding to the multiple nodes; normalize the third evaluation data matrix; determine the weights respectively corresponding to the functional layer core values, operating layer core values ​​and physical layer core values ​​of the multiple nodes based on the normalized third evaluation data matrix; determine the core values ​​respectively corresponding to the multiple nodes based on the functional layer core values, operating layer core values ​​and physical layer core values ​​respectively corresponding to the multiple nodes, and the weights respectively corresponding to the functional layer core values, operating layer core values ​​and physical layer core values ​​of the multiple nodes.

[0113] Similarly, this process is similar to the process described above of determining the core values ​​corresponding to multiple nodes based on the degree, clustering coefficient and betweenness corresponding to the multiple nodes, except that the degree, clustering coefficient and betweenness are replaced by the functional layer core value, operation layer core value and physical layer core value, and the specific process is not described here.

[0114] Of course, in practical applications, the first to sixth core values ​​mentioned above can also be directly used as the final node core values, and the functional layer core values ​​or operation layer core values ​​can also be directly used as the final node core values. The embodiments of the present application do not limit this.

[0115] Since the evaluation indicators used in the above process of determining the node core value include degree, clustering coefficient and node betweenness, the indicators are relatively diverse, and each indicator is obtained by combining with the electrical characteristics of the oilfield power grid, therefore, the determined node core value can accurately reflect the characteristics of the oilfield power grid and accurately reflect the importance of each node in the actual oilfield power grid. In addition, by weighted summing the node core values ​​of the functional layer, operation layer and physical layer networks to determine the final node core value, the final node core value can be more in line with the actual operation of the oilfield power grid. At the same time, it also ensures that the node core value can accurately reflect whether the corresponding node plays a key role in the oilfield power grid in terms of spatial structure.

[0116] Step 104: Divide the target core value range into multiple core value intervals, the minimum value of the target core value range is the minimum value of the core values ​​corresponding to the multiple nodes, and the maximum value of the target core value range is the maximum value of the core values ​​corresponding to the multiple nodes.

[0117] In some embodiments, the target kernel value range is divided into multiple intervals of a first length. When the key node to be determined is more accurate, the first length should be smaller. The first length is set in advance and can be adjusted according to actual application requirements, and the embodiments of the present application do not limit this.

[0118] Step 105: Screen multiple nodes according to the obtained multiple core value intervals to determine the nodes whose core values ​​are within the maximum core value interval among the multiple core value intervals, and use the nodes within the maximum core value interval as key nodes in the oilfield power grid.

[0119] For example, the node whose kernel value is within the maximum kernel value interval among multiple kernel value intervals may be determined in the following manner:

[0120] First, let i=1, obtain the i-th core value interval among multiple core value intervals sorted in order of core value from small to large, delete the nodes in the directed topological graph whose core values ​​are within the i-th core value interval, and obtain an updated directed topological graph; based on the updated directed topological graph and the weight of each edge in the updated directed topological graph, redetermine the core value of each node in the updated directed topological graph; if there are still nodes in the updated directed topological graph whose core values ​​are within the i-th core value interval, continue to delete the nodes in the i-th core value interval, and return to the step of redetermining the core values ​​of each node in the updated directed topological graph, until there are no nodes in the updated directed topological graph whose core values ​​are within the i-th core value interval.

[0121] Then, let i=i+1, obtain the i-th core value interval among multiple core value intervals sorted in ascending order of core value, delete the nodes in the updated directed topological graph whose core values ​​are within the i-th core value interval, and return the updated directed topological graph and the weight of each edge in the updated directed topological graph, and re-determine the core value of each node in the updated directed topological graph until the core values ​​of all nodes in the updated directed topological graph are within the maximum core value interval.

[0122] The weight of each edge in the directed topology graph after each update remains unchanged, but the connection relationship of the nodes in the directed topology graph after each update has changed. Therefore, it is necessary to re-determine the core value of each node in the directed topology graph after the update. Each time the core value of each node in the directed topology graph after the update is re-determined, the method used is the same as the method for determining the node core value described above, and the electrical characteristics based on each time are also consistent.

[0123] By screening nodes based on node core values ​​to obtain nodes within the maximum core value range, the key nodes in the oilfield power grid can be rigorously identified, which helps to ensure the safe operation of the oilfield power grid.

[0124] Next, taking the IEEE-39 system as an example, the method provided in this application is verified through the following processes (1)-(3).

[0125] (1) Determine the key nodes in the IEEE-39 system identified by the method provided by this application, and verify the rationality of the method provided by this application from the perspective of objective facts and field experience.

[0126] IEEE-39 system diagram Figure 2 According to the method provided by the present application, when the above-mentioned first core value is used as the final node core value, a directed topology graph of the IEEE-39 system is constructed according to the above-mentioned method, and the weight of each edge is determined based on the rated current between each two nodes with a connection relationship, and then the above-mentioned three evaluation indicators (degree, clustering coefficient, betweenness) and the first evaluation data matrix corresponding to each node are determined, and then the first evaluation data matrix after normalization is obtained, wherein the normalized values ​​of the three evaluation indicators corresponding to some nodes are shown in Table 1 below:

[0127] Table 1

[0128]

[0129]

[0130] Then, based on the normalized first evaluation data matrix, the weights corresponding to degree, clustering coefficient and betweenness are obtained: and They are 0.46374, 0.32169 and 0.21457 respectively. Finally, based on the degree, clustering coefficient and betweenness of the 39 nodes, and the weights of degree, clustering coefficient and betweenness of 0.46374, 0.32169 and 0.21457, the kernel values ​​of the 39 nodes in the IEEE-39 system are obtained. Among them, the kernel value of node i is K(i) = 0.463747S i +0.32169C i +0.21457B i , S i , C i and B i They represent the degree, clustering coefficient and betweenness corresponding to node i respectively.

[0131] After obtaining the core values ​​corresponding to 39 nodes, the nodes are iteratively screened according to the above method. The number of iterations in the experiment is 4. The iteration results are as follows: Figure 3 shown.

[0132] Please refer to Figure 3, the key node set identified by this method is the nodes in the innermost layer. The nodes in the innermost layer are sorted from large to small according to the core value, and the top 6 nodes in importance are nodes 35, 33, 38, 30, 16, and 34. Among them, the node ranked first in importance is node 35. Node 35 is the power generation node in the system with a power of 687MW and the largest output current. It plays a core role in maintaining the normal operation and network connectivity of the entire IEEE-39 system and has the highest degree of criticality. Therefore, it is reasonable to regard node 35 as the node with the highest importance based on objective facts and field experience, which shows the rationality of the method provided in this application.

[0133] (2) By comparing the method provided in this application with the key nodes identified by the method based on Theil entropy theory and the method based on the maximum flow method, the rationality of the method provided in this application is further verified.

[0134] Since the method based on Theil entropy theory and the method based on the maximum flow method finally rank the importance of the nodes and believe that the nodes with higher rankings are more important, and do not directly give a set of key nodes, therefore, considering the rationality of the comparison process, the top 10 nodes of importance identified by the three methods are compared.

[0135] Will Figure 3 The core values ​​of the middle and secondary inner nodes are also sorted from large to small, and the top 7-10 nodes in importance are 37, 31, 20, and 19, respectively. Finally, the top 10 nodes in importance identified by the method provided by the present application are 35, 33, 38, 30, 16, 34, 37, 31, 20, and 19, respectively, as shown in Table 2. Table 2 also shows the top 10 nodes in importance in the IEEE-39 system identified by the method based on the Theil entropy theory and the method based on the maximum flow method.

[0136] Table 2

[0137]

[0138]

[0139] It can be seen from Table 2 that the top 10 important nodes identified by the method provided in this application have a high overlap rate with the top 10 important nodes identified by the other two methods. In other words, the method provided in this application has a high consistency with other research methods, which further illustrates the rationality of the method provided in this application.

[0140] (3) The accuracy of the method provided in this application is verified by comparing the load loss rate, network efficiency loss rate and network connectivity of IEEE-39 after removing the top 10 nodes in importance in the three methods.

[0141] The top 10 nodes in terms of importance are removed individually, removed cumulatively, and removed completely. The load loss rate and network efficiency loss rate of the top 10 nodes in terms of importance after removing each node are obtained in the three methods, respectively. Figure 4 and Figure 5 As shown; the network connectivity after cumulative removal of the top 10 important nodes in the three methods is obtained, as shown Figure 6 As shown; the load loss rate and network efficiency loss rate after all the top 10 important nodes are removed in the three methods are obtained, as shown Figure 7 shown.

[0142] according to Figure 4 , in the three methods, the load loss rate after each node is removed individually is averaged, and the average value corresponding to the method provided by the present application is greater than the average values ​​corresponding to the other two methods. That is to say, after individually removing the top 10 nodes of importance identified by the method provided by the present application, the average load loss rate of the entire network is greater than the average load loss rate of the entire network corresponding to the other two methods. At the same time, by taking the average value of the load loss rate corresponding to the top 6 nodes of importance and comparing them, it can also be obtained that the average value corresponding to the method provided by the present application is greater than the average value corresponding to the other two methods. That is to say, after individually removing the top 6 nodes of importance identified by the method provided by the present application (key nodes), the average load loss rate of the entire network is greater than the average load loss rate of the entire network corresponding to the other two methods, which shows that the key nodes identified by the method of the present application are more important in the IEEE-39 system than the top 6 node sets of importance corresponding to the other two methods.

[0143] from Figure 4 and Figure 5 It can be seen that when the node with the 4th importance in the method provided by this application fails, the network efficiency loss rate caused by this node is slightly lower than the network efficiency loss rate caused by the node with the 4th importance in the other two methods, but the load loss rate caused is much higher than the load loss rate caused by the node with the 4th importance in the other two methods. At the same time, when the node with the 10th importance in the method provided by this application fails, the load loss rate caused is slightly higher than the load loss rate caused by the node with the 10th importance in the other two methods, and the network efficiency loss rate caused is much higher than the network efficiency loss rate caused by the node with the 10th importance in the other two methods. The above two examples also show that, overall, the accuracy of the method provided by this application is slightly higher than that of the other two methods.

[0144] from Figure 6It can be seen that after the top 6 nodes of importance determined by the method provided by the present application are removed cumulatively, the network connectivity is lower than the network connectivity after the top 6 nodes of importance determined by method 1 and method 2 are removed; after the top 10 nodes of importance determined by the method provided by the present application are removed cumulatively, the network connectivity is still lower than the network connectivity after the top 10 nodes of importance determined by method 1 and method 2 are removed. This shows that the degree of influence of the key node set determined by the method provided by the present application on the network connectivity is greater than the degree of influence of the node sets corresponding to the other two methods on the network connectivity. This also shows that the key node set found by the method of the present application is more accurate.

[0145] from Figure 7 It can be seen that if all the top 10 nodes identified by the method provided by this application are removed, the total load loss rate and total efficiency loss rate of the entire network are higher than the total load loss rate corresponding to the other two methods, indicating that the top 10 nodes identified by the method provided by this application are also higher in overall importance than the top 10 nodes found by the other two methods. This shows that the top 10 nodes found by the method of this application have a greater impact on the entire network, that is, the method of this application is more accurate.

[0146] Based on the above conclusions, it can be seen that for the IEEE-39 system, the key node set identified by the method provided in this application is highly reasonable from the perspective of objective facts and field experience. The method provided in this application identifies the top 10 nodes in terms of importance, which is highly consistent with other research results, further demonstrating the rationality of the method provided in this application. At the same time, the key node set identified by the method provided in this application, as well as the top 10 nodes in terms of importance, have a greater overall impact on the operation of the power grid after removal than the other two methods, indicating that the method provided in this application is more accurate.

[0147] In the embodiment of the present application, in the process of determining the node core value, the evaluation indexes used to determine the node core value include degree, clustering coefficient and node betweenness, the indexes are relatively diverse, and each index is obtained by combining with the electrical characteristics of the oilfield power grid, therefore, the determined node core value can accurately reflect the characteristics of the oilfield power grid and accurately reflect the importance of each node in the actual oilfield power grid. In addition, by weighted summing the node core values ​​of the functional layer, operation layer and physical layer networks to determine the final node core value, the final node core value can be made more in line with the actual oilfield power grid operation. At the same time, it also ensures in the spatial structure that the node core value can accurately reflect whether the corresponding node plays a key role in the oilfield power grid. By iteratively screening the nodes layer by layer based on the node core value, the key node set in the oilfield power grid can be rigorously and accurately found.

[0148] Figure 8 This is a schematic diagram of the structure of a device for identifying key nodes in an oilfield power grid provided by an embodiment of the present application. The device for identifying key nodes in an oilfield power grid can be implemented as part or all of a computer device by software, hardware, or a combination of both. Figure 8 The device includes: a construction module 801, a first determination module 802, a second determination module 803, an interval division module 804 and a screening module 805.

[0149] A construction module 801 is used to construct a directed topological graph of the oilfield power grid, wherein the directed topological graph indicates the connection relationship of multiple nodes included in the oilfield power grid and the electrical direction between the multiple nodes, wherein the multiple nodes include generators, substations, and power supply line buses in the oilfield power grid;

[0150] A first determination module 802 is used to determine the weight of an edge connecting two nodes based on the electrical characteristics between two nodes having a connection relationship in the directed topological graph, and obtain the weight of each edge in the directed topological graph;

[0151] A second determination module 803 is used to determine the core values ​​corresponding to the multiple nodes respectively based on the directed topological graph and the weight of each edge in the directed topological graph, and the core values ​​indicate the influence degree of the nodes on the oilfield power grid;

[0152] An interval division module 804 is used to divide the target core value range into multiple core value intervals, wherein the minimum value of the target core value range is the minimum value of the core values ​​corresponding to the multiple nodes, and the maximum value of the target core value range is the maximum value of the core values ​​corresponding to the multiple nodes;

[0153] The screening module 805 is used to screen multiple nodes according to multiple core value intervals to determine the nodes whose core values ​​are within the maximum core value interval among the multiple core value intervals, and use the nodes within the maximum core value interval as key nodes in the oilfield power grid.

[0154] Optionally, the second determining module 803 includes:

[0155] A first kernel value determination submodule is used to determine the degrees, clustering coefficients and betweenness corresponding to a plurality of nodes respectively based on the directed topological graph and the weight of each edge in the directed topological graph;

[0156] Among them, degree indicates the number of edges connected to a node, clustering coefficient indicates the degree of clustering of nodes, and betweenness indicates the number of shortest paths through a node;

[0157] The second kernel value determination submodule is used to determine the kernel values ​​corresponding to the multiple nodes respectively based on the degrees, clustering coefficients and betweennesses corresponding to the multiple nodes respectively.

[0158] Optionally, the first core value determination submodule includes:

[0159] An adjacency matrix construction unit is used to construct an adjacency matrix based on a directed topological graph, and the adjacency matrix is ​​used to describe the connection relationship between every two nodes in the directed topological graph;

[0160] A degree determination unit, used to determine the in-degree and out-degree corresponding to a plurality of nodes respectively based on the adjacency matrix and the weight of each edge in the directed topological graph, and take the sum of the in-degree and out-degree of the same node as the degree of the node;

[0161] A clustering coefficient determination unit is used to determine the in-clustering coefficients and out-clustering coefficients corresponding to the multiple nodes respectively based on the in-degrees and out-degrees corresponding to the multiple nodes and the weight of each edge in the directed topological graph, and take the sum of the in-clustering coefficient and the out-clustering coefficient of the same node as the clustering coefficient of the node;

[0162] The betweenness determination unit is used to determine the betweennesses corresponding to the multiple nodes respectively based on the directed topological graph.

[0163] Optionally, the second core value determination submodule includes:

[0164] An evaluation matrix construction unit, used to construct a first evaluation data matrix based on the degrees, clustering coefficients and betweenness corresponding to the plurality of nodes respectively;

[0165] A matrix normalization unit, used for normalizing the first evaluation data matrix;

[0166] A weight determination unit, used to determine the weights corresponding to the degrees, clustering coefficients and betweenness of the plurality of nodes respectively based on the normalized first evaluation data matrix;

[0167] The kernel value determination unit is used to determine the kernel values ​​corresponding to the multiple nodes respectively based on the degrees, clustering coefficients and betweennesses corresponding to the multiple nodes respectively and the weights corresponding to the degrees, clustering coefficients and betweennesses of the multiple nodes respectively.

[0168] Optionally, the screening module 805 is specifically used for:

[0169] Let i=1, obtain the i-th core value interval among the multiple core value intervals sorted in ascending order of core values, delete the nodes whose core values ​​are in the i-th core value interval in the directed topological graph, and obtain an updated directed topological graph;

[0170] Based on the updated directed topological graph and the weight of each edge in the updated directed topological graph, re-determine the core value of each node in the updated directed topological graph;

[0171] If there are still nodes whose core values ​​are within the i-th core value interval in the updated directed topological graph, continue to delete the nodes whose core values ​​are within the i-th core value interval, and return to the step of re-determining the core values ​​of each node in the updated directed topological graph until there are no nodes whose core values ​​are within the i-th core value interval in the updated directed topological graph;

[0172] Let i=i+1, obtain the i-th core value interval among multiple core value intervals sorted in ascending order of core value, delete the nodes whose core values ​​are within the i-th core value interval in the updated directed topological graph, and return to the step of re-determining the core value of each node in the updated directed topological graph based on the updated directed topological graph and the weight of each edge in the updated directed topological graph, until the core values ​​of all nodes in the updated directed topological graph are within the maximum core value interval.

[0173] Optionally, the electrical characteristics include a rated current, a rated power, a rated voltage, and an actual current, an actual power, and an actual voltage during actual operation, and the core value of the node is obtained by a first core value, a second core value, a third core value, a fourth core value, a fifth core value, a sixth core value, and a seventh core value;

[0174] Among them, the first core value is determined according to the rated current, the second core value is determined according to the rated power, the third core value is determined according to the rated voltage, the fourth core value is determined according to the actual current, the fifth core value is determined according to the actual power, the sixth core value is determined according to the actual voltage, and the seventh core value is determined according to the undirected topology graph of the oil field power grid.

[0175] In the embodiment of the present application, in the process of determining the node core value, the evaluation indexes used to determine the node core value include degree, clustering coefficient and node betweenness, the indexes are relatively diverse, and each index is obtained by combining with the electrical characteristics of the oilfield power grid, therefore, the determined node core value can accurately reflect the characteristics of the oilfield power grid and accurately reflect the importance of each node in the actual oilfield power grid. By iteratively screening the nodes layer by layer based on the node core value, the key node set in the oilfield power grid can be found rigorously and accurately.

[0176] It should be noted that: the device for identifying key nodes in the oilfield power grid provided in the above embodiment only uses the division of the above functional modules as an example when identifying key nodes in the oilfield power grid. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device for identifying key nodes in the oilfield power grid provided in the above embodiment and the method for identifying key nodes in the oilfield power grid belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0177] Fig. 9 1 is a block diagram of a computer device 900 provided in an embodiment of the present application. The computer device 900 may be a portable mobile terminal, such as a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The computer device 900 may also be referred to as a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.

[0178] Typically, the computer device 900 includes a processor 901 and a memory 902 .

[0179] The processor 901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 901 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), and PLA (Programmable Logic Array). The processor 901 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 901 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 901 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0180] The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 902 is used to store at least one instruction, which is used to be executed by the processor 901 to implement the method for identifying key nodes in the oil field power grid provided in the method embodiment of the present application.

[0181] Those skilled in the art will understand that Fig. 9 The structure shown in the figure does not constitute a limitation on the computer device 900, and the computer device 900 may include more or less components than those shown in the figure, or combine some components, or adopt a different arrangement of components.

[0182] In some embodiments, a computer-readable storage medium is also provided, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for identifying key nodes in the oil field power grid in the above embodiment are implemented. For example, the computer-readable storage medium can be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0183] It is worth noting that the computer-readable storage medium mentioned in the embodiments of the present application may be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0184] It should be understood that all or part of the steps to implement the above embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The computer instructions can be stored in the above-mentioned computer readable storage medium.

[0185] That is, in some embodiments, a computer program product containing instructions is also provided, which, when executed on a computer, enables the computer to execute the steps of the above-mentioned method for identifying key nodes in an oilfield power grid.

[0186] It should be understood that the "at least one" mentioned herein refers to one or more, and "multiple" refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second" and the like are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not limit them to be necessarily different.

[0187] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of the present application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0188] The above-mentioned embodiments are provided for the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for identifying key nodes in an oilfield power grid, characterized in that: The method comprises: Constructing a directed topological graph of the oilfield power grid, wherein the directed topological graph indicates the connection relationship of a plurality of nodes included in the oilfield power grid and the electrical direction between the plurality of nodes, wherein the plurality of nodes include generators, substations, and power supply line buses in the oilfield power grid; Determine the weight of an edge connecting the two nodes based on electrical characteristics between two nodes having a connection relationship in the directed topological graph, and obtain the weight of each edge in the directed topological graph; Based on the directed topological graph and the weight of each edge in the directed topological graph, determining the core values ​​corresponding to the plurality of nodes respectively, the core values ​​indicating the degree of influence of the nodes on the oilfield power grid; Divide the target core value range into multiple core value intervals, wherein the minimum value of the target core value range is the minimum value among the core values ​​corresponding to the multiple nodes, and the maximum value of the target core value range is the maximum value among the core values ​​corresponding to the multiple nodes; According to the multiple core value intervals, the multiple nodes are screened to determine the nodes whose core values ​​are within the maximum core value interval among the multiple core value intervals, and the nodes within the maximum core value interval are used as key nodes in the oilfield power grid.

2. The method according to claim 1, characterized in that The determining, based on the directed topological graph and the weight of each edge in the directed topological graph, the core values ​​corresponding to the plurality of nodes respectively includes: Based on the directed topological graph and the weight of each edge in the directed topological graph, determining the degrees, clustering coefficients and betweennesses corresponding to the plurality of nodes respectively; Wherein, the degree indicates the number of edges connected to the node, the clustering coefficient indicates the degree of clustering of the nodes, and the betweenness indicates the number of shortest paths passing through the node; Based on the degrees, clustering coefficients and betweennesses respectively corresponding to the multiple nodes, the kernel values ​​respectively corresponding to the multiple nodes are determined.

3. The method according to claim 2, characterized in that The determining, based on the directed topological graph and the weight of each edge in the directed topological graph, the degrees, clustering coefficients and betweennesses respectively corresponding to the plurality of nodes comprises: Based on the directed topological graph, construct an adjacency matrix, wherein the adjacency matrix is ​​used to describe the connection relationship between every two nodes in the directed topological graph; Based on the adjacency matrix and the weight of each edge in the directed topological graph, determine the in-degree and out-degree corresponding to the multiple nodes respectively, and take the sum of the in-degree and out-degree of the same node as the degree of the node; Based on the in-degrees and out-degrees respectively corresponding to the multiple nodes and the weight of each edge in the directed topological graph, determine the in-clustering coefficients and out-clustering coefficients respectively corresponding to the multiple nodes, and take the sum of the in-clustering coefficient and the out-clustering coefficient of the same node as the clustering coefficient of the node; Based on the directed topological graph, betweennesses corresponding to the plurality of nodes are determined.

4. The method according to claim 2, characterized in that The determining the kernel values ​​corresponding to the plurality of nodes respectively based on the degrees, clustering coefficients and betweennesses corresponding to the plurality of nodes respectively includes: Constructing a first evaluation data matrix based on the degrees, clustering coefficients and betweennesses respectively corresponding to the plurality of nodes; Normalizing the first evaluation data matrix; Based on the normalized first evaluation data matrix, determining the weights corresponding to the degrees, clustering coefficients and betweenness of the plurality of nodes respectively; Based on the degrees, clustering coefficients and betweennesses respectively corresponding to the multiple nodes and the weights respectively corresponding to the degrees, clustering coefficients and betweennesses of the multiple nodes, the kernel values ​​respectively corresponding to the multiple nodes are determined.

5. The method according to claim 1, characterized in that The screening of the multiple nodes according to the multiple core value intervals to determine a node whose core value is within a maximum core value interval among the multiple core value intervals includes: Let i=1, obtain the i-th core value interval among the multiple core value intervals sorted in ascending order of core values, delete the nodes in the directed topological graph whose core values ​​are within the i-th core value interval, and obtain an updated directed topological graph; Based on the updated directed topological graph and the weight of each edge in the updated directed topological graph, re-determine the core value of each node in the updated directed topological graph; If there are still nodes whose core values ​​are within the i-th core value interval in the updated directed topological graph, continue to delete the nodes whose core values ​​are within the i-th core value interval, and return to the step of re-determining the core values ​​of each node in the updated directed topological graph until there are no nodes whose core values ​​are within the i-th core value interval in the updated directed topological graph; Let i=i+1, obtain the i-th core value interval among the multiple core value intervals after sorting in ascending order of core value, delete the nodes in the updated directed topological graph whose core values ​​are within the i-th core value interval, and return to the step of re-determining the core value of each node in the updated directed topological graph based on the updated directed topological graph and the weight of each edge in the updated directed topological graph, until the core values ​​of all nodes in the updated directed topological graph are within the maximum core value interval.

6. The method according to any one of claims 1 to 5, characterized in that: The electrical characteristics include rated current, rated power, rated voltage, and actual current, actual power, and actual voltage during actual operation, and the core value of the node is obtained by a first core value, a second core value, a third core value, a fourth core value, a fifth core value, a sixth core value, and a seventh core value; Among them, the first core value is determined according to the rated current, the second core value is determined according to the rated power, the third core value is determined according to the rated voltage, the fourth core value is determined according to the actual current, the fifth core value is determined according to the actual power, the sixth core value is determined according to the actual voltage, and the seventh core value is determined according to the undirected topology graph of the oil field power grid.

7. A device for identifying key nodes in an oilfield power grid, characterized in that: The device comprises: A construction module, used to construct a directed topological graph of the oilfield power grid, wherein the directed topological graph indicates the connection relationship of multiple nodes included in the oilfield power grid and the electrical direction between the multiple nodes, wherein the multiple nodes include generators, substations, and power supply line buses in the oilfield power grid; A first determination module, configured to determine the weight of an edge connecting two nodes having a connection relationship in the directed topological graph based on electrical characteristics between the two nodes, and obtain the weight of each edge in the directed topological graph; A second determination module is used to determine the core values ​​corresponding to the multiple nodes respectively based on the directed topological graph and the weight of each edge in the directed topological graph, wherein the core values ​​indicate the influence degree of the nodes on the oilfield power grid; An interval division module, used to divide the target core value range into a plurality of core value intervals, wherein the minimum value of the target core value range is the minimum value among the core values ​​corresponding to the plurality of nodes, and the maximum value of the target core value range is the maximum value among the core values ​​corresponding to the plurality of nodes; A screening module is used to screen the multiple nodes according to the multiple core value intervals to determine the nodes whose core values ​​are within the maximum core value interval among the multiple core value intervals, and to use the nodes within the maximum core value interval as key nodes in the oilfield power grid.

8. The device according to claim 7, characterized in that The second determining module includes: A first kernel value determination submodule, configured to determine the degrees, clustering coefficients, and betweennesses corresponding to the plurality of nodes respectively based on the directed topological graph and the weight of each edge in the directed topological graph; Wherein, the degree indicates the number of edges connected to the node, the clustering coefficient indicates the degree of clustering of the nodes, and the betweenness indicates the number of shortest paths passing through the node; The second kernel value determination submodule is used to determine the kernel values ​​corresponding to the multiple nodes respectively based on the degrees, clustering coefficients and betweennesses corresponding to the multiple nodes respectively.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the steps of the method described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images