A power grid service and data deep fusion digital operation method and device

Abstract

The application relates to the technical field of digital operation, and discloses a digital operation method and device for deep fusion of power grid business and data, which comprises the following steps: acquiring multi-source heterogeneous data of a target power grid and performing a data processing operation to obtain a data processing result, constructing a business data association relationship to generate a business data chain; acquiring historical operation data and combining the business data chain to perform a data mining operation, obtaining a data mining result and generating an operation causal relationship; acquiring real-time operation data to determine a real-time operation event, performing an event clustering operation on the real-time operation event based on the real-time operation event and the operation causal relationship to obtain an event clustering result, determining operation strategy parameters, performing corresponding operation operations, and updating and optimizing based on operation results. It can be seen that the application can intelligently collect and analyze power grid data, thereby improving the accuracy and intelligence of power grid data processing, and further improving the operation effect of the power grid and the intelligence of the digital operation of the power grid.

Description

Technical Field

[0001] This invention relates to the field of digital operation technology, and in particular to a digital operation method and apparatus that deeply integrates power grid business with data. Background Technology

[0002] Currently, the construction of digital power grid operations largely relies on equipment such as smart sensors, cameras, and infrared thermal imagers to collect power grid data, followed by manual analysis and decision-making. However, current digital power grid operations still depend on manual decision-making, which is time-consuming and inefficient in data analysis. When a power grid fault occurs, manual location is required, leading to delays in fault handling and ultimately affecting the operational effectiveness of the power grid.

[0003] It is evident that improving the intelligence of digital power grid operation and enhancing the intelligence and reliability of power grid data processing are of paramount importance to improving the operational effectiveness of the power grid. Summary of the Invention

[0004] This invention provides a digital operation method and apparatus for deep integration of power grid business and data, which can intelligently collect and analyze power grid data to improve the accuracy and intelligence of power grid data processing, thereby improving the operation effect of the power grid and the intelligence of the digital operation of the power grid.

[0005] The first aspect of this invention discloses a digital operation method that deeply integrates power grid business with data, the method comprising: Acquire multi-source heterogeneous data of the target power grid, perform data processing operations on the multi-source heterogeneous data, and obtain data processing results; Based on the data processing results, a business data association relationship corresponding to the target power grid is constructed, and a business data chain corresponding to the target power grid is generated according to the data processing results and the business data association relationship. The historical operating data of the target power grid is obtained, and data mining operations are performed on the historical operating data and the business data chain to obtain data mining results. Based on the data mining results, the corresponding operational causal relationship of the target power grid is generated. The real-time operation data of the target power grid is obtained, the real-time operation events of the target power grid are determined, and based on the real-time operation events and the operation causal relationships, an event clustering operation is performed on the real-time operation events to obtain the event clustering results. Based on the event clustering results, the operation strategy parameters of the target power grid are determined, and operation operations matching the operation strategy parameters are performed on the target power grid. Obtain the operational result data corresponding to the target power grid, generate a correlation tracing link based on the operational result data and the operational strategy parameters, and determine the key influencing factors corresponding to the operational strategy parameters based on the correlation tracing link and the operational causal relationship. Based on the key influencing factors, operational optimization parameters are determined, and the operational strategy parameters are updated based on the operational optimization parameters.

[0006] As an optional implementation, in the first aspect of the present invention, before determining the operation strategy parameters of the target power grid based on the event clustering results, the method further includes: Based on the real-time operation data and the historical operation data, a set of power grid operation scenarios for the target power grid is constructed; Based on a pre-defined digital twin algorithm and the set of power grid operation scenarios, an operation simulation model corresponding to the target power grid is constructed. Based on the operation simulation model and the real-time operation data, simulated operation operations are performed on the target power grid to obtain simulated operation results; Based on the simulation operation results, the operational risk event information of the target power grid is determined; The step of determining the operation strategy parameters of the target power grid based on the event clustering results includes: Based on the event clustering results and the operational risk event information, the target operational demand information of the target power grid is determined, and based on the target operational demand information, the operational strategy parameters of the target power grid are determined.

[0007] As an optional implementation, in a first aspect of the invention, the event clustering result includes at least one event cluster, and each event cluster includes at least one power grid operation event; The step of determining the target operational demand information of the target power grid based on the event clustering results and the operational risk event information, and determining the operational strategy parameters of the target power grid based on the target operational demand information, includes: Based on the event clustering results and the operational risk event information, risk association information between the operational risk event information and each event cluster included in the event clustering results is determined, wherein the risk association information includes risk impact scope information and risk impact degree information between the operational risk event information and each event cluster; Based on each of the risk association information, the operational demand category corresponding to the target power grid is determined, and based on the operational demand category, the multi-dimensional demand data corresponding to the target power grid is determined, and the target operational demand information of the target power grid is determined based on all the multi-dimensional demand data, wherein the multi-dimensional demand data includes equipment reliability index data, load dispatch index data, and network security index data; Based on the target operational demand information, calculate the degree of demand matching between the target operational demand information and each operational strategy contained in the pre-determined operational strategy library, and determine the highest degree of demand matching among all the degree of demand matching. Based on the highest demand matching degree, a target matching strategy is determined, and based on the target matching strategy and the target operational demand information, the operational feedback effect is determined, and based on the operational feedback effect, strategy adjustment parameters corresponding to the target matching strategy are generated. Based on the target matching strategy and the strategy adjustment parameters, the operation strategy parameters of the target power grid are determined.

[0008] As an optional implementation, in a first aspect of the present invention, the method further includes: Obtain power grid security event data and power grid attack event data corresponding to the target power grid, and generate event processing relationships corresponding to the target power grid based on the power grid security event data and power grid attack event data; Based on the event processing relationship and the operational risk event information, the risk location information corresponding to the target power grid is determined, and the risk processing parameters of the target power grid are determined based on the risk location information. Based on the risk handling parameters and the operation strategy parameters of the target power grid, a safety handling assessment result for the target power grid is generated, wherein the safety handling assessment result includes a safety level assessment result after performing operation operations on the target power grid that match the operation strategy parameters; Determine whether the security processing assessment result meets the preset security processing conditions; When it is determined that the safety processing assessment result does not meet the preset safety processing conditions, a strategy update parameter for the operation strategy parameter of the target power grid is generated based on the safety processing assessment result and the risk processing parameter, and an update operation is performed on the operation strategy parameter of the target power grid based on the strategy update parameter.

[0009] As an optional implementation, in a first aspect of the present invention, the method further includes: The real-time environmental information corresponding to the target power grid is obtained, and a data coupling operation is performed on the real-time environmental information and the real-time operation data to obtain the data coupling result; wherein, the real-time environmental information includes the real-time environmental meteorological information of the current environment in which the target power grid is located, the power dispatch location distribution information of the current environment, and the power planning information of the current environment; Based on the data coupling results, the real-time operation status of the power grid corresponding to the target power grid is determined, and based on the real-time operation status of the power grid, the operation information of the power grid corresponding to the target power grid is determined. Based on the power grid operation information, the parameters to be scheduled are determined in the current environment, and the scheduling processing parameters corresponding to the target power grid are determined based on the parameters to be scheduled; wherein, the parameters to be scheduled include power grid power scheduling parameters, power grid location scheduling parameters, and power grid frequency scheduling parameters; Based on the scheduling processing parameters, an update processing operation is performed on the operation strategy parameters of the target power grid to update the operation strategy parameters of the target power grid.

[0010] As an optional implementation, in a first aspect of the present invention, determining the parameters to be scheduled in the current environment based on the power grid operation information, and determining the scheduling processing parameters corresponding to the target power grid based on the parameters to be scheduled, includes: Based on the power grid operation information and historical operation data, the predicted operation information of the target power grid in the current environment is determined, wherein the predicted operation information includes the predicted load operation information, predicted power information, predicted current information and predicted voltage information of the target power grid in the current environment within a preset future time period; Abnormal operating parameters are identified from the predicted operating information, and based on the abnormal operating parameters, abnormal operating factors in the target power grid are determined. Based on the abnormal operating factors, scheduling parameters that match the abnormal operating factors are determined. Extract the power grid feature information of the target power grid, wherein the power grid feature information includes the topology feature information, equipment status feature information, and historical scheduling feature information of the target power grid; Based on the parameters to be scheduled and the power grid characteristic information, a multi-dimensional scheduling parameter matching matrix is ​​constructed. By traversing the multi-dimensional scheduling parameter matching matrix, the scheduling processing parameters of the target power grid are determined. The scheduling processing parameters include power allocation coefficient, location priority weight, and frequency regulation rate.

[0011] As an optional implementation, in a first aspect of the present invention, determining the scheduling processing parameters of the target power grid by traversing the multi-dimensional scheduling parameter matching matrix includes: Traverse the multi-dimensional scheduling parameter matching matrix to determine each scheduling processing parameter combination contained in the multi-dimensional scheduling parameter matching matrix, wherein each scheduling processing parameter combination includes at least one sub-scheduling instruction, and each sub-scheduling instruction corresponds to at least one scheduling object in the target power grid; According to the predetermined scheduling priority strategy, a priority sorting operation is performed on each of the scheduling processing parameter combinations contained in the multi-dimensional scheduling parameter matching matrix to obtain the instruction scheduling priority strategy; Based on the scheduling priority strategy and the real-time operation data of the target power grid, a predicted scheduling effect corresponding to the scheduling priority strategy is generated, and it is determined whether the predicted scheduling effect meets the preset predicted scheduling result conditions. When it is determined that the predicted scheduling effect does not meet the preset predicted scheduling result conditions, scheduling operation deviation information is generated, and based on the scheduling operation deviation information, the instruction deviation information corresponding to each sub-scheduling instruction during the execution process is identified; Based on each instruction deviation information, correction parameters for the scheduling priority strategy are generated, and based on the scheduling priority strategy and the correction parameters, scheduling processing parameters for the target power grid are determined.

[0012] A second aspect of this invention discloses a digital operation device that deeply integrates power grid services and data, the device comprising: The acquisition module is used to acquire multi-source heterogeneous data of the target power grid; The processing module is used to perform data processing operations on the multi-source heterogeneous data to obtain data processing results; A construction module is used to construct the business data association relationship corresponding to the target power grid based on the data processing results; The generation module is used to generate the business data chain corresponding to the target power grid based on the data processing results and the business data association relationship; The acquisition module is also used to acquire historical operating data of the target power grid; The mining module is used to perform data mining operations on the historical operational data and the business data chain to obtain data mining results. The generation module is also used to generate the operational causal relationship corresponding to the target power grid based on the data mining results; The acquisition module is also used to acquire real-time operating data of the target power grid; A determination module is used to determine the real-time operational events of the target power grid; The clustering module is used to perform event clustering operations on the real-time operation events based on the real-time operation events and the operation causal relationships, and obtain event clustering results; The determining module is further configured to determine the operation strategy parameters of the target power grid based on the event clustering results; An execution module is used to perform operational operations on the target power grid that match the operational strategy parameters; The acquisition module is also used to acquire the operation result data corresponding to the target power grid; The generation module is also used to generate a related traceability link based on the operation result data and the operation strategy parameters; The determining module is further configured to determine the key influencing factors corresponding to the operational strategy parameters based on the associated tracing link and the operational causal relationship; and to determine operational optimization parameters based on the key influencing factors. The update module is used to update the operation strategy parameters based on the operation optimization parameters.

[0013] As an optional implementation, in a second aspect of the present invention, the construction module is further configured to, before the determining module determines the operation strategy parameters of the target power grid based on the event clustering results, construct a set of power grid operation scenarios for the target power grid based on the real-time operation data and the historical operation data; and construct an operation simulation model corresponding to the target power grid based on a pre-set digital twin algorithm and the set of power grid operation scenarios. The device further includes: The simulation module is used to perform simulated operation operations on the target power grid based on the operation simulation model and the real-time operation data, and obtain simulated operation results; The determining module is further configured to determine the operational risk event information of the target power grid based on the simulated operation results; The specific method by which the determining module determines the operation strategy parameters of the target power grid based on the event clustering results includes: Based on the event clustering results and the operational risk event information, the target operational demand information of the target power grid is determined, and based on the target operational demand information, the operational strategy parameters of the target power grid are determined.

[0014] As an optional implementation, in a second aspect of the invention, the event clustering result includes at least one event cluster, and each event cluster includes at least one power grid operation event; The specific methods by which the determining module determines the target operational demand information of the target power grid based on the event clustering results and the operational risk event information, and determines the operational strategy parameters of the target power grid based on the target operational demand information, include: Based on the event clustering results and the operational risk event information, risk association information between the operational risk event information and each event cluster included in the event clustering results is determined, wherein the risk association information includes risk impact scope information and risk impact degree information between the operational risk event information and each event cluster; Based on each of the risk association information, the operational demand category corresponding to the target power grid is determined, and based on the operational demand category, the multi-dimensional demand data corresponding to the target power grid is determined, and the target operational demand information of the target power grid is determined based on all the multi-dimensional demand data, wherein the multi-dimensional demand data includes equipment reliability index data, load dispatch index data, and network security index data; Based on the target operational demand information, calculate the degree of demand matching between the target operational demand information and each operational strategy contained in the pre-determined operational strategy library, and determine the highest degree of demand matching among all the degree of demand matching. Based on the highest demand matching degree, a target matching strategy is determined, and based on the target matching strategy and the target operational demand information, the operational feedback effect is determined, and based on the operational feedback effect, strategy adjustment parameters corresponding to the target matching strategy are generated. Based on the target matching strategy and the strategy adjustment parameters, the operation strategy parameters of the target power grid are determined.

[0015] As an optional implementation, in a second aspect of the present invention, the acquisition module is further configured to acquire power grid security event data and power grid attack event data corresponding to the target power grid; The generation module is also used to generate the event processing relationship corresponding to the target power grid based on the power grid security event data and the power grid attack event data; The determining module is further configured to determine the risk location information corresponding to the target power grid based on the event processing relationship and the operational risk event information, and to determine the risk processing parameters of the target power grid based on the risk location information; The generation module is further configured to generate a safety processing assessment result for the target power grid based on the risk processing parameters and the operation strategy parameters of the target power grid, wherein the safety processing assessment result includes a safety level assessment result after performing operation operations on the target power grid that match the operation strategy parameters; The device further includes: The judgment module is used to determine whether the security processing evaluation result meets the preset security processing conditions; The generation module is further configured to generate strategy update parameters for the operation strategy parameters of the target power grid based on the safety processing assessment result and the risk processing parameters when the judgment module determines that the safety processing assessment result does not meet the preset safety processing conditions. The update module is further configured to perform update operations on the operation strategy parameters of the target power grid according to the strategy update parameters.

[0016] As an optional implementation, in a second aspect of the present invention, the acquisition module is further configured to acquire real-time environmental information corresponding to the target power grid; The device further includes: The coupling module is used to perform data coupling operations on the real-time environmental information and the real-time operational data to obtain data coupling results; wherein, the real-time environmental information includes the real-time environmental meteorological information of the current environment in which the target power grid is located, the power dispatch location distribution information of the current environment, and the power planning information of the current environment; The determining module is further configured to determine the real-time operation status of the power grid corresponding to the target power grid based on the data coupling result, and determine the power grid operation information corresponding to the target power grid based on the real-time operation status of the power grid; determine the parameters to be scheduled in the current environment based on the power grid operation information, and determine the scheduling processing parameters corresponding to the target power grid based on the parameters to be scheduled; wherein, the parameters to be scheduled include power grid power scheduling parameters, power grid location scheduling parameters, and power grid frequency scheduling parameters; The update module is further configured to perform update processing operations on the operation strategy parameters of the target power grid based on the scheduling processing parameters, so as to update the operation strategy parameters of the target power grid.

[0017] As an optional implementation, in a second aspect of the present invention, the specific method by which the determining module determines the parameters to be scheduled in the current environment based on the power grid operation information, and determines the scheduling processing parameters corresponding to the target power grid based on the parameters to be scheduled includes: Based on the power grid operation information and historical operation data, the predicted operation information of the target power grid in the current environment is determined, wherein the predicted operation information includes the predicted load operation information, predicted power information, predicted current information and predicted voltage information of the target power grid in the current environment within a preset future time period; Abnormal operating parameters are identified from the predicted operating information, and based on the abnormal operating parameters, abnormal operating factors in the target power grid are determined. Based on the abnormal operating factors, scheduling parameters that match the abnormal operating factors are determined. Extract the power grid feature information of the target power grid, wherein the power grid feature information includes the topology feature information, equipment status feature information, and historical scheduling feature information of the target power grid; Based on the parameters to be scheduled and the power grid characteristic information, a multi-dimensional scheduling parameter matching matrix is ​​constructed. By traversing the multi-dimensional scheduling parameter matching matrix, the scheduling processing parameters of the target power grid are determined. The scheduling processing parameters include power allocation coefficient, location priority weight, and frequency regulation rate.

[0018] As an optional implementation, in a second aspect of the present invention, the specific method by which the determining module determines the scheduling processing parameters of the target power grid by traversing the multi-dimensional scheduling parameter matching matrix includes: Traverse the multi-dimensional scheduling parameter matching matrix to determine each scheduling processing parameter combination contained in the multi-dimensional scheduling parameter matching matrix, wherein each scheduling processing parameter combination includes at least one sub-scheduling instruction, and each sub-scheduling instruction corresponds to at least one scheduling object in the target power grid; According to the predetermined scheduling priority strategy, a priority sorting operation is performed on each of the scheduling processing parameter combinations contained in the multi-dimensional scheduling parameter matching matrix to obtain the instruction scheduling priority strategy; Based on the scheduling priority strategy and the real-time operation data of the target power grid, a predicted scheduling effect corresponding to the scheduling priority strategy is generated, and it is determined whether the predicted scheduling effect meets the preset predicted scheduling result conditions. When it is determined that the predicted scheduling effect does not meet the preset predicted scheduling result conditions, scheduling operation deviation information is generated, and based on the scheduling operation deviation information, the instruction deviation information corresponding to each sub-scheduling instruction during the execution process is identified; Based on each instruction deviation information, correction parameters for the scheduling priority strategy are generated, and based on the scheduling priority strategy and the correction parameters, scheduling processing parameters for the target power grid are determined.

[0019] A third aspect of this invention discloses another digital operation device for deep integration of power grid services and data, the device comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the digital operation method for deep integration of power grid business and data as described in any of the first aspects of the present invention.

[0020] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the digital operation method for deep integration of power grid business and data as described in any of the first aspects of the present invention.

[0021] Compared with the prior art, the present invention has the following beneficial effects: In this embodiment of the invention, multi-source heterogeneous data of the target power grid is acquired and data processing operations are performed to obtain data processing results. Business data relationships are constructed to generate business data chains. Historical operational data is acquired and combined with the business data chains to perform data mining operations, obtaining data mining results and generating operational causal relationships. Real-time operational data is acquired to determine real-time operational events. Based on real-time operational events and operational causal relationships, event clustering operations are performed on the real-time operational events to obtain event clustering results, thereby determining operational strategy parameters and executing corresponding operational operations. Updates and optimizations are then performed based on the operational results. Therefore, implementing this invention enables intelligent collection and analysis of power grid data, thereby improving the accuracy and intelligence of power grid data processing, which in turn helps improve the operational efficiency of the power grid and the intelligence of its digital operation. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a digital operation method for deep integration of power grid business and data, as disclosed in an embodiment of the present invention. Figure 2 This is a flowchart illustrating another digital operation method for deep integration of power grid business and data disclosed in an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of a digital operation device that deeply integrates power grid business and data, as disclosed in an embodiment of the present invention. Figure 4 This is a schematic diagram of the structure of another digital operation device for deep integration of power grid business and data disclosed in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of another digital operation device for deep integration of power grid business and data disclosed in an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. 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.

[0025] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0026] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0027] This invention discloses a digital operation method and apparatus for the deep integration of power grid business and data. It enables intelligent collection and analysis of power grid data, thereby improving the accuracy and intelligence of power grid data processing, and ultimately enhancing the operational efficiency and the intelligence of digital power grid operation. Detailed descriptions follow.

[0028] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a digital operation method for deep integration of power grid services and data, as disclosed in an embodiment of the present invention. Figure 1 The described digital operation method that deeply integrates power grid business and data can be applied to a digital operation device that deeply integrates power grid business and data. This device can be integrated into a cloud server or a local server; this embodiment of the invention does not impose limitations. Figure 1 As shown, this digital operation method that deeply integrates power grid business with data can include the following operations: 101. Obtain multi-source heterogeneous data of the target power grid, perform data processing operations on the multi-source heterogeneous data, and obtain the data processing results.

[0029] In this embodiment of the invention, optionally, the acquisition of multi-source heterogeneous data of the target power grid can be obtained through one or more of the following: target sensor, camera, and vision sensor. Further, the multi-source heterogeneous data of the target power grid can include one or more of the following: metering data, meteorological data, load data, power grid equipment data, geographic information data, and user data. Specifically, metering data includes active / reactive power, voltage, current, and electrical energy of each node and line in the target power grid; meteorological data includes wind speed, temperature, humidity, rainfall, and solar radiation intensity; load data includes historical load curves and real-time load forecast data; equipment data includes the model, parameters, health status, and maintenance records of equipment such as transformers, circuit breakers, and cables; geographic information data includes the power grid topology, substation locations, and line corridors; and user data includes a list of important users and historical power outage records.

[0030] In this embodiment of the invention, optional data processing operations may include data cleaning, data integration, and data transformation. Data cleaning may include missing value imputation, outlier identification and correction, and duplicate data removal. Data integration may include merging data from different data sources according to a common identifier. Data transformation may include converting data into a form suitable for analysis. This reduces analytical errors caused by data noise and inconsistency, integrates data scattered across various systems, lays the foundation for global analysis, and ensures comparability and analyzability of data from different sources.

[0031] In this embodiment of the invention, optionally, the data processing result may include the processing result obtained after all multi-source heterogeneous data has undergone data processing operations.

[0032] 102. Based on the data processing results, construct the business data association relationship corresponding to the target power grid, and generate the business data chain corresponding to the target power grid according to the data processing results and the business data association relationship.

[0033] In this embodiment of the invention, optionally, the above-mentioned construction of the business data association relationship corresponding to the target power grid based on the data processing results may include: Based on the data processing results, the correlation dimensions of the target power grid are determined. The correlation dimensions include spatial correlation, temporal correlation, and functional correlation. Spatial correlation includes the physical location of the power grid equipment contained in the target power grid. Temporal correlation includes the chronological order and time interval of events in the target power grid. Functional correlation includes the causal correlation of the power grid equipment. Based on the correlation dimensions of the target power grid, construct the correlation relationships of the business data corresponding to the target power grid.

[0034] In this embodiment of the invention, optionally, the process of generating the business data chain corresponding to the target power grid based on the data processing results and the business data correlation may include: Based on the data processing results and the business data correlation, determine the data chain length and data chain nodes corresponding to the target power grid, and generate the business data chain corresponding to the target power grid based on the data chain length and data chain nodes. The data chain length is determined based on the amount of data corresponding to the data processing results, and the data chain nodes are the key data determined based on the business data relationship and the key data is identified as the data chain nodes.

[0035] 103. Obtain historical operating data of the target power grid, perform data mining operations on the historical operating data and business data chain to obtain data mining results, and generate the corresponding operational causal relationship of the target power grid based on the data mining results.

[0036] In this embodiment of the invention, optionally, the historical operating data of the target power grid may include the target power grid's operating power data, operating status data, operating load data, operating electricity data, equipment health status data, power grid topology data, and power grid line data within a preset historical time period.

[0037] In this embodiment of the invention, optionally, the data mining operation performed on historical operational data and business data chains to obtain data mining results may include: Based on a predetermined data mining algorithm, data mining operations are performed on historical operational data and business data chains to determine the data mining correlation between historical operational data and business data chains, and the data mining results are determined based on the data mining correlation. The pre-determined data mining algorithms include one or more of the following: clustering algorithms (such as DBSCAN), regression analysis methods (such as linear regression and random forest regression), and classification algorithms (such as SVM). DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based clustering algorithm that can discover clusters of arbitrary shapes and automatically identify noise points. SVM (Support Vector Machine) is a powerful supervised learning algorithm mainly used for classification and regression. Its core idea is to find the optimal separating hyperplane that maximizes the margin between different categories.

[0038] In this embodiment of the invention, optionally, the above-mentioned generation of the operational causal relationship corresponding to the target power grid based on data mining results may include: Based on the data mining results, the correlation between each power grid event and the power grid result in the target power grid is determined, and the significance of each event is determined based on the correlation between each power grid event and the power grid result. Target event correlations with significance greater than or equal to a preset threshold are selected from all event significances, and the operational causal relationship corresponding to the target power grid is generated based on all target event correlations. The operational causal relationships corresponding to the target power grid include a list of statistically significant relationships with practical business significance.

[0039] In this embodiment of the invention, the operational causal relationship corresponding to the target power grid may further include subsequent real-time event analysis, strategy generation, fault diagnosis, and other related processes.

[0040] 104. Obtain real-time operation data of the target power grid, determine the real-time operation events of the target power grid, and perform event clustering operation on the real-time operation events based on the real-time operation events and the causal relationship of the operation to obtain the event clustering results.

[0041] In this embodiment of the invention, optionally, the real-time operation data of the target power grid may include real-time electrical operation data, real-time equipment status operation data, and real-time equipment event operation data; wherein, the real-time electrical operation data may include electrical data such as voltage, current, power, and frequency, the real-time equipment status operation data may include equipment data such as equipment switch status and equipment protection action status, and the real-time equipment event operation data may include equipment failure time operation data, equipment failure event operation data, and equipment operation operation data.

[0042] In this embodiment of the invention, optionally, the real-time operational events of the target power grid may include key events identified in the real-time operational data that affect the operating status of the target power grid.

[0043] In this embodiment of the invention, optionally, the above-mentioned event clustering operation based on real-time operational events and operational causal relationships to obtain event clustering results may include: Based on real-time operational events and operational causal relationships, event feature information is extracted for each real-time operational event. The event feature information may include event type features, event occurrence time features, event device features, and event geographical features. Based on the event characteristic information of each real-time operation event and the pre-determined data clustering algorithm, an event clustering operation is performed on the real-time operation events to obtain the event clustering results; The predetermined data clustering algorithms include one or more of the following: K-means clustering algorithm, hierarchical clustering algorithm, and DBSCAN clustering algorithm.

[0044] 105. Based on the event clustering results, determine the operation strategy parameters of the target power grid, and perform operation operations on the target power grid that match the operation strategy parameters.

[0045] In this embodiment of the invention, optionally, the operation strategy parameters of the target power grid may include one or more of the following: operation processing strategy parameters of the target power grid, operation processing area parameters, operation processing operation parameters, and operation processing time parameters.

[0046] 106. Obtain the operational result data corresponding to the target power grid, generate a correlation traceability link based on the operational result data and operational strategy parameters, and determine the key influencing factors corresponding to the operational strategy parameters based on the correlation traceability link and operational causal relationship.

[0047] In this embodiment of the invention, optionally, the operational result data corresponding to the target power grid includes operational result data obtained after performing operational operations on the target power grid that match the operational strategy parameters; wherein, the operational result data may include operational execution record data of the target power grid, power grid operation monitoring data, user feedback data, and fault handling result data.

[0048] In this embodiment of the invention, optionally, the generation of the associated traceability link based on operational result data and operational strategy parameters may include: Based on operational result data and operational strategy parameters, event-strategy correlations are generated. A visual traceability chain diagram is then established based on these relationships, and related traceability chains are generated from this diagram. The event-strategy correlations include the direct correlation between operational result data and specific operational strategy parameters. This allows for the reverse engineering of operational results by leveraging business data correlations and operational causal relationships, tracing back to the executed strategy parameters, and further investigating the root cause of the event. The visual traceability chain diagram clearly displays the logical relationships between events, strategies, operations, and results, clearly demonstrating the complete path from operational results to strategy execution and event occurrence.

[0049] In this embodiment of the invention, optionally, the determination of key influencing factors corresponding to operational strategy parameters based on the associated tracing chain and operational causal relationships may include: Based on the correlation tracing link and operational causal relationship, all factors that may affect the operational results are identified from the correlation tracing link. These factors may include strategy parameter factors, external environmental factors, and equipment status factors. Strategy parameter factors may include strategy execution speed and strategy execution accuracy; external environmental factors may include meteorological environmental factors and load change factors; and equipment status factors may include equipment health status factors. Based on all factors that may affect operational results, identify the key influencing factors corresponding to the operational strategy parameters.

[0050] 107. Based on key influencing factors, determine operational optimization parameters, and update operational strategy parameters based on operational optimization parameters.

[0051] In this embodiment of the invention, optionally, the determination of operational optimization parameters based on key influencing factors may include: Based on key influencing factors, optimization target parameters are determined. Optimization parameters that match the optimization target parameters are then identified from a pre-determined optimization parameter database. Finally, operational optimization parameters are determined based on all optimization parameters. The optimization target parameters may include operational time optimization parameters, operational power optimization parameters, and operational efficiency optimization parameters.

[0052] In this embodiment of the invention, optionally, the above-mentioned updating of operational strategy parameters based on operational optimization parameters may include: comparing the optimized operational strategy parameters with the original parameters to find the differences; or, replacing the original operational strategy parameters with the optimized parameters.

[0053] It is evident that implementation Figure 1The described digital operation method, which deeply integrates power grid operations and data, can acquire multi-source heterogeneous data from the target power grid and perform data processing operations to obtain data processing results, constructing business data relationships to generate business data chains; acquire historical operation data and combine it with business data chains to perform data mining operations, obtaining data mining results and generating operational causal relationships; acquire real-time operation data to determine real-time operation events, and based on real-time operation events and operational causal relationships, perform event clustering operations on real-time operation events to obtain event clustering results, thereby determining operation strategy parameters and executing corresponding operation operations, and updating and optimizing based on operation results. This method can quickly identify and cluster real-time power grid events, automatically match optimal operation strategies, and improve the efficiency and intelligence of generating operation strategy parameters and executing corresponding operation operations. It can also leverage historical data and... Predicting potential faults based on causal relationships improves the accuracy and reliability of generating operational strategy parameters and executing corresponding operational operations, enhances the safety of the target power grid operation, and enables real-time adjustment of strategy parameters based on operational results. This improves the real-time performance and accuracy of power grid operation control. Furthermore, integrating multi-source heterogeneous data for deep data fusion provides a global view and in-depth analysis, further improving the accuracy and reliability of generating operational strategy parameters and executing corresponding operational operations. Through clustered operational strategies, it effectively coordinates the interaction between distributed power sources and the traditional power grid, promoting collaborative optimization of the energy system. Moreover, it enables intelligent collection and analysis of power grid data, improving the accuracy and intelligence of power grid data processing, ultimately enhancing the operational effectiveness of the power grid and the intelligence of its digital operation.

[0054] Example 2 Please see Figure 2 , Figure 2 This is a flowchart illustrating another digital operation method for deep integration of power grid services and data, as disclosed in an embodiment of the present invention. Figure 2 The described digital operation method that deeply integrates power grid business and data can be applied to a digital operation device that deeply integrates power grid business and data. This device can be integrated into a cloud server or a local server; this embodiment of the invention does not impose limitations. Figure 2 As shown, this digital operation method that deeply integrates power grid business with data can include the following operations: 201. Obtain multi-source heterogeneous data of the target power grid, perform data processing operations on the multi-source heterogeneous data, and obtain the data processing results.

[0055] 202. Based on the data processing results, construct the business data association relationship corresponding to the target power grid, and generate the business data chain corresponding to the target power grid according to the data processing results and the business data association relationship.

[0056] 203. Obtain historical operating data of the target power grid, perform data mining operations on the historical operating data and business data chain to obtain data mining results, and generate the corresponding operational causal relationship of the target power grid based on the data mining results.

[0057] 204. Obtain real-time operation data of the target power grid, determine the real-time operation events of the target power grid, and perform event clustering operation on the real-time operation events based on the real-time operation events and the causal relationship of the operation to obtain the event clustering results.

[0058] 205. Based on real-time and historical operational data, construct a set of power grid operation scenarios for the target power grid.

[0059] In this embodiment of the invention, optionally, the above-mentioned set of power grid operation scenarios for the target power grid, constructed based on real-time operation data and historical operation data, may include: Based on real-time and historical operational data, the power grid scenario dimension information of the target power grid is determined. This scenario dimension information can include scenario time dimension information, scenario spatial dimension information, and scenario status dimension information. The scenario time dimension information includes information obtained by extracting timestamps from real-time and historical operational data and grouping them according to a preset granularity. The scenario spatial dimension information includes information obtained by dividing the power grid into different geographical regions based on geographic information system data and constructing the power grid topology based on the equipment connection relationships within the target power grid. The scenario status dimension information can include information obtained by statistically analyzing the average load and maximum load over different time periods from historical load data, as well as extracting the current status of equipment from equipment ledgers and maintenance records. Based on the grid scenario dimension information of the target grid, construct a set of grid operation scenarios for the target grid; The target power grid's set of power grid operation scenarios includes multiple standardized power grid operation scenarios, each with distinct temporal, spatial, and state characteristics.

[0060] 206. Based on the pre-set digital twin algorithm and the set of power grid operation scenarios, construct an operation simulation model corresponding to the target power grid.

[0061] In this embodiment of the invention, optionally, the construction of the operation simulation model corresponding to the target power grid based on a pre-set digital twin algorithm and the set of power grid operation scenarios may include: Based on a pre-defined digital twin algorithm and the set of power grid operation scenarios, modeling parameters corresponding to the target power grid are determined. These modeling parameters include the power grid topology modeling parameters, power grid equipment modeling parameters, and constraint modeling parameters of the template power grid. The power grid topology modeling parameters include virtual topology parameters that match the target power grid. The power grid equipment modeling parameters include modeling parameters identical to those of the power grid equipment in the target power grid, such as transformer capacity and line impedance. The constraint modeling parameters include physical constraints on power grid operation, such as voltage upper and lower limits, current limits, and power factor range. Based on the modeling parameters corresponding to the target power grid, determine the state mapping relationship between the modeling parameters and the target power grid. The state mapping relationship includes the mapping relationship between the target power grid and the virtual model corresponding to the modeling parameters. Based on the state mapping relationship between the modeling parameters and the target power grid, an operation simulation model corresponding to the target power grid is constructed; wherein, the operation simulation model corresponding to the target power grid is a virtual model that can simulate the power grid operation state, and can output corresponding simulation results when different scenario parameters and operation instructions are input.

[0062] 207. Based on the operation simulation model and real-time operation data, perform simulated operation operations on the target power grid and obtain the simulated operation results.

[0063] In this embodiment of the invention, optionally, the above-mentioned process of performing simulated operation operations on the target power grid based on the operation simulation model and real-time operation data to obtain simulated operation results may include: inputting real-time operation data into the operation simulation model, so as to perform simulated operation operations on the real-time operation data through the operation simulation model, and obtaining the simulated operation results corresponding to the target power grid. For example, real-time operation data is input into the operation simulation model to simulate the execution of corresponding operation operations. As needed, external disturbance parameters are injected into the virtual model to simulate the external influences on the power grid, thereby obtaining simulated operation results.

[0064] In this embodiment of the invention, the simulated operation results may further optionally include electrical quantity data (such as bus voltage, line current, active power, reactive power, and frequency), equipment status data (such as equipment operating status and protection device operation status), and safety indicator data (such as voltage qualification rate, current qualification rate, power factor qualification rate, and equipment overload rate).

[0065] 208. Based on the simulation operation results, determine the operational risk event information of the target power grid.

[0066] In this embodiment of the invention, optionally, the determination of operational risk event information of the target power grid based on simulation operation results may include: Based on the simulation operation results, the operation keywords in the simulation operation results are determined, and the operation risk keywords are filtered out from all the operation keywords. The operation events corresponding to the operation risk keywords are identified as the operation risk event information of the target power grid.

[0067] 209. Based on the event clustering results and operational risk event information, determine the target operational demand information of the target power grid, and based on the target operational demand information, determine the operational strategy parameters of the target power grid, and perform operational operations on the target power grid that match the operational strategy parameters.

[0068] In this embodiment of the invention, optionally, the determination of the target operational demand information of the target power grid based on event clustering results and operational risk event information may include: Based on the event clustering results and operational risk event information, the risk problem parameters corresponding to the target power grid are determined. Based on the risk problem parameters, the power grid operation objectives corresponding to the target power grid are determined. Based on the power grid operation objectives, the target operation demand information of the target power grid is determined.

[0069] In this embodiment of the invention, optionally, the above-mentioned determination of the operation strategy parameters of the target power grid based on the target operation demand information, and the execution of operation operations on the target power grid that match the operation strategy parameters, may include: Based on the target operational demand information, target strategy parameters that match the target operational demand information are determined from a pre-determined set of strategy parameters. Based on all target strategy parameters, the operational strategy parameters of the target power grid are determined, and operational operations that match the operational strategy parameters are executed on the target power grid.

[0070] 210. Obtain the operational result data corresponding to the target power grid, generate a correlation traceability link based on the operational result data and operational strategy parameters, and determine the key influencing factors corresponding to the operational strategy parameters based on the correlation traceability link and operational causal relationship.

[0071] 211. Based on key influencing factors, determine the operational optimization parameters, and update the operational strategy parameters based on the operational optimization parameters.

[0072] In this embodiment of the invention, for detailed descriptions of steps 201-204 and 210-211, please refer to the other descriptions of steps 101-104 and 106-107 in Embodiment 1. These descriptions will not be repeated in this embodiment of the invention.

[0073] It is evident that implementation Figure 2The described digital operation method, which deeply integrates power grid operations with data, can construct a set of power grid operation scenarios based on real-time and historical operation data. It then builds an operation simulation model using digital twin algorithms and the set of power grid operation scenarios. Based on the operation simulation model and real-time operation data, it performs simulated operation operations on the target power grid to obtain simulated operation results and identify operational risk event information. Based on event clustering results and operational risk event information, it determines target operational demand information and thus determines the operational strategy parameters of the target power grid. This method systematically covers typical operation modes of the power grid in different periods and environments through multi-dimensional features such as time, space, and state. The operation simulation model can load corresponding power grid operation scenarios based on real-time data, and the simulation results are closer to the actual operating state of the physical power grid. This improves the accuracy and reliability of subsequent determination of operational risk event information and operational strategy parameters. Furthermore, it can also... Operational simulation models can predict potential risk events before actual operations are carried out, making the identification of operational risk events forward-looking and providing early warnings for strategy formulation. This makes the identification of target operational needs more quantifiable and measurable, resulting in more targeted and effective operational strategy parameters. Through the analysis of simulated operational results, the determined operational strategy parameters can more effectively solve current operational problems, thereby improving operational intelligence and efficiency. The set of power grid operation scenarios and operational simulation models can dynamically adapt to the complex operating conditions of the power grid, making strategy formulation more adaptable and flexible. Furthermore, through the analysis and evaluation of simulated operational results, operational strategy parameters can be continuously optimized. This further enables intelligent collection and analysis of power grid data, thereby improving the accuracy and intelligence of power grid data processing, which in turn helps to improve the operational effectiveness of the power grid and the intelligence of its digital operation.

[0074] In an optional embodiment, the event clustering result includes at least one event cluster, and each event cluster includes at least one grid operation event; Specifically, based on event clustering results and operational risk event information, the target operational demand information of the target power grid is determined, and based on the target operational demand information, the operational strategy parameters of the target power grid are determined, including: Based on the event clustering results and operational risk event information, determine the risk association information between the operational risk event information and each event cluster included in the event clustering results. The risk association information includes the risk impact scope information and risk impact degree information between the operational risk event information and each event cluster. Based on each risk-related information, determine the operational demand category corresponding to the target power grid, and based on the operational demand category, determine the multi-dimensional demand data corresponding to the target power grid. Based on all the multi-dimensional demand data, determine the target operational demand information of the target power grid. The multi-dimensional demand data includes equipment reliability index data, load dispatch index data, and network security index data. Based on the target operational needs information, calculate the degree of matching between the target operational needs information and each operational strategy contained in the pre-determined operational strategy library, and determine the highest degree of matching among all the degree of matching. Based on the highest degree of demand matching, a target matching strategy is determined. Based on the target matching strategy and target operational demand information, the operational feedback effect is determined. Based on the operational feedback effect, strategy adjustment parameters corresponding to the target matching strategy are generated. Based on the target matching strategy and strategy adjustment parameters, determine the operating strategy parameters of the target power grid.

[0075] In this optional embodiment, the determination of the risk association information between the operational risk event information and each event cluster included in the event clustering results, based on the event clustering results and the operational risk event information, may include: Based on the event clustering results and operational risk event information, the influence weight corresponding to each dimension is determined. Based on the influence weight corresponding to each dimension, the event clustering results, and the operational risk event information, the risk correlation parameter is calculated, and the risk correlation information between each event cluster is determined according to the risk correlation parameter. The risk impact range information includes the geographical area coverage of each event in the event cluster, and the risk impact degree information includes the severity of the event cluster, the power outage duration caused by the event cluster, and the load loss caused by the event cluster.

[0076] In this optional embodiment, the process of determining the operational demand category corresponding to the target power grid based on each risk association information, determining the multi-dimensional demand data corresponding to the target power grid based on the operational demand category, and determining the target operational demand information of the target power grid based on all multi-dimensional demand data may include: Based on each risk association information, the risk category corresponding to the risk association information is determined, and the operational demand category corresponding to the target power grid is determined based on the risk category; wherein, the operational demand category corresponding to the target power grid may include equipment reliability demand category, load dispatch demand category, and power grid security demand category; Based on the operational demand categories, determine the corresponding power grid indicator demand data for each operational demand category, and then determine the multi-dimensional demand data for the target power grid based on the power grid indicator demand data. Among them, the multi-dimensional demand data for the target power grid includes equipment safety performance requirements, equipment operating status requirements, power grid operating load requirements, power grid capacity requirements, and equipment maintenance requirements. Perform data integration operations on all multi-dimensional demand data corresponding to the target power grid to obtain data integration results, and determine the target operation demand information of the target power grid based on the data integration results; wherein, the target operation demand information of the target power grid may include the specific problems that the power grid needs to solve and the expected goals to be achieved.

[0077] In this optional embodiment, the above-mentioned calculation of the degree of matching between the target operational demand information and each operational strategy included in the pre-determined operational strategy library, based on the target operational demand information, and determining the highest degree of matching among all degree of matching, may include: Based on the target operational needs information, the similarity between the target operational needs information and each operational strategy is calculated. The degree of demand matching between the target operational needs information and each operational strategy in the pre-determined operational strategy library is determined according to the similarity between the target operational needs information and each operational strategy. The highest similarity is determined as the highest degree of demand matching.

[0078] In this optional embodiment, optionally, the process of determining the target matching strategy based on the highest demand matching degree, determining the operational feedback effect based on the target matching strategy and target operational demand information, and generating strategy adjustment parameters corresponding to the target matching strategy based on the operational feedback effect may include: The matching strategy corresponding to the highest degree of demand matching is determined as the target matching strategy. Based on the target matching strategy and the target operational demand information, the predicted effect indicators that the target matching strategy is expected to achieve after execution are calculated. Based on the predicted effect indicators, the operational feedback effect is determined. The operational feedback effect may include strategy execution effect indicators, strategy execution cost effect indicators, and strategy execution time effect indicators. Based on the operational feedback, the original parameters of the target matching strategy are compared with the target operational needs information to obtain the difference parameters. Based on the difference parameters and the operational feedback, the strategy adjustment parameters corresponding to the target matching strategy are generated.

[0079] In this optional embodiment, optionally, for example, if the target operational requirement is "to improve the load transfer success rate" and the original parameter of the target matching strategy is "load transfer ratio of 50%", then the parameter can be adjusted to "load transfer ratio of 70%".

[0080] In this optional embodiment, the above-mentioned determination of the operation strategy parameters of the target power grid based on the target matching strategy and the strategy adjustment parameters may include: combining the original parameters of the target matching strategy with the strategy adjustment parameters to generate the final operation strategy parameters.

[0081] As can be seen, implementing this optional embodiment can determine risk correlation information based on event clustering results and operational risk event information. Based on the risk correlation information, it determines the operational demand category corresponding to the target power grid, thereby determining the multi-dimensional demand data of the target power grid and the target operational demand information. Based on the target operational demand information, it calculates the demand matching degree between each operational strategy included in the pre-determined operational strategy library, selects the strategy with the highest demand matching degree, and determines the target matching strategy. Based on the target matching strategy and the target operational demand information, it determines the operational feedback effect, generates strategy adjustment parameters, and determines the operational strategy parameters of the target power grid. Based on the level of risk correlation, the system can dynamically adjust the priority of operational demands, ensuring that strategy formulation always revolves around the most pressing risks, improving the strategy's targeting. Through multi-dimensional demand data such as equipment reliability, load scheduling, and network security, it is beneficial to improve the determination of multi-dimensional demand data. The system ensures the relevance, accuracy, and reliability of target operational needs information. By introducing multi-dimensional demand data, operational needs information can be quantified and measured, providing a unified standard for subsequent strategy matching and effect evaluation. By calculating the degree of matching between target operational needs information and each strategy in the operational strategy library, the system can select the target matching strategy that best matches the current needs, ensuring the scientific validity and effectiveness of the strategy. By determining the operational feedback effect, the system can dynamically adjust strategy parameters based on actual execution, further optimizing the strategy parameters and improving its execution effect. Based on precise demand matching and parameter adjustment, the strategy can more accurately solve current operational problems, thereby reducing unnecessary operations and improving operational efficiency and intelligence. Furthermore, it can intelligently collect and analyze power grid data, improving the accuracy and intelligence of power grid data processing, which in turn contributes to improving the operational effectiveness of the power grid and the intelligence of its digital operation.

[0082] In another alternative embodiment, the method further includes: Acquire power grid security event data and power grid attack event data corresponding to the target power grid, and generate event processing relationships corresponding to the target power grid based on the power grid security event data and power grid attack event data; Based on event handling relationships and operational risk event information, determine the risk location information corresponding to the target power grid, and based on the risk location information, determine the risk handling parameters of the target power grid; Based on the risk handling parameters and the target power grid's operation strategy parameters, a safety handling assessment result for the target power grid is generated. The safety handling assessment result includes an assessment result of the safety level after performing operation operations on the target power grid that match the operation strategy parameters. Determine whether the safety handling assessment results meet the preset safety handling conditions; When it is determined that the safety handling assessment results do not meet the preset safety handling conditions, the strategy update parameters of the target power grid's operation strategy parameters are generated based on the safety handling assessment results and risk handling parameters, and the operation strategy parameters of the target power grid are updated according to the strategy update parameters.

[0083] In this optional embodiment, the power grid security event data corresponding to the target power grid may include, but is not limited to, information such as timestamps, locations, types, severity, and scope of impact of events such as equipment failures (e.g., line tripping, transformer failures), natural disasters (e.g., lightning strikes, typhoons), human error (e.g., accidental switch contact), and equipment aging; the power grid attack event data corresponding to the target power grid may include, but is not limited to, information such as timestamps, source IPs, destination IPs, attack types, attack methods, and affected systems or devices of events such as hacker attacks, DDoS attacks, malicious code intrusions, and phishing attacks.

[0084] In this optional embodiment, the above-mentioned generation of the event processing relationship corresponding to the target power grid based on power grid security event data and power grid attack event data may include: Based on power grid security incident data and power grid attack incident data, the event correlation dimensions are determined. These dimensions can include temporal correlation, spatial correlation, causal correlation, and impact correlation. Event processing relationships corresponding to the target power grid are then generated based on these correlation dimensions.

[0085] In this optional embodiment, for example, historical data can be analyzed to count the co-occurrence frequency of different event combinations. Combinations with higher frequencies are considered to have causal relationships. Causal inference algorithms (such as Bayesian networks and causal forests) can be used to learn the causal relationships between events from the data. Based on the severity and scope of the events, the influence weight of one event on another event can be calculated.

[0086] In this optional embodiment, the process of determining the risk location information corresponding to the target power grid based on event processing relationships and operational risk event information, and determining the risk processing parameters of the target power grid based on the risk location information, may include: Based on time processing relationships and operational risk event information, the event types in the operational risk event information are matched with the risk source event types in the event processing relationships to obtain the risk location information corresponding to the target power grid; based on the risk location information, the risk handling objectives of the target power grid are determined, and the risk handling parameters of the target power grid are determined according to the risk handling objectives. The risk location information may include risk source location information, risk impact range information, risk occurrence probability information, and risk development trend information; the risk handling parameters of the target power grid may include risk handling objectives, risk handling priorities, risk handling measures, risk handling resources, and risk handling time limits.

[0087] In this optional embodiment, the generation of the safety assessment result for the target power grid based on the risk handling parameters and the target power grid's operational strategy parameters may include: Based on the risk handling parameters and the target power grid's operation strategy parameters, determine the execution results of the target power grid after implementing the risk handling parameters and operation strategy parameters, determine the execution safety level corresponding to the execution results, and generate the target power grid's safety handling assessment results based on the execution safety level.

[0088] In this optional embodiment, the safety assessment results may include the safety level assessment results after performing operational operations on the target power grid that match the operational strategy parameters. Further, the safety level assessment results may include safety status assessment results, equipment health status assessment results, risk mitigation effect assessment results, and safety hazard identification assessment results.

[0089] In this optional embodiment, the determination of whether the security processing assessment result meets the preset security processing conditions may include: Determine whether the security level corresponding to the security handling assessment result is greater than or equal to the preset security level threshold corresponding to the security handling conditions; When the security level corresponding to the security processing assessment result is determined to be greater than or equal to the security level threshold corresponding to the preset security processing conditions, the security processing assessment result is determined to meet the preset security processing conditions; when the security level corresponding to the security processing assessment result is determined to be less than the security level threshold corresponding to the preset security processing conditions, the security processing assessment result is determined to not meet the preset security processing conditions.

[0090] In this optional embodiment, optionally, when it is determined that the safety processing assessment result does not meet the preset safety processing conditions, generating strategy update parameters for the target power grid's operation strategy parameters based on the safety processing assessment result and risk processing parameters, and performing an update operation on the target power grid's operation strategy parameters based on the strategy update parameters, may include: Based on the safety assessment results and risk handling parameters, determine the strategy adjustment information corresponding to the operational strategy parameters. The strategy adjustment information includes the strategy adjustment type, the reason for the strategy adjustment, the basis for the strategy adjustment, the goal of the strategy adjustment, and the scope of the strategy adjustment. Based on the strategy adjustment information, specific problem points in the operation strategy parameters are identified, and strategy update parameters for the target power grid's operation strategy parameters are generated based on these specific problem points. The strategy update parameters for the target power grid's operation strategy parameters include the adjustment type, specific adjusted parameters, adjustment reasons, basis, objectives, and scope of impact. The generated strategy update parameters are applied to the existing operational strategy parameters to form the updated operational strategy parameters.

[0091] In this optional embodiment, it is further possible to terminate the process when the security processing assessment result is determined to meet the preset security processing conditions.

[0092] As can be seen, implementing this optional embodiment can acquire power grid security event data and power grid attack event data corresponding to the target power grid to generate event handling relationships for the target power grid. Based on the event handling relationships and operational risk event information, it determines the risk location information and risk handling parameters for the target power grid. Based on the risk handling parameters and the operational strategy parameters of the target power grid, it generates a security handling assessment result for the target power grid and determines whether it meets the preset security handling conditions. If not, it generates policy update parameters for the operational strategy parameters of the target power grid based on the security handling assessment result and risk handling parameters, and performs update operations on the operational strategy parameters. By integrating power grid security event data and power grid attack event data, it achieves full-dimensional coverage of the power grid. Based on the correlation analysis of event handling relationships and operational risk event information, it can accurately locate risk sources. This precise positioning, including the scope of impact and development trends, makes risk management more targeted, improving its accuracy and reliability. Furthermore, when safety assessments fail to meet preset conditions, it automatically generates strategy update parameters based on the assessment results and risk management parameters, updating operational strategies in real time. This enhances the accuracy, reliability, and real-time performance of risk management. Compared to traditional fixed strategies, the optimized strategies more accurately address current safety hazards. By identifying risks in advance, verifying strategy security, and rapidly optimizing adjustments, it effectively reduces the number of safety incidents and shortens their duration, improving the reliability and safety of the target power grid operation. Furthermore, it enables intelligent data collection and analysis of the power grid, improving the accuracy and intelligence of power grid data processing, ultimately enhancing the operational efficiency and the intelligence of the power grid's digital operation.

[0093] In yet another optional embodiment, the method further includes: The system acquires real-time environmental information corresponding to the target power grid, performs data coupling operations on the real-time environmental information and real-time operational data, and obtains the data coupling result. The real-time environmental information includes real-time meteorological information of the current environment in which the target power grid is located, power dispatch location distribution information of the current environment, and power planning information of the current environment. Based on the data coupling results, the real-time operation status of the target power grid is determined, and based on the real-time operation status of the power grid, the operation information of the target power grid is determined. Based on the power grid operation information, the parameters to be dispatched are determined in the current environment, and the dispatch processing parameters corresponding to the target power grid are determined based on the parameters to be dispatched; among them, the parameters to be dispatched include power grid power dispatch parameters, power grid location dispatch parameters, and power grid frequency dispatch parameters; Based on the scheduling processing parameters, update processing operations are performed on the operating strategy parameters of the target power grid to update the operating strategy parameters of the target power grid.

[0094] In this optional embodiment, the real-time environmental information corresponding to the target power grid may optionally include current environmental meteorological parameters that affect the operation of power grid equipment and load changes. These real-time environmental meteorological information may include temperature, humidity, wind speed, rainfall, snowfall, visibility, lightning activity, and air pressure. The current environmental power dispatch location distribution information may include the spatial distribution and operating status parameters of various dispatch nodes within the current power grid dispatch jurisdiction, supporting the rational allocation of dispatch resources. This includes the location and coverage of the dispatch center, the geographical location and operating status of substations / distribution rooms, the installation location and output status of distributed power sources, and the geographical location and load level of important load users. The current environmental power planning information is the execution status of short-term plans related to power grid operation within the current region, reflecting the phased goals and constraints of power grid operation. This may include short-term load growth plans, temporary equipment maintenance plans, new energy consumption plans, and cross-regional power exchange plans.

[0095] In this optional embodiment, the aforementioned data coupling operation on real-time environmental information and real-time operational data to obtain the data coupling result may include: performing time-related coupling, time-dynamic coupling, and semantic mapping coupling operations on real-time environmental information and real-time operational data to obtain the data coupling result. For example, data association is established based on GIS spatial coordinates. Using the latitude and longitude information of the device, its real-time operational data is bound to the real-time meteorological information of the corresponding region. The association strength is optimized based on time series correlation. For the spatially associated dataset, the Pearson correlation coefficient is used to calculate the time correlation between environmental parameters and operational parameters, establishing semantic association rules for environmental-operational data, supplementing the coupling logic, and combining the three to obtain the data coupling result.

[0096] In this optional embodiment, the above-mentioned determination of the real-time operation status of the target power grid based on the data coupling result, and the determination of the power grid operation information corresponding to the target power grid based on the real-time operation status, may include: Extract key operational information corresponding to the target power grid from the data coupling results, and determine the real-time operation status of the target power grid based on the key operational information corresponding to the target power grid. An information fusion operation is performed on the real-time operation status of the target power grid to obtain the information fusion result, and the power grid operation information corresponding to the target power grid is determined based on the information fusion result. Among them, the power grid operation information corresponding to the target power grid can transform the operation status assessment result into structured key information that can be used for dispatching decisions, and clarify the operation information between the current status, existing problems, and scope of impact.

[0097] In this optional embodiment, the process of determining the parameters to be dispatched in the current environment based on power grid operation information and determining the dispatch processing parameters corresponding to the target power grid based on the parameters to be dispatched may include: Based on power grid operation information, key adjustment targets are identified in the current environment, and corresponding dispatch parameters are determined. These dispatch parameters may include power grid power dispatch parameters, power grid location dispatch parameters, and power grid frequency dispatch parameters. Power grid power dispatch parameters include the active / reactive power allocation parameters that need adjustment to address issues such as load-power mismatch and equipment overload. Power grid location dispatch parameters include the operating status parameters of dispatch nodes (equipment / regions) that need adjustment to optimize the power grid topology and mitigate equipment operating pressure in high-risk areas. Power grid frequency dispatch parameters are used to ensure the system frequency remains within the rated range, preventing equipment damage due to frequency deviations.

[0098] In this optional embodiment, optionally, the above-mentioned update processing operation on the target power grid's operation strategy parameters based on scheduling processing parameters, to update the target power grid's operation strategy parameters, includes: Based on the scheduling processing parameters, operational adjustment parameters that match the scheduling processing parameters are determined from the operational strategy parameters. These operational adjustment parameters are then replaced with the scheduling processing parameters to update the operational strategy parameters of the target power grid. This process transforms the scheduling processing parameters into specific parameters for the operational strategy, completing the strategy update and ensuring that the updated strategy adapts to the current environment and operating status. It also guarantees the security and traceability of the update process.

[0099] As can be seen, implementing this optional embodiment can acquire real-time environmental information corresponding to the target power grid and perform data coupling operations in conjunction with real-time operational data to obtain data coupling results. Based on the data coupling results, the real-time operating status of the power grid is determined, thereby determining the power grid operating information. According to the power grid operating information, the parameters to be dispatched in the current environment are determined, thereby determining the dispatch processing parameters. Based on the dispatch processing parameters, the operating strategy parameters of the target power grid are updated. By coupling real-time environmental meteorological information with operational data, the dispatch processing parameters generated can enable the operating strategy to adjust the load allocation scheme in advance, avoiding equipment overload or resource waste caused by inaccurate load prediction. Furthermore, by coupling real-time meteorological information with distributed power generation operating data, the trend of new energy output changes can be dynamically predicted, generating targeted power dispatch parameters. Furthermore, by coupling current power planning information with real-time operational data, operational strategies can optimize resource allocation while meeting planning objectives. Based on the coupling of power dispatch location distribution information with real-time operational data, dispatch resources and operational needs can be accurately matched. Through the coupling of environmental information and equipment operational data, equipment operation and maintenance strategies can be dynamically adjusted. By coupling and analyzing multi-dimensional environmental information and operational data, the traditional dispatch mode relying on manual experience can be replaced, enabling algorithmic generation of dispatch parameters and automated updating of strategies. This is beneficial for improving the intelligence and efficiency of updating operational strategy parameters and can promote the upgrading of power grid operation to intelligent dispatch, adapting to future power grid development needs. It can further enable intelligent collection and analysis of power grid data, thereby improving the accuracy and intelligence of power grid data processing, which in turn is conducive to improving the operational effectiveness of the power grid and the intelligence of digital operation of the power grid.

[0100] In another optional embodiment, based on grid operation information, the parameters to be scheduled are determined in the current environment, and the scheduling processing parameters corresponding to the target grid are determined based on the parameters to be scheduled, including: Based on power grid operation information and historical operation data, the predicted operation information of the target power grid in the current environment is determined. The predicted operation information includes the predicted load operation information, predicted power information, predicted current information, and predicted voltage information of the target power grid in the current environment within a preset future time period. Abnormal operating parameters are identified from the predicted operating information, and based on the abnormal operating parameters, abnormal operating factors in the target power grid are determined. Then, the scheduling parameters that match the abnormal operating factors are determined. Extract the power grid characteristic information of the target power grid, which includes the topological structure characteristic information, equipment status characteristic information, and historical dispatch characteristic information of the target power grid; Based on the parameters to be scheduled and the power grid characteristic information, a multi-dimensional scheduling parameter matching matrix is ​​constructed. By traversing the multi-dimensional scheduling parameter matching matrix, the scheduling processing parameters of the target power grid are determined. The scheduling processing parameters include power allocation coefficient, location priority weight, and frequency regulation rate.

[0101] In this optional embodiment, the process of determining the predicted operating information of the target power grid in the current environment based on power grid operation information and historical operating data may include: First operational information of the target power grid is extracted based on power grid operation information, and second operational information of the target power grid is extracted based on historical operation data. Operation trend information of the target power grid is generated based on the first and second operational information. Based on the operational trend information, predicted operational information of the target power grid in the current environment is determined. The predicted operational information may include predicted load operational information (total predicted load of the region, predicted load by user type, predicted load of important users, load growth rate), predicted power operational information (predicted output of each power source, predicted power exchange quota between regions, predicted active / reactive power of each line), predicted current operational information (predicted current of each line, predicted load current of each transformer, current overload warning threshold), and predicted voltage information (predicted voltage of each bus, voltage deviation rate, voltage safety threshold).

[0102] In this optional embodiment, the process of identifying abnormal operating parameters from the predicted operating information, determining abnormal operating factors in the target power grid based on these parameters, and determining dispatch parameters matching the abnormal operating factors may include: Each parameter in the predicted operation information is compared with its corresponding safety threshold, and the operation parameters that are lower than the corresponding safety threshold are identified as abnormal operation parameters. Correlation analysis is performed between abnormal operating parameters and other parameters in power grid operation information, real-time environmental information, and predicted operating information to uncover correlations, verify the potential causes uncovered, and determine the abnormal operating factors in the target power grid. Based on the type of abnormal operation factor, match the scheduling parameters that correspond to the type of abnormal operation factor.

[0103] In this optional embodiment, the topological characteristics of the target power grid may include the connection relationship of power grid nodes, line impedance parameters, transformer turns ratio, power grid zoning, distribution and capacity of backup lines / power sources; the equipment status characteristics may include the rated parameters, current health status, predicted remaining lifespan, and maintenance plans of key equipment; and the historical dispatch characteristics may include dispatch measures under similar abnormal scenarios, dispatch parameter values, dispatch effects, and dispatch resource consumption.

[0104] In this optional embodiment, the construction of a multi-dimensional scheduling parameter matching matrix based on the parameters to be scheduled and grid characteristic information may include: Based on the parameters to be scheduled and the power grid characteristic information, several sub-scheduling instructions are determined, and instruction combination operations are performed according to all sub-scheduling instructions to construct a multi-dimensional scheduling parameter matching matrix.

[0105] In this optional embodiment, the power allocation coefficient may include the power allocation ratio between each power source / region to regulate the specific amount of power dispatch; the location priority weight may include the dispatch priority of each power supply region / equipment to determine the order of location dispatch; and the frequency regulation rate may include the output adjustment rate of the frequency regulation equipment to quickly stabilize the power grid frequency.

[0106] In this optional embodiment, the multi-dimensional scheduling parameter matching matrix may optionally include a scheduling parameter dimension and a power grid feature dimension, wherein the scheduling parameter dimension may include power scheduling sub-parameters, location scheduling sub-parameters, and frequency scheduling sub-parameters; and the power grid feature dimension may include topology feature sub-parameters, equipment feature sub-parameters, and historical scheduling feature sub-parameters.

[0107] As can be seen, implementing this optional embodiment can determine predicted operating information and abnormal operating parameters based on power grid operation information and historical operating data, thereby determining abnormal operating factors. Based on the abnormal operating factors, it determines matching parameters to be dispatched, extracts power grid characteristic information of the target power grid, and constructs a multi-dimensional dispatch parameter matching matrix in conjunction with the parameters to be dispatched, determining dispatch processing parameters. It can accurately trace the root cause of anomalies by deriving abnormal operating factors from abnormal operating parameters, thus improving the targeting and accuracy of prevention and control of the target power grid. Furthermore, by integrating power grid characteristic information to construct a multi-dimensional matching matrix, it ensures that parameters are deeply adapted to the actual operating conditions, topology characteristics, and equipment status of the power grid. It can extract power grid topology features and equipment status features, and integrate them into the multi-dimensional matching matrix, thus ensuring... Maintaining the generated scheduling parameters helps improve their intelligence, accuracy, and reliability. Furthermore, by incorporating historical scheduling characteristics, the accuracy of these parameters can be further enhanced. This allows for precise matching of scheduling resources, improving their utilization. Replacing traditional manual experience-based judgment with techniques such as predictive models, association rule mining, and multi-dimensional matrix filtering improves the intelligence and efficiency of generated scheduling parameters. This also drives the upgrade of power grid operations to intelligent scheduling, adapting to future power grid development needs. Additionally, it enables intelligent data collection and analysis of power grid data, improving the accuracy and intelligence of power grid data processing, ultimately enhancing the operational effectiveness and the intelligence of digital power grid operations.

[0108] In yet another optional embodiment, the scheduling processing parameters of the target power grid are determined by traversing a multi-dimensional scheduling parameter matching matrix, including: Traverse the multi-dimensional scheduling parameter matching matrix to determine each scheduling processing parameter combination contained in the multi-dimensional scheduling parameter matching matrix. Each scheduling processing parameter combination includes at least one sub-scheduling instruction, and each sub-scheduling instruction corresponds to at least one scheduling object in the target power grid. Based on the predetermined scheduling priority strategy, a priority sorting operation is performed on each combination of scheduling processing parameters contained in the multi-dimensional scheduling parameter matching matrix to obtain the instruction scheduling priority strategy. Based on the scheduling priority strategy and the real-time operation data of the target power grid, the predicted scheduling effect corresponding to the scheduling priority strategy is generated, and it is determined whether the predicted scheduling effect meets the preset predicted scheduling result conditions. When it is determined that the predicted scheduling effect does not meet the preset predicted scheduling result conditions, scheduling operation deviation information is generated, and based on the scheduling operation deviation information, the instruction deviation information corresponding to each sub-scheduling instruction during the execution process is identified. Based on the deviation information of each instruction, correction parameters for the scheduling priority strategy are generated, and based on the scheduling priority strategy and the correction parameters, the scheduling processing parameters of the target power grid are determined.

[0109] In this optional embodiment, the step of traversing the multi-dimensional scheduling parameter matching matrix to determine each combination of scheduling processing parameters contained in the multi-dimensional scheduling parameter matching matrix may include: The multi-dimensional scheduling parameter matching matrix is ​​traversed sequentially. For each row, the correlation between parameters in each dimension is verified. For valid combinations that pass verification, the values ​​of parameters in each dimension are extracted and organized into structured scheduling processing parameter combinations. This matrix traversal technique allows for the complete extraction of all scheduling processing parameter combinations in the multi-dimensional scheduling parameter matching matrix, clarifying the sub-scheduling instruction composition and corresponding scheduling object of each combination, laying the foundation for subsequent priority ranking. The scheduling processing parameter combination can include a complete scheduling scheme formed by the combination of parameter values ​​in the multi-dimensional matrix, containing all sub-instructions required to achieve the scheduling objective. Sub-scheduling instructions can include the smallest execution unit of the scheduling processing parameter combination, corresponding to a specific scheduling operation, and can be divided into three categories according to scheduling type: power scheduling instructions, location scheduling instructions, and frequency scheduling instructions. The scheduling object can include the execution carrier of the sub-scheduling instructions, i.e., the equipment, area, or system being operated on in the target power grid.

[0110] In this optional embodiment, the above-mentioned priority sorting operation performed on each combination of scheduling processing parameters contained in the multi-dimensional scheduling parameter matching matrix according to a predetermined scheduling priority strategy to obtain the instruction scheduling priority strategy may include: Based on a pre-determined scheduling priority strategy, the instruction weight corresponding to each sub-scheduling instruction contained in each scheduling processing parameter combination is determined. Then, based on the instruction weight corresponding to each sub-scheduling instruction, the parameter combination weight corresponding to each scheduling processing parameter combination is determined. Finally, a priority sorting operation is performed on each scheduling processing parameter combination according to all parameter combination weights to obtain the instruction scheduling priority strategy. Specifically, the higher the parameter combination weight, the higher the instruction scheduling priority; the lower the parameter combination weight, the lower the instruction scheduling priority. This allows for the quantitative scoring and sorting of all valid scheduling processing parameter combinations based on the pre-determined scheduling priority strategy, generating an instruction scheduling priority strategy, clarifying the execution order of each combination, and ensuring that high-priority combinations (such as those ensuring power supply to important users or those with low security risks) are verified and executed first. In this optional embodiment, the process of generating the predicted scheduling effect corresponding to the scheduling priority strategy based on the scheduling priority strategy and the real-time operating data of the target power grid may include: Based on the scheduling priority strategy and the real-time operation data of the target power grid, the power grid operation status after the execution of scheduling instructions is simulated, and the predicted scheduling effect corresponding to the scheduling priority strategy is generated according to the simulated power grid operation status after the execution of scheduling instructions. The predicted scheduling effect can include the predicted scheduling effect of safety indicators and the predicted scheduling effect of economic indicators. The predicted scheduling effect of safety indicators can include the predicted voltage deviation rate, the predicted current overload rate, the predicted frequency deviation, and the satisfaction of safety constraints. The predicted scheduling effect of economic indicators can include the predicted network loss rate, the amount of scheduling resource consumption, and the amount of cost savings.

[0111] In this optional embodiment, determining whether the predicted scheduling effect meets the preset predicted scheduling result conditions may include: comparing each indicator of the predicted scheduling effect with the preset conditions one by one to determine whether they meet the standards. For example, verifying "abnormal parameter correction rate 95% ≥ 90% (meets the standard)", "abnormal handling time 20 minutes ≤ 30 minutes (meets the standard)", and "network loss rate reduction 12% ≥ 10% (meets the standard)"; or, if all preset conditions are met, determining that "the predicted scheduling effect meets the preset conditions", and this combination is a candidate scheduling processing parameter combination; if at least one condition is not met, determining that "the preset conditions are not met", and proceeding to the subsequent deviation correction stage.

[0112] In this optional embodiment, it is further possible to terminate the process when it is determined that the predicted scheduling effect meets the preset predicted scheduling result conditions.

[0113] In this optional embodiment, optionally, when it is determined that the predicted scheduling effect does not meet the preset predicted scheduling result conditions, scheduling operation deviation information is generated, and based on the scheduling operation deviation information, the instruction deviation information corresponding to each sub-scheduling instruction during execution is identified, which may include: Calculate the difference between the predicted scheduling effect and the preset predicted scheduling result conditions, and generate scheduling operation deviation information based on the difference quantification data; Establish the instruction deviation correlation between deviation indicators and sub-scheduling instructions. Based on the instruction deviation correlation and scheduling operation deviation information, identify the instruction deviation information corresponding to each sub-scheduling instruction during execution. The instruction deviation information is the deviation details of the sub-scheduling instruction, which may include the sub-instruction ID, scheduling object, current parameter value, ideal parameter value, deviation amount, and indicators of deviation impact.

[0114] In this optional embodiment, the process of generating correction parameters for the scheduling priority strategy based on each instruction deviation information, and determining the scheduling processing parameters for the target power grid based on the scheduling priority strategy and the correction parameters, may include: Based on the deviation information of each instruction, a compensatory correction value is generated to make the adjusted sub-instruction parameter value close to the ideal value, and the correction parameters of the scheduling priority strategy are generated according to the compensatory correction value. Based on the scheduling priority strategy and correction parameters, the scheduling strategy correction parameters corresponding to the target power grid are determined, and the scheduling processing parameters of the target power grid are determined based on the scheduling strategy correction parameters.

[0115] In this optional embodiment, for example, the sub-scheduling instructions of the original high-priority scheduling processing parameter combination are adjusted based on the correction parameters to obtain the corrected scheduling processing parameter combination. The corrected parameter combination that achieves the prediction effect is determined as the final scheduling processing parameters of the target power grid.

[0116] As can be seen, implementing this optional embodiment can traverse the multi-dimensional scheduling parameter matching matrix to determine each combination of scheduling processing parameters contained in the multi-dimensional scheduling parameter matching matrix, and perform a priority sorting operation on each combination of scheduling processing parameters contained in the multi-dimensional scheduling parameter matching matrix in combination with the scheduling priority strategy to obtain the instruction scheduling priority strategy. Based on the scheduling priority strategy and the real-time operation data of the target power grid, the predicted scheduling effect corresponding to the scheduling priority strategy is generated, and it is judged whether the predicted scheduling effect meets the preset predicted scheduling result conditions. If it does not meet the conditions, scheduling operation deviation information is generated, and based on the scheduling operation deviation information, the instruction deviation information corresponding to each sub-scheduling instruction during the execution process is identified, thereby generating the correction parameters of the scheduling priority strategy. Based on the scheduling priority strategy and the correction parameters, the scheduling processing parameters of the target power grid are determined. It can completely extract all effective scheduling processing parameter combinations that meet the physical constraints of the power grid in the matrix through row-first traversal algorithm combined with dimensional correlation verification, ensuring that no potential optimal solutions are missed, based on the preset scheduling priority strategy. Objectively quantifying and ranking parameter combinations improves the accuracy, reliability, and objectivity of generating scheduling priority strategies. Each scheduling parameter combination explicitly includes sub-scheduling instructions and corresponding scheduling objects, ensuring precise implementation of the scheduling scheme. When the predicted effect does not meet the preset conditions, deviation source analysis can accurately locate the specific sub-scheduling instructions causing the deviation, quickly eliminating potential safety hazards in the scheduling scheme. This enhances the safety and reliability of the target power grid operation. Precise scheduling schemes and deviation corrections avoid resource and equipment losses in traditional scheduling. The entire process uses multi-dimensional matrix data and real-time operational data as input, and algorithms automate the combination extraction, ranking, prediction, and correction. This improves the intelligence and strategy of generating scheduling parameters for the target power grid, promotes the upgrade of power grid operation to intelligent scheduling, adapts to future power grid development needs, and further enables intelligent collection and analysis of power grid data, thereby improving the accuracy and intelligence of power grid data processing. Ultimately, this contributes to improving the operational efficiency of the power grid and the intelligence of its digital operation.

[0117] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a digital operation device that deeply integrates power grid services and data, as disclosed in an embodiment of the present invention. Figure 3 As shown, the digital operation device that deeply integrates power grid operations with data may include: Acquisition module 301 is used to acquire multi-source heterogeneous data of the target power grid; Processing module 302 is used to perform data processing operations on multi-source heterogeneous data and obtain data processing results; Module 303 is used to construct the business data association relationship corresponding to the target power grid based on the data processing results; The generation module 304 is used to generate the business data chain corresponding to the target power grid based on the data processing results and the business data correlation. The acquisition module 301 is also used to acquire historical operating data of the target power grid; The mining module 305 is used to perform data mining operations on historical operational data and business data chains to obtain data mining results. The generation module 304 is also used to generate the operational causal relationship corresponding to the target power grid based on the data mining results; The acquisition module 301 is also used to acquire real-time operational data of the target power grid; Module 306 is used to determine real-time operational events of the target power grid; Clustering module 307 is used to perform event clustering operations on real-time operational events based on real-time operational events and operational causal relationships, and obtain event clustering results; The determination module 306 is also used to determine the operation strategy parameters of the target power grid based on the event clustering results; The execution module 308 is used to perform operational operations on the target power grid that match the operational strategy parameters; The acquisition module 301 is also used to acquire the operation result data corresponding to the target power grid; The generation module 304 is also used to generate related traceability links based on operational result data and operational strategy parameters; The determination module 306 is also used to determine the key influencing factors corresponding to the operational strategy parameters based on the associated tracing links and operational causal relationships; and to determine the operational optimization parameters based on the key influencing factors. Update module 309, used to update operational strategy parameters based on operational optimization parameters.

[0118] It is evident that implementation Figure 3The described device can acquire multi-source heterogeneous data from a target power grid and perform data processing operations to obtain data processing results, construct business data relationships to generate business data chains; acquire historical operational data and combine it with business data chains to perform data mining operations, obtain data mining results and generate operational causal relationships; acquire real-time operational data to determine real-time operational events, and based on real-time operational events and operational causal relationships, perform event clustering operations on real-time operational events to obtain event clustering results, thereby determining operational strategy parameters and executing corresponding operational operations, and updating and optimizing based on operational results. It can quickly identify and cluster real-time power grid events, automatically match optimal operational strategies, improve the efficiency and intelligence of generating operational strategy parameters and executing corresponding operational operations, and also predict potential faults based on historical data and causal relationships. This approach helps improve the accuracy and reliability of generating operational strategy parameters and executing corresponding operational operations, as well as the safety of the target power grid operation. It also enables real-time adjustments to strategy parameters based on operational results, improving the real-time performance and accuracy of power grid operation control. Furthermore, it integrates multi-source heterogeneous data for deep data fusion, providing a global view and in-depth analysis, further enhancing the accuracy and reliability of generating operational strategy parameters and executing corresponding operational operations. Through clustered operational strategies, it effectively coordinates the interaction between distributed power sources and the traditional power grid, promoting collaborative optimization of the energy system. Finally, it enables intelligent collection and analysis of power grid data, improving the accuracy and intelligence of power grid data processing, ultimately enhancing the operational effectiveness and the intelligence of digital power grid operation.

[0119] In an optional embodiment, such as Figure 4 As shown, the construction module 303 is also used to construct a set of power grid operation scenarios for the target power grid based on real-time operation data and historical operation data before the determination module 306 determines the operation strategy parameters of the target power grid based on the event clustering results; and to construct an operation simulation model corresponding to the target power grid based on the pre-set digital twin algorithm and the set of power grid operation scenarios. The device also includes: The simulation module 310 is used to perform simulated operation operations on the target power grid based on the operation simulation model and real-time operation data, and obtain the simulated operation results; The determination module 306 is also used to determine operational risk event information of the target power grid based on the simulation operation results; The specific methods by which the determining module 306 determines the operating strategy parameters of the target power grid based on the event clustering results include: Based on the event clustering results and operational risk event information, the target operational demand information of the target power grid is determined, and based on the target operational demand information, the operational strategy parameters of the target power grid are determined.

[0120] It is evident that implementation Figure 4 The described device can construct a set of power grid operation scenarios based on real-time and historical operational data. It then builds an operation simulation model using a digital twin algorithm and the set of power grid operation scenarios. Based on the operation simulation model and real-time operational data, it performs simulated operation operations on the target power grid to obtain simulated operation results and determine operational risk event information. Based on event clustering results and operational risk event information, it determines target operational demand information and thus determines the operational strategy parameters of the target power grid. It can systematically cover typical operation modes of the power grid in different periods and environments through multi-dimensional features such as time, space, and state. The operation simulation model can load corresponding power grid operation scenarios based on real-time data, and the simulation results are closer to the actual operating state of the physical power grid. This helps improve the accuracy and reliability of subsequent determination of operational risk event information and operational strategy parameters. Furthermore, the operation simulation model can... Predicting potential risk events before actual operation allows for forward-looking identification of operational risk events, providing early warnings for strategy formulation. This makes the identification of target operational needs more quantifiable and measurable, resulting in more targeted and effective operational strategy parameters. Through analysis of simulated operational results, the determined operational strategy parameters can more effectively solve current operational problems, thereby improving operational intelligence and efficiency. The set of power grid operation scenarios and operational simulation models can dynamically adapt to the complex operating conditions of the power grid, making strategy formulation more adaptable and flexible. Furthermore, through analysis and evaluation of simulated operational results, operational strategy parameters can be continuously optimized. This further enables intelligent collection and analysis of power grid data, improving the accuracy and intelligence of power grid data processing, and ultimately enhancing the operational effectiveness and intelligence of power grid digital operation.

[0121] In another alternative embodiment, such as Figure 4 As shown, the event clustering results include at least one event cluster, and each event cluster includes at least one power grid operation event; Specifically, the determination module 306 determines the target operational demand information of the target power grid based on the event clustering results and operational risk event information, and determines the specific methods for determining the operational strategy parameters of the target power grid based on the target operational demand information, including: Based on the event clustering results and operational risk event information, determine the risk association information between the operational risk event information and each event cluster included in the event clustering results. The risk association information includes the risk impact scope information and risk impact degree information between the operational risk event information and each event cluster. Based on each risk-related information, determine the operational demand category corresponding to the target power grid, and based on the operational demand category, determine the multi-dimensional demand data corresponding to the target power grid. Based on all the multi-dimensional demand data, determine the target operational demand information of the target power grid. The multi-dimensional demand data includes equipment reliability index data, load dispatch index data, and network security index data. Based on the target operational needs information, calculate the degree of matching between the target operational needs information and each operational strategy contained in the pre-determined operational strategy library, and determine the highest degree of matching among all the degree of matching. Based on the highest degree of demand matching, a target matching strategy is determined. Based on the target matching strategy and target operational demand information, the operational feedback effect is determined. Based on the operational feedback effect, strategy adjustment parameters corresponding to the target matching strategy are generated. Based on the target matching strategy and strategy adjustment parameters, determine the operating strategy parameters of the target power grid.

[0122] It is evident that implementation Figure 4The described device can determine risk correlation information based on event clustering results and operational risk event information. Based on this risk correlation information, it determines the operational demand category corresponding to the target power grid, thereby determining the multi-dimensional demand data and target operational demand information for the target power grid. It calculates the demand matching degree between each operational strategy in a pre-determined operational strategy library based on the target operational demand information, selects the strategy with the highest demand matching degree, and determines the target matching strategy. Based on the target matching strategy and target operational demand information, it determines the operational feedback effect, generates strategy adjustment parameters, and then determines the operational strategy parameters for the target power grid. The system can dynamically adjust the priority of operational demands based on the degree of risk correlation, ensuring that strategy formulation always revolves around the most pressing risks, thus improving the strategy's relevance. Through multi-dimensional demand data such as equipment reliability, load scheduling, and network security, it helps to improve the determination of multi-dimensional demand data and target... The system ensures the relevance, accuracy, and reliability of operational demand information. By introducing multi-dimensional demand data, this information can be quantified and measured, providing a unified standard for subsequent strategy matching and effect evaluation. Through calculating the degree of matching between the target operational demand information and each strategy in the operational strategy library, the system can select the target matching strategy that best matches the current demand, ensuring the scientific validity and effectiveness of the strategy. By determining the operational feedback effect, the system can dynamically adjust strategy parameters based on actual execution, further optimizing the strategy parameters and improving its execution effect. Based on precise demand matching and parameter adjustment, the strategy can more accurately solve current operational problems, reducing unnecessary operations and improving operational efficiency and intelligence. Furthermore, it enables intelligent collection and analysis of power grid data, improving the accuracy and intelligence of power grid data processing, thereby contributing to improved power grid operational effectiveness and the intelligence of digital power grid operation.

[0123] In yet another alternative embodiment, such as Figure 4 As shown, the acquisition module 301 is also used to acquire power grid security event data and power grid attack event data corresponding to the target power grid; The generation module 304 is also used to generate the event processing relationship corresponding to the target power grid based on power grid security event data and power grid attack event data; The determination module 306 is also used to determine the risk location information corresponding to the target power grid based on the event processing relationship and operational risk event information, and to determine the risk processing parameters of the target power grid based on the risk location information; The generation module 304 is also used to generate a safety processing assessment result of the target power grid based on the risk processing parameters and the operation strategy parameters of the target power grid. The safety processing assessment result includes a safety assessment result after performing operation operations on the target power grid that match the operation strategy parameters. The device also includes: The judgment module 311 is used to determine whether the security processing assessment result meets the preset security processing conditions. The generation module 304 is also used to generate strategy update parameters for the operation strategy parameters of the target power grid based on the safety processing assessment results and risk processing parameters when the judgment module 311 determines that the safety processing assessment results do not meet the preset safety processing conditions. The update module 309 is also used to perform update operations on the operation strategy parameters of the target power grid according to the strategy update parameters.

[0124] It is evident that implementation Figure 4 The described device is capable of acquiring power grid security event data and power grid attack event data corresponding to a target power grid to generate event handling relationships for the target power grid. Based on the event handling relationships and operational risk event information, it determines the risk location information and risk handling parameters for the target power grid. Based on the risk handling parameters and the operational strategy parameters of the target power grid, it generates a security handling assessment result for the target power grid and determines whether it meets preset security handling conditions. If not, it generates policy update parameters for the operational strategy parameters of the target power grid based on the security handling assessment result and risk handling parameters, and performs an update operation on the operational strategy parameters. By integrating power grid security event data and power grid attack event data, it achieves full-dimensional coverage of the power grid. Based on the correlation analysis of event handling relationships and operational risk event information, it can accurately locate risk sources and impacts. This precise positioning, considering the scope and development trend, makes risk management more targeted, improving its accuracy and reliability. Furthermore, when a safety assessment fails to meet preset conditions, it automatically generates strategy update parameters based on the assessment results and risk management parameters, updating operational strategies in real time. This enhances the accuracy, reliability, and real-time performance of risk management. Compared to traditional fixed strategies, the optimized strategies more accurately address current safety hazards. By identifying risks in advance, verifying strategy security, and rapidly optimizing adjustments, it effectively reduces the number of safety incidents and shortens their duration, improving the reliability and safety of the target power grid operation. Moreover, it enables intelligent collection and analysis of power grid data, improving the accuracy and intelligence of power grid data processing, ultimately enhancing the operational efficiency and the intelligence of digital power grid operation.

[0125] In yet another alternative embodiment, such as Figure 4 As shown, the acquisition module 301 is also used to acquire real-time environmental information corresponding to the target power grid; The device also includes: The coupling module 312 is used to perform data coupling operations on real-time environmental information and real-time operational data to obtain data coupling results; wherein, the real-time environmental information includes real-time environmental meteorological information of the current environment in which the target power grid is located, power dispatch location distribution information of the current environment, and power planning information of the current environment; The determination module 306 is also used to determine the real-time operation status of the target power grid based on the data coupling results, and to determine the power grid operation information of the target power grid based on the real-time operation status of the power grid; to determine the parameters to be dispatched in the current environment based on the power grid operation information, and to determine the dispatch processing parameters corresponding to the target power grid based on the parameters to be dispatched; wherein, the parameters to be dispatched include power grid power dispatch parameters, power grid location dispatch parameters, and power grid frequency dispatch parameters; The update module 309 is also used to perform update processing operations on the operation strategy parameters of the target power grid based on the scheduling processing parameters, so as to update the operation strategy parameters of the target power grid.

[0126] It is evident that implementation Figure 4 The described device can acquire real-time environmental information corresponding to the target power grid and perform data coupling operations in conjunction with real-time operational data to obtain data coupling results. Based on the data coupling results, it determines the real-time operating status of the power grid and thus determines the power grid operating information. According to the power grid operating information, it determines the parameters to be dispatched in the current environment and then determines the dispatch processing parameters. Based on the dispatch processing parameters, it performs update processing operations on the operating strategy parameters of the target power grid to update the operating strategy parameters of the target power grid. Through the coupling of real-time environmental meteorological information and operational data, the dispatch processing parameters generated based on this allow the operating strategy to adjust the load allocation scheme in advance, avoiding equipment overload or resource waste caused by inaccurate load prediction. Furthermore, through the coupling of real-time meteorological information and distributed power generation operational data, it can dynamically predict the changing trend of renewable energy output, generate targeted power dispatch parameters, and... The coupling of pre-construction power planning information with real-time operational data allows operational strategies to optimize resource allocation while meeting planning objectives. The coupling of power dispatch location distribution information with real-time operational data enables precise matching of dispatch resources with operational needs. Furthermore, the coupling of environmental information with equipment operational data allows for dynamic adjustment of equipment maintenance strategies. Through multi-dimensional analysis of environmental information and operational data, the traditional dispatch model relying on manual experience can be replaced, enabling algorithmic generation of dispatch parameters and automated strategy updates. This improves the intelligence and efficiency of updating operational strategy parameters and promotes the upgrade of power grid operations to intelligent dispatch, adapting to future power grid development needs. It also enables intelligent collection and analysis of power grid data, improving the accuracy and intelligence of power grid data processing, ultimately enhancing the operational effectiveness and the intelligence of digital power grid operations.

[0127] In yet another alternative embodiment, such as Figure 4 As shown, the specific methods by which the determining module 306 determines the parameters to be scheduled in the current environment based on the power grid operation information, and determines the scheduling processing parameters corresponding to the target power grid based on the parameters to be scheduled, include: Based on power grid operation information and historical operation data, the predicted operation information of the target power grid in the current environment is determined. The predicted operation information includes the predicted load operation information, predicted power information, predicted current information, and predicted voltage information of the target power grid in the current environment within a preset future time period. Abnormal operating parameters are identified from the predicted operating information, and based on the abnormal operating parameters, abnormal operating factors in the target power grid are determined. Then, the scheduling parameters that match the abnormal operating factors are determined. Extract the power grid characteristic information of the target power grid, which includes the topological structure characteristic information, equipment status characteristic information, and historical dispatch characteristic information of the target power grid; Based on the parameters to be scheduled and the power grid characteristic information, a multi-dimensional scheduling parameter matching matrix is ​​constructed. By traversing the multi-dimensional scheduling parameter matching matrix, the scheduling processing parameters of the target power grid are determined. The scheduling processing parameters include power allocation coefficient, location priority weight, and frequency regulation rate.

[0128] It is evident that implementation Figure 4 The described device can determine predicted operating information and identify abnormal operating parameters based on power grid operation information and historical operating data, thereby determining abnormal operating factors. Based on these abnormal operating factors, it determines matching parameters to be dispatched, extracts power grid characteristic information of the target power grid, and constructs a multi-dimensional dispatch parameter matching matrix in conjunction with the parameters to be dispatched, determining dispatch processing parameters. It can accurately trace the root cause of anomalies by deriving abnormal operating factors from abnormal operating parameters, improving the targeting and accuracy of prevention and control of the target power grid. Furthermore, by fusing power grid characteristic information to construct a multi-dimensional matching matrix, it ensures that parameters are deeply adapted to the actual operating conditions, topology characteristics, and equipment status of the power grid. It can extract power grid topology features and equipment status features and integrate them into the multi-dimensional matching matrix, ensuring the generation of... The improved scheduling parameters enhance the intelligence, accuracy, and reliability of generated scheduling parameters. Furthermore, the integration of historical scheduling characteristics further improves the accuracy of generated parameters, enabling precise matching of scheduling resources and increasing their utilization. By employing predictive models, association rule mining, and multi-dimensional matrix filtering techniques to replace traditional manual experience-based judgment, the intelligence and efficiency of generated scheduling parameters are enhanced. This promotes the upgrading of power grid operations towards intelligent scheduling, adapting to future power grid development needs. Additionally, it allows for intelligent data collection and analysis of power grid data, improving the accuracy and intelligence of power grid data processing, ultimately contributing to improved power grid operational efficiency and the intelligence of digital power grid operations.

[0129] In yet another alternative embodiment, such as Figure 4 As shown, the specific method by which module 306 determines the scheduling processing parameters of the target power grid by traversing the multi-dimensional scheduling parameter matching matrix includes: Traverse the multi-dimensional scheduling parameter matching matrix to determine each scheduling processing parameter combination contained in the multi-dimensional scheduling parameter matching matrix. Each scheduling processing parameter combination includes at least one sub-scheduling instruction, and each sub-scheduling instruction corresponds to at least one scheduling object in the target power grid. Based on the predetermined scheduling priority strategy, a priority sorting operation is performed on each combination of scheduling processing parameters contained in the multi-dimensional scheduling parameter matching matrix to obtain the instruction scheduling priority strategy. Based on the scheduling priority strategy and the real-time operation data of the target power grid, the predicted scheduling effect corresponding to the scheduling priority strategy is generated, and it is determined whether the predicted scheduling effect meets the preset predicted scheduling result conditions. When it is determined that the predicted scheduling effect does not meet the preset predicted scheduling result conditions, scheduling operation deviation information is generated, and based on the scheduling operation deviation information, the instruction deviation information corresponding to each sub-scheduling instruction during the execution process is identified. Based on the deviation information of each instruction, correction parameters for the scheduling priority strategy are generated, and based on the scheduling priority strategy and the correction parameters, the scheduling processing parameters of the target power grid are determined.

[0130] It is evident that implementation Figure 4The described device can traverse a multi-dimensional scheduling parameter matching matrix to determine each combination of scheduling processing parameters contained in the matrix. It then performs a priority sorting operation on each combination of scheduling processing parameters in the matrix, combined with a scheduling priority strategy, to obtain an instruction scheduling priority strategy. Based on the scheduling priority strategy and real-time operational data of the target power grid, it generates a predicted scheduling effect corresponding to the scheduling priority strategy and determines whether the predicted scheduling effect meets preset predicted scheduling result conditions. If not, it generates scheduling operation deviation information and, based on this information, identifies the instruction deviation information corresponding to each sub-scheduling instruction during execution, thereby generating correction parameters for the scheduling priority strategy. Finally, based on the scheduling priority strategy and the correction parameters, it determines the scheduling processing parameters of the target power grid. Through a row-first traversal algorithm combined with dimensional correlation verification, it can completely extract all valid scheduling processing parameter combinations in the matrix that conform to the physical constraints of the power grid, ensuring that no potential optimal solutions are overlooked. Based on the preset scheduling priority strategy, it performs parameter sorting... Objectively quantifying and ranking the combined data improves the accuracy, reliability, and objectivity of the generated scheduling priority strategies. Each combination of scheduling parameters explicitly includes sub-scheduling instructions and corresponding scheduling objects, ensuring the precise implementation of the scheduling plan. When the predicted effect does not meet the preset conditions, deviation source analysis can accurately locate the specific sub-scheduling instructions causing the deviation, quickly eliminating potential safety hazards in the scheduling plan. This enhances the safety and reliability of the target power grid operation. Precise scheduling plans and deviation corrections avoid resource and equipment losses in traditional scheduling. The entire process uses multi-dimensional matrix data and real-time operational data as input, and algorithms automate the combined extraction, ranking, prediction, and correction processes. This improves the intelligence and strategy of generating scheduling parameters for the target power grid, promotes the upgrade of power grid operation to intelligent scheduling, adapts to future power grid development needs, and further enables intelligent collection and analysis of power grid data, thereby improving the accuracy and intelligence of power grid data processing. Ultimately, this contributes to improving the operational efficiency and the intelligence of digital power grid operation.

[0131] Example 4 Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a digital operation device that deeply integrates power grid services and data, as disclosed in an embodiment of the present invention. Figure 5 As shown, the digital operation device that deeply integrates power grid operations with data may include: Memory 401 storing executable program code; Processor 402 coupled to memory 401; The processor 402 calls the executable program code stored in the memory 401 to execute some or all of the steps in the digital operation of any power grid business and data deep integration in Embodiment 1 of the present invention.

[0132] Example 5 This invention discloses a computer storage medium storing computer instructions. When these computer instructions are invoked, they are used to execute some or all of the steps in any of the digital operation methods for deep integration of power grid business and data disclosed in Embodiment 1 of this invention.

[0133] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0134] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0135] Finally, it should be noted that the above embodiments are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, 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 of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A digital operation method that deeply integrates power grid business with data, characterized in that, The method includes: Acquire multi-source heterogeneous data of the target power grid, perform data processing operations on the multi-source heterogeneous data, and obtain data processing results; Based on the data processing results, a business data association relationship corresponding to the target power grid is constructed, and a business data chain corresponding to the target power grid is generated according to the data processing results and the business data association relationship. The historical operating data of the target power grid is obtained, and data mining operations are performed on the historical operating data and the business data chain to obtain data mining results. Based on the data mining results, the corresponding operational causal relationship of the target power grid is generated. The real-time operation data of the target power grid is obtained, the real-time operation events of the target power grid are determined, and based on the real-time operation events and the operation causal relationships, an event clustering operation is performed on the real-time operation events to obtain the event clustering results. Based on the event clustering results, the operation strategy parameters of the target power grid are determined, and operation operations matching the operation strategy parameters are performed on the target power grid. Obtain the operational result data corresponding to the target power grid, generate a correlation tracing link based on the operational result data and the operational strategy parameters, and determine the key influencing factors corresponding to the operational strategy parameters based on the correlation tracing link and the operational causal relationship. Based on the key influencing factors, operational optimization parameters are determined, and the operational strategy parameters are updated based on the operational optimization parameters.

2. The digital operation method for deep integration of power grid business and data according to claim 1, characterized in that, Before determining the operation strategy parameters of the target power grid based on the event clustering results, the method further includes: Based on the real-time operation data and the historical operation data, a set of power grid operation scenarios for the target power grid is constructed; Based on a pre-defined digital twin algorithm and the set of power grid operation scenarios, an operation simulation model corresponding to the target power grid is constructed. Based on the operation simulation model and the real-time operation data, simulated operation operations are performed on the target power grid to obtain simulated operation results; Based on the simulation operation results, the operational risk event information of the target power grid is determined; The step of determining the operation strategy parameters of the target power grid based on the event clustering results includes: Based on the event clustering results and the operational risk event information, the target operational demand information of the target power grid is determined, and based on the target operational demand information, the operational strategy parameters of the target power grid are determined.

3. The digital operation method for deep integration of power grid business and data according to claim 2, characterized in that, The event clustering results include at least one event cluster, and each event cluster includes at least one power grid operation event; The step of determining the target operational demand information of the target power grid based on the event clustering results and the operational risk event information, and determining the operational strategy parameters of the target power grid based on the target operational demand information, includes: Based on the event clustering results and the operational risk event information, risk association information between the operational risk event information and each event cluster included in the event clustering results is determined, wherein the risk association information includes risk impact scope information and risk impact degree information between the operational risk event information and each event cluster; Based on each of the risk association information, the operational demand category corresponding to the target power grid is determined, and based on the operational demand category, the multi-dimensional demand data corresponding to the target power grid is determined, and the target operational demand information of the target power grid is determined based on all the multi-dimensional demand data, wherein the multi-dimensional demand data includes equipment reliability index data, load dispatch index data, and network security index data; Based on the target operational demand information, calculate the degree of demand matching between the target operational demand information and each operational strategy contained in the pre-determined operational strategy library, and determine the highest degree of demand matching among all the degree of demand matching. Based on the highest demand matching degree, a target matching strategy is determined, and based on the target matching strategy and the target operational demand information, the operational feedback effect is determined, and based on the operational feedback effect, strategy adjustment parameters corresponding to the target matching strategy are generated. Based on the target matching strategy and the strategy adjustment parameters, the operation strategy parameters of the target power grid are determined.

4. The digital operation method for deep integration of power grid business and data according to claim 2, characterized in that, The method further includes: Obtain power grid security event data and power grid attack event data corresponding to the target power grid, and generate event processing relationships corresponding to the target power grid based on the power grid security event data and power grid attack event data; Based on the event processing relationship and the operational risk event information, the risk location information corresponding to the target power grid is determined, and the risk processing parameters of the target power grid are determined based on the risk location information. Based on the risk handling parameters and the operation strategy parameters of the target power grid, a safety handling assessment result for the target power grid is generated, wherein the safety handling assessment result includes a safety level assessment result after performing operation operations on the target power grid that match the operation strategy parameters; Determine whether the security processing assessment result meets the preset security processing conditions; When it is determined that the safety processing assessment result does not meet the preset safety processing conditions, a strategy update parameter for the operation strategy parameter of the target power grid is generated based on the safety processing assessment result and the risk processing parameter, and an update operation is performed on the operation strategy parameter of the target power grid based on the strategy update parameter.

5. The digital operation method for deep integration of power grid business and data according to claim 1, characterized in that, The method further includes: The real-time environmental information corresponding to the target power grid is obtained, and a data coupling operation is performed on the real-time environmental information and the real-time operation data to obtain the data coupling result; wherein, the real-time environmental information includes the real-time environmental meteorological information of the current environment in which the target power grid is located, the power dispatch location distribution information of the current environment, and the power planning information of the current environment; Based on the data coupling results, the real-time operation status of the target power grid is determined, and based on the real-time operation status of the power grid, the operation information of the target power grid is determined. Based on the power grid operation information, the parameters to be scheduled are determined in the current environment, and the scheduling processing parameters corresponding to the target power grid are determined based on the parameters to be scheduled; wherein, the parameters to be scheduled include power grid power scheduling parameters, power grid location scheduling parameters, and power grid frequency scheduling parameters; Based on the scheduling processing parameters, an update processing operation is performed on the operation strategy parameters of the target power grid to update the operation strategy parameters of the target power grid.

6. The digital operation method for deep integration of power grid business and data according to claim 5, characterized in that, The step of determining the parameters to be scheduled in the current environment based on the power grid operation information, and determining the scheduling processing parameters corresponding to the target power grid based on the parameters to be scheduled, includes: Based on the power grid operation information and historical operation data, the predicted operation information of the target power grid in the current environment is determined, wherein the predicted operation information includes the predicted load operation information, predicted power information, predicted current information and predicted voltage information of the target power grid in the current environment within a preset future time period; Abnormal operating parameters are identified from the predicted operating information, and based on the abnormal operating parameters, abnormal operating factors in the target power grid are determined. Based on the abnormal operating factors, scheduling parameters that match the abnormal operating factors are determined. Extract the power grid feature information of the target power grid, wherein the power grid feature information includes the topology feature information, equipment status feature information, and historical scheduling feature information of the target power grid; Based on the parameters to be scheduled and the power grid characteristic information, a multi-dimensional scheduling parameter matching matrix is ​​constructed. By traversing the multi-dimensional scheduling parameter matching matrix, the scheduling processing parameters of the target power grid are determined. The scheduling processing parameters include power allocation coefficient, location priority weight, and frequency regulation rate.

7. The digital operation method for deep integration of power grid business and data according to claim 6, characterized in that, The step of determining the scheduling processing parameters of the target power grid by traversing the multi-dimensional scheduling parameter matching matrix includes: Traverse the multi-dimensional scheduling parameter matching matrix to determine each scheduling processing parameter combination contained in the multi-dimensional scheduling parameter matching matrix, wherein each scheduling processing parameter combination includes at least one sub-scheduling instruction, and each sub-scheduling instruction corresponds to at least one scheduling object in the target power grid; According to the predetermined scheduling priority strategy, a priority sorting operation is performed on each of the scheduling processing parameter combinations contained in the multi-dimensional scheduling parameter matching matrix to obtain the instruction scheduling priority strategy; Based on the scheduling priority strategy and the real-time operation data of the target power grid, a predicted scheduling effect corresponding to the scheduling priority strategy is generated, and it is determined whether the predicted scheduling effect meets the preset predicted scheduling result conditions. When it is determined that the predicted scheduling effect does not meet the preset predicted scheduling result conditions, scheduling operation deviation information is generated, and based on the scheduling operation deviation information, the instruction deviation information corresponding to each sub-scheduling instruction during the execution process is identified; Based on each instruction deviation information, correction parameters for the scheduling priority strategy are generated, and based on the scheduling priority strategy and the correction parameters, scheduling processing parameters for the target power grid are determined.

8. A digital operation device that deeply integrates power grid business and data, characterized in that, The device includes: The acquisition module is used to acquire multi-source heterogeneous data of the target power grid; The processing module is used to perform data processing operations on the multi-source heterogeneous data to obtain data processing results; A construction module is used to construct the business data association relationship corresponding to the target power grid based on the data processing results; The generation module is used to generate the business data chain corresponding to the target power grid based on the data processing results and the business data association relationship; The acquisition module is also used to acquire historical operating data of the target power grid; The mining module is used to perform data mining operations on the historical operational data and the business data chain to obtain data mining results. The generation module is also used to generate the operational causal relationship corresponding to the target power grid based on the data mining results; The acquisition module is also used to acquire real-time operating data of the target power grid; A determination module is used to determine the real-time operational events of the target power grid; The clustering module is used to perform event clustering operations on the real-time operation events based on the real-time operation events and the operation causal relationships, and obtain event clustering results; The determining module is further configured to determine the operation strategy parameters of the target power grid based on the event clustering results; An execution module is used to perform operational operations on the target power grid that match the operational strategy parameters; The acquisition module is also used to acquire the operation result data corresponding to the target power grid; The generation module is also used to generate a related traceability link based on the operation result data and the operation strategy parameters; The determining module is further configured to determine the key influencing factors corresponding to the operational strategy parameters based on the associated tracing link and the operational causal relationship; and to determine operational optimization parameters based on the key influencing factors. The update module is used to update the operation strategy parameters based on the operation optimization parameters.

9. A digital operation device that deeply integrates power grid business and data, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the digital operation method for deep integration of power grid business and data as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the digital operation method for deep integration of power grid business and data as described in any one of claims 1-7.

Images