Method and device for tracking real-time operation topology of power distribution network

Abstract

The invention relates to the technical field of power system topology identification, and provides a tracking method and device for real-time operation topology of a power distribution network. The method comprises the steps of obtaining a topological association graph library according to a power distribution network frame structure and a switch state matrix of a target power distribution network so as to obtain a voltage and current time sequence evaluation Bayesian network; evaluating the Bayesian network according to the topology association graph library and the voltage and current time sequence of each operation topology in the target time period, and obtaining a topology tracking dynamic Bayesian network at the current tracking moment; acquiring a switch remote signaling real-time evidence set and a voltage and current real-time data evidence set at the current tracking moment, and a voltage and current time sequence distribution model of a target power distribution network in a target time period corresponding to the current tracking moment when the target power distribution network is in each operation topology, and updating the topology tracking dynamic Bayesian network at the current tracking moment, and obtaining an operation topology change sequence at the current tracking moment. By adopting the method, an accurate operation topology change sequence at the current tracking moment can be obtained.

Description

Technical Field

[0001] The present application relates to the technical field of power system topology identification, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for tracking the real-time operating topology of a distribution network. Background Art

[0002] With the development of new elements of distribution networks such as wind and solar power generation, electric vehicles, and new energy storage, the distribution network has transformed from a one-way power transmission role under traditional passive conditions to a two-way power regulation role under active conditions. In the case of multiple types of resources, the uncertainty in the operation of the distribution network has increased, and it is necessary to track the operating topology of the distribution network in real time to analyze the function of the distribution network.

[0003] At present, the distribution network model can be established through detailed parameters such as line impedance and transformer impedance of the distribution network, and the measured voltage phase angle is matched with the state estimation value under each topology to complete the tracking of the operating topology of the distribution network. However, it is easy to produce erroneous results when the measurement data and switch telesignaling data are missing. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for tracking the real-time operation topology of a distribution network in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for tracking the real-time operation topology of a distribution network, comprising:

[0006] A topology association library is obtained according to the distribution network grid structure and switch state matrix of the target distribution network; the target distribution network includes a plurality of nodes; the switch state matrix includes the switch states of the nodes of the operating topology to be tracked;

[0007] According to the topology association library and the historical operation data of the nodes of the target distribution network, a voltage and current time series evaluation Bayesian network is obtained for the target distribution network in multiple time periods when the target distribution network is in each operation topology;

[0008] Obtaining a voltage and current time series distribution model in multiple time periods when the target distribution network is in each operating topology;

[0009] Determine the target period corresponding to the current tracking moment;

[0010] According to the topology association library and the voltage and current time series of each operating topology in the target period, the Bayesian network is evaluated to obtain an initialized topology tracking dynamic Bayesian network;

[0011] If the current tracking moment is the first tracking moment, the initialized topology tracking dynamic Bayesian network is used as the topology tracking dynamic Bayesian network of the current tracking moment;

[0012] If the current tracking moment is not the first tracking moment, the topological tracking dynamic Bayesian network of the previous tracking moment is expanded to obtain the topological tracking dynamic Bayesian network of the current tracking moment;

[0013] The real-time evidence set of switch telesignaling and the real-time data evidence set of voltage and current at the current tracking moment are obtained, as well as the voltage and current time series distribution model of the target distribution network in the target time period when it is in each operating topology, and the topology tracking dynamic Bayesian network at the current tracking moment is updated to obtain the operating topology change sequence at the current tracking moment.

[0014] In one of the embodiments, obtaining a topology association library according to the distribution network grid structure and switch state matrix of the target distribution network includes:

[0015] Substitute the switch state matrix into the grid structure of the distribution network to obtain the operating topology set;

[0016] If the difference between any two operating topologies in the operating topology set is the closed state of a single switch, it is determined that the any two operating topologies have an associated relationship, so as to construct a topology conversion relationship diagram;

[0017] A topology association graph library is obtained according to the running topology set and the topology conversion relationship graph.

[0018] In one of the embodiments, the voltage and current time series evaluation Bayesian network of the target distribution network in multiple time periods when the target distribution network is in each operating topology is obtained according to the topology association graph library and the historical operation data of the nodes of the target distribution network, including:

[0019] Dividing the historical operation data of the nodes of the target distribution network into time periods to obtain the historical operation data of the nodes in multiple time periods;

[0020] Taking multiple time periods as target time periods in turn, and taking each operation topology as a target operation topology in turn;

[0021] According to the historical operation data of the nodes in the target period, a node voltage matrix and a node injection current matrix in the target period are obtained;

[0022] According to the target operating topology, a dependency relationship between a voltage random variable and an injected current random variable corresponding to the target operating topology is obtained;

[0023] According to the node voltage matrix and the node injection current matrix of the target time period, and the dependency relationship between the voltage random variable and the injection current random variable corresponding to the target operating topology, a voltage and current timing evaluation Bayesian network for the target time period when the target distribution network is in the target operating topology is obtained.

[0024] In one embodiment, the step of obtaining a voltage and current time series distribution model in multiple time periods when the target distribution network is in each operating topology includes:

[0025] Taking multiple time periods as target time periods in turn, and taking each operation topology as a target operation topology in turn;

[0026] The voltage and current timing evaluation Bayesian network in the target time period when the target distribution network is in the target operating topology is used as the target voltage and current timing evaluation Bayesian network;

[0027] The probability that each voltage random variable in the target voltage and current timing evaluation Bayesian network takes the actual value of each voltage, and the probability that each injected current random variable takes the actual value of each injected current are inferred and calculated to obtain a voltage and current timing distribution model in a target time period when the target distribution network is in a target operating topology; the voltage random variable and the injected current random variable are data measured by a measuring device.

[0028] In one embodiment, the method of evaluating the Bayesian network based on the topology association graph library and the voltage and current timing of each operating topology in the target time period to obtain an initialized topology tracking dynamic Bayesian network includes:

[0029] According to the topology association graph library and the voltage and current time series of each operating topology in the target period, the Bayesian network is evaluated to obtain an initial sub-Bayesian network and an extended sub-Bayesian network of each operating topology in the target period;

[0030] Constructing a dual Bayesian network for each operating topology in the target period according to the dependency relationship between the voltage random variable and the injection current random variable between the initial sub-Bayesian network and the extended sub-Bayesian network for each operating topology in the target period;

[0031] According to the double Bayesian network of each running topology in the target period, an initialized topology tracking dynamic Bayesian network is obtained.

[0032] In one embodiment, the real-time evidence set of switch telesignaling and the real-time data evidence set of voltage and current at the current tracking moment are obtained, as well as the voltage and current time series distribution model of the target distribution network in each operating topology in the target time period, and the topology tracking dynamic Bayesian network at the current tracking moment is updated to obtain the operating topology change sequence at the current tracking moment, including:

[0033] According to the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, and the voltage and current time series distribution model of the target distribution network in the target time period when it is in each operating topology, the conditional probability of each voltage random variable and each injected current random variable in the topology tracking dynamic Bayesian network at the current tracking moment is updated;

[0034] If the current tracking moment is the first tracking moment, the probability of the target distribution network being in each operating topology at the current tracking moment is obtained by tracking the dynamic Bayesian network according to the topology of the current tracking moment after updating the conditional probability;

[0035] Determine the operating topology corresponding to the current tracking moment according to the probability that the target distribution network is in each operating topology at the current tracking moment;

[0036] If the current tracking moment is not the first tracking moment, the probability of the target distribution network being in each operating topology from the first tracking moment to the current tracking moment is obtained by tracking the dynamic Bayesian network according to the topology of the current tracking moment after updating the conditional probability;

[0037] Any tracking moment from the first tracking moment to the current tracking moment is taken as the target tracking moment;

[0038] Determine the operating topology corresponding to the target tracking time according to the probability that the target distribution network is in each operating topology at the target tracking time;

[0039] According to the operation topology corresponding to each tracking moment from the first tracking moment to the current tracking moment, the operation topology change sequence of the current tracking moment is obtained.

[0040] In a second aspect, the present application also provides a device for tracking the real-time operation topology of a distribution network, comprising:

[0041] A topology association graph library acquisition module is used to obtain a topology association graph library according to a distribution network grid structure and a switch state matrix of a target distribution network; the target distribution network includes a plurality of nodes; the switch state matrix includes a plurality of node switch states of an operating topology to be tracked;

[0042] A voltage and current Bayesian network acquisition module is used to obtain a voltage and current time series evaluation Bayesian network for multiple time periods when the target distribution network is in each operating topology according to the topology association library and the historical operation data of the nodes of the target distribution network;

[0043] A time series distribution model acquisition module is used to obtain the voltage and current time series distribution models of the target distribution network in multiple time periods when the target distribution network is in each operating topology;

[0044] A topological Bayesian network acquisition module is used to determine the target time period corresponding to the current tracking moment; based on the topological association library and the voltage and current timing evaluation Bayesian network of each running topology in the target time period, an initialized topological tracking dynamic Bayesian network is obtained; if the current tracking moment is the first tracking moment, the initialized topological tracking dynamic Bayesian network is used as the topological tracking dynamic Bayesian network of the current tracking moment; if the current tracking moment is not the first tracking moment, the topological tracking dynamic Bayesian network of the previous tracking moment is expanded to obtain the topological tracking dynamic Bayesian network of the current tracking moment;

[0045] The operating topology change sequence acquisition module is used to obtain the switch telesignal real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, as well as the voltage and current time series distribution model of the target distribution network in the target time period when it is in each operating topology, and update the topology tracking dynamic Bayesian network at the current tracking moment to obtain the operating topology change sequence at the current tracking moment.

[0046] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the above method.

[0047] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to execute the above method.

[0048] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and the computer program is executed by a processor to execute the above method.

[0049] The above-mentioned tracking method, device, computer equipment, computer-readable storage medium and computer program product for the real-time operation topology of the distribution network obtain a topology association library according to the distribution network grid structure and switch state matrix of the target distribution network; the target distribution network includes a plurality of nodes; the switch state matrix includes the switch states of the nodes of the operation topology to be tracked; according to the topology association library and the historical operation data of the nodes of the target distribution network, a voltage and current timing evaluation Bayesian network for the target distribution network in multiple time periods when it is in each operation topology is obtained; the voltage and current timing distribution model for the target distribution network in multiple time periods when it is in each operation topology is obtained; the target time period corresponding to the current tracking moment is determined; according to the topology association library, and the target time period of each operation topology The voltage and current timing evaluation Bayesian network is used to obtain the initialized topology tracking dynamic Bayesian network; if the current tracking moment is the first tracking moment, the initialized topology tracking dynamic Bayesian network is used as the topology tracking dynamic Bayesian network at the current tracking moment; if the current tracking moment is not the first tracking moment, the topology tracking dynamic Bayesian network of the previous tracking moment is expanded to obtain the topology tracking dynamic Bayesian network at the current tracking moment; the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, as well as the voltage and current timing distribution model of the target distribution network in each operating topology in the target period, are obtained, the topology tracking dynamic Bayesian network at the current tracking moment is updated, and the operating topology change sequence at the current tracking moment is obtained. The present application obtains a topology association library according to the distribution network grid structure and switch state matrix of the target distribution network; based on the topology association library and the historical operation data of the nodes of the target distribution network, obtains a voltage and current timing evaluation Bayesian network for the target distribution network in multiple time periods when the target distribution network is in each operating topology; according to the topology association library and the voltage and current timing evaluation Bayesian network for each operating topology in the target time period, obtains a topology tracking dynamic Bayesian network at the current tracking moment, and updates the topology tracking dynamic Bayesian network at the current tracking moment by continuously collecting the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set, and obtains the operating topology change sequence at the current tracking moment, which can realize real-time perception of the changes of each switch in the distribution network in the scenario where the measurement data and the switch telesignaling data are lost, and can effectively solve the problem of inaccurate topology perception caused by communication failures in some measurement data and switch telesignaling data. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions 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 related drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 An application environment diagram of a method for tracking a real-time operation topology of a power distribution network in one embodiment;

[0052] Figure 2 A schematic flow chart of a method for tracking a real-time operating topology of a power distribution network in one embodiment;

[0053] Figure 3 is a calculation example structure diagram of a power distribution system in one embodiment;

[0054] Figure 4 A schematic diagram of the operating topology of a power distribution network in one embodiment;

[0055] Figure 5 A schematic diagram of the network structure of a Bayesian network for voltage and current timing evaluation in one embodiment;

[0056] Figure 6 A schematic diagram of a topological association library in an embodiment;

[0057] Figure 7 A schematic diagram of a double Bayesian network in an embodiment;

[0058] Figure 8 A schematic diagram of a topology tracking dynamic Bayesian network in one embodiment;

[0059] Fig. 9 A schematic diagram of a change path of a running topology in one embodiment;

[0060] Fig.10 A structural block diagram of a device for tracking the real-time operation topology of a power distribution network in one embodiment;

[0061] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0063] The present application embodiment provides a method for tracking the real-time operation topology of a distribution network. The present application embodiment can be executed by a computer device, such as Figure 1 As shown, the computer device can obtain the distribution network grid structure, switch state matrix and node historical operation data of the target distribution network, and then the operation topology change sequence at the current tracking moment. It can be understood that the computer device can be implemented through a server, a terminal, or an interactive system between a terminal and a server. In this embodiment, the method includes Figure 2The steps shown are:

[0064] Step S201, obtaining a topology association library according to the distribution network grid structure and switch state matrix of the target distribution network; the target distribution network includes a number of nodes; the switch state matrix includes the switch states of the nodes of the operating topology to be tracked.

[0065] Distribution network structure It refers to the overall layout and connection method of various power facilities and equipment in the power distribution system, which transmits electric energy from the distribution substation to the user through a certain network structure. Various power facilities and equipment can be used as nodes. The example structure diagram of the power distribution system is as follows Figure 3 shown.

[0066] Operation topology refers to the structural layout and organization of each node (such as substation, distribution line, user access point, etc.) in the target distribution network and their interconnection relationship. The target distribution network may include nodes.

[0067] If the node switch states of each node in the target distribution network are different, the operating topology of the target distribution network will be different. The switch state matrix includes the node switch states of several operating topologies to be tracked, so the topological association library of the target distribution network can be obtained according to the distribution network grid structure and the switch state matrix of the target distribution network.

[0068] Step S202, based on the topology association graph library and the historical operation data of the nodes of the target distribution network, a Bayesian network for evaluating the voltage and current time series of the target distribution network in multiple time periods when the target distribution network is in each operation topology is obtained.

[0069] The node historical operation data of the target distribution network may include the node voltage historical data of the entire network and the node injection current historical data of the entire network.

[0070] Multiple time periods can be taken as target time periods in turn, and each operating topology can be taken as the target operating topology in turn; based on the target operating topology in the topology association library and the historical operating data of the nodes in the target time period of the target distribution network, a Bayesian network for evaluating the voltage and current time series in the target time period when the target distribution network is in the target operating topology can be obtained.

[0071] The voltage and current timing evaluation Bayesian network is a directed acyclic graph, whose nodes represent random variables (such as voltage random variables and injected current random variables), and the edges represent the dependencies between random variables. The conditional probability distribution of each random variable can be defined through the historical operation data of the node to model the operation status of the target distribution network, so as to evaluate the voltage and current conditions of the target distribution network in the target period when it is in the target operation topology. Because there is a measurement error in the measurement itself, the voltage measurement value does not match the true voltage value. The measurement error will not be exactly the same each time, causing the voltage measurement value to fluctuate around the true voltage value, so the true voltage value is called the voltage random variable, the voltage measurement value is called the voltage measurement value random variable, the injected current true value is called the injected current random variable, and the injected current measurement value is called the injected current measurement value random variable.

[0072] Step S203, obtaining a voltage and current time series distribution model in multiple time periods when the target distribution network is in each operating topology.

[0073] Multiple time periods can be taken as target time periods in turn, and each operating topology can be taken as the target operating topology in turn; the Bayesian network can be evaluated according to the voltage and current time series of the target distribution network in the target time period when it is in the target operating topology, and a voltage and current time series distribution model of the target distribution network in the target time period when it is in the target operating topology can be obtained.

[0074] Step S204, determining the target time period corresponding to the current tracking moment.

[0075] The tracking time can include multiple times. The target time period corresponding to the current tracking time can be determined based on the current tracking time. The target time period corresponding to the current tracking time can be determined based on the hourly time interval of the current tracking time. For example, the current tracking time is 1:24, and the hourly time interval of the current tracking moment is (1:00, 2:00), then the target time period corresponding to the current tracking moment is 2:00.

[0076] Step S205 , evaluating the Bayesian network according to the topology association graph library and the voltage and current time series of each operating topology in the target time period, to obtain an initialized topology tracking dynamic Bayesian network.

[0077] The Bayesian network can be evaluated based on the topology association graph library and the voltage and current time series of each operating topology in the target period to obtain the initial sub-Bayesian network and extended sub-Bayesian network of each operating topology in the target period; based on the dependency between the voltage random variables and the injected current random variables between the initial sub-Bayesian network and the extended sub-Bayesian network of each operating topology in the target period, a double Bayesian network of each operating topology in the target period is constructed; based on the double Bayesian network of each operating topology in the target period, an initialized topology tracking dynamic Bayesian network is obtained.

[0078] Step S206: if the current tracking moment is the first tracking moment, the initialized topology tracking dynamic Bayesian network is used as the topology tracking dynamic Bayesian network of the current tracking moment.

[0079] Step S207: if the current tracking moment is not the first tracking moment, the topology tracking dynamic Bayesian network of the previous tracking moment is expanded to obtain the topology tracking dynamic Bayesian network of the current tracking moment.

[0080] For example, based on the last tracking time Double Bayesian Network , the last tracking time The topological tracking dynamic Bayesian network is expanded to the current tracking time The topology tracking dynamic Bayesian network is shown in Equation (1) and Equation (2).

[0081] (1)

[0082] (2)

[0083]

[0084]

[0085] In the formula, for Topological tracking of dynamic Bayesian networks at each moment; for Topological tracking of dynamic Bayesian networks at each moment; For topological tracing dynamic Bayesian networks in The number of moments in the time period when the topology needs to be tracked; Respectively indicate time Sub-Bayesian network of ; Represents the adjacency matrix of a directed acyclic graph, which represents and The dependencies of the random variables in .

[0086] Step S208, obtain the switch telesignal real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, as well as the voltage and current time series distribution model of the target distribution network in each operating topology in the target time period, update the topology tracking dynamic Bayesian network at the current tracking moment, and obtain the operating topology change sequence at the current tracking moment.

[0087] According to the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, and the voltage and current time series distribution model of the target distribution network in the target time period when it is in each operating topology, the conditional probability of each voltage random variable and each injected current random variable in the topology tracking dynamic Bayesian network at the current tracking moment is updated;

[0088] If the current tracking moment is the first tracking moment, the topological tracking dynamic Bayesian network at the current tracking moment after updating the conditional probability is used to obtain the probability that the target distribution network is in each operating topology at the current tracking moment; according to the probability that the target distribution network is in each operating topology at the current tracking moment, the operating topology corresponding to the current tracking moment is determined.

[0089] If the current tracing moment is not the first tracing moment, the topological tracing dynamic Bayesian network of the current tracing moment after updating the conditional probability is used to obtain the probability that the target distribution network is in each operating topology from the first tracing moment to the current tracing moment; any tracing moment from the first tracing moment to the current tracing moment is taken as the target tracing moment; according to the probability that the target distribution network is in each operating topology at the target tracing moment, the operating topology corresponding to the target tracing moment is determined; according to the operating topology corresponding to each tracing moment from the first tracing moment to the current tracing moment, the operating topology change sequence at the current tracing moment is obtained.

[0090] In the above-mentioned tracking method of the real-time operation topology of the distribution network, a topology association library is obtained according to the distribution network grid structure and the switch state matrix of the target distribution network; based on the topology association library and the historical operation data of the nodes of the target distribution network, a voltage and current time series evaluation Bayesian network for the target distribution network in multiple time periods when the target distribution network is in each operation topology is obtained; according to the topology association library and the voltage and current time series evaluation Bayesian network for each operation topology in the target time period, a topology tracking dynamic Bayesian network at the current tracking moment is obtained, and by continuously collecting the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set, the topology tracking dynamic Bayesian network at the current tracking moment is updated to obtain the operation topology change sequence at the current tracking moment, which can realize real-time perception of the changes of each switch in the distribution network in the scenario where the measurement data and the switch telesignaling data are lost, and can effectively solve the problem of inaccurate topology perception caused by communication failures in some measurement data and switch telesignaling data.

[0091] In one of the embodiments, a topology association graph library is obtained based on the distribution network grid structure and the switch state matrix of the target distribution network, and the specific steps are as follows: the switch state matrix is ​​substituted into the grid structure of the distribution network to obtain an operating topology set; if the difference between any two operating topologies in the operating topology set is the closed state of a single switch, it is determined that any two operating topologies have an association relationship to construct a topology transformation relationship graph; based on the operating topology set and the topology transformation relationship graph, a topology association graph library is obtained.

[0092] Switch state matrix As shown in formula (3).

[0093] (3)

[0094] In the formula, Indicates the number of running topologies to be traced; represents the number of switches in the target distribution network; Represents the switch state matrix, with dimension , consisting of elements 0 or 1. If Switches in the operating topology If disconnected, is 0, if in Switches in the operating topology Closure is 1; Represents the switch state matrix Middle OK.

[0095] The switch state matrix can be Substitute the grid structure of the distribution network , get the running topology set , as shown in formula (4).

[0096] (4)

[0097] (5)

[0098] In the formula, To run the topology collection; express Middle A running topology; Represents the grid structure of the distribution network Delete The operating topology obtained by setting the corresponding switches in 0.

[0099] If the difference between any two operating topologies in the operating topology set is the closed state of a single switch, it is determined that any two operating topologies have an association relationship; based on the association relationship between each operating topology, a topology conversion relationship diagram is constructed. , as shown in formula (6).

[0100] (6)

[0101]

[0102] In the formula, Topology conversion diagram The adjacency matrix of , for No. Line The elements of the column, express Middle The vertices and There is an edge between the vertices.

[0103] Based on the running topology collection And topology transformation relationship diagram , you can get the topological association library .

[0104] In this embodiment, the switch state matrix is ​​substituted into the grid structure of the distribution network to obtain an operating topology set; a topology transformation relationship diagram is constructed based on the association relationship between the operating topologies; and a relatively accurate topology association library is obtained based on the operating topology set and the topology transformation relationship diagram.

[0105] In one of the embodiments, based on the topology association library and the historical operation data of the nodes of the target distribution network, a Bayesian network for voltage and current timing evaluation in multiple time periods when the target distribution network is in each operation topology is obtained, and the specific steps are as follows: the historical operation data of the nodes of the target distribution network is divided into time periods to obtain the historical operation data of the nodes in multiple time periods; the multiple time periods are sequentially used as the target time periods, and each operation topology is sequentially used as the target operation topology; based on the historical operation data of the nodes in the target time period, a node voltage matrix and a node injection current matrix of the target time period are obtained; based on the target operation topology, a dependency relationship between the voltage random variables and the injection current random variables corresponding to the target operation topology is obtained; based on the node voltage matrix and the node injection current matrix of the target time period, and the dependency relationship between the voltage random variables and the injection current random variables corresponding to the target operation topology, a Bayesian network for voltage and current timing evaluation in the target time period when the target distribution network is in the target operation topology is obtained.

[0106] The node historical operation data of the target distribution network can be divided into time periods to obtain node historical operation data of multiple time periods. The node historical operation data of the target distribution network can include the node voltage historical data of the entire network and the node injection current historical data of the entire network.

[0107] Multiple time periods are used as target time periods in turn, and each operation topology is used as the target operation topology in turn; according to the target time period The node voltage matrix of the target period is obtained by using the historical data of the node historical operation data ;According to the historical data in the node historical operation data of the target period, the node injection current matrix of the target period is obtained .

[0108] According to the target operating topology, the dependency between the voltage random variable and the injected current random variable corresponding to the target operating topology is obtained, as shown in formula (7).

[0109] (7)

[0110] In the formula, Indicates running the topology according to the target The adjacency matrix formed has a dimension of , the directed acyclic graph corresponding to the adjacency matrix represents the target operation topology The corresponding dependence between the voltage random variable and the injected current random variable; Represents the dependency between voltage random variables, and its dimension is ; for dimensional identity matrix, which represents the dependency between the injected current random variable and the voltage random variable, meaning that in the Bayesian network, each injected current has a directed edge pointing to the corresponding voltage ; Submatrix The elements in are shown in formula (8).

[0111] (8)

[0112] In the formula, Represents a submatrix Middle Line The elements of the column, Meaning: In the Bayesian network The voltage random variable has a directed edge pointing to A voltage random variable, Meaning: In the Bayesian network The voltage random variable has a directed edge pointing to A voltage random variable.

[0113] According to the target period The node voltage matrix and node injection current matrix , and the target running topology The corresponding dependence between the voltage random variable and the injected current random variable , the voltage and current time series evaluation Bayesian network of the target distribution network in the target operation topology during the target period is obtained , where the voltage and current time series evaluation Bayesian network Including the conditional probability distribution of each voltage random variable and the conditional probability distribution of the injected current random variable, the calculation formulas are shown in equations (9) and (10) respectively.

[0114] (9)

[0115] (10)

[0116] In the formula, , represents the mth voltage random variable, For There is a directed edge pointing to the voltage random variable The set of all voltage random variables; represents the mth injected current random variable; Indicates that according to Calculate the conditional probability distribution based on the hourly voltage history data; Indicates that according to The conditional probability distribution is calculated based on the hourly injection current history data.

[0117] In this embodiment, based on the node voltage matrix and the node injection current matrix of the target time period, and the dependency relationship between the voltage random variables and the injection current random variables corresponding to the target operating topology, a relatively accurate Bayesian network for evaluating the voltage and current timing in the target time period when the target distribution network is in the target operating topology can be obtained.

[0118] In one of the embodiments, a voltage and current time series distribution model of a target distribution network in multiple time periods when it is in each operating topology is obtained, and the specific steps are as follows: taking multiple time periods as target time periods in turn, and taking each operating topology as a target operating topology in turn; taking a voltage and current time series evaluation Bayesian network for the target distribution network in the target operating topology in the target time period as a target voltage and current time series evaluation Bayesian network; performing inference calculation on the probability that each voltage random variable in the target voltage and current time series evaluation Bayesian network takes the actual value of each voltage, and the probability that each injected current random variable takes the actual value of each injected current, to obtain a voltage and current time series distribution model for the target distribution network in the target operating topology in the target time period; the voltage random variable and the injected current random variable are data measured by a measuring device.

[0119] Multiple time periods are taken as target time periods in turn, and each operation topology is taken as the target operation topology in turn; the target distribution network is in the target operation topology During the target period Bayesian network for voltage and current time series evaluation , as the target voltage and current time series to evaluate the Bayesian network.

[0120] Evaluate Bayesian network for target voltage and current time series based on evidence propagation method The probability of each voltage random variable taking the actual value of each voltage, and the probability of each injected current random variable taking the actual value of each injected current are inferred and calculated to obtain the voltage and current time series distribution model of the target distribution network in the target operation topology during the target period, as shown in formula (11). The voltage random variable is the voltage data measured by the voltage measurement device set at each node in the target distribution network, and the injected current random variable is the current data measured by the current measurement device set at each node in the target distribution network.

[0121] (11)

[0122] In the formula, Represents an array of random variables of the voltage of the entire network; Represents an array of random variables of the current injected into the entire network; Indicates that the target distribution network is in the target operating topology During the target period The voltage and current time series distribution model, According to the evidence propagation method The probability of the random variables taking each actual value is used for inference calculation.

[0123] by Figure 4 Taking the operation topology of the distribution network shown in FIG. 1 as an example, the network structure of the voltage and current timing evaluation Bayesian network constructed according to the method described in this embodiment is as follows: Figure 5 shown.

[0124] In this embodiment, the probability that each voltage random variable in the target voltage and current timing evaluation Bayesian network takes the actual value of each voltage, and the probability that each injected current random variable takes the actual value of each injected current are inferred and calculated, so that a more accurate voltage and current timing distribution model can be obtained in the target time period when the target distribution network is in the target operating topology.

[0125] In one of the embodiments, based on the topology association graph library and the voltage and current timing evaluation Bayesian network of each operating topology in the target time period, an initialized topology tracking dynamic Bayesian network is obtained, and the specific steps are as follows: based on the topology association graph library and the voltage and current timing evaluation Bayesian network of each operating topology in the target time period, an initial sub-Bayesian network and an extended sub-Bayesian network of each operating topology in the target time period are obtained; based on the dependency relationship between the voltage random variable and the injected current random variable between the initial sub-Bayesian network and the extended sub-Bayesian network of each operating topology in the target time period, a dual Bayesian network of each operating topology in the target time period is constructed; based on the dual Bayesian network of each operating topology in the target time period, an initialized topology tracking dynamic Bayesian network is obtained.

[0126] According to the topology association library and the voltage and current time series of each operating topology in the target period, the Bayesian network is evaluated to obtain the initial sub-Bayesian network of each operating topology in the target period. and the extended sub-Bayesian network . The initial sub-Bayesian network The random variables included are: A voltage random variable, The injected current is a random variable, voltage measurement random variables, The injected current measurement value random variable, 1 current topology random variable, a total of random variables. Initial sub-Bayesian network and the extended sub-Bayesian network contain the same random variables.

[0127] The voltage random variable is the true value of the voltage at each node in the target distribution network, and the voltage measurement value random variable is the voltage measured by the voltage measurement device. The difference between the two is that each node in the distribution network has voltage, and the number of voltage random variables is the same as the number of grid nodes; while the distribution network only has voltage measurement devices at some nodes, and the number of voltage measurement values ​​is relatively small. Due to the measurement error, the voltage measurement value is not completely equal to the true value of the voltage.

[0128] The injected current random variable is the true value of the injected current at each node in the power grid, and the injected current measurement value random variable is the current measured by the current measurement device. The difference between the two is that each node in the distribution network has injected current, and the number of injected current random variables is the same as the number of grid nodes; while the distribution network only has current measurement devices at some nodes, and the number of injected current measurement value random variables is relatively small. Due to the existence of measurement errors, the injected current measurement value is not completely equal to the true value of the injected current.

[0129] According to the dependency relationship between the voltage random variable and the injected current random variable between the initial sub-Bayesian network and the extended sub-Bayesian network of each operating topology in the target period , construct a double Bayesian network for each running topology in the target period. The dependency relationship between the voltage random variable and the injected current random variable between the initial sub-Bayesian network and the extended sub-Bayesian network is As shown in formula (12).

[0130] (12)

[0131] In the formula, is an adjacency matrix, and the directed acyclic graph corresponding to the adjacency matrix represents the dependency relationship between random variables; the submatrix To represent the dependency between voltage random variables; for dimensional identity matrix, which means injecting current random variables into the directed acyclic graph to point to voltage random variables; for dimensional matrix, which means that in the directed acyclic graph, the voltage random variable points to the voltage measurement value random variable. When the kth node is equipped with the mth voltage measurement, the element of the kth row and mth column of the matrix is ​​1; for dimensional matrix, which means that in the directed acyclic graph, the injected current random variable points to the current injection measurement value random variable. When the kth node installs the mth injected current measurement, the element of the kth row and mth column of the matrix is ​​1; for dimensional unit vector, indicating that the current topological random variable points to the node voltage random variable. As shown in formula (13).

[0132] (13)

[0133] In the formula, Represents a submatrix Middle Line Elements of a column.

[0134] According to the double Bayesian network of each operating topology in the target period, the probability of the target distribution network being in each operating topology in the target period is obtained, and the double Bayesian network corresponding to the operating topology with the largest probability in the target period is used as the initialization topology tracking dynamic Bayesian network.

[0135] In this embodiment, a double Bayesian network for each operating topology in the target time period is constructed based on the dependency relationship between the voltage random variable and the injected current random variable between the initial sub-Bayesian network and the extended sub-Bayesian network of each operating topology in the target time period; based on the double Bayesian network of each operating topology in the target time period, a more accurate initialized topology tracking dynamic Bayesian network is obtained.

[0136] In one of the embodiments, a switch telesignaling real-time evidence set and a voltage and current real-time data evidence set at the current tracking moment, as well as a voltage and current time series distribution model when the target distribution network is in each operating topology in the target time period are obtained, and the topology tracking dynamic Bayesian network at the current tracking moment is updated to obtain the operating topology change sequence at the current tracking moment. The specific steps are as follows: according to the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, as well as the voltage and current time series distribution model when the target distribution network is in each operating topology in the target time period, the conditional probability of each voltage random variable and each injected current random variable in the topology tracking dynamic Bayesian network at the current tracking moment is updated; if the current tracking moment is the first tracking moment, according to the topology tracking dynamic Bayesian network at the current tracking moment after the updated conditional probability, The dynamic Bayesian network is used to obtain the probability that the target distribution network is in each operating topology at the current tracking moment; the operating topology corresponding to the current tracking moment is determined according to the probability that the target distribution network is in each operating topology at the current tracking moment; if the current tracking moment is not the first tracking moment, the topological tracking dynamic Bayesian network at the current tracking moment after updating the conditional probability is used to obtain the probability that the target distribution network is in each operating topology from the first tracking moment to the current tracking moment; any tracking moment from the first tracking moment to the current tracking moment is taken as the target tracking moment; the operating topology corresponding to the target tracking moment is determined according to the probability that the target distribution network is in each operating topology at the target tracking moment; the operating topology change sequence at the current tracking moment is obtained according to the operating topology corresponding to each tracking moment from the first tracking moment to the current tracking moment.

[0137] The switch telesignal real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment can be obtained, and the switch telesignal real-time evidence set and the voltage and current real-time data evidence set can be called the real-time evidence set, as shown in formula (14). The switch telesignal real-time evidence set and the voltage and current real-time data evidence set are shown in formulas (15) and (16) respectively.

[0138] (14)

[0139] (15)

[0140]

[0141] (16)

[0142] In the formula, To track the time A real-time evidence collection; To track the time Real-time evidence set of switch remote signaling, including all switches in the time period The breaking state and breaking time between them; Indicates A switch in The open and closed state at the moment; To track the time Real-time data evidence set of voltage and current, including time periods The voltage measurement value and the injected current measurement value between them; Indicates The voltage measurement device at each node is The measurement data at the time. If the voltage measurement data is missing, it is -1; Indicates The injected current measurement device of each node is The measurement data at the moment. If the current measurement data is missing, it is -1; is the number of voltage measuring devices, is the number of devices measuring the injected current.

[0143] According to the real-time evidence set of switch telesignaling and the real-time data evidence set of voltage and current at the current tracking moment, as well as the voltage and current time series distribution model of the target distribution network in each operating topology in the target period, the conditional probability of each voltage random variable and each injected current random variable in the topology tracking dynamic Bayesian network at the current tracking moment is updated, as shown in Equations (17) and (18).

[0144] (17)

[0145] (18)

[0146] To track the time Topology Tracking Dynamic Bayesian Network The random variables in To track the time Topology Tracking Dynamic Bayesian Network A random variable, For all switches in the entire network at all times To time The open and closed state; Represented in the topology transformation diagram Zhongcong It can be reached within two steps from the start and the switch status meets the requirements The set of topologies of known states in ; For collection The number of topologies included; Indicates that the target distribution network is in the operating topology During the target period Voltage and current timing distribution model.

[0147] Reasoning and updating time To time The specific process of the conditional probability of each voltage random variable and each injection current random variable in the topological tracking dynamic Bayesian network is:

[0148] Real-time evidence collection Substitute into the topology to track the dynamic Bayesian network , as shown in formula (19).

[0149] (19)

[0150]

[0151]

[0152] In the formula, Indicated in Middle time To time All voltage and injected current measurement values ​​are collected; Indicates that The voltage and injected current measurement random variables are set to the obtained measurement values.

[0153] If the current tracking moment is the first tracking moment, the topological tracking dynamic Bayesian network at the current tracking moment after updating the conditional probability is used to obtain the probability that the target distribution network is in each operating topology at the current tracking moment; according to the probability that the target distribution network is in each operating topology at the current tracking moment, the maximum probability is determined, and the operating topology corresponding to the maximum probability is determined as the operating topology corresponding to the current tracking moment.

[0154] If the current tracing moment is not the first tracing moment, the topological tracing dynamic Bayesian network of the current tracing moment after updating the conditional probability is used to obtain the probability that the target distribution network is in each operating topology from the first tracing moment to the current tracing moment; any tracing moment from the first tracing moment to the current tracing moment is taken as the target tracing moment; according to the probability that the target distribution network is in each operating topology at the target tracing moment, the operating topology corresponding to the target tracing moment is determined; according to the operating topology corresponding to each tracing moment from the first tracing moment to the current tracing moment, the operating topology change sequence at the current tracing moment is obtained.

[0155] Specifically, the time is calculated based on the evidence propagation method To time The probability that the target distribution network is in each operating topology is shown in formula (20).

[0156] (20)

[0157] In the formula, For the moment To time The probability that the target distribution network is in each operating topology.

[0158] According to the probability that the target distribution network is in each operating topology at the target tracking moment, the target maximum probability is determined, and the operating topology corresponding to the target maximum probability is determined as the operating topology corresponding to the target tracking moment. According to the operating topology corresponding to each tracking moment from the first tracking moment to the current tracking moment, the operating topology change sequence at the current tracking moment is obtained, and then the topology change path is obtained.

[0159] In this embodiment, based on the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, as well as the voltage and current time series distribution model of the target distribution network in each operating topology in the target time period, the conditional probability of each voltage random variable and each injected current random variable in the topology tracking dynamic Bayesian network at the current tracking moment is updated to obtain a more accurate operating topology change sequence at the current tracking moment.

[0160] In order to verify the effectiveness of the method for tracking the real-time operation topology of the distribution network proposed in this application, in this embodiment, the selected distribution network structure and measurement configuration are as follows: Figure 4 9 operating topologies to be tracked are selected to form a switch state matrix, and the node historical operating data under each operating topology are obtained according to the tracking method of the real-time operating topology of the distribution network proposed in this application. Figure 6 As shown in Figure 7 As shown in the figure, the topological tracking dynamic Bayesian network updated during the tracking process is as follows Figure 8 shown.

[0161] Set up the first tracking moment , tracking time limit The time interval between two tracking is During this period, the topology changes 16 times, and the tracking accuracy of the tracking method of the real-time operation topology of the distribution network under different measurement conditions is tested. The computer hardware environment for real-time tracking is Intel(R) Xeon(R) W-2102 CPU, with a main frequency of 2.9GHz and a memory of 64GB; the software environment is Windows 10 operating system.

[0162] (1) Impact of measurement error on tracking accuracy

[0163] The standard deviations of voltage and current measurements are set to 1%, 5%, and 10% respectively, and the missing rates of switch telesignaling data and measurement data are 2%. The tracking accuracy is shown in Table 1. In the table, "real-time accuracy" indicates the accuracy of the first tracking after the operation topology changes; "30-minute accuracy" indicates the accuracy of tracking the change within 30 minutes of the operation topology change, which is equivalent to the accuracy of finding the change within two trackings; "60-minute accuracy" indicates the accuracy of tracking the change within 60 minutes of the operation topology change, which is equivalent to the accuracy of finding the change within four trackings.

[0164] Table 1 The impact of measurement error on tracking accuracy

[0165]

[0166] By comparing the changes in real-time accuracy, 30-minute accuracy, and 60-minute accuracy in Table 1, as well as the tracking accuracy under different measurement standard deviations, it can be seen that the accuracy of the measurement itself has a great influence on the accuracy of real-time tracking. The tracking results can only be corrected based on the data over a long period of time before and after the running topology changes.

[0167] (2) Impact of missing data on tracking accuracy

[0168] The missing rates of switch telesignal data and measurement data are set to 2%, 5%, and 10% respectively, and the standard deviation of voltage and current measurement is 5%. The tracking accuracy is shown in Table 2. In the table, "real-time accuracy" means the accuracy of the first tracking after the operation topology changes; "30-minute accuracy" means the accuracy of tracking the change within 30 minutes of the operation topology change, which is equivalent to the accuracy of finding the change within two trackings; "60-minute accuracy" means the accuracy of tracking the change within 60 minutes of the operation topology change, which is equivalent to the accuracy of finding the change within four trackings.

[0169] Table 2 The impact of missing data on tracking accuracy

[0170]

[0171] By comparing the changes in real-time accuracy, 30-minute accuracy, and 60-minute accuracy in Table 2, as well as the tracking accuracy under different switch telesignaling data and measurement data missing rates, it can be seen that data missing has little effect on the tracking accuracy, indicating that the tracking method for the real-time operation topology of the distribution network proposed in this application has good adaptability to data missing scenarios.

[0172] Tests (1) and (2) show that after the operating topology changes, as the tracking time and the number of tracking times increase, the tracking accuracy of the distribution network real-time operating topology tracking method proposed in this application based on the measurement data continues to increase, and the original operating topology change tracking results can also be corrected.

[0173] Fig. 9 The figure shows the first four topology changes found by the method for tracking the real-time operation topology of the distribution network proposed in this application. It can be seen that this method can track the operation topology from Departure , changes to The process reflects the path of running topology changes and completes more refined tracking of topology changes.

[0174] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0175] Based on the same inventive concept, the embodiment of the present application also provides a distribution network real-time operation topology tracking device for implementing the distribution network real-time operation topology tracking method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more distribution network real-time operation topology tracking device embodiments provided below can refer to the limitations of the distribution network real-time operation topology tracking method above, and will not be repeated here.

[0176] In an exemplary embodiment, Fig.10 As shown, a device for tracking the real-time operation topology of a distribution network is provided, wherein:

[0177] A topology association graph library acquisition module 1001 is used to obtain a topology association graph library according to a distribution network grid structure and a switch state matrix of a target distribution network; the target distribution network includes a plurality of nodes; the switch state matrix includes a plurality of node switch states of an operating topology to be tracked;

[0178] The voltage and current Bayesian network acquisition module 1002 is used to obtain the voltage and current time series evaluation Bayesian network of the target distribution network in multiple time periods when the target distribution network is in each operation topology according to the topology association library and the historical operation data of the nodes of the target distribution network;

[0179] A time series distribution model acquisition module 1003 is used to acquire a voltage and current time series distribution model in multiple time periods when the target distribution network is in each operation topology;

[0180] The topological Bayesian network acquisition module 1004 is used to determine the target time period corresponding to the current tracking moment; based on the topological association graph library and the voltage and current timing evaluation Bayesian network of each running topology in the target time period, an initialized topological tracking dynamic Bayesian network is obtained; if the current tracking moment is the first tracking moment, the initialized topological tracking dynamic Bayesian network is used as the topological tracking dynamic Bayesian network of the current tracking moment; if the current tracking moment is not the first tracking moment, the topological tracking dynamic Bayesian network of the previous tracking moment is expanded to obtain the topological tracking dynamic Bayesian network of the current tracking moment;

[0181] The operating topology change sequence acquisition module 1005 is used to obtain the switch telesignal real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, as well as the voltage and current time series distribution model of the target distribution network in the target time period when it is in each operating topology, and update the topology tracking dynamic Bayesian network at the current tracking moment to obtain the operating topology change sequence at the current tracking moment.

[0182] In one of the embodiments, the topology association library acquisition module 1001 is also used to: substitute the switch state matrix into the grid structure of the distribution network to obtain an operating topology set; if the difference between any two operating topologies in the operating topology set is the closed state of a single switch, then determine that any two operating topologies have an association relationship to construct a topology transformation relationship diagram; and obtain a topology association library based on the operating topology set and the topology transformation relationship diagram.

[0183] In one of the embodiments, the voltage and current Bayesian network acquisition module 1002 is also used to: divide the node historical operation data of the target distribution network into time periods to obtain the node historical operation data of multiple time periods; sequentially use multiple time periods as target time periods, and sequentially use each operation topology as the target operation topology; obtain the node voltage matrix and node injection current matrix of the target time period based on the node historical operation data of the target time period; obtain the dependency relationship between the voltage random variables and the injection current random variables corresponding to the target operation topology based on the target operation topology; obtain the voltage and current timing evaluation Bayesian network of the target distribution network in the target time period when it is in the target operation topology based on the node voltage matrix and node injection current matrix of the target time period, and the dependency relationship between the voltage random variables and the injection current random variables corresponding to the target operation topology.

[0184] In one embodiment, the topological Bayesian network acquisition module 1004 is also used to: sequentially take multiple time periods as target time periods, and sequentially take each operating topology as a target operating topology; take the voltage and current timing evaluation Bayesian network in the target time period when the target distribution network is in the target operating topology as the target voltage and current timing evaluation Bayesian network; perform inference calculations on the probability that each voltage random variable in the target voltage and current timing evaluation Bayesian network takes the actual value of each voltage, and the probability that each injected current random variable takes the actual value of each injected current, to obtain a voltage and current timing distribution model in the target time period when the target distribution network is in the target operating topology; the voltage random variables and the injected current random variables are data measured by a measuring device.

[0185] In one embodiment, the topological Bayesian network acquisition module 1004 is also used to: obtain an initial sub-Bayesian network and an extended sub-Bayesian network of each operating topology in the target time period based on the topological association library and the voltage and current timing evaluation Bayesian network of each operating topology in the target time period; construct a dual Bayesian network of each operating topology in the target time period based on the dependency relationship between the voltage random variable and the injected current random variable between the initial sub-Bayesian network and the extended sub-Bayesian network of each operating topology in the target time period; obtain an initialized topology tracking dynamic Bayesian network based on the dual Bayesian network of each operating topology in the target time period.

[0186] In one embodiment, the operating topology change sequence acquisition module 1005 is also used to: update the conditional probability of each voltage random variable and each injected current random variable in the topology tracking dynamic Bayesian network at the current tracking moment according to the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, and the voltage and current time series distribution model when the target distribution network is in each operating topology in the target time period; if the current tracking moment is the first tracking moment, obtain the probability of the target distribution network being in each operating topology at the current tracking moment according to the topology tracking dynamic Bayesian network at the current tracking moment after the updated conditional probability; and obtain the probability of the target distribution network being in each operating topology at the current tracking moment according to the target distribution network in the current tracking moment. The probability of the target distribution network being in each operating topology at the target tracking moment is determined to determine the operating topology corresponding to the current tracking moment; if the current tracking moment is not the first tracking moment, the topological tracking dynamic Bayesian network at the current tracking moment after updating the conditional probability is used to obtain the probability that the target distribution network is in each operating topology from the first tracking moment to the current tracking moment; any tracking moment from the first tracking moment to the current tracking moment is used as the target tracking moment; according to the probability that the target distribution network is in each operating topology at the target tracking moment, the operating topology corresponding to the target tracking moment is determined; according to the operating topology corresponding to each tracking moment from the first tracking moment to the current tracking moment, the operating topology change sequence at the current tracking moment is obtained.

[0187] Each module in the above-mentioned tracking device for real-time operation topology of distribution network can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0188] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.11As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data of an embodiment of a method for tracking the real-time operation topology of a distribution network. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for tracking the real-time operation topology of a distribution network is implemented.

[0189] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0190] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0191] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0192] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0193] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0194] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0195] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0196] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for tracking the real-time operation topology of a distribution network, characterized in that: The method comprises: A topology association library is obtained according to the distribution network grid structure and switch state matrix of the target distribution network; the target distribution network includes a plurality of nodes; the switch state matrix includes the switch states of the nodes of the operating topology to be tracked; According to the topology association library and the historical operation data of the nodes of the target distribution network, a voltage and current time series evaluation Bayesian network is obtained for the target distribution network in multiple time periods when the target distribution network is in each operation topology; Obtaining a voltage and current time series distribution model in multiple time periods when the target distribution network is in each operating topology; Determine the target period corresponding to the current tracking moment; According to the topology association library and the voltage and current time series of each operating topology in the target period, the Bayesian network is evaluated to obtain an initialized topology tracking dynamic Bayesian network; If the current tracking moment is the first tracking moment, the initialized topology tracking dynamic Bayesian network is used as the topology tracking dynamic Bayesian network of the current tracking moment; If the current tracking moment is not the first tracking moment, the topological tracking dynamic Bayesian network of the previous tracking moment is expanded to obtain the topological tracking dynamic Bayesian network of the current tracking moment; The real-time evidence set of switch telesignaling and the real-time data evidence set of voltage and current at the current tracking moment are obtained, as well as the voltage and current time series distribution model of the target distribution network in the target time period when it is in each operating topology, and the topology tracking dynamic Bayesian network at the current tracking moment is updated to obtain the operating topology change sequence at the current tracking moment.

2. The method according to claim 1, characterized in that The method of obtaining a topology association library according to the distribution network grid structure and switch state matrix of the target distribution network includes: Substitute the switch state matrix into the grid structure of the distribution network to obtain the operating topology set; If the difference between any two operating topologies in the operating topology set is the closed state of a single switch, it is determined that the any two operating topologies have an associated relationship, so as to construct a topology conversion relationship diagram; A topology association graph library is obtained according to the running topology set and the topology conversion relationship graph.

3. The method according to claim 1, characterized in that The method of obtaining a voltage and current time series evaluation Bayesian network for multiple time periods when the target distribution network is in each operation topology according to the topology association graph library and the historical operation data of the nodes of the target distribution network comprises: Dividing the historical operation data of the nodes of the target distribution network into time periods to obtain the historical operation data of the nodes in multiple time periods; Taking multiple time periods as target time periods in turn, and taking each operation topology as a target operation topology in turn; According to the historical operation data of the nodes in the target period, a node voltage matrix and a node injection current matrix in the target period are obtained; According to the target operating topology, a dependency relationship between a voltage random variable and an injected current random variable corresponding to the target operating topology is obtained; According to the node voltage matrix and the node injection current matrix of the target time period, and the dependency relationship between the voltage random variable and the injection current random variable corresponding to the target operating topology, a voltage and current timing evaluation Bayesian network for the target time period when the target distribution network is in the target operating topology is obtained.

4. The method according to claim 1, characterized in that: The step of obtaining a voltage and current time series distribution model in multiple time periods when the target distribution network is in each operating topology includes: Taking multiple time periods as target time periods in turn, and taking each operation topology as a target operation topology in turn; The voltage and current timing evaluation Bayesian network in the target time period when the target distribution network is in the target operating topology is used as the target voltage and current timing evaluation Bayesian network; The probability that each voltage random variable in the target voltage and current timing evaluation Bayesian network takes the actual value of each voltage, and the probability that each injected current random variable takes the actual value of each injected current are inferred and calculated to obtain a voltage and current timing distribution model in a target time period when the target distribution network is in a target operating topology; the voltage random variable and the injected current random variable are data measured by a measuring device.

5. The method according to claim 1, characterized in that The method of evaluating the Bayesian network based on the topology association graph library and the voltage and current timing of each operating topology in the target period to obtain an initialized topology tracking dynamic Bayesian network includes: According to the topology association graph library and the voltage and current time series of each operating topology in the target period, the Bayesian network is evaluated to obtain an initial sub-Bayesian network and an extended sub-Bayesian network of each operating topology in the target period; Constructing a dual Bayesian network for each operating topology in the target period according to the dependency relationship between the voltage random variable and the injection current random variable between the initial sub-Bayesian network and the extended sub-Bayesian network for each operating topology in the target period; According to the double Bayesian network of each running topology in the target period, an initialized topology tracking dynamic Bayesian network is obtained.

6. The method according to claim 1, characterized in that The real-time evidence set of switch telesignaling and the real-time data evidence set of voltage and current at the current tracking moment are obtained, as well as the voltage and current time series distribution model of the target distribution network in each operating topology in the target time period, and the topology tracking dynamic Bayesian network at the current tracking moment is updated to obtain the operating topology change sequence at the current tracking moment, including: According to the switch telesignaling real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, and the voltage and current time series distribution model of the target distribution network in the target time period when it is in each operating topology, the conditional probability of each voltage random variable and each injected current random variable in the topology tracking dynamic Bayesian network at the current tracking moment is updated; If the current tracking moment is the first tracking moment, the probability of the target distribution network being in each operating topology at the current tracking moment is obtained by tracking the dynamic Bayesian network according to the topology of the current tracking moment after updating the conditional probability; Determine the operating topology corresponding to the current tracking moment according to the probability that the target distribution network is in each operating topology at the current tracking moment; If the current tracking moment is not the first tracking moment, the probability of the target distribution network being in each operating topology from the first tracking moment to the current tracking moment is obtained by tracking the dynamic Bayesian network according to the topology of the current tracking moment after updating the conditional probability; Any tracking moment from the first tracking moment to the current tracking moment is taken as the target tracking moment; Determine the operating topology corresponding to the target tracking time according to the probability that the target distribution network is in each operating topology at the target tracking time; According to the operation topology corresponding to each tracking moment from the first tracking moment to the current tracking moment, the operation topology change sequence of the current tracking moment is obtained.

7. A device for tracking the real-time operation topology of a distribution network, characterized in that: The device comprises: A topology association graph library acquisition module is used to obtain a topology association graph library according to a distribution network grid structure and a switch state matrix of a target distribution network; the target distribution network includes a plurality of nodes; the switch state matrix includes a plurality of node switch states of an operating topology to be tracked; A voltage and current Bayesian network acquisition module is used to obtain a voltage and current time series evaluation Bayesian network for multiple time periods when the target distribution network is in each operating topology according to the topology association library and the historical operation data of the nodes of the target distribution network; A time series distribution model acquisition module is used to obtain the voltage and current time series distribution models of the target distribution network in multiple time periods when the target distribution network is in each operating topology; A topological Bayesian network acquisition module is used to determine the target time period corresponding to the current tracking moment; based on the topological association library and the voltage and current timing evaluation Bayesian network of each running topology in the target time period, an initialized topological tracking dynamic Bayesian network is obtained; if the current tracking moment is the first tracking moment, the initialized topological tracking dynamic Bayesian network is used as the topological tracking dynamic Bayesian network of the current tracking moment; if the current tracking moment is not the first tracking moment, the topological tracking dynamic Bayesian network of the previous tracking moment is expanded to obtain the topological tracking dynamic Bayesian network of the current tracking moment; The operating topology change sequence acquisition module is used to obtain the switch telesignal real-time evidence set and the voltage and current real-time data evidence set at the current tracking moment, as well as the voltage and current time series distribution model of the target distribution network in the target time period when it is in each operating topology, and update the topology tracking dynamic Bayesian network at the current tracking moment to obtain the operating topology change sequence at the current tracking moment.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: 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.

10. A computer program product, comprising a computer program, characterized in that 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