A method and system for generating a power grid topology simulation

Abstract

This invention discloses a method and system for generating simulated power grid topology, applied in the field of power system technology. The method includes: acquiring multi-source dispatch data of the target power grid; processing the multi-source dispatch data to obtain a fused dataset; processing the fused dataset to construct a scenario narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data; generating a three-dimensional mapping table; constructing a first topology space and a second topology space according to the fused dataset and the three-dimensional mapping table; processing the first topology space to obtain initial electrical connections; processing the second topology space to obtain a polymorphic topology structure; and processing the initial electrical connections and the polymorphic topology structure to generate a simulated power grid topology model. The method provided by this invention can solve the problem of single-form basic topology generated by topology generation technology, and achieve the effect of constructing a simulated power grid topology model that adapts to multiple scenario dimensions.

Description

Technical Field

[0001] This invention relates to the field of power system technology, and in particular to a method and system for generating simulated power grid topology. Background Technology

[0002] In the construction of new power systems and the digital transformation of the power industry, the analog power grid is the main carrier for dispatcher training, power grid security and stability analysis, power grid planning and extended verification. Its reasonable topology matching and scenario adaptability are important guarantees for the implementation of related work.

[0003] In existing technologies, topology generation uses fixed rules to generate a single-form basic topology, which only considers electrical and physical feasibility and does not take into account the dimensional relationships between various power grid scenarios. Therefore, existing topology generation technologies are difficult to adapt to multi-dimensional power grid operating conditions, and the single-form basic topology model does not conform to the actual power grid and is difficult to adapt to complex scenarios, which can no longer meet the application needs of new power systems. Summary of the Invention

[0004] This invention provides a simulated power grid topology generation method and system to solve the technical problems of existing topology generation technologies that do not consider the multi-scenario dimensional correlation of the power grid, the generated single-form basic topology is difficult to adapt to multi-dimensional power grid operating conditions, does not conform to the actual power grid, and cannot meet the needs of complex scenarios. It realizes the construction of a simulated power grid topology model that adapts to the multi-scenario dimensional correlation, thereby supporting the coordinated interaction of power generation, grid, load and storage, new energy consumption and risk coverage of complex operating conditions, and enhancing the reliability and economy of power grid operation.

[0005] To address the aforementioned technical problems, this invention provides a method for generating a simulated power grid topology, the method comprising:

[0006] Acquire multi-source scheduling data of the target power grid;

[0007] The multi-source scheduling data is filtered and graded to obtain the fused dataset of the target power grid;

[0008] The fused dataset is processed using dynamic narrative technology, and a scene narrative dynamic fingerprint is constructed based on the obtained teaching objective matching degree data and risk condition coverage breadth data.

[0009] Based on the scene narrative dynamic fingerprint, a three-dimensional mapping table of the target power grid is generated;

[0010] Based on the fused dataset and the three-dimensional mapping table, a first topology space and a second topology space are constructed; electrical topology analysis is performed on the first topology space to obtain initial electrical connections; polymorphic state estimation is used to process the second topology space to obtain a polymorphic topology structure.

[0011] The initial electrical connections and the polymorphic topology are processed using polymorphic bridging technology to generate a simulated power grid topology model of the target power grid.

[0012] As one preferred embodiment, the step of filtering and classifying the multi-source scheduling data to obtain the fused dataset of the target power grid includes:

[0013] The multi-source scheduling data is filtered and graded to obtain real-time monitoring data, historical operation data, and planning data;

[0014] Cluster analysis technology is used to correlate the real-time monitoring data, the historical operation data, and the planning data to obtain the fused dataset of the target power grid.

[0015] As one preferred embodiment, the process of processing the fused dataset using dynamic narrative technology, and constructing a scene narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data, includes:

[0016] The fused dataset is processed using dynamic narrative technology to obtain teaching objective matching data and risk condition coverage data.

[0017] The teaching objective matching degree data and the risk condition coverage breadth data are weighted and fused to obtain the scene narrative dynamic fingerprint of the target power grid.

[0018] As one preferred embodiment, generating a three-dimensional mapping table of the target power grid based on the scene narrative dynamic fingerprint includes:

[0019] The scene narrative dynamic fingerprint is subjected to structural parsing processing to obtain fingerprint vector structure data;

[0020] The fingerprint vector structure data is processed using dynamic mapping construction technology to obtain a three-dimensional mapping table of the target power grid.

[0021] As one preferred embodiment, the step of constructing the first topological space and the second topological space based on the fused dataset and the three-dimensional mapping table includes:

[0022] The fused dataset and the 3D mapping table are subjected to digital twin binding processing to obtain digital twin feature data;

[0023] Based on the digital twin feature data of the target power grid, the first topology space and the second topology space are constructed.

[0024] As one preferred embodiment, the process of processing the second topological space using polymorphic state estimation to obtain a polymorphic topological structure includes:

[0025] The second topological space is processed using polymorphic state estimation to obtain data on potential topological change schemes;

[0026] The data on potential topology change schemes are sequentially subjected to security verification and topology integration processing to obtain the polymorphic topology structure.

[0027] As a preferred embodiment, the step of processing the initial electrical connection and the multi-state topology using multi-state bridging technology to generate a simulated power grid topology model of the target power grid includes:

[0028] The initial electrical connection and the polymorphic topology are sequentially subjected to topology mapping and state transition processing to obtain scene adaptation data;

[0029] The scene adaptation data is processed using 3D topology modeling technology to obtain a simulated power grid topology model of the target power grid.

[0030] The present invention also provides a simulated power grid topology generation system, comprising:

[0031] The acquisition module is used to acquire multi-source scheduling data of the target power grid;

[0032] The fusion module is used to filter and classify the multi-source scheduling data to obtain the fusion dataset of the target power grid;

[0033] The module is used to process the fused dataset using dynamic narrative technology, and to construct a scene narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data.

[0034] The generation module is used to generate a three-dimensional mapping table of the target power grid based on the scene narrative dynamic fingerprint;

[0035] The first processing module is configured to construct a first topological space and a second topological space based on the fused dataset and the three-dimensional mapping table; perform electrical topology analysis on the first topological space to obtain initial electrical connections; and process the second topological space using polymorphic state estimation to obtain a polymorphic topological structure.

[0036] The second processing module is used to process the initial electrical connection and the polymorphic topology using polymorphic bridging technology to generate a simulated power grid topology model of the target power grid.

[0037] As one preferred embodiment, the process of processing the fused dataset using dynamic narrative technology, and constructing a scene narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data, includes:

[0038] The fused dataset is processed using dynamic narrative technology to obtain teaching objective matching data and risk condition coverage data.

[0039] The teaching objective matching degree data and the risk condition coverage breadth data are weighted and fused to obtain the scene narrative dynamic fingerprint of the target power grid.

[0040] As one preferred embodiment, generating a three-dimensional mapping table of the target power grid based on the scene narrative dynamic fingerprint includes:

[0041] The scene narrative dynamic fingerprint is subjected to structural parsing processing to obtain fingerprint vector structure data;

[0042] The fingerprint vector structure data is processed using dynamic mapping construction technology to obtain a three-dimensional mapping table of the target power grid.

[0043] The present invention also provides a simulated power grid topology generation device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the simulated power grid topology generation method as described above.

[0044] The present invention further provides a computer-readable storage medium storing a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the simulated power grid topology generation method as described above.

[0045] Compared with the prior art, the beneficial effects of the present invention are at least one of the following:

[0046] This invention acquires multi-source scheduling data of a target power grid; filters and classifies the multi-source scheduling data to obtain a fused dataset of the target power grid; processes the fused dataset using dynamic narrative technology, and constructs a scenario narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data; generates a three-dimensional mapping table of the target power grid based on the scenario narrative dynamic fingerprint; constructs a first topology space and a second topology space according to the fused dataset and the three-dimensional mapping table; performs electrical topology analysis on the first topology space to obtain initial electrical connections; processes the second topology space using polymorphic state estimation to obtain a polymorphic topology structure; and processes the initial electrical connections and the polymorphic topology structure using polymorphic bridging technology to generate a simulated power grid topology model of the target power grid.

[0047] Compared with existing technologies, this invention obtains a fused dataset by acquiring multi-source dispatch data of the target power grid and filtering and classifying it. Then, it uses dynamic narrative technology to process the fused dataset and combines it with data on the matching degree of teaching objectives and the breadth of risk condition coverage to construct a dynamic fingerprint of the scenario narrative. Based on this fingerprint, a three-dimensional mapping table is generated. Furthermore, relying on the fused dataset and the three-dimensional mapping table, first and second topology spaces are constructed. Initial electrical connections are obtained through electrical topology analysis, and a multi-state topology structure is obtained through multi-state estimation. Finally, multi-state bridging technology is used to fuse the initial electrical connections and the multi-state topology structure to generate a simulated power grid topology model. The entire process allows the generated topology model to break through the limitations of fixed rules and single forms, conforming to the underlying rules of electrical physics and accurately matching the dimensional correlation requirements of multiple scenarios such as dispatch training, safety analysis, and planning expansion, effectively adapting to the multi-dimensional operating conditions of new power systems. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating a simulated power grid topology generation method in one embodiment of the present invention;

[0049] Figure 2 This is a schematic diagram of the structure of a simulated power grid topology generation system in one embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of the structure of a simulated power grid topology generation device in one embodiment of the present invention;

[0051] Figure label:

[0052] Among them, 11 is the acquisition module; 12 is the fusion module; 13 is the construction module; 14 is the generation module; 15 is the first processing module; 16 is the second processing module; 21 is the processor; and 22 is the memory. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0054] In the description of this invention, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0055] In the description of this invention, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0056] One embodiment of the present invention provides a method for generating a simulated power grid topology. For details, please refer to [link to documentation]. Figure 1 , Figure 1 The diagram shown illustrates a flowchart of a simulated power grid topology generation method according to one embodiment of the present invention. The method includes:

[0057] S1: Obtain multi-source scheduling data of the target power grid;

[0058] S2: The multi-source scheduling data is filtered and graded to obtain the fused dataset of the target power grid;

[0059] S3: Process the fused dataset using dynamic narrative technology, and construct a scene narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data;

[0060] S4: Based on the scene narrative dynamic fingerprint, generate a three-dimensional mapping table of the target power grid;

[0061] S5: Based on the fused dataset and the three-dimensional mapping table, construct a first topology space and a second topology space; perform electrical topology analysis on the first topology space to obtain initial electrical connections; process the second topology space using polymorphic state estimation to obtain a polymorphic topology structure;

[0062] S6: Use polymorphic bridging technology to process the initial electrical connection and the polymorphic topology to generate a simulated power grid topology model of the target power grid.

[0063] Specifically, before using the simulated power grid, users should first clarify the application scenario of the power grid topology. The scenario types include at least training, contingency plans, and planning. The data processing device synchronously collects SCADA real-time data, EMS application results, equipment ledgers, dispatch logs, protection information, and GIS spatial data to provide basic data for topology generation.

[0064] The multi-source scheduling data is filtered and graded to obtain a fused dataset of the target power grid, including: filtering and grading the multi-source scheduling data to obtain real-time monitoring data, historical operation data, and planning data; and using cluster analysis technology to correlate the real-time monitoring data, the historical operation data, and the planning data to obtain a fused dataset of the target power grid.

[0065] First, the collected multi-source scheduling data is filtered. Through data validity verification rules, invalid data, redundant and duplicate data, and abnormal and distorted data are removed, such as null data caused by collection failure, erroneous data exceeding the physical threshold of the power grid, and duplicate data collected from multiple terminals. Valid data that has practical significance for power grid operation and meets the data accuracy standards are retained.

[0066] The filtered valid data is then classified and categorized according to its core attributes, collection dimensions, time characteristics, and power grid application. It is precisely categorized based on the core dimensions of "real-time dynamic monitoring," "historical operation records," and "future planning and design." This includes real-time monitoring data reflecting the current operating status of the power grid, such as current bus voltage, line power flow, and generator output; historical operation data recording the power grid's operation under different conditions / scenarios, such as historical fault conditions, daily operation conditions, and operation data during special periods; and planning data pointing to the future development of the power grid, such as power grid expansion plans, capacity configuration plans, new energy access plans, and regional power grid upgrade plans.

[0067] Then, combining the electrical and physical characteristics of the power grid and the multi-scenario dimension correlation requirements, core indicators for cluster analysis are set, including power grid topology correlation indicators, operating condition characteristic indicators, and scenario dimension correlation indicators. The real-time monitoring data, historical operating data, and planning data obtained in the first step are then input into the cluster analysis model. Clustering algorithms are used to uncover the inherent correlation patterns between different types of data, such as the matching correlation of electrical parameters under the same operating conditions in real-time monitoring data and historical operating data, the adaptation correlation of the grid structure between planning data and existing real-time / historical data, and the cross-time dimension data correlation under the same topology nodes in the three types of data. Finally, based on the correlation results obtained from the cluster analysis, cross-type data with strong inherent correlations are integrated, merged, and structured to form a fused dataset of the target power grid.

[0068] Next, the fused dataset is processed using dynamic narrative technology. Based on the obtained teaching objective matching degree data and risk condition coverage breadth data, a scene narrative dynamic fingerprint is constructed, including: processing the fused dataset using dynamic narrative technology to obtain teaching objective matching degree data and risk condition coverage breadth data; performing weighted fusion processing on the teaching objective matching degree data and the risk condition coverage breadth data to obtain the scene narrative dynamic fingerprint of the target power grid.

[0069] Specifically, based on the core application scenarios of the simulated power grid topology, such as dispatcher training and power grid security and stability analysis, an analytical framework is set for the teaching objective dimension and risk condition dimension of the integrated dataset.

[0070] The teaching objectives dimension is broken down into sub-dimensions such as skill point matching, practical scenario adaptation, and knowledge point coverage for dispatch training. The risk conditions dimension is broken down into sub-dimensions such as fault type coverage, extreme operating condition adaptation, power grid safety boundary coverage, and multi-dimensional fault evolution scenario coverage.

[0071] Based on this framework, the fused dataset is then subjected to structured analysis. From the fused data, which includes real-time, historical, and planning dimensions, electrical operation features, topology features, and operating condition evolution features that are strongly correlated with each sub-dimension are extracted. Subsequently, through a quantitative evaluation model using dynamic narrative technology, the data features are matched and calculated one by one with the teaching objective sub-dimension and the risk operating condition sub-dimension to obtain the quantitative value of each sub-dimension. Finally, the dimensions are aggregated to form the overall teaching objective matching degree data and risk operating condition coverage breadth data.

[0072] It should be noted that the teaching objective matching degree data is a quantitative indicator system used to characterize the degree of fit between the integrated dataset and various teaching objectives of scheduling training, including matching degree values ​​for different teaching scenarios and training objectives; the risk condition coverage breadth data is a quantitative indicator system used to characterize the coverage and depth of the integrated dataset for various risk conditions and fault scenarios of the power grid, including coverage breadth values ​​for different fault types and operating conditions.

[0073] Then, based on the actual application requirements of the simulated power grid topology in the new power system, the weight coefficients of the teaching objective matching degree data and the risk condition coverage breadth data are determined. It should be noted that the weights are determined based on the proportion of dispatch training and power grid security and stability analysis in the application of the topology model, the importance of the scenario, and through scoring by power grid industry experts, the analytic hierarchy process, or the quantitative requirements of actual application scenarios.

[0074] Subsequently, the two types of quantitative data are standardized to eliminate differences in the dimensions and numerical ranges of different indicator systems, ensuring the fairness and accuracy of the fusion calculation. Then, according to the determined weight coefficients, the standardized two types of data are weighted and fused to obtain the fused comprehensive quantitative feature set. Finally, the feature set is structured and dynamically labeled to transform the comprehensive quantitative features into a dynamic fingerprint of the scenario narrative. This fingerprint can fully map the dimensional correlation features of the two major scenarios of teaching and risk conditions, and can be dynamically adjusted as the fused dataset is updated.

[0075] Weighted fusion computation can be linear or nonlinear, depending on the correlation characteristics of the power grid scenario.

[0076] Based on the scene narrative dynamic fingerprint, a three-dimensional mapping table of the target power grid is generated, including: performing structural parsing processing on the scene narrative dynamic fingerprint to obtain fingerprint vector structure data; and using dynamic mapping construction technology to process the fingerprint vector structure data to obtain the three-dimensional mapping table of the target power grid.

[0077] Specifically, the overall digital coding structure of the scene narrative dynamic fingerprint is deconstructed to identify core elements such as the core feature dimensions, feature quantization values, correlation coupling coefficients between scene dimensions, and dynamic update identifiers. Then, the abstract structured coding in the fingerprint is professionally interpreted, transforming the non-intuitive digital identifiers into concrete feature parameters that can be directly calculated and analyzed, fully preserving the core information of multi-scene dimension correlations in the fingerprint. Finally, according to the technical requirements of power grid topology generation, the interpreted feature parameters are vectorized and standardized, integrating the scattered multi-dimensional features into an ordered vector structure. Each vector dimension precisely corresponds to a scene feature or the correlation between features, while unifying the dimensions and value range of the vector data, ultimately forming standardized and structured fingerprint vector structure data.

[0078] Based on the core requirements of simulated power grid topology generation, three core mapping dimensions of the 3D mapping table are determined: scene feature dimension, topology generation parameter dimension, and electrical and physical constraint dimension, thus establishing the overall framework of the 3D mapping table. Subsequently, relying on dynamic mapping construction technology, the inherent coupling relationship between scene features and topology generation parameters and electrical and physical constraints in the fingerprint vector structure data is explored, and association mapping rules that conform to the actual operation law of the power grid are formulated, clarifying the corresponding topology parameter value range and electrical constraint threshold under different combination of scene features. Then, according to the mapping rules, the fingerprint vector structure data is mapped one by one to the intersection nodes of the 3D dimensions, and the feature-parameter-constraint correspondence and quantified values ​​of each node are filled to form an initial 3D mapping table. Finally, combined with the multi-scenario adaptation requirements of the new power system and the electrical and physical feasibility requirements of the power grid, the initial mapping table is dynamically verified and deviations are corrected, unreasonable mapping relationships are eliminated, and the accuracy of parameter values ​​is optimized to ensure the rationality, uniqueness, and dynamism of the mapping table, ultimately obtaining a standardized target power grid 3D mapping table.

[0079] Among them, the scenario feature dimension corresponds to the multi-scenario dimension association features in the fingerprint vector, such as teaching and risk conditions; the topology generation parameter dimension corresponds to the core technical parameters of topology construction, such as grid node configuration, line connection method, unit output threshold, and grid structure form; and the electrical and physical constraint dimension corresponds to the underlying rules of electrical operation, such as voltage level limits, line power flow constraints, and grid safety and stability criteria.

[0080] Constructing a first topology space and a second topology space based on the fused dataset and the three-dimensional mapping table includes: performing digital twin binding processing on the fused dataset and the three-dimensional mapping table to obtain digital twin feature data; and constructing the first topology space and the second topology space based on the digital twin feature data of the target power grid.

[0081] Specifically, a basic digital twin is constructed that fully corresponds to the physical entity of the target power grid. This twin completely replicates the core physical foundation of the target power grid, including its physical topology, electrical equipment attributes, and grid connection relationships, serving as the binding carrier for the fusion dataset and the 3D mapping table. Subsequently, the full-dimensional data in the fusion dataset (electrical and physical data from real-time monitoring, historical operation, and planning data, scenario-related data, and operating condition evolution data) is mapped and bound to the corresponding equipment, nodes, and topology dimensions of the basic digital twin according to the correspondence between physical entities, data features, and operating condition dimensions, achieving a deep association between data and the physical entity of the power grid. At the same time, the 3D mapping rules of scenario features, topology generation parameters, and electrical and physical constraints in the 3D mapping table are bound to the topology generation logic layer of the digital twin, making the mapping rules the core basis for constructing the topology features of the digital twin. Finally, the bound data and rules are cross-validated and feature fused to eliminate conflicting items that do not match between data and rules, or between rules and the physical twin, integrating the scattered bound data and rules into a dataset, namely, the digital twin feature data.

[0082] The digital twin feature data is split into two non-overlapping but common feature subsets based on the two core functional orientations of electrical and physical feasibility and multi-scenario multi-mode adaptation: the electrical and physical core feature subset and the multi-scenario multi-mode adaptation feature subset.

[0083] Subsequently, topology feature space modeling was carried out based on two feature subsets: Based on the core electrical and physical feature subset, following the electrical and physical constraint dimension of the three-dimensional mapping table, a first topology space was constructed with the underlying electrical connection logic and physical operation rules of the target power grid as its core. This space only retains the core topology features of the power grid's electrical and physical layer and replicates the basic topology attributes of the power grid that conform to physical laws. Based on the multi-scenario multi-morphic adaptation feature subset, combined with the scenario feature-topology generation parameter dimension of the three-dimensional mapping table, a second topology space was constructed with multi-scenario adaptation and multi-morphic topology as its core. This space incorporates the topology adaptation requirements of different scenarios, breaks the limitations of fixed rules, and constructs a feature space that can support the generation of multi-morphic topology structures.

[0084] Finally, the boundaries of the two topological spaces are defined and their features are solidified. The core representation dimensions, functional boundaries and data association channels of the two spaces are clarified to ensure that their functional orientations are clear, their features do not overlap, and they have a natural foundation for integration because they both originate from digital twin feature data, thus completing the final spatial construction.

[0085] It should be noted that the first topology space is the basic electrical topology feature space that takes the electrical and physical essence of the target power grid as its core and strictly follows the underlying rules of the electrical operation of the power grid. Its core characterizes the underlying basic topology features and electrical connection logic of the target power grid that meet the requirements of electrical and physical feasibility.

[0086] The second topology space is a multi-mode topology feature space that is guided by the needs of multiple scenarios and adapted to the complex operating conditions of new power systems. Its core characterization is the diversified topology features and scenario adaptation logic of the target power grid in multiple scenarios such as adaptation to dispatch training, risk condition analysis, and planning expansion.

[0087] Electrical topology analysis is performed on the first topology space to obtain the initial electrical connections.

[0088] Specifically, core electrical and physical feature data is extracted from the first topology space and standardized. Then, based on this data, electrical topology nodes and core equipment are modeled and analyzed to build the basic framework of node-equipment association. Next, the effective electrical connection relationships between nodes and equipment are initially screened to construct a basic electrical topology network model. Subsequently, the model is fully validated for electrical constraints using classic electrical analysis algorithms such as power flow calculation and short-circuit current verification. Connection relationships that do not meet the constraints are corrected in a targeted manner. Finally, while retaining the underlying core electrical connection logic of the target power grid, the core features of the model are simplified, and the core electrical connection relationships are structured and solidified. The final output is an initial electrical connection that conforms to the underlying electrical and physical rules and is highly matched with the physical entity of the target power grid.

[0089] The process of processing the second topological space using polymorphic state estimation to obtain a polymorphic topological structure includes: processing the second topological space using polymorphic state estimation to obtain topological potential change scheme data; and sequentially performing security verification processing and topological integration processing on the topological potential change scheme data to obtain the polymorphic topological structure.

[0090] Next, based on the multi-scenario multi-morphic adaptation feature subset of the second topology space, feature data related to multiple scenarios such as scheduling training, risk condition analysis, and planning expansion are extracted. Combined with the algorithm logic of multi-morphic state estimation, state estimation dimensions are set to adapt to different scenarios, such as the topology reconstruction dimension in the fault scenario, the practical topology dimension in the training scenario, and the network structure expansion dimension in the planning scenario.

[0091] Subsequently, the extracted scene feature data is input into the polymorphic state estimation model. The algorithm explores the potential changes in the target power grid topology in terms of node configuration, line connection method, grid structure form, and equipment access combination under different scene dimensions, generating multiple sets of different topology adjustment schemes. At the same time, the scene adaptability of each scheme is quantitatively evaluated, and key information such as the adaptable scene, core adjustment point, and scene matching degree of each scheme is marked. All topology adjustment schemes with quantitative annotations are integrated into structured topology potential change scheme data. This data contains multiple sets of topology change prototypes covering different scenarios and retains the scene-oriented characteristics of each scheme.

[0092] Based on the electrical and physical constraints in the three-dimensional mapping table and the new power system grid safety and stability criteria, a full-dimensional electrical safety feasibility verification is carried out on each group of topology adjustment schemes in the potential topology change scheme data. Through classic electrical analysis methods such as power flow calculation, node voltage verification, and short-circuit current calculation, it is checked whether each scheme meets electrical and physical requirements such as voltage level limits, line power flow constraints, and equipment capacity matching. Invalid schemes that only meet the needs of the scenario but violate electrical safety constraints are eliminated, and topology feasible schemes that simultaneously meet the requirements of scenario adaptability and electrical safety are retained to form a set of effective schemes after safety verification.

[0093] The effective solution set after security verification is classified and structured by scenario dimension. First, according to core application scenarios such as dispatcher training, power grid security and stability analysis, power grid planning and extended verification, the effective solutions are divided into topology subsets corresponding to the scenarios. Then, the core characteristics and applicable operating conditions of the topology solutions within each scenario subset are sorted out, and the switching logic and feature correlation between different scenario topology forms are clarified. Finally, the classified topology subsets are standardized and organized, and key information such as the applicable scenarios, core parameters and applicable operating conditions of each topology form are marked, integrating all scenario-based feasible topology forms into a structured and systematic polymorphic topology structure.

[0094] The initial electrical connection and the polymorphic topology are processed using polymorphic bridging technology to generate a simulated power grid topology model of the target power grid. This includes: sequentially performing topology mapping and state transition processing on the initial electrical connection and the polymorphic topology to obtain scene adaptation data; and processing the scene adaptation data using three-dimensional topology modeling technology to obtain a simulated power grid topology model of the target power grid.

[0095] Using the initial electrical connection as the core electrical foundation and topology mapping benchmark, its core anchoring elements are extracted: core electrical nodes, critical connecting lines, basic equipment access relationships, voltage level matching logic, etc., to clarify the fixed topology skeleton of the underlying electrical connection. Then, the topology forms corresponding to each scenario in the polymorphic topology structure are accurately mapped to the initial electrical connection, and the scenario-based adjustment features of the polymorphic topology are mapped to the corresponding topology positions of the initial electrical connection, ensuring that the scenario-based form of the polymorphic topology always relies on the underlying electrical skeleton and does not deviate from the core electrical connection logic.

[0096] Subsequently, topology state transformation is carried out, transforming the abstract scene adaptation features in the polymorphic topology into structured and parameterized topology state data that can be embedded in the initial electrical connections, realizing the transformation of scene-based topology features into electrical physical parameters. Finally, the mapped and transformed topology data undergoes compatibility cross-validation to eliminate problems such as electrical connection conflicts and parameter mismatches caused by morphological differences. Targeted topology fine-tuning and parameter optimization are performed on conflict points. The full set of data, which integrates the underlying electrical connection logic and multi-scene topology state features after validation and optimization, is structured and integrated to form scene adaptation data.

[0097] In response to the application requirements of new power systems for simulated power grid topology, a three-dimensional topology modeling framework is constructed. This framework includes three core dimensions: electrical physics, scenario adaptation, and dynamic evolution. At the same time, the modeling standards, data association rules, and visualization presentation specifications for each dimension within the framework are defined.

[0098] Subsequently, the scenario adaptation data was divided according to the dimensions of the modeling framework and accurately imported into the corresponding modeling modules to carry out full-element 3D digital modeling: In the electrical physics dimension, the core network structure of the initial electrical connection, the digital model of the equipment, and the electrical connection relationship were restored, giving the model electrical physics attributes that conform to the actual power grid; In the scenario adaptation dimension, the topology state data of each scenario was embedded into the corresponding 3D topology position to construct exclusive topology forms that adapt to different scenarios and clarify the boundaries and characteristics of each scenario's topology; In the dynamic evolution dimension, the switching logic and triggering conditions between the topology forms of each scenario were implanted, such as the triggering correspondence between fault types and topology forms in risky operating conditions, and the linkage between practical steps and topology adjustments in teaching scenarios, so that the model has the ability to dynamically adapt to scenarios.

[0099] Next, the initially constructed 3D topology model is refined, including detailed optimization of equipment models, accurate assignment of topology parameters, logical debugging of scene switching, and simulation linkage settings for electrical operation, to improve the model's realism and practicality. Finally, a full-dimensional final verification is carried out on the refined model, which verifies the electrical and physical feasibility of the model in various scenarios, such as power flow calculation and short-circuit current verification, as well as the model's accuracy in adapting to various application scenarios. Problems found during verification are finally optimized and adjusted, and the model is solidified and output to obtain the simulated power grid topology model of the target power grid.

[0100] Another embodiment of the present invention provides a simulated power grid topology generation system; for details, please refer to [link to relevant documentation]. Figure 2 , Figure 2 The diagram shown illustrates the structure of a simulated power grid topology generation system according to one embodiment of the present invention. The system includes:

[0101] Module 11 is used to acquire multi-source scheduling data of the target power grid;

[0102] The fusion module 12 is used to filter and classify the multi-source scheduling data to obtain the fusion dataset of the target power grid;

[0103] Module 13 is used to process the fused dataset using dynamic narrative technology, and to construct a scene narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data.

[0104] The generation module 14 is used to generate a three-dimensional mapping table of the target power grid based on the scene narrative dynamic fingerprint;

[0105] The first processing module 15 is configured to construct a first topological space and a second topological space based on the fused dataset and the three-dimensional mapping table; perform electrical topology analysis on the first topological space to obtain initial electrical connections; and process the second topological space using polymorphic state estimation to obtain a polymorphic topological structure.

[0106] The second processing module 16 is used to process the initial electrical connection and the polymorphic topology using polymorphic bridging technology to generate a simulated power grid topology model of the target power grid.

[0107] See Figure 3 This is a schematic diagram of the structure of a simulated power grid topology generation device provided in an embodiment of the present invention. The simulated power grid topology generation device includes a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, it implements the steps described in the above-described embodiment of the simulated power grid topology generation method, for example... Figure 1 The steps S1 to S6 described above; or, when the processor 21 executes the computer program, it implements the functions of each module in the above-described device embodiments, such as the acquisition module 11.

[0108] For example, the computer program can be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the simulated power grid topology generation device. For example, the computer program can be divided into an acquisition module 11, a fusion module 12, a construction module 13, etc., with the specific functions of each module as follows:

[0109] Module 11 is used to acquire multi-source scheduling data of the target power grid;

[0110] The fusion module 12 is used to filter and classify the multi-source scheduling data to obtain the fusion dataset of the target power grid;

[0111] Module 13 is used to process the fused dataset using dynamic narrative technology, and to construct a scene narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data.

[0112] The generation module 14 is used to generate a three-dimensional mapping table of the target power grid based on the scene narrative dynamic fingerprint;

[0113] The first processing module 15 is configured to construct a first topological space and a second topological space based on the fused dataset and the three-dimensional mapping table; perform electrical topology analysis on the first topological space to obtain initial electrical connections; and process the second topological space using polymorphic state estimation to obtain a polymorphic topological structure.

[0114] The second processing module 16 is used to process the initial electrical connection and the polymorphic topology using polymorphic bridging technology to generate a simulated power grid topology model of the target power grid.

[0115] The simulated power grid topology generation device may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of a simulated power grid topology generation device and does not constitute a limitation on the device. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the simulated power grid topology generation device may also include input / output devices, network access devices, buses, etc.

[0116] The processor 21 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 21 is the control center of the simulated power grid topology generation device, connecting various parts of the device via various interfaces and lines.

[0117] The memory 22 can be used to store the computer program and / or modules. The processor 21 implements various functions of the simulated power grid topology generation device by running or executing the computer program and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0118] If the modules integrated into the simulated power grid topology generation device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0119] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0120] Accordingly, embodiments of the present invention provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform steps in the simulated power grid topology generation method of the above embodiments, for example... Figure 1 Steps S1 to S6 as described above.

[0121] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for generating a simulated power grid topology, characterized in that, include: Acquire multi-source scheduling data of the target power grid; The multi-source scheduling data is filtered and graded to obtain the fused dataset of the target power grid; The fused dataset is processed using dynamic narrative technology. Based on the obtained teaching objective matching degree data and risk condition coverage breadth data, a scene narrative dynamic fingerprint is constructed. The process of processing the fused dataset using dynamic narrative technology includes setting a parsing framework for the teaching objective dimension and risk condition dimension of the fused dataset; performing structured parsing on the fused dataset based on the parsing framework to extract electrical operation features, topological structure features, and condition evolution features that are strongly correlated with each sub-dimension; and using the quantitative evaluation model of dynamic narrative technology, matching and calculating the data features with the teaching objective sub-dimension and the risk condition sub-dimension one by one to obtain the quantitative value of each sub-dimension. Finally, the teaching objective matching degree data and the risk condition coverage breadth data are formed by dimension aggregation. Based on the scene narrative dynamic fingerprint, a three-dimensional mapping table of the target power grid is generated; Based on the fused dataset and the three-dimensional mapping table, a first topology space and a second topology space are constructed; electrical topology analysis is performed on the first topology space to obtain initial electrical connections; polymorphic state estimation is used to process the second topology space to obtain a polymorphic topology structure, including: processing the second topology space using polymorphic state estimation to obtain topology potential change scheme data; and performing security verification processing and topology integration processing on the topology potential change scheme data in sequence to obtain the polymorphic topology structure. The initial electrical connections and the polymorphic topology are processed using polymorphic bridging technology to generate a simulated power grid topology model of the target power grid.

2. The simulated power grid topology generation method as described in claim 1, characterized in that, The step of filtering and classifying the multi-source scheduling data to obtain the fused dataset of the target power grid includes: The multi-source scheduling data is filtered and graded to obtain real-time monitoring data, historical operation data, and planning data; Cluster analysis technology is used to correlate the real-time monitoring data, the historical operation data, and the planning data to obtain the fused dataset of the target power grid.

3. The simulated power grid topology generation method as described in claim 1, characterized in that, The process of processing the fused dataset using dynamic narrative technology, and constructing a scene narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data, includes: The fused dataset is processed using dynamic narrative technology to obtain teaching objective matching data and risk condition coverage data. The teaching objective matching degree data and the risk condition coverage breadth data are weighted and fused to obtain the scene narrative dynamic fingerprint of the target power grid.

4. The simulated power grid topology generation method as described in claim 1, characterized in that, The step of generating a three-dimensional mapping table of the target power grid based on the scene narrative dynamic fingerprint includes: The scene narrative dynamic fingerprint is subjected to structural parsing processing to obtain fingerprint vector structure data; The fingerprint vector structure data is processed using dynamic mapping construction technology to obtain a three-dimensional mapping table of the target power grid.

5. The simulated power grid topology generation method as described in claim 1, characterized in that, The step of constructing a first topological space and a second topological space based on the fused dataset and the 3D mapping table includes: The fused dataset and the 3D mapping table are subjected to digital twin binding processing to obtain digital twin feature data; Based on the digital twin feature data of the target power grid, the first topology space and the second topology space are constructed.

6. The simulated power grid topology generation method as described in claim 1, characterized in that, The process of using multi-state bridging technology to process the initial electrical connections and the multi-state topology to generate a simulated power grid topology model of the target power grid includes: The initial electrical connection and the polymorphic topology are sequentially subjected to topology mapping and state transition processing to obtain scene adaptation data; The scene adaptation data is processed using 3D topology modeling technology to obtain a simulated power grid topology model of the target power grid.

7. A simulated power grid topology generation system, characterized in that, include: The acquisition module is used to acquire multi-source scheduling data of the target power grid; The fusion module is used to filter and classify the multi-source scheduling data to obtain the fusion dataset of the target power grid; A construction module is used to process the fused dataset using dynamic narrative technology. Based on the obtained teaching objective matching degree data and risk condition coverage breadth data, a scene narrative dynamic fingerprint is constructed. The process of processing the fused dataset using dynamic narrative technology includes setting a parsing framework for the teaching objective dimension and risk condition dimension of the fused dataset; performing structured parsing on the fused dataset based on the parsing framework to extract electrical operation features, topological structure features, and condition evolution features that are strongly correlated with each sub-dimension; and using the quantitative evaluation model of dynamic narrative technology, matching and calculating the data features with the teaching objective sub-dimension and risk condition sub-dimension one by one to obtain the quantitative value of each sub-dimension. Finally, the teaching objective matching degree data and the risk condition coverage breadth data are formed by dimension aggregation. The generation module is used to generate a three-dimensional mapping table of the target power grid based on the scene narrative dynamic fingerprint; A first processing module is configured to construct a first topology space and a second topology space based on the fused dataset and the three-dimensional mapping table; perform electrical topology analysis on the first topology space to obtain initial electrical connections; and process the second topology space using polymorphic state estimation to obtain a polymorphic topology structure, including: processing the second topology space using polymorphic state estimation to obtain topology potential change scheme data; and sequentially performing security verification processing and topology integration processing on the topology potential change scheme data to obtain the polymorphic topology structure. The second processing module is used to process the initial electrical connection and the polymorphic topology using polymorphic bridging technology to generate a simulated power grid topology model of the target power grid.

8. The simulated power grid topology generation system as described in claim 7, characterized in that, The process of processing the fused dataset using dynamic narrative technology, and constructing a scene narrative dynamic fingerprint based on the obtained teaching objective matching degree data and risk condition coverage breadth data, includes: The fused dataset is processed using dynamic narrative technology to obtain teaching objective matching data and risk condition coverage data. The teaching objective matching degree data and the risk condition coverage breadth data are weighted and fused to obtain the scene narrative dynamic fingerprint of the target power grid.

9. The simulated power grid topology generation system as described in claim 7, characterized in that, The step of generating a three-dimensional mapping table of the target power grid based on the scene narrative dynamic fingerprint includes: The scene narrative dynamic fingerprint is subjected to structural parsing processing to obtain fingerprint vector structure data; The fingerprint vector structure data is processed using dynamic mapping construction technology to obtain a three-dimensional mapping table of the target power grid.

Images