Power grid multi-energy dynamic aggregation equivalent control method and system based on knowledge graph

Abstract

The invention discloses a power grid multi-energy dynamic aggregation equivalence control method and system based on a knowledge graph, and relates to the technical field of power grid energy aggregation equivalence modeling, and the method comprises the following steps: obtaining power grid energy structure multi-source data, and constructing a power grid multi-class energy aggregation equivalence knowledge graph database; based on the electrical similarity between the knowledge graph database and the node residual voltage, quickly aggregating and dynamically regulating and controlling the multiple energy sources of the power grid, and constructing an aggregation equivalent model of the multiple energy sources of the power grid; performing power flow simulation on the aggregation equivalence model, obtaining evaluation data of the aggregation equivalence model, and controlling the structure and parameters of the aggregation equivalence model according to the evaluation data; according to the invention, flexible equivalence of the multiple types of energy sources of the power grid is carried out through a knowledge graph-based rapid real-time aggregation equivalence method considering the multiple types of energy sources of the power grid, so that the problem that centralized and distributed new energy sources and shearable load energy structures cannot be automatically and flexibly aggregated and equivalence to power grids of any voltage class rapidly and in real time is solved; and the method is not suitable for rapid real-time aggregation equivalence of multiple types of energy sources.

Description

Technical Field

[0001] The present invention relates to the technical field of grid energy aggregation equivalent modeling, and more specifically, to a method and system for dynamic aggregation equivalent control of multi-energy in a power grid based on a knowledge graph. Background Art

[0002] At present, with the continuous improvement of the national economic level and the continuous progress of energy Internet technology, the grid energy structure gradually shows the characteristics of multiple energy types, complex structure, wide distribution, and strong coupling. Compared with traditional thermal power generation, the existing energy structure has significant differences in characteristics, operation modes, response speeds, etc. At the same time, the grid topology is complex and changeable, bringing huge challenges to the stable operation, real-time optimal scheduling, and analysis and calculation of the power grid. Traditional grid equivalent methods often focus on establishing equivalent models for the main grid of large power grids, making it difficult to effectively integrate various distributed energy information in real time and accurately reflect its comprehensive role in the power grid, and no longer meeting the needs of fast real-time aggregation and equivalence of multiple types of energy, resulting in limited accuracy and efficiency of power grid operation control.

[0003] For example, a method for aggregating and equivalent modeling of a new energy base with multiple control strategies disclosed in the invention patent with the publication number of CN119644722A includes: constructing an equivalent model of the relationship satisfied by the terminal voltage of a new energy station in a new energy base with multiple control strategies and the voltage of the bus where the new energy base converges; constructing a positive-sequence network equivalent model and a negative-sequence network equivalent model of the new energy station; performing aggregation and equivalence of the new energy base according to the relationship equivalent model and the positive-sequence network equivalent model to obtain a positive-sequence network aggregation equivalent model; performing series-parallel aggregation and equivalent calculation according to the topological relationship of the new energy base and the negative-sequence network equivalent model to obtain a negative-sequence network aggregation equivalent model; and constructing a new energy base aggregation equivalent model according to the positive-sequence network aggregation equivalent model and the negative-sequence network aggregation equivalent model, where the new energy base aggregation equivalent model is used for short-circuit calculation of a power system containing a new energy base.

[0004] For example, the new energy power station equivalent method and application based on the improved k-means algorithm disclosed in the invention patent with the announcement number CN114513004A include deriving the analytical expression of the multi-machine short-circuit current of the new energy power source and performing phase conversion; establishing the analytical relationship between the equivalent error and the electrical quantities of the power station; based on the voltage-controlled current source characteristics of the new energy power source, using an optimization algorithm to calculate the equivalent voltage and impedance for the grouped units, taking the obtained equivalent error as the particle spacing of each particle, taking the equivalent voltage as the clustering center, using this algorithm to perform grouped equivalence on the new energy units, determining the final number of groups according to the silhouette coefficient, and completing the grouped equivalence of the units. The present invention takes the equivalent error as the particle spacing of the clustering algorithm, uses the improved k-means algorithm for grouped equivalence, simplifies the model complexity of the new energy power source, ensures a certain accuracy, reduces the calculation amount and simulation duration, reduces the number of nodes during the calculation of the network current of the network containing the new energy power source, and improves the calculation speed and iterative calculation efficiency.

[0005] In the above-disclosed technical solution, there are at least the following technical problems: Existing power grid equivalent methods are difficult to effectively integrate various types of distributed energy information in real time, and cannot automatically and flexibly aggregate and equivalent the energy structures such as centralized and distributed new energy, wind power, thermal power, and switchable loads to any voltage level power grid in real time and quickly, and are no longer applicable to the fast real-time aggregation and equivalence of multiple types of energy. In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0006] In order to overcome the above defects of the prior art, the embodiments of the present invention provide a power grid multi-energy dynamic aggregation equivalent control method and system based on a knowledge graph. By considering the fast real-time aggregation equivalent method of multiple types of energy in the power grid based on the knowledge graph, flexible equivalence of multiple types of energy in the power grid is performed to solve the problem that the energy structures such as centralized and distributed new energy, wind power, thermal power, and switchable loads cannot be automatically and flexibly aggregated and equivalent to any voltage level power grid in real time and quickly, and are no longer applicable to the fast real-time aggregation and equivalence of multiple types of energy.

[0007] To achieve the above object, the present invention provides the following technical solutions: A power grid multi-energy dynamic aggregation equivalent control method based on a knowledge graph includes the following steps: obtaining multi-source data of the power grid energy structure, and constructing a knowledge graph library for the aggregation and equivalence of multiple types of energy in the power grid; based on the electrical similarity between the knowledge graph library and the residual voltage of the node, quickly aggregating and dynamically regulating multiple types of energy in the power grid, and constructing an aggregation equivalent model of the power grid multi-energy; performing power flow simulation on the aggregation equivalent model, obtaining evaluation data of the aggregation equivalent model, and controlling the structure and parameters of the aggregation equivalent model according to the evaluation data, where the evaluation data includes the error of the aggregation equivalent model.

[0008] In a preferred embodiment, the acquisition of multi-source data of the power grid energy structure and the construction of a knowledge graph library for aggregating and equivalenting various types of energy in the power grid are as follows: preprocess the multi-source structure data of the area to be measured to establish a structured data set; extract the features of the processed multi-source structure data, and use various energy devices as entity nodes in the knowledge graph; obtain power grid entity relationship data according to the triple pattern, and set three types of attribute information for each entity node to construct a triple knowledge graph model; map the processed multi-source structure data to the entities and attributes in the triple knowledge graph, and automatically generate the edges between entities according to the power grid topology structure to obtain a knowledge graph for aggregating and equivalenting various types of energy in the power grid.

[0009] In a preferred embodiment, the rapid aggregation and dynamic regulation of various types of energy in the power grid based on the electrical similarity between the knowledge graph library and the residual voltage of the nodes, and the construction of an aggregation and equivalent model for multiple energies in the power grid are as follows: identify the aggregation target based on the graph attribute information, retrieve the adjustable energy devices at all voltage levels through the knowledge graph, screen out the node devices that meet the aggregation conditions, and identify the groups of node devices of the same type and the same access conditions; based on the residual voltage of the nodes and the device information, obtain the electrical similarity of different nodes, and divide the node devices with similar characteristics into the same coherent group; equivalent the aggregated coherent group to a single equivalent device, and output the operation data of the aggregated equivalent device through the weighted average method; according to the node residual voltage attribute in the equivalent information class in the knowledge graph library, as a physical quantity to measure the electrical distance, construct an aggregation and equivalent model.

[0010] In a preferred embodiment, the construction of an aggregation and equivalent model by using the node residual voltage attribute in the equivalent information class in the knowledge graph library as a physical quantity to measure the electrical distance is as follows: extract the node residual voltage values of each node according to the power grid operation data and the knowledge graph information, and divide the external system and the system to be equivalent according to the node residual voltage values; through the knowledge graph structure, retrieve the shortest path from the source power generation equipment node to the target bus; based on the node residual voltage value and its change trend, analyze and obtain the electrical coupling degree, and select the equivalent nodes according to the electrical coupling degree and the shortest path to construct an aggregation and equivalent model at the target voltage level.

[0011] In a preferred embodiment, based on the node residual voltage value and its change trend, the electrical coupling degree is analyzed, and equivalent nodes are selected according to the electrical coupling degree and the shortest path to construct an aggregated equivalent model at the target voltage level, which is specifically as follows: Obtain the operation data of the equipment to be equivalent, and extract the node residual voltage values between the nodes of the equipment to be equivalent and the nodes at the target voltage level; Based on the power grid topology and impedance model, output the equivalent electrical distance from the source node to the target node; Output the electrical coupling degree according to the node residual voltage value and the electrical distance, and screen out the injection nodes of the aggregated equivalent model; According to the set residual voltage threshold and distance threshold, screen out the equivalent equipment among the equivalent nodes participating in the equivalent modeling; Aggregate the operation parameters of the equipment to be equivalent by weighting to form an equivalent equipment model; In the power grid power flow model, connect the equivalent equipment model in parallel to the injection nodes, and delete the original equipment nodes in the network topology to obtain the aggregated equivalent model.

[0012] In a preferred embodiment, perform power flow simulation on the aggregated equivalent model, obtain the evaluation data of the aggregated equivalent model, and control the structure and parameters of the aggregated equivalent model according to the evaluation data, which is specifically as follows: Obtain the real-time operation data of the equipment and input it into the aggregated equivalent model for steady-state power flow and short-circuit simulation to generate power flow simulation prediction results; Compare the power flow simulation prediction results with the actual operation data to obtain the error of the aggregated equivalent model; Control the structure and parameters of the aggregated equivalent model according to the error results; Simulate the operation state of multiple energies in the power grid through the corrected aggregated equivalent model, and dynamically update the knowledge graph database in combination with the topological structure and energy data.

[0013] In a preferred embodiment, controlling the structure and parameters of the aggregated equivalent model according to the error results is specifically as follows: According to the error heat map of the power flow simulation prediction results and the actual operation data, identify the error distribution characteristics and concentrated areas, and extract the error positions and error intensities of the nodes; According to the error positions and error intensities, correct the operation parameters of the aggregated equivalent model and reconstruct the model structure, and the model structure reconstruction includes judging the mismatch state of the injection nodes.

[0014] In a preferred embodiment, the model structure reconstruction is specifically as follows: Based on the node residual voltage and electrical distance, re-divide the attribution boundary of the aggregated equipment and update the subordinate relationship between the equipment entity and the target node in the knowledge graph; Obtain the error intensity of the adjacent nodes of the injection node based on the error heat map. If the average difference in error intensity between adjacent nodes exceeds the threshold, it is determined that the current injection node is mismatched; Based on the analysis of the real-time electrical coupling degree and path length, re-select the injection nodes, adjust the aggregated structure and update the equivalent connection relationship.

[0015] A system for a method of dynamically aggregating and equivalent controlling multi - energy in a power grid based on a knowledge graph, characterized by comprising a knowledge graph database module, a module for constructing an aggregated equivalent model, and a module for adjusting the aggregated equivalent model, with connections between the modules; the knowledge graph database module is used to obtain multi - source data of the power grid energy structure and construct a knowledge graph database for aggregating and equivalent of various types of energy in the power grid; the module for constructing an aggregated equivalent model is used to quickly aggregate and dynamically regulate various types of energy in the power grid based on the electrical similarity between the knowledge graph database and the node residual voltage, and construct an aggregated equivalent model of the power grid multi - energy; the module for adjusting the aggregated equivalent model is used to perform power flow simulation on the aggregated equivalent model, obtain evaluation data of the aggregated equivalent model, and control the structure and parameters of the aggregated equivalent model according to the evaluation data, where the evaluation data includes the error of the aggregated equivalent model.

[0016] The technical effects and advantages of a method and system for dynamically aggregating and equivalent controlling multi - energy in a power grid based on a knowledge graph of the present invention: 1. The present invention constructs a multi - source data - driven power grid energy structure model through knowledge graph technology, realizing the efficient aggregation of distributed energy devices in the power grid. Based on the entity node and attribute mapping of the knowledge graph, it can accurately identify device groups of the same type and the same access conditions, and form a coherent group through electrical similarity analysis, significantly reducing the model complexity. For example, aggregating the coherent generator groups into a single device greatly reduces the computational amount, and at the same time outputs the operating data of the equivalent device through the weighted average method, ensuring the accuracy and real - time performance of the model. The knowledge graph database module realizes the deep integration and intelligent analysis of multi - source data of the power grid through a unified structured data set and a triple model. This module not only supports the rapid retrieval and relationship reasoning of device entities, but also provides high - precision data support for subsequent aggregation and equivalence through the attribute mapping and topology generation of entity nodes. For example, when dealing with the access of distributed energy, the knowledge graph can automatically identify the device type and access conditions, significantly improving the modeling efficiency.

[0017] 2. The present invention constructs an aggregated equivalent model based on the knowledge graph through the dynamic analysis of node residual voltage and electrical distance. This method can extract the node residual voltage value in real time and divide the system boundary according to the power grid operation data and knowledge graph information, screen equivalent nodes through the shortest path and electrical coupling degree, and form a dynamic equivalent model at the target voltage level. For example, when the power grid topology changes or a device fails, the system can quickly adjust the equivalent nodes to ensure that the model is always consistent with the actual power grid state. The electrical similarity analysis method based on node residual voltage and device information breaks through the limitations of traditional aggregation methods. Through the joint analysis of the residual voltage change trend and electrical coupling degree, this method can accurately identify node devices with similar characteristics, ensuring that the aggregated equivalent device is highly consistent with the original system in electrical characteristics. For example, when constructing an equivalent model, the system can screen equivalent nodes based on the residual voltage threshold and distance threshold to avoid model errors caused by parameter mismatch. Description of the Drawings

[0018] Figure 1 This is a schematic flow diagram of the method for controlling the dynamic aggregation and equivalent of multiple energies in the power grid based on the knowledge graph according to the present invention.

[0019] Figure 2 This is a schematic structural diagram of the system for the method for controlling the dynamic aggregation and equivalent of multiple energies in the power grid based on the knowledge graph according to the present invention.

[0020] Figure 3 This is a model diagram of the triple knowledge graph.

[0021] Figure 4 This is a diagram for dividing the external system and the system to be equivalent. Detailed Embodiments

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Embodiment 1 Figure 1 The method for controlling the dynamic aggregation and equivalent of multiple energies in the power grid based on the knowledge graph according to the present invention is given, and it includes the following steps: S1. Obtain multi-source data of the power grid energy structure and construct a knowledge graph library for aggregating and equivalenting multiple types of energies in the power grid.

[0024] In this embodiment, obtaining multi-source data of the power grid energy structure and constructing a knowledge graph library for aggregating and equivalenting multiple types of energies in the power grid are specifically as follows: Obtain multi-source structure data of the area to be measured, establish a structured data set, and identify and eliminate abnormal data in the multi-source structure data through a rule engine, and perform standardization processing on parameters with large dimension differences (such as voltage levels, capacities) to ensure data comparability. The multi-source structure data includes main grid data and distribution network data; The main grid data is obtained through the power grid full-time and full-space system, the "one map" of the power grid, PMS, and the D5000 platform; The distribution network data obtains distributed new energy-related data through the distribution network diagram model system and the marketing system; Extract the features of the processed multi-source structure data. According to the characteristics of the multi-source structure data, various energy devices (such as wind farms, photovoltaic stations, load nodes, small hydropower stations, etc.) are used as entity nodes in the knowledge graph, and each type of entity corresponds to a specific device unit; Based on a structured data set, according to the standard triple pattern of "subject - predicate - object", automatically extract power grid entity relationship data, and set three types of attribute information for each entity node to construct a triple knowledge graph model for describing the structural characteristics, operating status, and equivalent modeling parameters of equipment. The three types of attribute information include equipment information class, equivalent information class, and power flow information class. The entity relationship data refers to various types of equipment in the power grid and their mutual relationships, specifically referring to the data represented in the form of a triple model (subject - predicate - object) in the power grid knowledge graph. These data include the definitions of entities and the connections between them; Among them, the equipment information class has four attributes: voltage level, grid - connected power station, equipment model, and energy type. The power flow information class has five attributes: voltage, current, active power, reactive power, and power factor. The equivalent information class has five attributes: node residual voltage, rated capacity, equivalent load, equivalent generator voltage, and equivalent branch current; Map the processed multi - source structure data to the entities and attributes in the triple knowledge graph through the Neo4j graph database (as Figure 3 shown), and automatically generate the edges between entities according to the power grid topology structure, thereby realizing the automatic construction of a power grid multi - energy aggregation equivalent knowledge graph library.

[0025] S2. Based on the electrical similarity between the knowledge graph library and the node residual voltage, quickly aggregate and dynamically regulate multi - energy in the power grid, and construct an aggregation equivalent model for multi - energy in the power grid.

[0026] In this embodiment, based on the electrical similarity between the knowledge graph library and the node residual voltage, quickly aggregate and dynamically regulate multi - energy in the power grid, and construct an aggregation equivalent model for multi - energy in the power grid as follows: Identify the aggregation target based on the graph attribute information, and through the knowledge graph, perform parallel automated retrieval on adjustable energy equipment at all voltage levels, quickly screen out node equipment meeting the aggregation conditions, and identify groups of node equipment of the same type and the same access conditions according to attributes such as the voltage level, grid - connected power station, equipment model, and energy type of the entity; Taking the node residual voltage and equipment information as a reference, obtain the electrical similarity of different nodes, and divide node equipment with similar characteristics into a coherent group (for example, merge multiple wind turbines into a wind power group); Equivalent the aggregated coherent generator group to an equivalent equipment, reduce the model complexity, and output the operating data of the aggregated equivalent equipment through the weighted average method; According to the node residual voltage attribute in the equivalent information class in the knowledge graph library, as a physical quantity for measuring the electrical distance, construct an aggregation equivalent model.

[0027] It should be noted that the node electrical similarity is a key indicator for judging equipment attribution and injection node selection in aggregated modeling. By fusing voltage deviation, electrical distance, and power output characteristics, a unified scoring function is constructed and a matrix-based analysis system is formed. Based on this method, electrically similar regions can be dynamically identified, improving the matching accuracy of equivalent models and the credibility of power flow simulation.

[0028] In this embodiment, according to the node residual voltage attribute in the equivalent information class in the knowledge graph library, which is used as a physical quantity to measure the electrical distance, an aggregated equivalent model is constructed as follows: According to the power grid operation data and knowledge graph information, the residual voltage values of each node are extracted (i.e., the steady-state deviation of the node voltage recovery after a fault or disturbance). Nodes with residual voltage values higher than the threshold are classified as the external system, and nodes lower than the threshold are classified as the system to be equivalent (as Figure 4 shown); Through the knowledge graph structure, the shortest path from the source power generation equipment node to the target bus is retrieved; Based on the node residual voltage and the residual voltage change trend, the electrical coupling degree is obtained. According to the electrical coupling degree and the shortest path, equivalent nodes are selected, and an aggregated equivalent model under the target voltage level is established.

[0029] In this embodiment, based on the node residual voltage and the residual voltage change trend, the electrical coupling degree is obtained. According to the electrical coupling degree and the shortest path, equivalent nodes are selected, and an aggregated equivalent model under the target voltage level is established as follows: Obtain the operation data of the equipment to be equivalent, and extract the node residual voltage values between the nodes of the equipment to be equivalent and the nodes of the target voltage level; Based on the power grid topology and impedance model, the equivalent electrical distance from the source node to the target node is output; Output the electrical coupling degree according to the node residual voltage value and the electrical distance, and screen out the injection nodes of the aggregated equivalent model according to the electrical coupling degree; According to the set residual voltage threshold and distance threshold, screen out the equivalent equipment among the equivalent nodes participating in equivalent modeling; Weightedly aggregate the operation parameters of the equipment to be equivalent to form an equivalent equipment model, and the operation parameters include rated capacity, dynamic data (inertia, damping); In the power grid power flow model, connect the equivalent equipment to the injection node in parallel, and at the same time delete the original equipment node in the network topology, so as to obtain the aggregated equivalent model.

[0030] It should be noted that after selecting the injection node, it is necessary to evaluate the equivalent impedance path between the target node and the virtual connection of the equivalent device. If the reactance differences of the paths from multiple original device nodes to the injection node are large, an equivalent connection impedance needs to be constructed to reflect the equivalent coupling relationship between the aggregated device and the power grid, avoid electrical model distortion caused by directly connecting the aggregated model to the bus, and improve the simulation accuracy.

[0031] The aggregation calculation formula for dynamic data is as follows:

[0032] In the formula: is the total dynamic data of the aggregated equivalent unit, is the dynamic data of the i-th power generation unit, is the rated capacity of the i-th device, is the total number of aggregated devices.

[0033] The calculation formula for the electrical coupling degree is as follows:

[0034] In the formula: is the electrical coupling degree, is the node residual voltage difference, , is the node residual voltage of node i, is the node residual voltage of node j, is the electrical distance from node i to node j, and are the weight coefficients, satisfying , and are used to balance the influence of the residual voltage and the electrical distance on the coupling degree.

[0035] It should be noted that the node residual voltage difference represents the similarity of voltage behavior, especially whether the responses are consistent after system disturbances. The electrical distance reflects the topological and impedance coupling and represents the path cost of energy transmission or disturbance propagation. The larger the node residual voltage difference and the electrical distance, the less similar or farther they are. Taking the reciprocal form makes the coupling degree larger, indicating that the two nodes are closer, more similar, and more tightly coupled.

[0036] S3. Conduct power flow simulation on the aggregated equivalent model to obtain the evaluation data of the aggregated equivalent model, and control the structure and parameters of the aggregated equivalent model according to the evaluation data. The evaluation data includes the error of the aggregated equivalent model.

[0037] In this embodiment, conducting power flow simulation on the aggregated equivalent model to obtain the evaluation data of the aggregated equivalent model, and controlling the structure and parameters of the aggregated equivalent model according to the evaluation data are as follows: Obtain the real-time operation data of the device, and input the real-time operation data into the aggregated equivalent model for steady-state power flow and short-circuit simulation to generate power flow simulation prediction results, where the power flow simulation prediction results include predicted node voltages and branch power distributions; Compare the power flow simulation prediction results with the actual operation data, evaluate the error of the aggregated equivalent model, and generate an error heat map; Control the structure and parameters of the aggregated equivalent model according to the error results; Simulate the operation states of multiple energies in the power grid through the corrected aggregated equivalent model, and dynamically update the knowledge graph database in combination with the topological structure and energy data; Re-input the corrected model into the power flow simulation, and compare whether the system responses before and after correction tend to be consistent. If the error decreases and the stability improves, confirm that the correction is effective; otherwise, start the model rollback mechanism to restore to the previous effective aggregation state.

[0038] In this embodiment, controlling the structure and parameters of the aggregated equivalent model according to the error results is specifically as follows: According to the error heat map of the power flow simulation prediction results and the actual operation data, identify the error distribution characteristics and concentrated areas, and extract the error positions and error intensities of the nodes; If the error is concentrated near a certain injection node, it may indicate that the current injection node selection is unreasonable; If the error shows a systematic deviation, it may be due to the aggregation distortion of device parameters or the deviation of dynamic data settings; If the error appears after the topology change, the aggregation structure mismatch or topological path error needs to be considered; According to the error positions and intensities, directionally correct the operation parameters in the aggregated equivalent model. The directional correction method includes replacing the corresponding data in the aggregated device with the latest real-time data and re-aggregating the dynamic data; When the injection node is mismatched, control the structure of the aggregated equivalent model.

[0039] In this embodiment, controlling the structure of the aggregated equivalent model is specifically as follows: Based on the node residual voltage and electrical distance, re-divide the attribution boundaries of the aggregated devices, and update the subordinate relationships between the device entities and the target nodes in the knowledge graph; Based on the error heat map, obtain the error intensities of the adjacent nodes of the injection node. If the average difference in error intensities between adjacent nodes exceeds the threshold, it is determined that the current injection node is mismatched; Based on the latest electrical coupling degree and path length analysis, re-select the injection node, adjust the aggregation structure, and update the equivalent connection relationship; Based on the real-time residual voltage and power flow sensitivity, select the node with the highest electrical coupling degree as the injection point of the equivalent model again. If the system supports multi-node injection, use the decentralized parallel injection method.

[0040] In this embodiment, the operation state of the multi-energy of the power grid is simulated through the corrected aggregated equivalent model, and the knowledge graph library is dynamically updated in combination with the topological structure and energy data, as follows: After completing the structure and parameter correction, perform power flow simulation again to verify the correction effect; Compare the simulation error values and the heat map comparison before and after correction, and update and write the corrected parameter values, aggregation boundaries, and injection node positions into the knowledge graph library to realize the dynamic accumulation and update of model knowledge.

[0041] Embodiment 2 Figure 2 A system for a multi-energy dynamic aggregation equivalent control method of a power grid based on a knowledge graph according to the present invention is given, including a knowledge graph library module, an aggregated equivalent model construction module, and an aggregated equivalent model adjustment module, and there are connections between the modules; The knowledge graph library module is used to obtain multi-source data of the power grid energy structure and construct a multi-energy aggregated equivalent knowledge graph library of the power grid; The aggregated equivalent model construction module is used to quickly aggregate and dynamically regulate multi-energies of the power grid based on the electrical similarity between the knowledge graph library and the node residual voltage, and construct an aggregated equivalent model of the multi-energies of the power grid; The aggregated equivalent model adjustment module is used to perform power flow simulation on the aggregated equivalent model, obtain the evaluation data of the aggregated equivalent model, and control the structure and parameters of the aggregated equivalent model according to the evaluation data.

[0042] The above formulas are all dimensionless and take their numerical values for calculation. The formula is a formula obtained by collecting a large amount of data for software simulation to get the closest real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0043] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product.

[0044] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0045] In addition, in each embodiment of the present application, each functional module can be integrated into one processing module, can exist separately as individual physical modules, or two or more modules can be integrated into one module.

[0046] As described above, only the specific embodiments of the present application are provided, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0047] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should all be included within the protection scope of the present invention.

Claims

1. A knowledge graph-based power grid multi-energy dynamic aggregation equivalent control method, characterized in that: The steps include: Obtain multi-source data on the power grid energy structure and build a knowledge graph library of multi-type energy aggregation equivalents in the power grid; Based on the electrical similarity between the knowledge graph library and the node residual voltage, multiple types of energy in the power grid are quickly aggregated and dynamically regulated to build an aggregation equivalent model of multiple energy sources in the power grid; The aggregate equivalent model power flow is simulated to obtain evaluation data of the aggregate equivalent model, and the structure and parameters of the aggregate equivalent model are controlled according to the evaluation data, wherein the evaluation data includes an error of the aggregate equivalent model.

2. The method for controlling the dynamic aggregation of multiple energy sources in a power grid based on knowledge graph according to claim 1 is characterized in that: The method of obtaining multi-source data of the power grid energy structure and constructing a knowledge graph library of multi-type energy aggregation equivalents of the power grid is as follows: Preprocess the multi-source structural data of the area to be measured and establish a structured data set; Extract the features of the processed multi-source structured data and treat various types of energy equipment as entity nodes in the knowledge graph; The power grid entity relationship data is obtained according to the triple pattern, and three types of attribute information are set for each entity node to construct a triple knowledge graph model; The processed multi-source structured data are mapped to the entities and attributes in the triple knowledge graph, and the edges between entities are automatically generated according to the power grid topology structure to obtain the equivalent knowledge graph of multi-category energy aggregation in the power grid.

3. The method for controlling the dynamic aggregation of multiple energy sources in a power grid based on knowledge graph according to claim 2 is characterized in that: Based on the electrical similarity between the knowledge graph library and the node residual voltage, the multiple types of energy in the power grid are quickly aggregated and dynamically regulated to build an aggregation equivalent model of multiple energy sources in the power grid, as follows: Identify aggregation targets based on graph attribute information, retrieve adjustable energy devices at all voltage levels through the knowledge graph, screen out node devices that meet aggregation conditions, and identify groups of node devices of the same type and access conditions; Based on the node residual voltage and device information, the electrical similarity of different nodes is obtained, and node devices with similar characteristics are divided into synchronization groups; The aggregated coherent group is equal to a single equal-value device, and the operation data of the aggregated equal-value device is output through the weighted average method; According to the node residual voltage attribute in the equivalent information class in the knowledge graph library, an aggregate equivalent model is constructed as a physical quantity to measure the electrical distance.

4. The method for controlling the dynamic aggregation of multiple energy sources in a power grid based on knowledge graph according to claim 3 is characterized in that: According to the node residual voltage attribute in the equivalent information class in the knowledge graph library, as a physical quantity to measure the electrical distance, an aggregate equivalent model is constructed, as follows: Extract the node residual voltage value of each node based on the grid operation data and knowledge graph information, and divide the external system and the equivalent value system according to the node residual voltage value; Through the knowledge graph structure, the shortest path from the source power generation equipment node to the target bus is retrieved; Based on the node residual voltage value and its changing trend, the electrical coupling degree is analyzed and obtained, and the equivalent nodes are selected according to the electrical coupling degree and the shortest path to construct an aggregate equivalent model under the target voltage level.

5. The method for controlling the dynamic aggregation of multiple energy sources in a power grid based on knowledge graph according to claim 4 is characterized in that: Based on the node residual voltage value and its change trend, the electrical coupling degree is analyzed, and the equivalent nodes are selected according to the electrical coupling degree and the shortest path to construct an aggregate equivalent model under the target voltage level, as follows: Obtain the operating data of the device to be equivalent, and extract the node residual voltage value between the node of the device to be equivalent and the node of the target voltage level; Based on the grid topology and impedance model, the equivalent electrical distance from the source node to the target node is output; Output the electrical coupling degree according to the node residual voltage value and electrical distance, and select the injection nodes of the aggregate equivalent model; According to the set residual pressure threshold and distance threshold, select the equivalent devices in the equivalent nodes participating in the equivalent modeling; The operating parameters of the equipment to be equivalent are weighted and aggregated to form an equivalent equipment model; In the power grid flow model, the equivalent device model is connected to the injection node in parallel, and the original device node is deleted in the network topology to obtain the aggregated equivalent model.

6. The method for controlling the dynamic aggregation of multiple energy sources in a power grid based on knowledge graph according to claim 5 is characterized in that: The aggregation equivalent model power flow simulation is performed to obtain evaluation data of the aggregation equivalent model, and the structure and parameters of the aggregation equivalent model are controlled according to the evaluation data, as follows: Obtain the real-time operation data of the equipment and input it into the aggregation equivalent model to perform steady-state power flow and short-circuit simulation to generate power flow simulation prediction results; Compare the power flow simulation prediction results with the actual operation data to obtain the error of the aggregate equivalent model; Control the structure and parameters of the aggregate equivalent model according to the error results; The modified aggregation equivalent model is used to simulate the operating status of multiple energy sources in the power grid, and the knowledge graph library is dynamically updated by combining the topological structure and energy data.

7. The method for controlling the dynamic aggregation of multiple energy sources in a power grid based on knowledge graph according to claim 6 is characterized in that: The structure and parameters of the aggregation equivalent model are controlled according to the error results, as follows: According to the error heat map of power flow simulation prediction results and actual operation data, the error distribution characteristics and concentrated areas are identified, and the error position and error intensity of the node are extracted; According to the error position and the error intensity, the operating parameters of the aggregate equivalent model are corrected, and the model structure is reconstructed, wherein the model structure reconstruction includes the determination of the mismatch state of the injection node.

8. The method for controlling the dynamic aggregation of multiple energy sources in a power grid based on knowledge graph according to claim 7 is characterized in that: The model structure reconstruction is as follows: Based on the node residual voltage and electrical distance, the belonging boundary of the aggregated device is re-divided, and the subordinate relationship between the device entity and the target node in the knowledge graph is updated; The error strength of the adjacent nodes of the injected node is obtained based on the error heat map. If the average difference in the error strength between adjacent nodes exceeds the threshold, the current injected node is determined to be mismatched. Based on real-time electrical coupling and path length analysis, the injection nodes are reselected, the aggregation structure is adjusted, and the equivalent connection relationship is updated.

9. A system using the knowledge graph-based power grid multi-energy dynamic aggregation equivalent control method as described in any one of claims 1 to 8, characterized in that: It includes a knowledge graph library module, an aggregation equivalent model building module and an aggregation equivalent model adjustment module, and there are connections between the modules; The knowledge graph library module is used to obtain multi-source data on the power grid energy structure and build a knowledge graph library with equivalent aggregation values ​​for multiple types of energy in the power grid; Construct an aggregation equivalent model module to quickly aggregate and dynamically regulate multiple types of energy in the power grid based on the electrical similarity of the knowledge graph library and the node residual voltage, and construct an aggregation equivalent model of multiple energy sources in the power grid; The aggregation equivalent model adjustment module is used to simulate the aggregation equivalent model power flow, obtain evaluation data of the aggregation equivalent model, and control the structure and parameters of the aggregation equivalent model according to the evaluation data, wherein the evaluation data includes the error of the aggregation equivalent model.

Images