Method and device for determining node importance in power supply network and electronic equipment

Abstract

The invention relates to the technical field of power supply networks, and discloses a method and device for determining the importance degree of nodes in a power supply network and electronic equipment, and the method comprises the steps: determining a basic path set between power supply nodes and demand nodes in a Markov random field model; length weighting and reliability weighting of each path are determined according to the length of each path in the basic path set and the importance degree of nodes in each path; and determining the importance of the nodes in the power supply network based on the length weighting and the reliability weighting. According to the determination method, modeling is carried out on the power supply system in a probability graph mode, the importance degree of the nodes in the power supply network is determined based on length weighting and reliability weighting, the problems of data acquisition, pre-disaster emergency preparation and the like can be effectively solved, and related departments can be supported to pertinently arrange monitoring nodes under different budget standards; a low-cost, high-precision and large-range state sensing task of the power supply network under extreme disasters is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply networks, and in particular, to a method for determining the importance degree of nodes in a power supply network, a device for determining the importance degree of nodes in a power supply network, an electronic device, a non-transitory computer-readable storage medium, and a computer program product. Background Art

[0002] In recent years, extreme climate disasters have occurred frequently worldwide. After the chain amplification effect of the urban system, unexpected catastrophic consequences have been caused. In rainstorm events, there are problems such as the outage of substations, the damage or outage of high-voltage transmission lines. At the same time, communication base stations are damaged, and the emergency management department cannot collect comprehensive disaster information in the first time, which greatly delays the rescue and recovery process. As the most important urban critical infrastructure system, the power supply network needs to quickly evaluate its damaged condition at the first time of an extreme disaster, immediately make an emergency response for investigation and repair, and quickly restore the function of the power grid to provide energy guarantee for other subsequent emergency rescue links.

[0003] In related technologies, in addition to arranging a large number of monitoring devices, the belief propagation method based on a probabilistic graph provides a reasoning method for obtaining the state of unknown nodes with high accuracy according to the state information of some nodes, meeting the requirement of evaluating the overall disaster situation at the first time of emergency response. However, this method has two deficiencies: one is that the scale of nodes whose operating status can be obtained is uncontrollable. In extreme disasters, if communication is severely affected, no information may be collected. In severe cascading disasters, if the randomly collected node information is less, the prediction accuracy will drop significantly, which will misjudge the disaster situation; the other is that this method cannot guide relevant departments to make targeted deployments before disasters and does not provide an optimization direction for the emergency response process. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the related technologies to some extent. For this reason, the first object of the present invention is to propose a method for determining the importance degree of nodes in a power supply network. By modeling the power supply system in the form of a probabilistic graph and determining the importance degree of nodes in the power supply network based on length weighting and reliability weighting, it can effectively solve problems such as data acquisition and pre-disaster emergency preparation. Starting from the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments to targetedly arrange monitoring nodes under different budget standards, and achieve low-cost, high-precision, and large-scale state perception tasks for the power supply network in extreme disasters.

[0005] The second object of the present invention is to propose a device for determining the importance degree of nodes in a power supply network.

[0006] The third object of the present invention is to propose an electronic device.

[0007] The fourth object of the present invention is to propose a non-transitory computer-readable storage medium.

[0008] The fifth object of the present invention is to propose a computer program product.

[0009] To achieve the above object, an embodiment of the first aspect of the present invention provides a method for determining the importance of nodes in a power supply network, including: determining a set of basic paths between a power supply node and a demand node in a Markov random field model; determining the length weighting and reliability weighting of each path based on the length of each path in the set of basic paths and the importance of nodes in each path; and determining the importance of nodes in the power supply network based on the length weighting and reliability weighting.

[0010] In addition, the method for determining the importance of nodes in the power supply network according to the above embodiment of the present invention may further have the following additional technical features:

[0011] According to some embodiments of the present invention, before determining the set of basic paths between the power supply node and the demand node, the method further includes: obtaining a network flow model of the power supply network; wherein the network flow model is generated based on the adjacency relationship of several target nodes in the power supply network; determining the failed nodes in the network flow model, and updating the current states of other nodes in the network flow model based on the failed nodes; wherein the failed nodes at least include physically damaged nodes and nodes without energy input; determining the state correlation matrix of adjacent nodes in the network flow model according to the current states of other nodes; and converting the network flow model into a Markov random field model based on the state correlation matrix.

[0012] According to some embodiments of the present invention, determining the set of basic paths between the power supply node and the demand node in the Markov random field model includes: determining a first connected path and a second connected path between several power supply nodes and several demand nodes in the Markov random field model based on a depth-first search algorithm; in response to determining that the first connected path includes the second connected path, generating a set of basic paths based on the first connected path; and in response to determining that the first connected path does not include the second connected path, generating a set of basic paths based on the first connected path and the second connected path.

[0013] According to some embodiments of the present invention, the length weighting and reliability weighting of each path are determined based on the length of each path in the basic path set and the importance of the nodes in each path, including: determining the number of nodes on each basic path in the basic path set, and the importance of each node on each basic path; determining the length of each basic path based on the number of nodes on each basic path, and determining the length weighting of each basic path based on the length of each basic path; determining the reliability weighting of each basic path based on the importance of each node on each basic path.

[0014] According to some embodiments of the present invention, determining the length weight of each path includes:

[0015]

[0016] Among them, H1(i) represents the length weight of each path, l js (i) indicates whether node i is on path ljs. If so, it participates in weighting, otherwise it returns to calculation.

[0017] According to some embodiments of the present invention, determining the reliability weight of each path includes:

[0018]

[0019] Among them, H2(i) represents the reliability weight of the node on the path, and pk represents the reliability of node k.

[0020] According to an embodiment of the present invention, a method for determining the importance of nodes in a power supply network includes: determining a basic path set between power supply nodes and demand nodes in a Markov random field model; determining the length weighting and reliability weighting of each path according to the length of each path in the basic path set and the importance of the nodes in each path; and determining the importance of nodes in the power supply network based on the length weighting and reliability weighting. Therefore, this method can effectively solve problems such as data acquisition and pre-disaster emergency preparedness by modeling the power supply system in a probability graph manner and determining the importance of nodes in the power supply network based on length weighting and reliability weighting. Based on the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments to arrange monitoring nodes in a targeted manner under different budget standards, and realize low-cost, high-precision, and large-scale state perception tasks for the power supply network under extreme disasters.

[0021] The second object of the present invention is to propose a device for determining the importance degree of nodes in a power supply network. By modeling the power supply system in the form of a probability graph and determining the importance degree of nodes in the power supply network based on length weighting and reliability weighting, it can effectively solve problems such as data acquisition and pre-disaster emergency preparation. Starting from the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments to deploy monitoring nodes targeted under different budget standards, and achieve the tasks of low-cost, high-precision, and large-scale state perception of the power supply network under extreme disasters.

[0022] To achieve the above object, an embodiment of the second aspect of the present invention proposes a device for determining the importance degree of nodes in a power supply network, including: a basic path set determination module configured to determine a basic path set between a power supply node and a demand node in a Markov random field model; a weighting determination module configured to determine the length weighting and reliability weighting of each path according to the length of each path in the basic path set and the importance degree of the nodes in each path; an importance degree determination module configured to determine the importance degree of nodes in the power supply network based on the length weighting and reliability weighting.

[0023] The device for determining the importance degree of nodes in a power supply network according to an embodiment of the present invention includes: a basic path set determination module configured to determine a basic path set between a power supply node and a demand node in a Markov random field model; a weighting determination module configured to determine the length weighting and reliability weighting of each path according to the length of each path in the basic path set and the importance degree of the nodes in each path; an importance degree determination module configured to determine the importance degree of nodes in the power supply network based on the length weighting and reliability weighting. Thus, by modeling the power supply system in the form of a probability graph and determining the importance degree of nodes in the power supply network based on length weighting and reliability weighting, this device can effectively solve problems such as data acquisition and pre-disaster emergency preparation. Starting from the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments to deploy monitoring nodes targeted under different budget standards, and achieve the tasks of low-cost, high-precision, and large-scale state perception of the power supply network under extreme disasters.

[0024] To achieve the above object, an embodiment of the third aspect of the present invention proposes an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the above method for determining the importance degree of nodes in a power supply network.

[0025] The electronic device according to the embodiment of the present invention, by executing the above method for determining the importance of nodes in the power supply network, modeling the power supply system in the form of a probability graph, and determining the importance of nodes in the power supply network based on length weighting and reliability weighting, can effectively solve problems such as data acquisition and pre-disaster emergency preparation. Starting from the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments to deploy monitoring nodes targeted under different budget standards, and achieve low-cost, high-precision, and large-scale state perception tasks for the power supply network under extreme disasters.

[0026] To achieve the above object, an embodiment of the fourth aspect of the present invention proposes a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the above method for determining the importance of nodes in the power supply network.

[0027] The storage medium according to the embodiment of the present invention, by the above method for determining the importance of nodes in the power supply network, modeling the power supply system in the form of a probability graph, and determining the importance of nodes in the power supply network based on length weighting and reliability weighting, can effectively solve problems such as data acquisition and pre-disaster emergency preparation. Starting from the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments to deploy monitoring nodes targeted under different budget standards, and achieve low-cost, high-precision, and large-scale state perception tasks for the power supply network under extreme disasters.

[0028] To achieve the above object, an embodiment of the fifth aspect of the present invention proposes a computer program product including computer program instructions that, when executed on a computer, cause the computer to execute the above method for determining the importance of nodes in the power supply network.

[0029] The computer program product according to the embodiment of the present invention, by executing the above method for determining the importance of nodes in the power supply network, modeling the power supply system in the form of a probability graph, and determining the importance of nodes in the power supply network based on length weighting and reliability weighting, can effectively solve problems such as data acquisition and pre-disaster emergency preparation. Starting from the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments to deploy monitoring nodes targeted under different budget standards, and achieve low-cost, high-precision, and large-scale state perception tasks for the power supply network under extreme disasters.

[0030] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flowchart of a method for determining the importance of nodes in a power supply network according to some embodiments of the present invention;

[0032] Figure 2 Schematic diagram of a power supply network according to some embodiments of the present invention;

[0033] Figure 3 Schematic diagram of the inference accuracy of the belief propagation algorithm under different known node ratio scenarios for different metrics according to some embodiments of the present invention;

[0034] Figure 4 Schematic diagram of an apparatus for determining node importance in a power supply network according to some embodiments of the present invention;

[0035] Figure 5 Block diagram of an electronic device according to some embodiments of the present invention. Detailed implementation manners

[0036] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to specific embodiments and the accompanying drawings.

[0037] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should be the ordinary meanings understood by those of ordinary skill in the technical field to which the present invention belongs. The "first", "second" and similar terms used in the embodiments of the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0038] As described in the background art section, in recent years, extreme climate disasters have occurred frequently worldwide. After the chain amplification effect of the urban system, unexpected catastrophic consequences have been caused. In rainstorm events, there are problems such as substation outages, damage or outages of high-voltage transmission lines. At the same time, if communication base stations are damaged, the emergency management department may not be able to collect comprehensive disaster information in a timely manner, which greatly delays the rescue and recovery process. As the most important urban critical infrastructure system, the power supply network needs to quickly evaluate its damaged condition at the first time of an extreme disaster, immediately make an emergency response for inspection and repair, and quickly restore the function of the power grid to provide energy guarantee for other subsequent emergency rescue links.

[0039] In the process of implementing the present invention, the applicant found that in the related art, in addition to deploying a large number of monitoring devices, the belief propagation method based on probabilistic graphs provides a method for inferring the state of unknown nodes with relatively high accuracy based on the state information of partial nodes, meeting the requirement of evaluating the overall disaster situation in the first time of emergency response. However, this method has two deficiencies: one is that the scale of nodes whose operating status can be obtained is uncontrollable. In extreme disasters, if communication is severely disrupted, no information may be collected. In severe cascading disasters, if the randomly collected node information is scarce, the prediction accuracy will drop significantly, leading to misjudgment of the disaster situation; the other is that this method cannot guide relevant departments to make targeted deployments before disasters and does not provide an optimization direction for the emergency response process.

[0040] Therefore, the present invention models the power supply system by means of probabilistic graphs, determines the importance of nodes in the power supply network based on length weighting and reliability weighting, can effectively solve problems such as data acquisition and pre-disaster emergency preparation. Starting from the characteristics of urban infrastructure systems and belief propagation algorithms, it can support relevant departments to deploy monitoring nodes targeted under different budget standards, and achieve low-cost, high-precision, and large-scale state perception tasks for the power supply network in extreme disasters.

[0041] Next, the method for determining the importance of nodes in a power supply network, the device for determining the importance of nodes in a power supply network, an electronic device, a non-transitory computer-readable storage medium, and a computer program product proposed in the embodiments of the present invention will be described with reference to the accompanying drawings.

[0042] Reference Figure 1 , is a flowchart of the method for determining the importance of nodes in a power supply network according to some embodiments of the present invention.

[0043] As Figure 1 shown, the method for determining the importance of nodes in a power supply network according to the embodiments of the present invention may include the following steps:

[0044] S101, in the Markov random field model, determine the set of basic paths between the power source nodes and the demand nodes.

[0045] S102, according to the length of each path in the set of basic paths and the importance of the nodes in each path, determine the length weighting and reliability weighting of each path.

[0046] S103, based on the length weighting and reliability weighting, determine the importance of nodes in the power supply network.

[0047] Specifically, in the power supply network application scenario of the present invention, key nodes can be abstracted from the power supply network. The key nodes can be understood as the nodes that have a greater impact on the entire power supply network (i.e., the target nodes in this application). Further, the adjacency relationship of the target nodes can be determined according to the corresponding Geographic Information System (GIS) data of the power supply network, and a network flow model of the power supply network can be generated. However, not all nodes are meaningful. In some cases, the nodes in the power supply network may fail. Therefore, the corresponding failed nodes need to be removed from the network flow model, and the states of other nodes in the network flow model need to be updated after removing the failed nodes. Further, after obtaining the state correlation matrix (i.e., the potential function) between adjacent nodes through a heuristic search algorithm, the network flow model of the power supply network is converted into a Markov random field model in the probability graph. Further, in the Markov random field model, a basic path set between the power source node and the demand node is determined. The power source node can be understood as the power supply head in the power supply network, and the demand node can be understood as the node in the power supply network that has a power transmission relationship with the power source node.

[0048] In some embodiments of the present invention, before determining the basic path set between the power source node and the demand node, the above method further includes: obtaining the network flow model of the power supply network; wherein, the network flow model is generated based on the adjacency relationship of several target nodes in the power supply network; determining the failed nodes in the network flow model, and updating the current states of other nodes in the network flow model based on the failed nodes; wherein, the failed nodes at least include physically damaged nodes and nodes without energy input; determining the state correlation matrix of adjacent nodes in the network flow model according to the current states of other nodes; converting the network flow model into a Markov random field model based on the state correlation matrix.

[0049] Specifically, before determining the basic path set between the power source node and the demand node, refer to Figure 2, which is a schematic diagram of a power supply network according to some embodiments of the present invention. By abstracting the key nodes in the power supply network, they can be divided into three levels: power plant—(transmission network)—substation—(distribution network)—transformer. According to the specific geographic information system, the adjacency relationship of several target nodes in the power supply network is determined, and then, based on the adjacency relationship of several target nodes in the power supply network, a network flow model of the power supply network is generated. Among them, in the coarse-grained demonstration network, only the substation level is concerned, and the substation level represents the power supply situation within a relatively large geographic grid. Determine the failed nodes in the network flow model. Among them, nodes mainly experience failure events in two types of situations: physically damaged nodes and nodes without energy input caused by the damage of upstream nodes, that is, there is no path connecting the node to the source point in the current network flow model. Since the flow of the failed nodes needs to be redistributed to other nodes to ensure that the flow distribution of the network still satisfies the constraint conditions, it is necessary to update the current state of other nodes in the network flow model based on the failed nodes. An heuristic search algorithm is used to determine the state association matrix (potential function) of adjacent nodes in the network flow model according to the current state of other nodes. Among them, the heuristic search algorithm is a search algorithm that introduces a heuristic function on the basis of the ordinary search algorithm. The role of the heuristic function is to evaluate each branch of the search based on the existing information, select the most promising branch for expansion, so as to improve the search efficiency. The core of the heuristic search algorithm lies in using the heuristic function to guide the search process to quickly find the optimal solution or a better solution in a large search space. This algorithm is particularly suitable for problems that are difficult to directly solve using the exhaustive search method due to the large search space. Based on the state association matrix, the power grid model is converted from the network flow model into a Markov random field model in the probability graph.

[0050] For example, a node located on multiple paths from the source point to other nodes may mean that the node is a key relay point. If such a node fails, it will cause multiple downstream nodes to lose energy input, so its failure impact range is large and its importance is high. For example, in the power grid, a hub node connects multiple regions, and its failure will cause a large-scale power outage.

[0051] The state of the remaining nodes can be inferred by means of the state of some nodes and the state correlation matrix of adjacent nodes, with the help of the belief propagation algorithm. Among them, the belief propagation algorithm (BP) is an inference algorithm based on message passing, which is widely used in probabilistic graphical models (such as Markov random fields, Bayesian networks) to calculate the marginal probability distribution of nodes. It updates the belief (i.e., the marginal probability distribution) of nodes by passing messages in the graph, so as to achieve efficient inference. The belief propagation algorithm takes the nodes with known states as evidence and outputs belief values according to the potential function constraints. The unknown nodes will receive information from all neighbor nodes, and the sum is used as the belief distribution of this iteration. Then, according to the constraint relationship, information is passed to the neighbor nodes until the belief distribution of the entire network converges. By synthesizing the criterion for node failure in the integrated power supply network and the calculation process of the belief propagation algorithm, it can be analyzed that the importance of a node should be related to the path it is on and the amount of information.

[0052] In some embodiments of the present invention, determining a set of basic paths between power nodes and demand nodes in a Markov random field model includes: in the Markov random field model, determining a first connected path and a second connected path between a plurality of power nodes and a plurality of demand nodes based on the depth-first search algorithm; in response to determining that the first connected path includes the second connected path, generating a set of basic paths based on the first connected path; in response to determining that the first connected path does not include the second connected path, generating a set of basic paths based on the first connected path and the second connected path.

[0053] Specifically, in the Markov random field model, the first connected path and the second connected path between several power nodes and several demand nodes are determined based on the depth-first search algorithm. The depth-first search algorithm is an algorithm used to traverse or search a tree or graph. It starts from the starting node, visits nodes as deeply as possible along a path until it can no longer continue, then backtracks to the previous node and continues to visit other paths until the entire graph or tree is traversed. When it is determined that the first connected path includes the second connected path, that is, the second connected path is a subset of the first connected path, the first connected path is used as the basic path set at this time. When it is determined that the first connected path does not include the second connected path, that is, the second connected path is not a subset of the first connected path, the first connected path and the second connected path are used as the basic path set together at this time. For example, in the Markov random field model, there are three nodes A, B, and C. A and B are demand nodes, and C is a power node. Suppose A, B, and C are the first connected path, and B, C are the second connected path. The second connected path is a subset of the first connected path (B and C are included in A, B, and C). At this time, the first connected path (A, B, and C) is used as the basic path set. Another example, suppose B, C are the first connected path, and A, C are the second connected path. The second connected path is not a subset of the first connected path (A and C are not included in B and C). At this time, the first connected path (B, C) and the second connected path (A, C) are used as the basic path set together.

[0054] In some embodiments of the present invention, determining the length weighting and reliability weighting of each path according to the length of each path in the basic path set and the importance of the nodes in each path includes: determining the number of nodes on each basic path in the basic path set and the importance of each node on each basic path; determining the length of each basic path based on the number of nodes on each basic path, and determining the length weighting of each basic path based on the length of each basic path; determining the reliability weighting of each basic path based on the importance of each node on each basic path.

[0055] In some embodiments of the present invention, determining the length weighting of each path includes:

[0056]

[0057] where H1(i) represents the length weighting of each path, and l js (i) represents determining whether node i is on the path ljs. If so, it participates in the weighting; otherwise, the calculation is returned.

[0058] Further, in some embodiments of the present invention, determining the reliability weighting of each path includes:

[0059]

[0060] Among them, H2(i) represents the reliability weighting of nodes on the path, and pk represents the reliability of node k.

[0061] Specifically, assume there are two different basic paths. One basic path contains 3 nodes, and the other basic path contains 10 nodes. When the reliabilities of all nodes are the same, the basic path with only 3 nodes is more likely to be undamaged than the basic path with 10 nodes under extreme disasters. Therefore, after obtaining the set of basic paths, it is necessary to distinguish different-length paths in terms of weights, determine the number of nodes on each basic path in the set of basic paths, determine the length of each basic path based on the number of nodes on each basic path, and determine the length weighting of each basic path based on the length of each basic path. Through the formula The length weighting of each path can be calculated. Since connectivity and reliability are very important for the set of basic paths, it is necessary to determine the importance of each node on each basic path, determine the reliability weighting of each basic path based on the importance of each node on each basic path, and through the formula The reliability weighting of the nodes on the path can be calculated, so that the importance of the nodes in the power supply network can be determined according to the length weighting and the reliability weighting.

[0062] In some embodiments, information entropy can be used to measure the amount of information carried by a system. Among them, information entropy is used to measure the uncertainty or randomness of information. The higher the information entropy, the greater the uncertainty of the information; the lower the information entropy, the smaller the uncertainty of the information. Its basic calculation formula is:

[0063]

[0064] Among them, H(x) represents the magnitude of the system information entropy; P(x i ) represents the probability that the system is in the xi state, and P(x1) + P(x2) +... + P(xn) = 1. According to the above definition, it is easy to know that the smaller H(x) is, the higher the information content of the system. The expression of information entropy and the expression of the potential function can be well combined, that is, it can be used to represent the strength of the relationship between any two adjacent nodes. If a node has more neighbor nodes, the correlation between its state and the states of surrounding nodes is stronger, and the importance of this node in information propagation and state inference tasks is higher. The degree of the node is the larger the better, and the information entropy is the smaller the better. Taking the reciprocal of the information entropy of the node makes the trends of the two consistent. Under this definition, the larger the numerical calculation result of the node, the more important it is. The calculation formula is:

[0065]

[0066] Among them, H1i (Φij) represents the contribution of the potential function between nodes i and j to the information entropy of node i; P(yij) represents the value of each component in the potential function. Under the definition of formula H3(i), there is

[0067] H 1i (Φ ij ) = H 1j (Φ ij )

[0068] That is, the contributions of the potential function to the two nodes are the same. In formula H4(i), the states of each node are classified as 0 and 1, normalized, and then the information entropy is calculated. Under this definition, the contributions of the potential function to the two nodes are generally different.

[0069] Among them, H3(i) represents the importance algorithm proposed in this application, corresponding to evaluation indicators 3 and 4 for node importance.

[0070] In the above definition, it can be found that the difference in node degrees causes certain difficulties in the calculation of information entropy. To solve the problem that the criteria directions of degree and information entropy are inconsistent, the information entropy theory and the Louvain community detection algorithm are combined. First, the network is divided into different communities, and then the information entropy of each node within the community is calculated. The Louvain algorithm is a community detection algorithm based on modularity, which can efficiently discover the network hierarchy. Its calculation formula is:

[0071]

[0072] ki = ΣjAij

[0073]

[0074] Among them, A represents the adjacency matrix of the network; Aij represents the edge weight between nodes i and j, which are all taken as 1 in the present invention; δ(c i , c j ) represents 1 if nodes i and j are in the same community, otherwise 0. After obtaining the community structure using the Louvain algorithm, the calculation formula for node information entropy is: Q is the modularity, that is, the calculation target of this formula. By appropriate community partitioning, make O maximum, m is the sum of the weights of all the connecting edges between nodes, and K i represents the sum of the weights of all the connecting edges of node i.

[0075]

[0076] Among them, H5(i) represents the node information entropy.

[0077] In some embodiments, refer to Figure 3, which is a schematic diagram of the inference accuracy of the belief propagation algorithm under different known node ratio scenarios for different indicators according to some embodiments of the present invention. The above 5 new node importance indicators (information entropy - 1, information entropy - 2, information entropy - community, betweenness - 1, and betweenness - 2) are compared with 4 traditional indicators, namely degree centrality, betweenness centrality, closeness centrality, and random sampling. As can be seen from Figure 3 It can be seen that the Monte Carlo simulation results are as follows:

[0078] At low known node ratios, path - based importance indicators perform better. Based on the betweenness - 1 indicator, the inference accuracy has reached 70% when only 15% of the node states are known. When the ratio of known nodes increases, degree - based methods perform better because nodes with higher degrees provide more information, which is more conducive to the inference task. Generally speaking, after introducing the concept of information entropy, the information entropy - 1 method has a slight improvement on the degree - centrality - based indicator, but not much, indicating that from the perspective of information transmission, the influence of node degree is greater than the potential function distribution. The accuracy of the random method varies little under different known node ratios, indicating that there is indeed a more suitable indicator system for the inference task. Generally, when the proportion of monitored nodes is small, the node importance indicators based on the basic path set proposed by the present invention can greatly improve the accuracy of the inference task; when the monitoring ratio is large, the node importance indicators based on information entropy also have a certain improvement effect on traditional importance indicators.

[0079] Therefore, the present invention proposes a series of more applicable node importance indicators for the probabilistic graphical model and belief propagation algorithm of the power supply network, and conducts sufficient comparison and discussion under different circumstances, which can provide certain guidance for the emergency management department in preparing measures for pre - disaster information collection.

[0080] By comparing with traditional importance indicators under different known state node ratios, the present invention can improve the inference results, especially greatly improving the inference accuracy of the belief propagation algorithm when the ratio of known state nodes is low: ① Based on the characteristics of the power supply network and the information propagation process, starting from the mathematical models of network structure and information entropy, a new node importance indicator is designed, which has good interpretability and expansibility and improves the inference accuracy. ② Sufficiently discuss the performance of different indicators under different circumstances, providing sufficient reference for relevant departments to customize emergency preparations in combination with the expected disaster intensity, emergency budget, etc. in various regions.

[0081] In summary, the method for determining the importance of nodes in the power supply network according to the embodiments of the present invention includes: in the Markov random field model, determining the set of basic paths between the power supply nodes and the demand nodes; determining the length weighting and reliability weighting of each path based on the length of each path in the set of basic paths and the importance of the nodes in each path; and determining the importance of the nodes in the power supply network based on the length weighting and reliability weighting. Thus, by modeling the power supply system in the form of a probability graph and determining the importance of the nodes in the power supply network based on the length weighting and reliability weighting, this method can effectively solve problems such as data acquisition and pre-disaster emergency preparation. Starting from the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments to deploy monitoring nodes targeted under different budget standards, and achieve the task of low-cost, high-precision, and large-scale state perception of the power supply network under extreme disasters.

[0082] It should be noted that the method of the embodiments of the present invention can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiments of the present invention, and these multiple devices will interact with each other to complete the above method.

[0083] It should be noted that some embodiments of the present invention have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the above embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] Corresponding to the above embodiments, the present invention also proposes a device for determining the importance of nodes in a power supply network.

[0085] As Figure 4 shown, the device for determining the importance of nodes in the power supply network according to the embodiments of the present invention includes: a basic path set determination module 410, a weighting determination module 420, and an importance determination module 430.

[0086] Among them, the basic path set determination module 410 is configured to: in the Markov random field model, determine the basic path set between the power supply node and the demand node; the weighted determination module 420 is configured to: determine the length weight and reliability weight of each path according to the length of each path in the basic path set and the importance degree of the nodes in each path; the importance degree determination module 430 is configured to: determine the importance degree of the nodes in the power supply network based on the length weight and the reliability weight.

[0087] In some embodiments of the present invention, before determining the basic path set between the power supply node and the demand node, the basic path set determination module 410 is further configured to obtain a network flow model of the power supply network; wherein, the network flow model is generated based on the adjacency relationship of several target nodes in the power supply network; determine the failed nodes in the network flow model, and update the current states of other nodes in the network flow model based on the failed nodes; wherein, the failed nodes at least include physically damaged nodes and nodes without energy input; determine the state correlation matrix of adjacent nodes in the network flow model according to the current states of other nodes; convert the network flow model into a Markov random field model based on the state correlation matrix.

[0088] In some embodiments of the present invention, the basic path set determination module 410 determines the basic path set between the power supply node and the demand node in the Markov random field model, specifically: in the Markov random field model, determine the first connected path and the second connected path between several power supply nodes and several demand nodes based on the depth-first search algorithm; in response to determining that the first connected path includes the second connected path, generate the basic path set based on the first connected path; in response to determining that the first connected path does not include the second connected path, generate the basic path set based on the first connected path and the second connected path.

[0089] In some embodiments of the present invention, the weighted determination module 420 determines the length weight and reliability weight of each path according to the length of each path in the basic path set and the importance degree of the nodes in each path, specifically: determine the number of nodes on each basic path in the basic path set, and the importance degree of each node on each basic path; determine the length of each basic path based on the number of nodes on each basic path, and determine the length weight of each basic path based on the length of each basic path; determine the reliability weight of each basic path based on the importance degree of each node on each basic path.

[0090] In some embodiments of the present invention, the weighted determination module 420 determines the length weight of each path, specifically:

[0091]

[0092] Among them, H1(i) represents the length weight of each path, ljs (i) indicates whether node i is on path ljs. If so, it participates in weighting, otherwise it returns to calculation.

[0093] In some embodiments of the present invention, the weighted determination module 420 determines the reliability weight of each path, specifically for:

[0094]

[0095] Among them, H2(i) represents the reliability weight of the node on the path, and pk represents the reliability of node k.

[0096] It should be noted that for details not disclosed in the device for determining the importance of nodes in a power supply network in an embodiment of the present invention, please refer to the details disclosed in the method for determining the importance of nodes in a power supply network in an embodiment of the present invention, and no further details will be given.

[0097] In summary, the device for determining the importance of nodes in the power supply network according to the embodiment of the present invention includes: a basic path set determination module, which is configured to: determine the basic path set between the power supply node and the demand node in the Markov random field model; a weighted determination module, which is configured to: determine the length weighting and reliability weighting of each path according to the length of each path in the basic path set and the importance of the node in each path; and an importance determination module, which is configured to: determine the importance of the node in the power supply network based on the length weighting and the reliability weighting. Therefore, the device can effectively solve the problems of data acquisition and pre-disaster emergency preparation by modeling the power supply system in the form of a probability graph and determining the importance of the nodes in the power supply network based on the length weighting and the reliability weighting. Based on the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support the relevant departments to arrange monitoring nodes in a targeted manner under different budget standards, and realize the task of low-cost, high-precision, and large-scale state perception of the power supply network under extreme disasters.

[0098] For the convenience of description, the above system is described as being divided into various modules according to their functions. Of course, when implementing the present invention, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0099] The system of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0100] Corresponding to the above embodiment, the present invention further provides an electronic device.

[0101] refer to Figure 5, is a block diagram of an electronic device according to some embodiments of the present invention, showing a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 510, a memory 520, an input / output interface 530, a communication interface 540, and a bus 550. Among them, the processor 510, the memory 520, the input / output interface 530, and the communication interface 540 are communicatively connected to each other inside the device through the bus 550.

[0102] The processor 510 can be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0103] The memory 520 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 520 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 520 and are called and executed by the processor 510.

[0104] The input / output interface 530 is used to connect to an input / output module to implement information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0105] The communication interface 540 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module can communicate through a wired method (such as USB, network cable, etc.) or through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.).

[0106] The bus 550 includes a path for transmitting information between various components of the device (such as the processor 510, the memory 520, the input / output interface 530, and the communication interface 540).

[0107] It should be noted that, although the above device only shows the processor 510, the memory 520, the input / output interface 530, the communication interface 540 and the bus 550, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0108] The electronic device of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0109] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method of any of the above embodiments.

[0110] The above-mentioned non-transitory computer-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)), etc.

[0111] The computer instructions stored in the storage medium of the above embodiment are used to enable a computer to execute the method of any embodiment in the above exemplary method part, and have the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0112] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present invention also provides a computer program product, including computer program instructions, which, when executed on a computer, enables the computer to execute the above method for determining the importance of nodes in the power supply network.

[0113] According to the computer program product of the embodiment of the present invention, by executing the above-mentioned method for determining the importance of nodes in the power supply network, the power supply system is modeled in the form of a probability graph, and the importance of nodes in the power supply network is determined based on length weighting and reliability weighting. This can effectively solve problems such as data acquisition and pre-disaster emergency preparedness. Based on the characteristics of the urban infrastructure system and the belief propagation algorithm, it can support relevant departments in the targeted deployment of monitoring nodes under different budget standards, and realize low-cost, high-precision, and large-scale status perception tasks for the power supply network under extreme disasters.

[0114] In addition, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this is not a requirement or implication that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. On the contrary, the order of the steps depicted in the flowchart can be changed. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

[0115] It should be understood that the various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0116] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention pertains. The terms "first", "second", and similar terms used in the embodiments of the present invention do not denote any order, quantity, or importance, but are merely used to distinguish different components. The terms "including" or "comprising" and similar terms mean that the elements or items appearing before the term cover the elements or items listed after the term and their equivalents, without excluding other elements or items. The terms "connected" or "coupled" and similar terms are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right", etc. are only used to indicate relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0117] Although the spirit and principles of the present invention have been described with reference to several specific embodiments, it should be understood that the present invention is not limited to the specific embodiments disclosed, and the division of various aspects does not mean that the features in these aspects cannot be combined for benefits. This division is only for convenience of expression. The present invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the appended claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

Claims

1. A method for determining the importance degree of nodes in a power supply network, characterized in that Including: In a Markov random field model, determining a set of basic paths between a power supply node and a demand node; Determining the length weighting and reliability weighting of each path according to the length of each path in the set of basic paths and the importance of the nodes in each path; Determining the importance of the nodes in the power supply network based on the length weighting and reliability weighting.

2. The method for determining the importance degree of nodes in a power supply network according to claim 1, wherein Before determining the set of basic paths between the power supply node and the demand node, the method further includes: Obtaining a network flow model of the power supply network; wherein, the network flow model is generated based on the adjacency relationship of several target nodes in the power supply network; Determining the failed nodes in the network flow model, and updating the current states of other nodes in the network flow model based on the failed nodes; wherein, the failed nodes at least include physically damaged nodes and nodes without energy input; Determining a state correlation matrix of adjacent nodes in the network flow model according to the current states of the other nodes; Converting the network flow model into a Markov random field model based on the state correlation matrix.

3. The method for determining the importance degree of nodes in the power supply network according to claim 1, wherein The determining of the set of basic paths between the power supply node and the demand node in the Markov random field model includes: In the Markov random field model, determining a first connected path and a second connected path between several power supply nodes and several demand nodes based on a depth-first search algorithm; In response to determining that the first connected path includes the second connected path, generating a set of basic paths based on the first connected path; In response to determining that the first connected path does not include the second connected path, generating a set of basic paths based on the first connected path and the second connected path.

4. The method for determining the importance degree of nodes in the power supply network according to claim 1, wherein The determining of the length weighting and reliability weighting of each path according to the length of each path in the set of basic paths and the importance of the nodes in each path includes: Determining the number of nodes on each basic path in the set of basic paths, and the importance of each node on each basic path; Determining the length of each basic path based on the number of nodes on each basic path, and determining the length weighting of each basic path based on the length of each basic path; Determining the reliability weighting of each basic path based on the importance of each node on each basic path.

5. The method for determining the importance degree of nodes in the power supply network according to claim 4, wherein The determining of the length weighting of each path includes: Among them, H1(i) represents the length weighting of each path, and l js (i) represents determining whether node i is on path l js If so, it participates in the weighting; if not, the calculation is returned.

6. The method for determining the importance of nodes in a power supply network according to claim 5, characterized in that, The determining of the reliability weighting of each path includes: Wherein, H2(i) represents the reliability weighting of the nodes on the path, and pk represents the reliability of node k.

7. An apparatus for determining the importance of nodes in a power supply network, including: A basic path set determining module, configured to: in a Markov random field model, determine a set of basic paths between a power supply node and a demand node; A weighting determining module, configured to: determine the length weighting and reliability weighting of each path according to the length of each path in the set of basic paths and the importance of the nodes in each path; An importance determining module, configured to: determine the importance of the nodes in the power supply network based on the length weighting and reliability weighting.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, the method for determining the importance of nodes in the power supply network according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method for determining the importance of nodes in the power supply network according to any one of claims 1 to 6.

10. A computer program product comprising computer program instructions which, when executed on a computer, cause the computer to execute the method for determining the importance of nodes in the power supply network according to any one of claims 1 to 6.

Images