Knowledge graph-based rapid real-time aggregation equivalence method considering multiple energy sources of power grid

Abstract

The invention relates to a rapid real-time aggregation equivalence method considering multiple types of energy of a power grid based on a knowledge graph. Comprising the following steps: collecting and preprocessing multi-source data of a power grid energy structure, constructing a power grid multi-class energy aggregation equivalence knowledge graph database, considering a quick real-time power grid multi-class energy aggregation equivalence model based on a knowledge graph, and dynamically updating and correcting the quick real-time power grid multi-class energy aggregation equivalence model. According to the method, the full-amount adjustable energy of the power grid is considered as a whole, various power supplies are automatically and flexibly aggregated and equalized to the power grid of any voltage class by constructing the full-voltage class multi-class energy knowledge graph database of the power grid, and the output of various power supplies and the actual electrical load are decoupled in real time; a power grid load flow calculation model is built for full-amount adjustable energy in a power grid topology flexible equivalence mode, rapid real-time aggregation equivalence of multiple types of energy is achieved, and technical reference is provided for power grid operation management personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid energy aggregation equivalent modeling technology, and specifically to a knowledge graph-based method for rapid real-time aggregation of multiple energy sources in a power grid. Background Art

[0002] Currently, with the continuous improvement of the national economic level and the continuous advancement of energy internet technology, the power grid energy structure has gradually shown 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, operating mode, and response speed. At the same time, the complex and changing power grid topology poses a huge challenge to the stable operation, real-time optimization scheduling, and analytical calculation of the power grid. Traditional power grid equivalence methods often focus on establishing equivalence models for the main grid of large power grids. However, they are unable to effectively integrate information from various distributed energy sources in real time and accurately reflect their comprehensive role in the power grid. They are no longer suitable for the rapid and real-time aggregation of equivalence of multiple energy types, resulting in limited accuracy and efficiency of power grid operation control. Summary of the Invention

[0003] The present invention aims to address the shortcomings of the existing technology and provides a knowledge graph-based method for rapid real-time aggregation of multiple energy sources in the power grid.

[0004] In order to solve the above problems, the technical solutions adopted by the present invention are as follows:

[0005] The knowledge graph-based method for rapid real-time aggregation of multiple energy types in the power grid includes the following steps:

[0006] Step 1: Multi-source data collection and preprocessing of power grid energy structure;

[0007] Step 2: Build a knowledge graph library of the aggregated equivalent value of multiple energy types in the power grid;

[0008] Step 3: Consider the fast real-time aggregation equivalent model of multiple types of energy in the power grid based on the knowledge graph;

[0009] Step 4: Dynamically update and correct the equivalent model considering the rapid real-time aggregation of multiple energy types in the power grid.

[0010] Furthermore, in step 1, the multi-source data collection and preprocessing of the power grid energy structure includes:

[0011] The original data of the power grid is used as the basic data for constructing a knowledge graph library of the aggregation equivalent of multiple types of energy in the power grid.

[0012] The main grid energy structure data can be obtained through the grid's full-time and space system, the grid's "one map", PMS, and D5000 data platform.

[0013] The distribution network diagram system and marketing system can be used to obtain distribution network energy structure data such as distributed new energy sources in the power grid.

[0014] The collected data is cleaned, filtered, and normalized to remove abnormal data and noise interference, making the data consistent and comparable. Then, through standardized grid dispatch naming, the grid entities are uniformly named. The data levels and units collected from different sources are compared to establish a unified and usable structured data set.

[0015] Furthermore, in step 2, constructing a knowledge graph library of aggregated equivalent values of multiple energy types in the power grid includes:

[0016] Based on the results of multi-source data collection and preprocessing of the power grid energy structure in step 1, a knowledge graph library of the aggregation and equivalence of multiple types of energy in the power grid is established to achieve real-time and rapid aggregation and equivalence of multiple types of energy in multiple power grids. Each power grid device is regarded as an entity, and the connection relationship between entities is directly the connection relationship of the power grid topology itself.

[0017] Based on the aggregated equivalent values of multiple types of energy in the power grid, three categories are set for each entity: equipment information, flow information, and equivalent information.

[0018] The equipment information category has four attributes: voltage level, grid-connected power station, equipment model, and energy type.

[0019] The power flow information category has five attributes: voltage, current, active power, reactive power, and power factor;

[0020] The equivalent information class has five attributes: node residual voltage, rated capacity, equivalent load, equivalent generator voltage, and equivalent branch current.

[0021] The Neo4j graph database is used to store the knowledge graph library of the aggregation and equivalent value of multiple types of energy in the power grid. The results of the multi-source data collection and preprocessing of the power grid energy structure in step one are used, and then the one-to-one correspondence of entities is achieved according to the above-mentioned triple knowledge graph model to automatically construct the knowledge graph library of the aggregation and equivalent value of multiple types of energy in the power grid.

[0022] Furthermore, in step 3, the knowledge graph-based and real-time aggregation equivalent model considering multiple types of energy in the power grid includes:

[0023] Based on the grid multi-type energy aggregation equivalent knowledge graph library in step 2, automatic rapid parallel retrieval of all adjustable energy at all voltage levels of the grid is achieved, providing support for rapid and flexible aggregation.

[0024] Based on the connection relationship and operating characteristics of different energy structures in the grid's multi-energy aggregation equivalent knowledge graph library, through the rapid aggregation of voltage level, grid-connected power station, equipment model, and energy type in the equipment information class of the equipment entity, it is possible to automatically aggregate similar equipment models of the same type to establish a synchronous generator group, aggregate the same units in the synchronous generator group, reduce the number of grid-connected generators of multiple energy types, and preliminarily establish a multi-energy equivalent model.

[0025] Furthermore, in step 4, the dynamic updating and correction of the equivalent model considering the rapid real-time aggregation of multiple energy types in the power grid includes:

[0026] According to the third step, the knowledge graph-based rapid real-time aggregation equivalent model of multiple types of power grid energy can be established to realize the grid steady-state flow and short-circuit calculation modeling. The accuracy and reliability of the aggregation equivalent model can be verified and evaluated by using methods such as real-time data comparison, flow calculation result verification and historical data backtesting.

[0027] Based on the verification results, the model structure and parameter settings are further adjusted to ensure that the model can continuously and accurately simulate the actual operation of multiple types of energy in the power grid, providing effective support for real-time operation analysis, dispatching decisions and stable control of the power grid.

[0028] Furthermore, according to the real-time updates and changes of the grid operation status, topology and energy data, the grid multi-category energy aggregation equivalent knowledge graph library is used to continuously update parameters to achieve dynamic updates of online monitoring data and knowledge graphs.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention proposes a method for rapid and real-time aggregation of multiple energy types in a power grid based on a knowledge graph. Compared with existing technologies, it can comprehensively consider all adjustable energy sources in the power grid. By constructing a knowledge graph library of multiple energy types at all voltage levels of the power grid, various power sources can be automatically and flexibly aggregated to any voltage level power grid, realizing real-time decoupling of the output of various power sources from the actual power load, and building a power grid flow calculation model with all adjustable energy in a flexible and equivalent way of the power grid topology, realizing rapid and real-time aggregation of multiple energy types, and providing technical reference for power grid operation and management personnel.

[0031] This application is used to comprehensively consider the full amount of adjustable energy in the power grid, including centralized, distributed new energy, wind power, thermal power and switchable loads. By constructing a knowledge graph library of multiple energy types at all voltage levels of the power grid, various power sources such as distributed new energy, centralized new energy, small hydropower, small thermal power, etc. are automatically and flexibly aggregated to any voltage level power grid, realizing real-time decoupling of the output of various power sources from the actual power load, and building a power grid flow calculation model with a flexible equivalent of the full amount of adjustable energy in the form of power grid topology, realizing rapid and real-time aggregation of multiple energy types, laying the foundation for flexible and rapid modeling, optimization, analysis and control of the power grid. The method of rapid and real-time aggregation of multiple energy types in the power grid based on knowledge graph proposed in this application is of great significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a flow chart of the method for rapidly and real-timely aggregating the equivalent values of multiple energy sources in a power grid based on a knowledge graph according to the present invention;

[0033] Figure 2 This is a schematic diagram of multi-source data collection and preprocessing of the power grid energy structure;

[0034] Figure 3 Schematic diagram for constructing a knowledge graph library of multiple energy aggregation equivalents for power grids;

[0035] Figure 4 This is a diagram of a multi-energy equivalent model according to an embodiment of the present invention;

[0036] Figure 5 This is an equivalent model for rapid real-time aggregation of multiple energy types in a power grid according to an embodiment of the present invention.

[0037] Figure 6 This is a schematic diagram of a dynamic update and correction process of an equivalent model that considers the rapid real-time aggregation of multiple energy types in a power grid according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The present invention will be described below with reference to specific embodiments, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar components or components with the same or similar functions.

[0039] Directional terms used in the present invention, such as up, down, left, right, front, back, inside, outside, front, back, and side, are merely referenced to the accompanying drawings. The embodiments described below with reference to the accompanying drawings and the directional terms used are exemplary and intended only to explain the present invention and are not to be construed as limiting the present invention. Furthermore, the various specific process and material examples provided herein are examples of other processes and / or materials that one of ordinary skill in the art would recognize.

[0040] See also Figure 1 , Figure 1 This is a flow chart of the present invention's method for rapid real-time aggregation of multiple energy sources in a power grid based on knowledge graphs.

[0041] Knowledge graph technology, with its ability to analyze multi-label big data and reason about knowledge, is currently widely used in the power system sector. Considering the full range of adjustable energy sources in the power grid, including centralized and distributed renewable energy, wind power, thermal power, and shelving loads, and the flexible spatial and grid topology, computational complexity and scenarios are substantial. Knowledge graph technology, which leverages graph models to retrieve and match real-time data from multiple energy sources across big data grid topologies, is particularly well-suited for the rapid, real-time aggregation of multiple energy sources in the power grid described in this invention.

[0042] Neo4j is an open source graph database storage software. Its extensive practical applications both at home and abroad have enabled Neo4j software to achieve new development both at home and abroad. Neo4j can also be regarded as a high-performance graph engine with all the characteristics of a mature database, providing a basis for realizing the rapid real-time aggregation of multiple energy types in the power grid of the present invention.

[0043] In order to provide a further understanding and appreciation of the structural features and effects achieved by the present invention, a detailed description is provided with reference to preferred embodiments and accompanying drawings as follows:

[0044] See also Figure 2 , Figure 2 This is a schematic diagram of multi-source data collection and preprocessing of the power grid energy structure;

[0045] Step 1: Multi-source data collection and preprocessing of power grid energy structure

[0046] The present invention first uses the original data of the power grid as the basic data for constructing a knowledge graph library of the aggregation of multiple energy types in the power grid. The main grid energy structure data can be obtained through the power grid full-time and space system, the power grid "one map", PMS, and the D5000 data platform. The distribution network energy structure data such as distributed new energy can be obtained through the distribution network model system and the marketing system. However, due to the differences in data structure and data source, the power grid data cannot be used directly. The present invention will perform pre-processing operations such as cleaning, filtering, and normalization on the collected data to remove abnormal data and noise interference, so that the data has consistency and comparability. Through standardized power grid dispatch naming, the power grid entities are uniformly named, and the magnitude and unit of the same collected data are compared by different sources, thereby establishing a unified and usable structured data set.

[0047] Please participate Figure 3 , Figure 3 Schematic diagram for constructing a knowledge graph library for the aggregation of multiple energy types in the power grid.

[0048] Step 2: Build a knowledge graph library for the aggregation of multiple energy types in the power grid

[0049] The present invention first establishes a knowledge graph library for the aggregation and equivalence of multiple energy types in a power grid based on the results of the aforementioned multi-source data collection and preprocessing of the power grid energy structure. Its purpose is to achieve real-time and rapid aggregation and equivalence of multiple energy types in multiple power grids. Therefore, the present invention uses power grid equipment such as new energy sources and loads as entities, and the connections between these entities directly correspond to the connections of the power grid topology itself. Based on the aggregation and equivalence of multiple energy types in the power grid, three categories are defined for each entity: equipment information, flow information, and equivalent information. The equipment information category has four attributes: voltage level, grid-connected power station, equipment model, and energy type; the flow information category has five attributes: voltage, current, active power, reactive power, and power factor; and the equivalent information category has five attributes: node residual voltage, rated capacity, equivalent load, equivalent generator voltage, and equivalent branch current. The present invention uses a Neo4j graph database to store the knowledge graph library for the aggregation and equivalence of multiple energy types in the power grid. Using the results of the aforementioned multi-source data collection and preprocessing of the power grid energy structure, the present invention achieves a one-to-one correspondence between entities according to the aforementioned triple knowledge graph model, automatically constructing the knowledge graph library for the aggregation and equivalence of multiple energy types in the power grid.

[0050] Please also refer to Figure 4 and Figure 5 ,in Figure 4 This is a diagram of the equivalent model of multiple energy types in an embodiment of the present invention. Figure 5 This is an equivalent model for rapid real-time aggregation of multiple energy types in a power grid according to an embodiment of the present invention.

[0051] Step 3: Considering the fast real-time aggregation model of multiple energy types in the power grid based on the knowledge graph

[0052] The aforementioned grid multi-energy aggregation equivalent knowledge graph enables automatic, rapid, and parallel retrieval of all adjustable energy sources across all voltage levels, thus supporting rapid and flexible aggregation. Based on the connectivity and operational characteristics of different energy structures within the grid multi-energy aggregation equivalent knowledge graph, rapid aggregation of voltage levels, grid-connected power stations, equipment models, and energy types within the device entity's equipment information allows for the automatic aggregation of similar equipment models of the same type, thereby establishing synchronized generator clusters. Identical units within synchronized generator clusters can be aggregated, reducing the number of grid-connected generators across multiple energy types and establishing a preliminary multi-energy equivalent model.

[0053] by Figure 4 For example, wind farms A and B share the same equipment information, including voltage level, grid-connected power station, equipment model, and energy type, enabling rapid aggregation. After the synchronized generator cluster is simplified to a single equivalent generator, its parameters are calculated using a weighted average method, using the ratio of the generator's rated capacity to the equivalent generator's rated capacity as the weight.

[0054] Then, based on the above-mentioned rapid real-time aggregation of multiple types of energy in the power grid, rapid aggregation of multiple types of energy in the power grid can be achieved. In order to realize the automatic and flexible aggregation of various types of power sources such as distributed new energy, centralized new energy, small hydropower, small thermal power, etc. to any voltage level power grid, and realize the real-time decoupling of the output of various power sources and the actual power load, the present invention uses the node residual voltage attribute in the equivalent information class in the knowledge graph library as the physical quantity to measure the electrical distance, thereby establishing an equivalent model based on the knowledge graph that considers the rapid real-time aggregation of multiple types of energy in the power grid. First, the external system and the system requiring equivalent value are divided according to the node residual voltage and voltage level, so as to establish an equivalent model for the multiple types of energy in the power grid to any voltage level network.

[0055] like Figure 5 As shown, wind farm C is converted to a 220kV grid structure. The shortest bus path to 220kV is retrieved through the knowledge graph, and the required equivalent systems are divided according to node residual voltage data, thereby converting wind farm C to a 220kV grid structure. Based on the knowledge graph-based model for rapid and real-time aggregation of multiple energy types in the grid, it is possible to quickly and flexibly aggregate multiple energy types into a grid of any voltage level, achieving real-time decoupling of various power outputs from actual power load. A grid power flow calculation model is constructed by flexibly equating all adjustable energy sources to the grid topology, achieving rapid and real-time aggregation of multiple energy types, and providing a technical reference for grid operation and management personnel.

[0056] See also Figure 6 , Figure 6 This is a schematic diagram of a dynamic update and correction process of an equivalent model that considers the rapid real-time aggregation of multiple energy types in a power grid according to an embodiment of the present invention.

[0057] Step 4: Dynamic update and correction of the equivalent model considering the rapid real-time aggregation of multiple energy types in the power grid

[0058] By rapidly and in real time, the knowledge graph-based equivalent model for multiple energy sources in the power grid can be used to establish a power grid equivalent model, enabling steady-state power flow and short-circuit calculation modeling. However, the accuracy of the equivalent model requires verification and analysis based on actual power flow results. The accuracy and reliability of the aggregated equivalent model are verified and evaluated using methods such as real-time data comparison, power flow calculation result verification, and historical data backtesting. Based on the verification results, the model structure and parameter settings are further adjusted to ensure that the model can consistently and accurately simulate the actual operation of multiple energy sources in the power grid, providing effective support for real-time operation analysis, dispatch decision-making, and stable control of the power grid. Furthermore, as the power grid's operating status, topology, and energy data are updated and changed in real time, the parameters are continuously updated using the aforementioned knowledge graph library for the aggregated equivalent value of multiple energy sources in the power grid, thereby enabling dynamic updating of online monitoring data and the knowledge graph.

[0059] The present invention proposes a method for rapid and real-time aggregation of multiple energy types in a power grid based on a knowledge graph. Compared with existing technologies, it can comprehensively consider all adjustable energy sources in the power grid. By constructing a knowledge graph library of multiple energy types at all voltage levels of the power grid, various power sources can be automatically and flexibly aggregated to any voltage level power grid, realizing real-time decoupling of the output of various power sources from the actual power load, and building a power grid flow calculation model with all adjustable energy in a flexible and equivalent way of the power grid topology, realizing rapid and real-time aggregation of multiple energy types, and providing technical reference for power grid operation and management personnel.

[0060] This application is used to comprehensively consider the full amount of adjustable energy in the power grid, including centralized, distributed new energy, wind power, thermal power and switchable loads. By constructing a knowledge graph library of multiple energy types at all voltage levels of the power grid, various power sources such as distributed new energy, centralized new energy, small hydropower, small thermal power, etc. are automatically and flexibly aggregated to any voltage level power grid, realizing real-time decoupling of the output of various power sources from the actual power load, and building a power grid flow calculation model with a flexible equivalent of the full amount of adjustable energy in the form of power grid topology, realizing rapid and real-time aggregation of multiple energy types, laying the foundation for flexible and rapid modeling, optimization, analysis and control of the power grid. The method of rapid and real-time aggregation of multiple energy types in the power grid based on knowledge graph proposed in this application is of great significance.

[0061] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A knowledge graph-based method for rapid real-time aggregation of multiple energy types in a power grid, characterized by: The following steps are involved: Step 1: Multi-source data collection and preprocessing of power grid energy structure; Step 2: Construct a knowledge graph library of the aggregated equivalent value of multiple energy types in the power grid; Step 3: Consider the fast real-time aggregation equivalent model of multiple types of energy in the power grid based on the knowledge graph; Step 4: Dynamically update and correct the equivalent model considering the rapid real-time aggregation of multiple energy types in the power grid.

2. The method for rapid real-time aggregation of multiple energy types in a power grid based on a knowledge graph according to claim 1 is characterized by: In step 1, the multi-source data collection and preprocessing of the power grid energy structure includes: Use the original data of the power grid as the basic data for building a knowledge graph library of multiple energy aggregation equivalents in the power grid; The main grid energy structure data can be obtained through the grid's full-time and space system, the grid "one map", PMS, and D5000 data platform; The distribution network diagram system and marketing system can obtain the distribution network energy structure data such as distributed new energy sources; The collected data is cleaned, filtered, and normalized to remove abnormal data and noise interference, making the data consistent and comparable. Then, through standardized grid dispatch naming, the grid entities are named in a unified manner. The data levels and units collected from different sources are compared to establish a unified and usable structured data set.

3. The method for rapid real-time aggregation of multiple energy types in a power grid based on a knowledge graph according to claim 2 is characterized by: In the second step, building a knowledge graph library of multiple energy aggregation equivalents in the power grid includes: Based on the results of multi-source data collection and preprocessing of the power grid energy structure in step 1, a knowledge graph library of aggregated equivalent values of multiple types of energy in the power grid is established to achieve real-time and rapid aggregation of multiple types of energy in multiple power grids. Each power grid device is regarded as an entity, and the connection relationship between entities is directly the connection relationship of the power grid topology itself. Based on the aggregated equivalent values of multiple types of energy in the power grid, three categories are set for each entity: equipment information, flow information, and equivalent information; The equipment information category has four attributes: voltage level, grid-connected power station, equipment model, and energy type; The power flow information category 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; The Neo4j graph database is used to store the knowledge graph library of the aggregation and equivalent value of multiple types of energy in the power grid. The results of the multi-source data collection and preprocessing of the power grid energy structure in step one are used, and then the one-to-one correspondence of entities is achieved according to the above-mentioned triple knowledge graph model to automatically construct the knowledge graph library of the aggregation and equivalent value of multiple types of energy in the power grid.

4. The method for rapid real-time aggregation of multiple energy types in a power grid based on a knowledge graph according to claim 3 is characterized by: In step 3, the knowledge graph-based and real-time aggregation equivalent model considering multiple energy types in the power grid includes: Based on the grid multi-energy aggregation equivalent knowledge graph in step 2, automatic and rapid parallel retrieval of all adjustable energy sources at all voltage levels of the grid is achieved, providing support for rapid and flexible aggregation; Based on the connection relationship and operating characteristics of different energy structures in the grid's multi-energy aggregation equivalent knowledge graph library, through the rapid aggregation of voltage level, grid-connected power station, equipment model, and energy type in the equipment information class of the equipment entity, it is possible to automatically aggregate similar equipment models of the same type to establish a synchronous generator group, aggregate the same units in the synchronous generator group, reduce the number of grid-connected generators of multiple energy types, and preliminarily establish a multi-energy equivalent model.

5. The method for rapid real-time aggregation of multiple energy types in a power grid based on a knowledge graph according to claim 4 is characterized by: In step 4, the dynamic updating and correction of the equivalent model considering the rapid real-time aggregation of multiple energy types in the power grid includes: According to the third step, a fast real-time aggregation equivalent model of multiple types of energy in the power grid based on the knowledge graph is established to realize the grid steady-state power flow and short-circuit calculation modeling. The accuracy and reliability of the aggregation equivalent model are verified and evaluated by using methods such as real-time data comparison, power flow calculation result verification and historical data backtesting. Based on the verification results, the model structure and parameter settings are further adjusted to ensure that the model can continuously and accurately simulate the actual operation of multiple types of energy in the power grid, providing effective support for real-time operation analysis, dispatching decisions and stable control of the power grid.

6. The method for rapid real-time aggregation of multiple energy types in a power grid based on a knowledge graph according to claim 4 is characterized by: According to the real-time updates and changes of the grid operation status, topology and energy data, the grid multi-type energy aggregation equivalent knowledge graph library is used to continuously update parameters to achieve dynamic updates of online monitoring data and knowledge graphs.

Images