Intelligent power grid optimization scheduling method based on digital twinning

Abstract

The invention discloses an intelligent power grid optimization scheduling method based on digital twinning, and relates to the technical field of power grid optimization scheduling, and the method comprises the steps: building a dynamic power grid mirror image model according to a standardized power grid data matrix, and generating an evolution trajectory prediction report through a quantum magnetic coupling mechanism; establishing a variable association network based on the evolution trajectory prediction report, and generating an optimization scheduling instruction set in combination with the standardized data matrix; executing an optimization scheduling instruction set to obtain magnetic potential gradient distribution, and generating a topology reconstruction scheme by identifying a magnetic potential change trend; and inputting the topology reconstruction scheme into the dynamic power grid mirror image model to generate an electromagnetic field evolution trajectory, and generating a safety scheduling report in combination with magnetic potential energy gradient distribution. According to the method, the power grid magnetic field data is coded into an evolution trajectory prediction report through a quantum-magnetic coupling mechanism, and high-precision risk pre-judgment is realized; a topology reconstruction scheme is dynamically generated according to the electromagnetic energy gathering trend, and the power grid optimization scheduling efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid optimal scheduling, and in particular to an intelligent power grid optimal scheduling method based on digital twinning. BACKGROUND

[0002] The deepening development of smart grid construction promotes digital twinning technology to become the core support of power system scheduling, and the technical evolution focuses on multi-dimensional technology fusion: in the data perception layer, the wide-area monitoring network constructed relying on the standardized system realizes the holographic collection and efficient processing of the power grid operation state; in the modeling and simulation layer, the dynamic mirroring modeling technology gradually replaces the static topology analysis, realizing the accurate mapping of the real-time operation situation of the power grid; in the decision optimization layer, the collaborative application of intelligent algorithms and physical models continuously improves the adaptive ability of the scheduling strategy. The current technology development presents a transformation trend from single data driving to multi-physical field coupling paradigm, especially the collaborative computing architecture of electromagnetic field, quantum field and magnetic potential field is becoming the technical frontier of the new generation of digital twinning system, providing theoretical basis and method support for the stable operation of the power grid under high proportion of renewable energy access.

[0003] However, the existing technology still has two major bottlenecks: on the one hand, the physical field information field is fragmented, traditional digital twins are mostly limited to data visualization and state monitoring, and cannot deeply integrate physical evolution mechanisms such as electromagnetic field and magnetic potential field, resulting in prediction models ignoring quantum scale correlation and insufficient ability to capture transient risks such as subsynchronous oscillation; on the other hand, the reconstruction decision has lag and subjectivity, the existing topology optimization relies on artificial experience rules and offline verification mechanism, and the response efficiency is difficult to meet the real-time scheduling demand, even if intelligent algorithms are introduced, they are still limited by weight parameters, and are easy to cause chain failures due to improper parameters. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides an intelligent power grid optimal scheduling method based on digital twinning to solve the problems of new energy fluctuation prediction inaccuracy and topology reconstruction lag.

[0006] To solve the above technical problems, the present application provides the following technical solutions: The present application provides an intelligent power grid optimal scheduling method based on digital twinning, which comprises, The real-time operation state data of the power grid is collected and preprocessed to obtain a standardized power grid data matrix; a dynamic power grid mirror model is constructed according to the standardized power grid data matrix, and an evolution trajectory prediction report is generated through a quantum magnetic coupling mechanism; a variable correlation network is established based on the evolution trajectory prediction report, and an optimized scheduling instruction set is generated in combination with the standardized data matrix; the optimized scheduling instruction set is executed to obtain a magnetic potential energy gradient distribution, a topology reconstruction scheme is generated by identifying the change trend of the magnetic potential energy; and the topology reconstruction scheme is input into the dynamic power grid mirror model to generate an electromagnetic field evolution trajectory, and a safe scheduling report is generated in combination with the magnetic potential energy gradient distribution.

[0007] As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, the real-time operation state data of the power grid includes active and reactive power of the generator, line flow parameters, magnetic field strength data, node voltage amplitude and topology switch opening and closing state. The preprocessing includes time alignment, dimensionless normalization, topology state coding and outlier cleaning. As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, the standardized power grid data matrix includes a generator output vector, a node electrical quantity matrix, a line flow tensor and a topology adjacency table.

[0008] As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, the dynamic power grid mirror model is constructed according to the standardized power grid data matrix, and the specific steps are as follows, Based on the topology adjacency table in the standardized power grid data matrix, a node connection relationship network is constructed; The node electrical quantity matrix is loaded into the node connection relationship network to obtain an electrical node network, and the line flow tensor is bound to generate a power flow transmission network; Based on the power flow transmission network, the generator output vector is dynamically mapped through power balance constraints to construct a dynamic power grid mirror model.

[0009] As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, the evolution trajectory prediction report is generated through a quantum magnetic coupling mechanism, and the specific steps are as follows, The magnetic field strength data in the real-time operation state data of the power grid is extracted, and a magnetic field distribution thermodynamic map data is generated through a magneto-electric coupling equation; The magnetic field distribution thermodynamic map data is quantum amplitude encoded based on the dynamic power grid mirror model to generate an evolution trajectory prediction report.

[0010] As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, the evolution trajectory prediction report includes a new energy fluctuation interval, a load curve and a risk thermodynamic map.

[0011] As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, wherein: the variable correlation network is established based on the evolution trajectory prediction report, and the optimization scheduling instruction set is generated in combination with the standardized data matrix, and the specific steps are as follows, Based on the evolution trajectory prediction report, the variable correlation network is obtained through time-varying mutual information entropy; The topology adjacency table in the standardized data matrix is extracted, and the topology constraint variable cluster set is generated by superimposing the variable correlation network; The topology constraint variable cluster set is optimized for power balance, and the optimization scheduling instruction set is generated.

[0012] As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, wherein: the optimization scheduling instruction set is executed to obtain the magnetic potential energy gradient distribution, and the topology reconstruction scheme is generated by identifying the magnetic potential energy change trend, and the specific steps are as follows, The optimization scheduling instruction set is executed in the digital twinning environment to obtain the updated power grid operation state data set; Based on the updated real-time operation state data of the power grid, the magnetic potential energy gradient distribution thermal map is generated by calculating the global magnetic potential energy distribution; The magnetic potential energy change trend vector diagram is obtained by identifying the magnetic field line aggregation direction and intensity change trend in the magnetic potential energy gradient distribution thermal map; Based on the magnetic potential energy change trend vector diagram, the topology reconstruction scheme is generated by the magnetic field line navigation path algorithm.

[0013] As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, wherein: the topology reconstruction scheme is input into the dynamic power grid mirror model to generate the electromagnetic field evolution trajectory, which means that the topology reconstruction scheme is input into the dynamic power grid mirror model, the electromagnetic field space-time evolution data is obtained by the finite difference time domain method, and the electromagnetic field evolution trajectory is generated by extracting the electric field intensity evolution curve.

[0014] As a preferred scheme of the intelligent power grid optimization scheduling method based on digital twinning, wherein: the safety scheduling report is generated in combination with the magnetic potential energy gradient distribution, and the specific steps are as follows, In combination with the electromagnetic field evolution trajectory and the magnetic potential energy gradient distribution, the risk intensity distribution map is generated by field strength gradient dot product operation; Based on the risk intensity distribution map, the high-risk equipment and the safety operation boundary are marked by the edge detection algorithm to generate the safety scheduling report.

[0015] The application has the beneficial effects that: the power grid magnetic field data is encoded into evolution trajectory prediction reports through a quantum magnetic coupling mechanism, the prediction limitation of traditional models for strong randomness of new energy is broken through, and high-precision risk prediction is realized; combined with magnetic potential energy gradient navigation technology, a topology reconstruction scheme is dynamically generated according to the electromagnetic energy aggregation trend, and the optimization and dispatching efficiency of the power grid is improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Fig. 1 The flowchart of the intelligent power grid optimization and dispatching method based on digital twinning; Fig. 2 The flowchart of constructing a dynamic grid mirror model; Fig. 3 The flowchart of generating an evolution trajectory prediction report; Fig. 4 The flowchart of generating a topology reconstruction scheme. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0019] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0020] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0021] REFERENCE Figs. 1-4 For one embodiment of the present application, the embodiment provides an intelligent power grid optimization and dispatching method based on digital twinning, comprising the following steps: S1, collecting real-time operation state data of the power grid and preprocessing to obtain a standardized power grid data matrix; S1.1 Real-time operation state data of the power grid includes generator active and reactive power, line flow parameters, magnetic field intensity data, node voltage amplitude and topology switch opening and closing state; It should be noted that the generator active and reactive power refers to the effective power actually output by the power generation equipment and the reactive power for maintaining voltage stability, which is used to represent the power output characteristics of the power source; The line flow parameters include the active power transmission value, the reactive power transmission value and the current phase angle of the transmission line, reflecting the energy distribution state of the power grid; The magnetic field intensity data are obtained by a magnetic induction sensor to obtain the magnetic field intensity value around the equipment, which is used to monitor the energy aggregation degree of the electromagnetic field; The node voltage amplitude records the effective value of the alternating voltage of each connection point of the power grid, indicating the voltage stability of the system; The topology switch opening and closing state describes the on-off state of the circuit breaker and the disconnecting switch with a Boolean value, which determines the physical connection relationship of the power grid.

[0022] S1.2 Preprocessing includes time alignment, dimensionless normalization, topology state coding and outlier cleaning.

[0023] It should be noted that the time alignment unifies the collection time stamps of multiple source equipment through the clock synchronization protocol, eliminating the time difference caused by sensor response delay; The dimensionless normalization converts the voltage and current values into unit values and the power values into percentage values, solving the problem of incomparable data of different dimensions; The topology state coding converts the on-off state of the switch into a Boolean logic value, establishing a machine-recognizable topology relationship network; The outlier cleaning uses a sliding window detection and interpolation algorithm to correct outliers and noise data.

[0024] S2, according to the standardized power grid data matrix, a dynamic power grid mirror model is constructed, and an evolution trajectory prediction report is generated through a quantum magnetic coupling mechanism; S2.1 The standardized power grid data matrix includes the generator output vector, the node electrical quantity matrix, the line flow tensor and the topology adjacency list; It should be noted that the generator output vector records the real-time data of the active and reactive power output of all generators in the grid in the form of a column vector, which is used to represent the power output characteristics of the power source side.

[0025] The node electrical quantity matrix is a two-dimensional matrix, with rows corresponding to the node numbers of the power grid and columns storing the node voltage amplitude, phase angle and load power data, which are used to describe the electrical state of each connection point of the power grid.

[0026] The line flow tensor adopts a three-dimensional data structure, with the first dimension marking the transmission line number, the second dimension recording the time sequence, and the third dimension storing the active power value, the reactive power value and the current phase angle of the line, which is used to represent the space-time distribution characteristics of the energy transmission of the power grid.

[0027] The topological adjacency table defines the physical structure of the power grid in the form of a Boolean matrix, the rows and columns of the matrix correspond to node numbers respectively, and the element value "1" indicates that there is a direct line between nodes, and "0" indicates no connection.

[0028] S2.2 Based on the topological adjacency table in the standardized power grid data matrix, a node connection relationship network is constructed; It should be noted that the rows and columns in the topological adjacency table correspond to the network node numbers respectively, and the number of network nodes is equal to the dimension of the topological adjacency table matrix; each row and each column of the topological adjacency table is traversed; when the element value is a logical value "1", a directed edge connecting the node index nodes corresponding to the row index and the column index is established in the node connection relationship network. Each node in the node connection relationship network is assigned a power grid node number attribute; each edge is assigned a line physical connection state attribute, and the node connection relationship network is output.

[0029] S2.3 Load the node electrical quantity matrix to the node connection relationship network to obtain an electrical node network, and bind it with the line flow tensor to generate a flow transmission network; It should be noted that the node connection relationship network includes a power grid node set and a physical connection relationship between nodes. Load the node electrical quantity matrix to the node connection relationship network; the node electrical quantity matrix is a two-dimensional array, the row index corresponds to the power grid node number, and the column stores the node voltage amplitude, phase angle and load power data; each node in the node connection relationship network is assigned a corresponding electrical parameter to form an electrical node network.

[0030] The line flow tensor adopts a three-dimensional data structure, the first dimension marks the transmission line number, the second dimension records the time sequence, and the third dimension stores the line active power value, reactive power value and current phase angle. The line flow tensor is bound with the electrical node network; the binding operation takes the transmission line as the association unit, and the flow data in the line flow tensor is mapped to the corresponding connection edge of the electrical node network to generate a flow transmission network.

[0031] S2.4 Based on the flow transmission network, dynamically map the generator output vector through power balance constraints to construct a dynamic power grid mirror model; It should be noted that the flow transmission network includes a node set with electricity and a connection edge set with flow parameters. Read the load power value of the node with electricity in the flow transmission network and the active power loss value of the connection edge with flow parameters; the total active power demand is the sum of the load power value of the node with electricity and the active power loss value of the connection edge with flow parameters.

[0032] The generator output vector stores the total active power of the generator. The difference between the total active power of the generator and the total active power demand is obtained; according to the generator regulation capacity, the active power value of each generator in the generator output vector is dynamically adjusted; the total active power of the generator after adjustment needs to meet the condition that the total active power of the generator is equal to the total active power demand. The updated generator output vector is mapped to the power flow transmission network; the injection power value of the power supply node in the node with live electricity is updated. The state of the power flow transmission network is refreshed, and the dynamic power grid mirror model meeting the power balance constraint is output.

[0033] S2.5 Extract the magnetic field strength data in the real-time operation state data of the power grid, and generate the magnetic field distribution heat map data through the magneto-electric coupling equation; It should be noted that the magnetic field strength data includes the three-dimensional space coordinates of the measurement point, the magnetic field strength value and the magnetic field strength vector component. A rectangular coordinate system covering the entire domain of the power grid equipment is established based on the three-dimensional space coordinates of the measurement point, and the origin of the coordinate system is set at the center point of the main transformer. The number of spatial grids in the rectangular coordinate system is counted.

[0034] The magneto-electric coupling equation is applied to each grid point, and the product of the magnetic field strength vector component in the X / Y / Z direction and the vacuum permeability is taken as the magnetic induction intensity; the dimension of the magnetic field distribution heat map corresponds to the number of spatial grids; the element value of the magnetic field distribution heat map stores the magnetic induction intensity value; the index of the magnetic field distribution heat map is mapped with the three-dimensional space coordinates of the measurement point. Output the magnetic field distribution heat map data.

[0035] S2.6 Quantum amplitude encoding is performed on the magnetic field distribution heat map data based on the dynamic power grid mirror model to generate an evolution trajectory prediction report.

[0036] It should be pointed out that the dynamic power grid mirror model includes a set of charged nodes and a set of connection edges with power flow parameters. The magnetic field distribution heat map data includes spatial coordinate system parameters and a three-dimensional matrix of magnetic induction intensity. Match the spatial grid point coordinates of the magnetic field distribution heat map data with the physical position coordinates of the charged nodes in the dynamic power grid mirror model to establish a spatial coordinate mapping relationship. Perform quantum amplitude encoding operations on each matched charged node. First, define the power grid evolution Hamiltonian based on the magnetic induction intensity value. The Hamiltonian includes a node current amplitude operator term and a connection edge coupling operator term. The node current amplitude is taken from the charged node electrical parameters. The connection edge coupling coefficient is taken from the active power value of the connection edge with power flow parameters. Apply the Hamiltonian to the initial quantum state to perform unitary evolution. Perform projection measurement on the evolved quantum state to measure the probability distribution in the generator subspace. Extract the high confidence interval as the new energy fluctuation interval. Extract the expected value in the load node subspace to generate the load curve time series. Calculate the risk probability value in the device risk subspace. Render the risk probability value on the spatial coordinates of the dynamic power grid mirror model to form a risk heat map. Output the evolution trajectory prediction report. The expression for calculating the risk probability value is: ; wherein, is the risk probability value, is the base number of the exponential function, is the curvature coefficient, is the magnetic potential energy gradient vector, is the electric field intensity gradient vector, is the risk threshold value.

[0037] The risk threshold value is in the range of: According to the magnetic potential energy gradient peak value and the electric field gradient dispersion, the boundary conditions for risk triggering are defined. The curvature coefficient is determined according to the safety margin of high-voltage equipment, and the value range is: For example, when the safety margin of high-voltage equipment is 10, the curvature coefficient is 0.95.

[0038] S3, based on the evolution trajectory prediction report, establish a variable correlation network, and generate an optimized scheduling instruction set combined with a standardized data matrix; S3.1 The evolution trajectory prediction report includes new energy fluctuation interval, load curve and risk heat map; It should be pointed out that the new energy fluctuation interval in the evolution trajectory prediction report refers to the upper and lower limit values of the variation range of the output power of renewable energy power generation equipment, which is used to quantify the uncertainty interval of clean energy output such as wind power and photovoltaic power, and provides power side fluctuation boundary constraints for dispatching decisions.

[0039] The load curve refers to a continuous numerical sequence of the power consumption of each node in the power grid over time, reflecting the power demand distribution law at different time periods, and supporting load distribution and power flow control.

[0040] The risk thermodynamic diagram refers to a matrix distribution diagram of device operation risk probability values marked on the geographical spatial coordinates of the power grid, which intuitively displays the spatial distribution of hidden dangers such as electromagnetic overload and voltage instability, and identifies safety weak links.

[0041] S3.2 Based on the evolution trajectory prediction report, the variable correlation network is obtained by time-varying mutual information entropy; It should be noted that the new energy output value of each new energy station node in the new energy fluctuation interval is extracted; the load power value of each load node in the load curve is read; the risk intensity value of each grid in the risk thermodynamic diagram is read, the total risk intensity value is obtained by accumulating the risk intensity value of each grid, the ratio of the risk intensity value to the total risk intensity value is taken as the risk intensity average, and the devices in the grid whose risk intensity value is higher than the risk intensity average are marked as high-risk devices. The new energy output value, the load power value and the risk intensity value are superimposed to obtain the state interval.

[0042] The total number of data points in the time window and the frequency of the new energy output value falling into the state interval are counted; the ratio of the frequency to the total number of data points in the time window is taken as the new energy output state probability value, and the new energy output state probability distribution is obtained.

[0043] The total number of data points in the time window and the frequency of the load power value falling into the state interval are counted; the ratio of the frequency to the total number of data points in the time window is taken as the load power state probability value, and the load power state probability distribution is obtained.

[0044] The total number of data points in the time window is counted, and the frequency of the new energy output value and the load power value falling into the state interval at the same time is obtained; the ratio of the frequency to the total number of data points in the time window is taken as the joint probability value of the new energy output state and the load power state, and the joint probability distribution of the new energy output and the load power is obtained.

[0045] Based on the new energy output state probability value, the load power state probability value and the joint probability value of the new energy output state and the load power state, mutual information entropy calculation is performed to obtain the mutual information entropy value. The expression for calculating the mutual information entropy value is: ; wherein, is the mutual information entropy value, is a specific discrete state in the new energy output state space, is the new energy output state space, is a specific discrete state in the load power state space, is the load power state space, is the joint probability value of the new energy output state and the load power state, Promoting new energy The probability value of The load power is in the state The probability value of For The mutual information entropy value is quantified into binary bit units using a logarithmic function with base 2 to directly reflect the minimum amount of information contained in the correlation between the output status of renewable energy and the load power status.

[0046] The new energy station nodes, load nodes, and high-risk equipment nodes are considered as the network node set. The edge set includes the connecting edges between the new energy station nodes and the load nodes, the connecting edges between the new energy station nodes and the high-risk equipment nodes, and the connecting edges between the load nodes and the high-risk equipment nodes. The network node set and the edge set are superimposed to generate a variable association network.

[0047] S3.3 extracts the topological adjacency table from the standardized data matrix and generates a set of topologically constrained variable clusters by superimposing the variable association network; It should be noted that the node set union operation is first performed to union the power grid node set, new energy station node set, load node set and high-risk equipment node set to form an extended node set; the extended node set includes the power grid node number, new energy station entity, load node entity and high-risk equipment entity.

[0048] Then, an edge set merging operation is performed to form an extended edge set by combining the connection edges between the new energy station nodes and the load nodes, the connection edges between the new energy station nodes and the high-risk equipment nodes, and the connection edges between the load nodes and the high-risk equipment nodes. The elements of the extended edge set are a combination of node pair numbers. The extended edge set includes two types: physical connection edges and association edges.

[0049] On the expanded node set and expanded edge set, start from any unvisited node; traverse all reachable nodes along the expanded edge set; connect all reachable nodes and record them as a cluster. Next, perform entity type integrity check to check whether each cluster contains four types of elements: grid node number, new energy station entity, load node entity, and high-risk equipment entity. If any of these entity types are missing, merge the cluster with the adjacent cluster.

[0050] Implement physical connection constraint enforcement to detect whether there are physical connection edges defined by the topological adjacency table within the cluster; if there are no physical connection edges within the cluster, decompose the cluster into single-node clusters. Finally, generate a set of topological constraint variable clusters.

[0051] S3.4 performs power balance optimization on the topology constraint variable cluster set and generates an optimized scheduling instruction set.

[0052] It should be noted that the median of the new energy fluctuation interval is taken as the reference output; the square sum of the deviation of the new energy output state from the reference output is superimposed on the total risk intensity value of the high-risk equipment as a constraint condition.

[0053] The target function and the constraint condition are converted into a standard quadratic programming form; the target output value of the new energy station entity is output as the optimization result; and the risk control action intensity of the high-risk equipment entity.

[0054] An output instruction field is created for each new energy station entity, including the unique identifier of the new energy station and the target output value. A risk control instruction field is created for each high-risk equipment entity, including the unique identifier of the high-risk equipment and the risk control action intensity. Encapsulate the cluster instruction: each cluster outputs an independent instruction unit; the instruction unit includes the cluster identifier, the new energy output instruction list, and the risk control instruction list. The cluster instruction units are aggregated to form an optimized scheduling instruction set.

[0055] S4, execute the optimized scheduling instruction set to obtain the magnetic potential energy gradient distribution, and generate a topology reconstruction scheme by identifying the magnetic potential energy change trend; S4.1 Execute the optimized scheduling instruction set in the digital twin environment to obtain an updated power grid operating state data set; It should be noted that the unique identifier of the new energy station and the target output value in the instruction field are extracted by traversing the new energy output instruction list; the corresponding new energy station entity is located in the dynamic power grid mirror model; and the output value of the new energy station entity is adjusted to the target output value.

[0056] Traverse the high-risk equipment risk control instruction list; extract the unique identifier of the high-risk equipment and the control action description in the instruction field; locate the corresponding high-risk equipment entity in the dynamic power grid mirror model; and perform load reduction according to the control action description field.

[0057] Refresh the state parameters of the dynamic power grid mirror model; deploy sensors to collect generator active and reactive power values, line flow parameter values, node voltage amplitude values, and magnetic field strength data. Encapsulate the updated data; generate an updated power grid operating state data set; the updated power grid operating state data set includes the generator active and reactive power field, the line flow parameter field, the magnetic field strength data field, and the node voltage amplitude field.

[0058] S4.2 Based on the updated real-time operating state data of the power grid, generate a magnetic potential energy gradient distribution thermal map by calculating the global magnetic potential energy distribution; It should be noted that a spatial grid coordinate system is established; the spatial grid coordinate system covers the entire domain of the power grid equipment, and the number of spatial grids is counted; the spatial grid coordinates are obtained by aligning the origin of the spatial grid coordinate system with the origin of the dynamic power grid mirror model spatial coordinate system.

[0059] reading the magnetic field strength vector components of the spatial grid; applying the magnetoelectric coupling equation, taking the product of the vacuum permeability and the magnetic field strength vector components as the magnetic induction strength components.

[0060] taking the ratio of the square sum of the magnetic induction strength components and twice the vacuum permeability as the magnetic potential energy density value. Filling the magnetic potential energy density distribution matrix, the dimension of the matrix corresponds to the number of spatial grids; the matrix element value stores the magnetic potential energy density value; the matrix row and column index maps the spatial grid coordinates.

[0061] Performing spatial gradient operation on the magnetic potential energy density distribution matrix; taking the physical position spacing of the magnetic field sensor as the grid spacing, using the central difference method to take the ratio of the difference of the magnetic potential energy density values of the adjacent grid points and twice the grid spacing as the X-axis directional derivative component along the X-axis direction of the spatial grid coordinate system. Using the central difference method to take the ratio of the difference of the magnetic potential energy density values of the adjacent grid points and twice the grid spacing as the Y-axis directional derivative component along the Y-axis direction of the spatial grid coordinate system. Using the central difference method to take the ratio of the difference of the magnetic potential energy density values of the adjacent grid points and twice the grid spacing as the Z-axis directional derivative component along the Z-axis direction of the spatial grid coordinate system. Synthesizing the gradient vector, which contains the X-axis directional derivative component, the Y-axis directional derivative component and the Z-axis directional derivative component.

[0062] S4.3 Obtain the magnetic potential energy change trend vector diagram by identifying the magnetic force line gathering direction and intensity change trend in the magnetic potential energy gradient distribution heat map; It should be noted that the magnetic potential energy gradient distribution heat map includes a gradient intensity matrix and a gradient direction matrix. Select the local maximum value point in the gradient intensity matrix as the seed point; based on the gradient direction angle component recorded in the gradient direction matrix; starting from the local maximum value point of the gradient intensity matrix, iteratively advancing along the vector direction recorded in the gradient direction matrix, recording the path point coordinate sequence and connecting it into a continuous magnetic force line to generate a magnetic force line path set.

[0063] Divide the spatial grid coordinate system into density calculation grids; count the number of magnetic force line paths passing through each density calculation grid; the ratio of the number of magnetic force line paths to the number of density calculation grids is the average magnetic force line density.

[0064] Scan the magnetic force line density distribution; mark the area where the magnetic force line density value is greater than the average magnetic force line density as the gathering area; extract the direction of the magnetic force line path in the gathering area; the vector total value of all magnetic force line path directions in the gathering area is obtained by accumulation, and the ratio of the vector total value to the vector total number is taken as the vector average value; the direction of the magnetic force line path whose vector is greater than the vector average value is taken as the magnetic force line gathering direction.

[0065] Tracing gradient intensity value along magnetic field line path; obtaining intensity change rate according to ratio of difference of gradient intensity value of adjacent grid points and grid spacing; obtaining cumulative change amount along magnetic field line path intensity change rate.

[0066] Creating vector graph matrix, dimension of vector graph matrix corresponds to number of space grid; matrix element stores vector structure; vector structure contains direction component and intensity component; intensity component records cumulative change amount value, finally generating magnetic potential energy change trend vector graph.

[0067] S4.4 Generating topology reconstruction scheme based on magnetic potential energy change trend vector graph through magnetic field line navigation path algorithm.

[0068] It should be noted that the power grid topology graph node set is created; the node set element is the power grid node number; the power grid node number comes from the topology adjacency table row and column index. The power grid topology graph edge set is created; each element of the topology adjacency table is traversed; when the element value is a logical value "1"; the node pair corresponding to the row and column index is added to the edge set; each edge is assigned an initial connection state attribute "connected".

[0069] Traversing each edge of the power grid topology graph edge set; obtaining the spatial coordinates of the nodes at both ends of the edge; the spatial coordinates are automatically mapped to the dynamic power grid mirror model space mapping relationship. Positioning the corresponding position of the spatial coordinates in the magnetic potential energy change trend vector graph; reading the intensity component value of the vector structure at the position; the arithmetic mean of the intensity component values of the two end nodes is taken as the basic generation value of the edge.

[0070] Selecting a new energy rich area node as a path source point in the power grid topology graph; the new energy rich area node is determined through the peak value of the new energy fluctuation interval in the evolution trajectory prediction report. Selecting a load center area node as a path sink point; the load center area node is determined through the peak node of the load curve in the evolution trajectory prediction report. Traversing all nodes of the power grid topology graph, identifying all path sink points of the path source point to obtain the total generation value of the adjacent edges; the sum of the generation value of the path source point and the total generation value of the adjacent edges is the path generation value of the path sink point; if the path generation value of the path sink point is less than the existing path generation value of the path sink point; recording the path source point as the predecessor node of the path sink point to generate an optimal path node sequence.

[0071] Detecting adjacent node pairs in the optimal path node sequence; querying the connection state of the node pair in the topology adjacency table; if the connection state is a logical value "0"; generating a closed switch instruction; the instruction includes a switch unique identifier and an action type "closed". Traversing all connected edges of the power grid topology graph; if the total generation value of the edge is greater than the average risk intensity; generating an open switch instruction; the instruction includes a switch unique identifier and an action type "open".

[0072] Packaging switch operation instruction list; switch operation instruction list element contains switch identifier field and action type field; action type field takes value "close" or "open". Output topology reconfiguration scheme; topology reconfiguration scheme is stored as structured instruction set.

[0073] S5, input the topology reconfiguration scheme into the dynamic power grid mirror model to generate the electromagnetic field evolution trajectory, and combine the magnetic potential energy gradient distribution to generate the safety scheduling report.

[0074] S5.1 input the topology reconfiguration scheme into the dynamic power grid mirror model, obtain electromagnetic field space-time evolution data by finite difference time domain method, and generate electromagnetic field evolution trajectory by extracting electric field intensity evolution curve; It should be noted that the topology reconfiguration scheme is loaded into the dynamic power grid mirror model; the topology reconfiguration scheme contains a switch operation instruction list. Perform switch state update operation, traverse each instruction of switch operation instruction list; read switch unique identifier field; update switch state according to action type field: if action type is "close", set switch connection state to logical value "1"; if action type is "open", set switch connection state to logical value "0".

[0075] Divide the spatial domain of the dynamic power grid mirror model into cubic grid; the grid node coordinates are strictly aligned with the device positions of the dynamic power grid mirror model; When the electric field intensity component and the magnetic field intensity component are zero, update the magnetic field intensity component according to Faraday's law, and the change of the magnetic field intensity with time is excited by the spatial rotation of the electric field intensity; the central difference method is used to approximate the spatial derivative, and the symmetric difference value of the electric field intensity values of the adjacent grid points is taken to obtain the approximate value of the change rate of the electric field intensity component along the coordinate axis direction.

[0076] Update the electric field intensity component according to Ampere's law, and the change of the electric field intensity with time is excited by the spatial rotation of the magnetic field intensity; and the central difference method is used to approximate the spatial derivative, and the symmetric difference value of the magnetic field intensity values of the adjacent grid points is taken to obtain the approximate value of the change rate of the magnetic field intensity component along the coordinate axis direction. Apply exponential decay function to process the magnetic field intensity component and the electric field intensity component, and output the electromagnetic field space-time evolution data.

[0077] Set monitoring points in new energy station entities; set monitoring points at the positions of load node entity access points; set monitoring points at the positions of core components of high-risk equipment entities; record the electric field intensity components at the monitoring points in each time step; create a two-dimensional array of time-electric field intensity; the time sequence is the horizontal axis data, and the electric field intensity component is the vertical axis data, to generate the electric field intensity evolution curve of the monitoring point. Package the electric field intensity evolution curve of the monitoring point to generate the electromagnetic field evolution trajectory.

[0078] S5.2 combine the electromagnetic field evolution trajectory and the magnetic potential energy gradient distribution to generate the risk intensity distribution graph by field strength gradient dot product operation; It should be noted that each grid point in the spatial grid coordinate system is traversed; the electric field intensity component values ​​in the electromagnetic field spatiotemporal evolution data are read. The difference in the electric field intensity component values ​​of adjacent grid points is obtained along the three axes of the spatial grid coordinate system; the ratio of twice the grid spacing to the difference in the electric field intensity component values ​​of adjacent grid points is the spatial variation rate component. The resulting electric field spatial variation rate vector is obtained. Create a risk intensity distribution matrix; the dimensions of the risk intensity distribution matrix are consistent with the spatial grid coordinate system; the matrix elements store risk intensity values. The matrix row and column indices map to the spatial grid coordinates; write the risk intensity value of each grid point to generate a risk intensity distribution map.

[0079] S5.3 Based on the risk intensity distribution map, high-risk equipment and safe operation boundaries are marked using edge detection algorithms to generate a safety scheduling report.

[0080] It should be noted that the matrix elements of the risk intensity distribution map store risk intensity values; the matrix row and column indices map to spatial grid coordinates. An edge detection algorithm is performed on the risk intensity distribution matrix, using the Sobel operator to calculate the spatial gradient amplitude of the risk intensity. Local maximum points along the gradient direction are retained; gradient amplitude peaks are marked as strong edge points; gradient amplitude valleys are marked as weak edge points; and strong edge points are connected to adjacent weak edge points to form a continuous edge line. The expression for calculating the spatial gradient amplitude of risk intensity is: ; in, is the spatial gradient amplitude of risk intensity, is the risk intensity along the spatial direction The partial derivative of is the risk intensity distribution matrix, is the horizontal axis of the spatial rectangular coordinate system, Risk intensity along the spatial direction The partial derivative of is the vertical axis of the spatial rectangular coordinate system.

[0081] Locate the contour area within the continuous edge line; mark areas within the contour area with risk intensity values ​​higher than the mean risk intensity as high-risk areas. Match the spatial coordinates of the high-risk areas within the dynamic grid mirror model; obtain the equipment entities covered by the high-risk areas; equipment entities include new energy station entities, load node entities, and high-risk equipment entities. Label the equipment entities as high-risk equipment; and record the equipment's unique identifier and peak risk intensity.

[0082] Create a high-risk device list; the high-risk device list element includes a device type field, a device identifier field, and a risk intensity peak field. Encapsulate a security dispatch report; the security dispatch report includes a high-risk device list field and a risk intensity distribution map identifier field.

[0083] The embodiment also provides a computer device suitable for the case of the intelligent power grid optimal scheduling method based on digital twinning, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the intelligent power grid optimal scheduling method based on digital twinning proposed in the above embodiment.

[0084] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. 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 and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0085] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to realize the intelligent power grid optimal scheduling method based on digital twinning proposed in the above embodiment. The storage medium can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk.

[0086] To sum up, the application encodes power grid magnetic field data into evolution trajectory prediction report through quantum magnetic coupling mechanism, breaks through the prediction limitation of traditional model on strong randomness of new energy, and realizes high-precision risk prediction; in combination with magnetic potential energy gradient navigation technology, a topology reconstruction scheme is dynamically generated according to the electromagnetic energy aggregation trend, and the optimization and dispatching efficiency of the power grid is improved.

[0087] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and they should be covered in the scope of claims of the present application.

Claims

1. A smart power grid optimization and scheduling method based on digital twins, characterized by: include, Collect real-time grid operation status data and pre-process it to obtain a standardized grid data matrix; Construct a dynamic grid mirror model based on the standardized grid data matrix and generate an evolution trajectory prediction report through the quantum magnetic coupling mechanism; Establish a variable association network based on the evolution trajectory prediction report, and generate an optimized scheduling instruction set based on the standardized data matrix; Execute the optimized scheduling instruction set to obtain the magnetic potential energy gradient distribution, and generate a topology reconstruction plan by identifying the trend of magnetic potential energy changes; The topology reconstruction plan is input into the dynamic grid mirror model to generate the electromagnetic field evolution trajectory, and the safety scheduling report is generated in combination with the magnetic potential energy gradient distribution.

2. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 1, characterized in that: The real-time operation status data of the power grid includes the active and reactive power of the generator, the line flow parameters, the magnetic field strength data, the node voltage amplitude and the opening and closing status of the topological switch; The preprocessing includes time alignment, dimension normalization, topological state encoding and outlier cleaning.

3. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 2, characterized in that: The standardized power grid data matrix includes a generator output vector, a node electrical quantity matrix, a line flow tensor and a topological adjacency table.

4. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 3 is characterized in that: The specific steps of constructing a dynamic grid mirror model based on the standardized grid data matrix are as follows: Based on the topological adjacency table in the standardized power grid data matrix, a node connection relationship network is constructed; Load the node electrical quantity matrix into the node connection relationship network to obtain the electrical node network, and bind it with the line power flow tensor to generate the power flow transmission network; Based on the power flow transmission network, the generator output vector is dynamically mapped through power balance constraints to construct a dynamic grid mirror model.

5. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 4 is characterized in that: The specific steps of generating the evolution trajectory prediction report through the quantum magnetic coupling mechanism are as follows: Extract magnetic field strength data from real-time grid operation status data and generate magnetic field distribution thermal map data through magneto-electric coupling equation; Based on the dynamic power grid mirror model, the magnetic field distribution thermal map data is quantum-encoded to generate an evolution trajectory prediction report.

6. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 5, characterized in that: The evolution trajectory prediction report includes new energy fluctuation range, load curve and risk heat map.

7. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 6, characterized in that: The variable association network is established based on the evolution trajectory prediction report, and the optimized scheduling instruction set is generated by combining the standardized data matrix. The specific steps are as follows: Based on the evolution trajectory prediction report, the variable association network is obtained through time-varying mutual information entropy; Extract the topological adjacency table from the standardized data matrix and generate a set of topologically constrained variable clusters by superimposing the variable association network; Power balance optimization is performed on a set of topology constraint variable clusters to generate an optimized scheduling instruction set.

8. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 7, characterized in that: The execution of the optimized scheduling instruction set obtains the magnetic potential energy gradient distribution, and generates a topology reconstruction plan by identifying the trend of magnetic potential energy changes. The specific steps are as follows: Execute the optimized scheduling instruction set in the digital twin environment to obtain the updated power grid operation status data set; Based on the updated real-time grid operation status data set, the magnetic potential energy gradient distribution heat map is generated by calculating the global magnetic potential energy distribution; By identifying the concentration direction and intensity change trend of magnetic lines in the magnetic potential energy gradient distribution thermodynamic map, a vector diagram of the magnetic potential energy change trend is obtained; Based on the magnetic potential energy change trend vector diagram, a topology reconstruction plan is generated through the magnetic line navigation path algorithm.

9. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 8, characterized in that: The step of inputting the topology reconstruction scheme into the dynamic power grid mirror model to generate the electromagnetic field evolution trajectory refers to inputting the topology reconstruction scheme into the dynamic power grid mirror model, obtaining the electromagnetic field spatiotemporal evolution data through the time-domain finite difference method, and generating the electromagnetic field evolution trajectory by extracting the electric field intensity evolution curve.

10. The method for optimizing and dispatching a smart power grid based on digital twins according to claim 9, characterized in that: The specific steps of generating a safety dispatch report by combining the magnetic potential energy gradient distribution are as follows: Combining the electromagnetic field evolution trajectory with the magnetic potential energy gradient distribution, a risk intensity distribution map is generated through the field intensity gradient dot product operation; Based on the risk intensity distribution map, high-risk equipment and safe operation boundaries are marked through edge detection algorithms to generate a safety scheduling report.

Images