A data processing method and system for multi-source heterogeneous data fusion and intelligent analysis

Abstract

This invention discloses a data processing method and system for multi-source heterogeneous data fusion and intelligent analysis. The method includes: acquiring multi-source heterogeneous data from a power system and inputting it into a preset unified data model for data preprocessing; generating multi-source heterogeneous processed data carrying unified data tags; performing power business analysis on the multi-source heterogeneous processed data; mapping and associating all multi-source heterogeneous processed data for the same power business to generate multi-source heterogeneous associated data related to the business; acquiring the topology of the power system; optimizing the topology using historical disturbance events as training samples; analyzing the propagation logic of historical disturbance events; constructing a data analysis model; inputting the multi-source heterogeneous associated data into the data analysis model for dynamic simulation and multi-dimensional analysis of disturbance events; and linking and identifying key business information for business decision-making. This application has the effect of unified management of diverse grid data after the integration of new energy sources into a new power system.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data processing method and system for multi-source heterogeneous data fusion and intelligent analysis. Background Technology

[0002] Currently, with the continuous construction and development of new power systems, new energy power generation such as wind, solar, hydro, thermal, and energy storage is being connected to the traditional power grid, becoming one of the main sources of electricity. However, the data format, communication protocol, and sampling frequency of new energy power data are not uniform, and they fluctuate greatly due to external weather conditions. Therefore, higher requirements are placed on the data management of the power grid system after the inclusion of new energy.

[0003] Existing power grid systems typically manage the data of new energy sources from different power sources in a fragmented manner, and process the data through manual aggregation and analysis and make decisions based on experience. The information silos of power data and the data barriers of multi-source heterogeneous data restrict the accuracy of decision-making, making it impossible to accurately predict power generation and regulation demand, and affecting the grid's absorption efficiency. Summary of the Invention

[0004] To address the problems in existing technologies where information silos in power data and data barriers caused by heterogeneous multi-source data restrict the accuracy of decision-making, making it impossible to accurately predict power generation and regulation demand, and affecting grid absorption efficiency, this application provides a data processing method and system for multi-source heterogeneous data fusion and intelligent analysis. This method can coordinate and link data from wind, solar, hydro, thermal, and energy storage to accurately analyze grid data and make intelligent decisions. It can also uniformly manage the diverse grid data after the integration of new energy sources into the new power system, providing accurate data support for power generation and regulation.

[0005] Firstly, the above-mentioned inventive objective of this application is achieved through the following technical solution: A data processing method for multi-source heterogeneous data fusion and intelligent analysis, the method comprising: Acquire multi-source heterogeneous data from the power system, input the multi-source heterogeneous data into a preset unified data model for data preprocessing, and generate multi-source heterogeneous processed data carrying unified data tags; Power business analysis is performed on the multi-source heterogeneous processed data, and all multi-source heterogeneous processed data of the same power business are mapped and associated to generate multi-source heterogeneous associated data of business association. The topology of the power system is obtained, and the topology is optimized using historical disturbance events as training samples. The propagation logic of the historical disturbance events is analyzed, and a data analysis model is constructed. The multi-source heterogeneous correlation data is input into the data analysis model to perform dynamic simulation and multi-dimensional analysis of disturbance events, and to identify key business information for business decision-making.

[0006] In a preferred embodiment, this application can be further configured as follows: acquiring multi-source heterogeneous data from the power system, inputting the multi-source heterogeneous data into a preset data unification model for data preprocessing, and generating multi-source heterogeneous processed data carrying unified data tags, specifically includes: By calling various communication protocols pre-encapsulated in the unified data model, the multi-source heterogeneous data is identified to obtain all multi-source heterogeneous data connected to the power system. Extract the data acquisition time and data source of the multi-source heterogeneous data, generate unique data tags for the multi-source heterogeneous data according to a preset tag format, and perform classification and labeling processing on the multi-source heterogeneous data; Using a pre-defined unified data model, key information is extracted from the classified and labeled multi-source heterogeneous data, and mapped to the model's standardized vocabulary for unstructured data transformation, generating multi-source heterogeneous processed data carrying unified data labels.

[0007] In a preferred embodiment, this application can be further configured as follows: The step of performing power business analysis on the multi-source heterogeneous processed data, mapping and associating all multi-source heterogeneous processed data for the same power business, and generating multi-source heterogeneous associated data for business association specifically includes: The power business to which the multi-source heterogeneous processing data belongs is analyzed. Based on the analysis results, all multi-source heterogeneous processing data belonging to the same power business are aggregated to construct a multi-source heterogeneous processing data pool for each power business. According to the business processing order, the data in the multi-source heterogeneous processing data pool are associated with business scheduling to generate multi-source heterogeneous associated data that carries power business tags and has power scheduling association.

[0008] In a preferred embodiment, this application can be further configured as follows: acquiring the topology of the power system, optimizing the topology using historical disturbance events as training samples, analyzing the propagation logic of the historical disturbance events, and constructing a data analysis model, specifically including: Obtain the equipment entities and their corresponding connection relationships in the power system, construct the topology of the power system with equipment entities as nodes and connection relationships as edges, and generate a power grid topology graph. Historical disturbance events of the power system are acquired, and the historical disturbance events are simulated using the power grid topology map to analyze the propagation logic of the historical disturbance events. Based on the disturbance propagation logic analysis results, disturbance propagation logic constraints are applied to the power grid topology map to construct a data analysis model.

[0009] In a preferred embodiment, this application can be further configured as follows: acquiring historical disturbance events of the power system, simulating the historical disturbance events using the power grid topology map, and analyzing the propagation logic of the historical disturbance events, specifically includes: During the simulation, the line power flow distribution data and node voltage change data of relevant disturbance nodes are acquired, and the electrical impact analysis of the disturbance nodes is performed to obtain the electrical interference logic of historical disturbance events. The timing of instruction transmission and execution delay during the simulation operation are obtained, and the control response delay of the actual associated entities in the power topology map is analyzed to obtain the control response logic of historical disturbance events. During the simulation operation, it is determined whether the relevant disturbance nodes have failed. When a failure occurs, a new disturbance event is generated to iteratively simulate the power grid topology map and generate a hierarchical linkage risk detection logic for historical disturbance events.

[0010] In a preferred embodiment, this application can be further configured as follows: the step of inputting the multi-source heterogeneous correlation data into the data analysis model for dynamic simulation and multi-dimensional analysis of disturbance events, and linking the identification of key business information for business decision-making, specifically includes: The multi-source heterogeneous correlation data is input into the data analysis model, the corresponding power grid topology map is called, and the multi-source heterogeneous correlation data is dynamically simulated under the corresponding disturbance propagation logic constraints. Based on the simulation results, a multi-dimensional analysis is performed on the multi-source heterogeneous correlation data, and the key business information in the multi-source heterogeneous correlation data is identified based on the analysis results. Based on the analysis of the key business information, the vulnerability points under the disturbance constraints are identified, and a comprehensive profile of the vulnerability points is created. Then, hierarchical decision-making and processing are carried out according to the degree of vulnerability.

[0011] In a preferred embodiment, this application can be further configured as follows: the step of analyzing business vulnerabilities under disturbance constraints based on the key business information, creating a comprehensive profile of the business vulnerabilities, and making hierarchical decisions and handling according to the degree of vulnerability specifically includes: Based on key business information, perform multiple graph index analyses on relevant business nodes in the power grid topology map, and assess the structural vulnerability of the relevant business nodes based on the graph index analysis results. Based on the key business information, determine whether the relevant business nodes are in a critical edge state, and assess the state vulnerability of the relevant business nodes based on the determination result; Calculate the loss load and disturbance recovery time for a specific disturbance event based on the key business information, and assess the functional vulnerability of the relevant business nodes based on the calculation results; A comprehensive profile is created based on the structural vulnerability, the state vulnerability, and the functional vulnerability. The vulnerability level is then graded based on the comprehensive profile results, and hierarchical decision-making and processing are carried out.

[0012] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions: A data processing system for multi-source heterogeneous data fusion and intelligent analysis, the system being applied to the aforementioned data processing method for multi-source heterogeneous data fusion and intelligent analysis, the system comprising: The data preprocessing module is used to acquire multi-source heterogeneous data from the power system, input the multi-source heterogeneous data into a preset data unification model for data preprocessing, and generate multi-source heterogeneous processed data carrying unified data tags. The data association module is used to perform power business analysis on the multi-source heterogeneous processed data, map and associate all multi-source heterogeneous processed data of the same power business, and generate multi-source heterogeneous association data of business association. The model building module is used to obtain the topology of the power system, optimize the topology using historical disturbance events as training samples, analyze the propagation logic of the historical disturbance events, and build a data analysis model. The data analysis module is used to input the multi-source heterogeneous correlation data into the data analysis model to perform dynamic simulation and multi-dimensional analysis of disturbance events, and to identify key business information for business decision-making.

[0013] Thirdly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned data processing method for multi-source heterogeneous data fusion and intelligent analysis.

[0014] Fourthly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned data processing method for multi-source heterogeneous data fusion and intelligent analysis.

[0015] In summary, this application includes at least one of the following beneficial technical effects: 1. This application processes multi-source heterogeneous data through a unified data model, breaks down data silos of different communication protocols or data formats through unified data tags, and achieves cross-source unified management and monitoring of data across the entire process of "source-grid-load-storage", improving data synergy. It also increases the correlation strength between heterogeneous data of the same power business by associating data based on power business, trains the model through the topology of the power system in conjunction with historical disturbance events, optimizes the topology based on the propagation logic of disturbance events, and then builds a data analysis model to improve the intelligence and accuracy of data analysis. It outputs real-world key business data from multi-source heterogeneous correlated data under dynamic simulation of disturbance events, and makes accurate decisions through multi-dimensional analysis and cross-source linkage of information, thereby achieving unified management of multi-source heterogeneous data in the power system. 2. This application extracts knowledge from multi-source heterogeneous data through knowledge graphs, and builds a power topology graph by combining it with the power system topology structure. This facilitates simulation and deduction. The power topology graph is used to simulate historical disturbance events, analyze the power interference logic, control response logic, or hierarchical linkage risk detection logic of each disturbance event, and transform isolated data with information barriers into system-level knowledge with deep correlation and semantics. This constrains the power topology graph, builds an intelligent data analysis model, and improves the rationality and authenticity of the data analysis model. 3. This application uses multi-dimensional analysis of multi-source heterogeneous related data to extract key business information for business vulnerability analysis, including structural vulnerability, state vulnerability and functional vulnerability. Through multi-dimensional comprehensive profiling of business vulnerabilities, hierarchical decision-making and data processing are carried out to improve the orderliness and comprehensiveness of data processing and decision-making. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0017] Figure 1 This is a flowchart illustrating the implementation of the data processing method for multi-source heterogeneous data fusion and intelligent analysis in this embodiment.

[0018] Figure 2 This is a flowchart illustrating the implementation of step S10 of the data processing method for multi-source heterogeneous data fusion and intelligent analysis in this embodiment.

[0019] Figure 3 This is a flowchart illustrating the implementation of step S20 of the data processing method for multi-source heterogeneous data fusion and intelligent analysis in this embodiment.

[0020] Figure 4 This is a flowchart illustrating the implementation of step S30 of the data processing method for multi-source heterogeneous data fusion and intelligent analysis in this embodiment.

[0021] Figure 5 This is a flowchart illustrating step S302 of the data processing method for multi-source heterogeneous data fusion and intelligent analysis in this embodiment.

[0022] Figure 6 This is a flowchart illustrating the implementation of step S40 of the data processing method for multi-source heterogeneous data fusion and intelligent analysis in this embodiment.

[0023] Figure 7 This is a flowchart illustrating step S403 of the data processing method for multi-source heterogeneous data fusion and intelligent analysis in this embodiment.

[0024] Figure 8 This is a structural block diagram of the data processing system for multi-source heterogeneous data fusion and intelligent analysis in this embodiment.

[0025] Figure 9 This is a schematic diagram of the internal structure of a computer device used to realize data processing methods for multi-source heterogeneous data fusion and intelligent analysis. Detailed Implementation

[0026] 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, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0028] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0029] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0030] In one embodiment, such as Figure 1 As shown, this application discloses a data processing method for multi-source heterogeneous data fusion and intelligent analysis, which specifically includes the following steps: S10: Acquire multi-source heterogeneous data from the power system, input the multi-source heterogeneous data into a preset unified data model for data preprocessing, and generate multi-source heterogeneous processed data carrying unified data labels.

[0031] Specifically, such as Figure 2 As shown, step S10 includes: S101: By calling various communication protocols pre-encapsulated in the unified data model, multi-source heterogeneous data is identified to obtain all multi-source heterogeneous data connected to the power system.

[0032] Specifically, multi-source heterogeneous data of the power system is collected through smart meters, sensors, etc., and multi-source heterogeneous data is obtained through SCADA system and PMU system. By calling the common protocol adapted to each heterogeneous data by calling the various communication protocols pre-encapsulated in the unified data model, the information in the heterogeneous data is identified, and all multi-source heterogeneous data connected to the power system is obtained.

[0033] The unified data model encapsulates multiple mainstream industrial protocols such as IEC 61850, IEC 104, Modbus, OPCUA, and MQTT. When multi-source heterogeneous data is input, it performs protocol matching and calls the successfully matched common protocol to receive and identify the multi-source heterogeneous data.

[0034] In this embodiment, the unified data model performs object mapping on all devices connected to the power system, identifies the communication protocol type of the devices and associates them with similar pre-encapsulated communication protocols, generates unique data tags by combining data acquisition time and data source, and associates multi-source heterogeneous data obtained by calling pre-encapsulated communication protocols to unify the multi-source heterogeneous data.

[0035] S102: Extract the data acquisition time and data source of multi-source heterogeneous data, generate unique data labels for multi-source heterogeneous data according to the preset label format, and perform classification and labeling processing on multi-source heterogeneous data.

[0036] Specifically, the data acquisition time and data source ID of the multi-source heterogeneous data are extracted, a unique data label is generated for the multi-source heterogeneous data according to the set label format, the unique data label is associated with the multi-source heterogeneous data, and then classified.

[0037] S103: Using a pre-defined unified data model, extract key information from the classified and labeled multi-source heterogeneous data, and map it to the model's standardized vocabulary for unstructured data transformation, generating multi-source heterogeneous processed data with unified data labels.

[0038] Specifically, by using a pre-defined unified data model to call an NLP (Natural Language Processing) algorithm, key information of key items such as voltage, current, load, temperature, and power are identified in the classified and labeled multi-source heterogeneous data. This information is then mapped to the model's standardized vocabulary, which carries a standardized vocabulary of unified data labels for unstructured data such as images and text, resulting in multi-source heterogeneous processed data with unified data labels.

[0039] S20: Perform power business analysis on multi-source heterogeneous processed data, map and associate all multi-source heterogeneous processed data of the same power business, and generate multi-source heterogeneous associated data of business association.

[0040] Specifically, such as Figure 3 As shown, step S20 includes: S201: Analyze the power business to which the multi-source heterogeneous processing data belongs, and based on the analysis results, aggregate all multi-source heterogeneous processing data belonging to the same power business to construct a multi-source heterogeneous processing data pool for each power business.

[0041] Specifically, the business information in the multi-source heterogeneous processing data is identified, the power business to which the multi-source heterogeneous processing data belongs, such as power transmission, distribution, and substation, is analyzed, all multi-source heterogeneous processing data of the same power business are collected and stored in a temporary multi-source heterogeneous processing data pool for each power business.

[0042] S202: According to the business processing order, perform business scheduling association on the data in the multi-source heterogeneous processing data pool to generate multi-source heterogeneous association data that carries power business tags and has power scheduling association.

[0043] Specifically, according to the business processing order, such as power dispatching order, power transmission order, and power distribution order, the data in the multi-source heterogeneous processing data pool are associated with business scheduling to form multi-source heterogeneous associated data that are related to the business processing order and carry power business tags, such as power dispatch associated data of "correlation between sudden drop in photovoltaic output and wind speed change in the same area", which further increases the correlation between heterogeneous data.

[0044] S30: Obtain the topology of the power system, optimize the topology using historical disturbance events as training samples, analyze the propagation logic of historical disturbance events, and build a data analysis model.

[0045] Specifically, such as Figure 4As shown, step S30 includes: S301: Obtain the equipment entities of the power system and their corresponding connection relationships, construct the topology of the power system with the equipment entities as nodes and the connection relationships as edges, and generate a power grid topology map.

[0046] Specifically, the process involves acquiring physical entities of the power system, such as wind, solar, hydro, and thermal generators, transformers, transmission lines, and energy storage stations, as well as logical entities such as control areas, market entities, and weather systems. It also includes related electrical connections, energy flow relationships, control and response relationships, and geographical location relationships. The power system topology is constructed using these physical entities as nodes and connections as edges. Relevant power knowledge is extracted from each data source using a knowledge graph. For example, various measurement values ​​are extracted from the power grid SCADA system; unit combinations, scheduling plans, and control commands are extracted from the wind, solar, hydro, thermal, and energy storage power station management system; and information such as wind speed, irradiance, and wind and solar power stations is extracted from meteorological stations. This extracted knowledge is then appended to the relevant nodes of the topology to generate a power grid topology graph.

[0047] S302: Obtain historical disturbance events of the power system, simulate the operation of historical disturbance events through the power grid topology map, and analyze the propagation logic of historical disturbance events.

[0048] Specifically, such as Figure 5 As shown, step S302 includes: S3021: During simulation operation, acquire line power flow distribution data and node voltage change data of relevant disturbance nodes, and perform electrical impact analysis of disturbance nodes to obtain the electrical interference logic of historical disturbance events.

[0049] Specifically, during the simulation, route power flow allocation data and node voltage change data of the relevant disturbance nodes corresponding to each historical disturbance event are acquired. Electrical impact analysis is performed through power flow redistribution and voltage change estimation. In this embodiment, route power flow allocation is performed using both DC power flow estimation and AC power flow estimation. When a power deficit occurs at a disturbance node, it indicates the presence of electrical impact. The power angle change of the disturbance node is then calculated using the following formula: (1) in, This represents the power perturbation vector of the perturbed node, and this represents the power deficit of the perturbed node. This represents the Jordan matrix formed by the nodes after filtering out other balancing nodes in the simulation, and its value is the sum of the reciprocals of the reactances of all branches connected to the disturbed node. It represents the change in the work angle.

[0050] The branch power flow change of each branch connected to the disturbance node is calculated using formula (2), as shown in the following formula: (2) in, Indicates the perturbation node With neighboring nodes Branch roads between The change in active power flow. , The nodes are calculated using formula (1). ,node The change in work angle, Indicates a branch The reactance.

[0051] The calculated changes in active power flow are compared with the original power flow without any disturbance events. Overload risk lines that exceed the original power flow are marked, and AC power flow assessment is performed.

[0052] By placing the power grid topology in Apache Spark GraphX ​​or Neo4j and leveraging their parallel graph traversal algorithms, we can quickly identify affected areas and critical paths associated with overload-risk lines. Furthermore, we can rapidly delineate affected areas based on the neighbor subgraphs of the affected areas centered on the disturbance nodes along the critical paths, thus enabling high-voltage power grids to quickly define their impact. (Active-Phase) Characteristics and (Reactive power-voltage) characteristics are used to quickly decouple adjacent subgraphs and obtain adjacent subnets. The affected area is equivalent to (active power, reactive power, voltage). Based on the equivalent data, the AC power flow is evaluated and the voltage change is analyzed by comparing it with the original power when no disturbance event was added. When the power or voltage exceeds the original power or voltage, there is an electrical impact, and the electrical interference logic of historical disturbance events is obtained.

[0053] S3022: Obtain the instruction transmission timing and execution delay during the simulation operation, analyze the control response delay of the actual associated entities in the power topology map, and obtain the control response logic of historical disturbance events.

[0054] Specifically, the system acquires the instruction transmission timing and execution delays of relevant physical equipment during the simulation operation, including the execution of superior scheduling instructions, standby unit scheduling instructions, load adjustment and response instructions, and energy storage scheduling instructions. By comparing the response delay times of similar services and instructions, the system analyzes whether control response delays occur, thereby obtaining the control response logic for historical disturbance events.

[0055] S3023: During the simulation operation, determine whether the relevant disturbance nodes have failed. When a failure occurs, generate new disturbance events to iteratively simulate the power grid topology map and generate hierarchical linkage risk detection logic for historical disturbance events.

[0056] Specifically, during the simulation operation, it is determined whether the relevant disturbance nodes have failed. If the addition of a disturbance event causes other components such as lines and transformers to overload, then a fault has occurred. The relevant data of the fault occurrence is used as a new disturbance event to iteratively simulate the power grid topology map until the overload problem is resolved or no new fault problem occurs. Then, the hierarchical linkage contribution detection logic of historical disturbance events is generated.

[0057] S303: Based on the results of disturbance propagation logic analysis, apply disturbance propagation logic constraints to the power grid topology map and construct a data analysis model.

[0058] Specifically, based on the results of disturbance propagation logic analysis, such as electrical impact, control response, and hierarchical linkage risk detection, disturbance propagation logic constraints are applied to the power grid topology map to construct a data analysis model.

[0059] S40: Input multi-source heterogeneous correlated data into the data analysis model to perform dynamic simulation and multi-dimensional analysis of disturbance events, and link them to identify key business information for business decision-making.

[0060] Specifically, such as Figure 6 As shown, step S40 includes: S401: Input multi-source heterogeneous correlation data into the data analysis model, call the corresponding power grid topology map, and perform dynamic simulation of multi-source heterogeneous correlation data under the corresponding disturbance propagation logic constraints.

[0061] Specifically, multi-source heterogeneous correlation data is input into the data analysis model, the corresponding power grid topology map is called, and cross-source data linkage simulation is carried out under the constraints of disturbance propagation logic.

[0062] S402: Perform multi-dimensional analysis on multi-source heterogeneous correlation data based on simulation results, and identify key business information in the multi-source heterogeneous correlation data based on the analysis results.

[0063] Specifically, based on the simulation results, multi-dimensional analysis of the heterogeneous correlation data of team members is conducted, including trend analysis, capacity analysis, carbon emission analysis, etc. Based on the analysis results, key business information is extracted from the multi-source heterogeneous correlation data, such as equipment load rate, voltage stability margin, frequency response rate, etc.

[0064] S403: Analyze business vulnerabilities under disturbance constraints based on key business information, create a comprehensive profile of these vulnerabilities, and make tiered decisions and take appropriate actions based on their degree of vulnerability.

[0065] Specifically, such as Figure 7 As shown, step S403 includes: S4031: Perform multiple graph index analyses on relevant business nodes in the power grid topology map based on key business information, and assess the structural vulnerability of relevant business nodes based on the graph index analysis results.

[0066] Specifically, based on key business information, the relevant business nodes in the power grid topology are analyzed using multiple graph indicators such as degree centrality, betweenness centrality, and node connectivity. For example, degree centrality is represented by counting the number of other nodes directly connected to a relevant business node; the more connections, the higher the degree. Betweenness is represented by counting the frequency of relevant business nodes on the shortest paths formed by their connected nodes. The importance of the neighboring nodes of relevant business nodes is counted; the more important nodes connected to relevant business nodes, the more important the relevant business node. The structural vulnerability of relevant business nodes is assessed by comprehensively considering the above indicators.

[0067] S4032: Determine whether relevant business nodes are in an edge critical state based on key business information, and assess the state vulnerability of relevant business nodes based on the judgment results.

[0068] Specifically, key business information such as equipment load rate, voltage stability margin, and frequency response rate is obtained to determine whether relevant business nodes are in a critical state. For example, a higher percentage between the real-time power flow and the rated capacity indicates a higher equipment load rate. Voltage stability margin is assessed by using the distance between the peak point of the PV or QV curve and the current operating point to represent the distance between the voltage of the relevant business node and the voltage collapse point. Under high power deficit conditions, the maximum slope or initial rate of change of frequency drop, as well as the lowest point of frequency drop, are used to determine the frequency response rate. Critical states include areas of prolonged high load or insufficient regulation capacity; the closer to the critical state, the higher the vulnerability.

[0069] S4033: Calculate the loss load and disturbance recovery time for a specific disturbance event based on key business information, and assess the functional vulnerability of relevant business nodes based on the calculation results.

[0070] Specifically, based on key business information, the loss load and disturbance recovery time for specific disturbance events such as new energy fluctuations and cascading failures are calculated. The loss load is represented by the sum of the initial disturbance direct loss, the total loss during the cascading failure stage, and the sum of the stability destruction loss. The disturbance recovery time is represented by the sum of the fault isolation time, the action time of all recovery operation switches, and the sum of the synchronous grid connection or charging time when power is restored. The higher the loss load and the longer the disturbance recovery time, the greater the functional vulnerability.

[0071] S4034: Conduct a comprehensive profile based on structural vulnerability, state vulnerability, and functional vulnerability, classify the degree of vulnerability based on the comprehensive profile results, and make hierarchical decisions and take appropriate actions.

[0072] Specifically, structural vulnerability, state vulnerability, and functional vulnerability are associated with corresponding disturbance events and disturbance nodes, and a comprehensive vulnerability profile of the disturbance events is created. Based on the comprehensive vulnerability profile, the vulnerability level is classified. The vulnerability level is the highest when there is high structural centrality, high load rate, and low backup support. These are marked as the highest priority and given priority processing, forming a multi-level hierarchical decision-making system corresponding to the vulnerability level.

[0073] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0074] In one embodiment, a data processing system for multi-source heterogeneous data fusion and intelligent analysis is provided, which corresponds one-to-one with the data processing method for multi-source heterogeneous data fusion and intelligent analysis described in the above embodiments. For example... Figure 8 As shown, this data processing system for multi-source heterogeneous data fusion and intelligent analysis includes a data preprocessing module, a data association module, a model building module, and a data analysis module. Detailed descriptions of each functional module are as follows: The data preprocessing module is used to acquire multi-source heterogeneous data from the power system, input the multi-source heterogeneous data into a preset unified data model for data preprocessing, and generate multi-source heterogeneous processed data carrying unified data labels.

[0075] The data association module is used to perform power business analysis on multi-source heterogeneous processed data, map and associate all multi-source heterogeneous processed data of the same power business, and generate multi-source heterogeneous association data of business association.

[0076] The model building module is used to obtain the topology of the power system, optimize the topology using historical disturbance events as training samples, analyze the propagation logic of historical disturbance events, and build a data analysis model.

[0077] The data analysis module is used to input multi-source heterogeneous correlated data into the data analysis model to perform dynamic simulation and multi-dimensional analysis of disturbance events, and to identify key business information for business decision-making.

[0078] Preferably, the data preprocessing module specifically includes: The data identification submodule is used to identify multi-source heterogeneous data by calling various communication protocols pre-encapsulated in the unified data model, so as to obtain all multi-source heterogeneous data connected to the power system.

[0079] The data tagging submodule is used to extract the data collection time and data source of multi-source heterogeneous data, generate unique data tags for multi-source heterogeneous data according to a preset tag format, and perform classification and tagging processing on multi-source heterogeneous data.

[0080] The data processing submodule is used to extract key information from the classified and labeled multi-source heterogeneous data through a preset unified data model, and map it to the model's standardized vocabulary for unstructured data transformation, generating multi-source heterogeneous processed data with unified data labels.

[0081] Preferably, the data association module specifically includes: The data aggregation submodule is used to analyze the power business to which the multi-source heterogeneous processing data belongs. Based on the analysis results, it aggregates all multi-source heterogeneous processing data belonging to the same power business and constructs a multi-source heterogeneous processing data pool for each power business.

[0082] The business association submodule is used to associate data in the multi-source heterogeneous processing data pool with business scheduling according to the business processing order, and generate multi-source heterogeneous association data with power business tags and power scheduling association.

[0083] Preferably, the model building module specifically includes: The graph construction submodule is used to obtain the equipment entities of the power system and their corresponding connection relationships. It constructs the topology of the power system with the equipment entities as nodes and the connection relationships as edges, and generates a power grid topology graph.

[0084] The logic analysis submodule is used to acquire historical disturbance events of the power system, simulate the operation of historical disturbance events through the power grid topology map, and analyze the propagation logic of historical disturbance events.

[0085] The model building submodule is used to impose disturbance propagation logic constraints on the power grid topology map based on the disturbance propagation logic analysis results, and to build a data analysis model.

[0086] Preferably, the logic analysis submodule specifically includes: The electrical interference analysis unit is used to acquire line power flow distribution data and node voltage change data of relevant disturbance nodes during simulation operation, and to perform electrical impact analysis of disturbance nodes to obtain electrical interference logic of historical disturbance events.

[0087] The control response analysis unit is used to obtain the instruction transmission timing and execution delay during the simulation operation, analyze the control response delay of the actual associated entities in the power topology map, and obtain the control response logic of historical disturbance events.

[0088] The risk detection and analysis unit is used to determine whether relevant disturbance nodes have failed during the simulation operation. When a failure occurs, it generates new disturbance events to iteratively simulate the power grid topology map and generate hierarchical linkage risk detection logic for historical disturbance events.

[0089] Preferably, the data analysis module specifically includes: The data simulation submodule is used to input multi-source heterogeneous correlation data into the data analysis model, call the corresponding power grid topology map, and perform dynamic simulation of multi-source heterogeneous correlation data under the corresponding disturbance propagation logic constraints.

[0090] The information identification submodule is used to perform multi-dimensional analysis on multi-source heterogeneous correlation data based on simulation results, and to identify key business information in the multi-source heterogeneous correlation data based on the analysis results.

[0091] The hierarchical decision-making and processing submodule is used to analyze business vulnerabilities under disturbance constraints based on key business information, create a comprehensive profile of these vulnerabilities, and make hierarchical decisions and processes according to their degree of vulnerability.

[0092] Preferably, the hierarchical decision-making and processing submodule specifically includes: The structural vulnerability analysis unit is used to perform multiple graph index analyses on relevant business nodes in the power grid topology map based on key business information, and to assess the structural vulnerability of relevant business nodes based on the graph index analysis results.

[0093] The state vulnerability analysis unit is used to determine whether relevant business nodes are in an edge critical state based on key business information, and to assess the state vulnerability of relevant business nodes based on the judgment results.

[0094] The functional vulnerability analysis unit is used to calculate the loss load and disturbance recovery time of a specific disturbance event based on key business information, and to assess the functional vulnerability of relevant business nodes based on the calculation results. The hierarchical decision-making and processing unit is used to create a comprehensive profile based on structural vulnerability, state vulnerability, and functional vulnerability, and to classify the degree of vulnerability based on the comprehensive profile results and make hierarchical decisions and processes accordingly.

[0095] Specific limitations regarding the data processing system for multi-source heterogeneous data fusion and intelligent analysis can be found in the limitations of the data processing methods for multi-source heterogeneous data fusion and intelligent analysis described above, and will not be repeated here. Each module in the aforementioned data processing system for multi-source heterogeneous data fusion and intelligent analysis can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0096] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data during the fusion and processing of multi-source heterogeneous data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a data processing method for multi-source heterogeneous data fusion and intelligent analysis.

[0097] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a data processing method for multi-source heterogeneous data fusion and intelligent analysis.

[0098] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application of the technical solution and the constraints involved. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0099] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0100] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the specification of the present invention.

Claims

1. A data processing method for multi-source heterogeneous data fusion and intelligent analysis, characterized in that, The method includes: Acquire multi-source heterogeneous data from the power system, input the multi-source heterogeneous data into a preset unified data model for data preprocessing, and generate multi-source heterogeneous processed data carrying unified data tags; Power business analysis is performed on the multi-source heterogeneous processed data, and all multi-source heterogeneous processed data of the same power business are mapped and associated to generate multi-source heterogeneous associated data of business association. The topology of the power system is obtained, and the topology is optimized using historical disturbance events as training samples. The propagation logic of the historical disturbance events is analyzed, and a data analysis model is constructed. The multi-source heterogeneous correlation data is input into the data analysis model to perform dynamic simulation and multi-dimensional analysis of disturbance events, and to identify key business information for business decision-making.

2. The data processing method for multi-source heterogeneous data fusion and intelligent analysis according to claim 1, characterized in that, The process of acquiring multi-source heterogeneous data from the power system, inputting the multi-source heterogeneous data into a preset unified data model for data preprocessing, and generating multi-source heterogeneous processed data carrying unified data tags specifically includes: By calling various communication protocols pre-encapsulated in the unified data model, the multi-source heterogeneous data is identified to obtain all multi-source heterogeneous data connected to the power system. Extract the data acquisition time and data source of the multi-source heterogeneous data, generate unique data tags for the multi-source heterogeneous data according to a preset tag format, and perform classification and labeling processing on the multi-source heterogeneous data; Using a pre-defined unified data model, key information is extracted from the classified and labeled multi-source heterogeneous data, and mapped to the model's standardized vocabulary for unstructured data transformation, generating multi-source heterogeneous processed data carrying unified data labels.

3. The data processing method for multi-source heterogeneous data fusion and intelligent analysis according to claim 1, characterized in that, The step of performing power business analysis on the multi-source heterogeneous processed data, mapping and associating all multi-source heterogeneous processed data for the same power business to generate multi-source heterogeneous associated data for business association, specifically includes: The power business to which the multi-source heterogeneous processing data belongs is analyzed. Based on the analysis results, all multi-source heterogeneous processing data belonging to the same power business are aggregated to construct a multi-source heterogeneous processing data pool for each power business. According to the business processing order, the data in the multi-source heterogeneous processing data pool are associated with business scheduling to generate multi-source heterogeneous associated data that carries power business tags and has power scheduling association.

4. The data processing method for multi-source heterogeneous data fusion and intelligent analysis according to claim 1, characterized in that, The process of acquiring the power system topology, optimizing the topology using historical disturbance events as training samples, analyzing the propagation logic of the historical disturbance events, and constructing a data analysis model specifically includes: Obtain the equipment entities and their corresponding connection relationships in the power system, construct the topology of the power system with equipment entities as nodes and connection relationships as edges, and generate a power grid topology graph. Historical disturbance events of the power system are acquired, and the historical disturbance events are simulated using the power grid topology map to analyze the propagation logic of the historical disturbance events. Based on the disturbance propagation logic analysis results, disturbance propagation logic constraints are applied to the power grid topology map to construct a data analysis model.

5. The data processing method for multi-source heterogeneous data fusion and intelligent analysis according to claim 4, characterized in that, The acquisition of historical disturbance events in the power system, the simulation of these historical disturbance events using the power grid topology map, and the analysis of the propagation logic of these historical disturbance events specifically include: During the simulation, the line power flow distribution data and node voltage change data of relevant disturbance nodes are acquired, and the electrical impact analysis of the disturbance nodes is performed to obtain the electrical interference logic of historical disturbance events. The timing of instruction transmission and execution delay during the simulation operation are obtained, and the control response delay of the actual associated entities in the power topology map is analyzed to obtain the control response logic of historical disturbance events. During the simulation operation, it is determined whether the relevant disturbance nodes have failed. When a failure occurs, a new disturbance event is generated to iteratively simulate the power grid topology map and generate a hierarchical linkage risk detection logic for historical disturbance events.

6. The data processing method for multi-source heterogeneous data fusion and intelligent analysis according to claim 1, characterized in that, The process of inputting the multi-source heterogeneous correlation data into the data analysis model for dynamic simulation and multi-dimensional analysis of disturbance events, and linking this with the identification of key business information for business decision-making, specifically includes: The multi-source heterogeneous correlation data is input into the data analysis model, the corresponding power grid topology map is called, and the multi-source heterogeneous correlation data is dynamically simulated under the corresponding disturbance propagation logic constraints. Based on the simulation results, a multi-dimensional analysis is performed on the multi-source heterogeneous correlation data, and the key business information in the multi-source heterogeneous correlation data is identified based on the analysis results. Based on the analysis of the key business information, the vulnerability points under the disturbance constraints are identified, and a comprehensive profile of the vulnerability points is created. Then, hierarchical decision-making and processing are carried out according to the degree of vulnerability.

7. The data processing method for multi-source heterogeneous data fusion and intelligent analysis according to claim 6, characterized in that, The process of analyzing business vulnerabilities under disturbance constraints based on the key business information, creating a comprehensive profile of these vulnerabilities, and making tiered decisions and handling based on their vulnerability severity includes: Based on key business information, perform multiple graph index analyses on relevant business nodes in the power grid topology map, and assess the structural vulnerability of the relevant business nodes based on the graph index analysis results. Based on the key business information, determine whether the relevant business nodes are in a critical edge state, and assess the state vulnerability of the relevant business nodes based on the determination result; Calculate the loss load and disturbance recovery time for a specific disturbance event based on the key business information, and assess the functional vulnerability of the relevant business nodes based on the calculation results; A comprehensive profile is created based on the structural vulnerability, the state vulnerability, and the functional vulnerability. The vulnerability level is then graded based on the comprehensive profile results, and hierarchical decision-making and processing are carried out.

8. A data processing system for multi-source heterogeneous data fusion and intelligent analysis, characterized in that, The system includes: The data preprocessing module is used to acquire multi-source heterogeneous data from the power system, input the multi-source heterogeneous data into a preset data unification model for data preprocessing, and generate multi-source heterogeneous processed data carrying unified data tags. The data association module is used to perform power business analysis on the multi-source heterogeneous processed data, map and associate all multi-source heterogeneous processed data of the same power business, and generate multi-source heterogeneous association data of business association. The model building module is used to obtain the topology of the power system, optimize the topology using historical disturbance events as training samples, analyze the propagation logic of the historical disturbance events, and build a data analysis model. The data analysis module is used to input the multi-source heterogeneous correlation data into the data analysis model to perform dynamic simulation and multi-dimensional analysis of disturbance events, and to identify key business information for business decision-making.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the data processing method for multi-source heterogeneous data fusion and intelligent analysis as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the data processing method for multi-source heterogeneous data fusion and intelligent analysis as described in any one of claims 1 to 7.

Images