Power network data driving optimization method and system based on dynamic authority modeling

Abstract

The invention relates to the technical field of data analysis, and provides a power network data-driven optimization method and system based on dynamic authority modeling, which are used for improving the self-adaptability and anti-risk capability of a power network in a complex operation environment. The method comprises the steps of obtaining a power network operation data set, performing dynamic permission modeling processing on the power network operation data set, generating a user permission feature set and an equipment permission feature set, and generating a power resource dynamic allocation strategy according to the user permission feature set and the equipment permission feature set, and feeding back the power resource dynamic allocation strategy to the power network control system to activate a permission configuration updating operation. Therefore, through deep coupling of the permission model and resource scheduling, a technical path giving consideration to both elasticity and reliability is provided for intelligent upgrading of a power system, so that the self-adaptability and anti-risk capability of a power network in a complex operation environment can be improved.

Description

Technical Field

[0001] The present application belongs to the field of data analysis technology, and specifically relates to a data-driven optimization method and system for power networks based on dynamic authority modeling. Background Art

[0002] With the expansion of power grids and the widespread integration of distributed energy resources, real-time identification and precise control of power system operating status have become core requirements for ensuring safe and stable grid operation. Traditional power network status identification technologies primarily rely on device sensor data collection and static topology analysis, using threshold alarms and pre-set rules to achieve anomaly detection and resource scheduling. However, in the new power system environment, the complexity of user-side interactions has increased dramatically, and devices are frequently dynamically connected. Existing technologies struggle to effectively address the real-time correlation analysis and dynamic decision-making requirements of multi-dimensional, heterogeneous data.

[0003] Current technologies have the following limitations: First, the permission management mechanism and resource scheduling logic are separated from each other. User operation permissions are usually set based on fixed role templates and cannot be dynamically adjusted according to real-time network status (such as load fluctuations and equipment failures), resulting in frequent permission overload or resource allocation conflicts. Second, existing resource allocation strategies mostly rely on offline simulation or historical experience configuration, lack the ability to collaboratively model user behavior patterns and equipment operating status, and it is difficult to quickly generate the optimal scheduling path when the topology structure changes dynamically. Third, permission configuration updates lag behind changes in the operating status of the power grid. The traditional batch update mechanism results in a long policy implementation cycle, which cannot meet the dual needs of security protection and resource optimization in high-real-time scenarios.

[0004] Therefore, existing technologies struggle to dynamically adapt user permissions, device resources, and network operating status. This is especially true when responding to sudden load migrations or security threats, which can lead to policy rigidity and response delays. Therefore, a technical solution is urgently needed to improve the adaptability and risk resilience of power networks in complex operating environments. Summary of the Invention

[0005] The present application provides a data-driven optimization method and system for power networks based on dynamic authority modeling, which is used to improve the adaptability and risk resistance of power networks in complex operating environments.

[0006] In the first aspect, an embodiment of the present application provides a power network data-driven optimization method based on dynamic authority modeling, which is applied to a power network data-driven optimization system, and the method includes: obtaining a power network operation data set, wherein the power network operation data set includes real-time device status data, user operation behavior logs and network topology connection relationships; performing dynamic authority modeling processing on the power network operation data set to generate a user authority feature set and a device authority feature set; the user authority feature set represents the access control parameters of different user roles to power resources, and the device authority feature set represents the resource allocation permissions of different power equipment in the operating environment; based on the user authority feature set and the device authority feature set, a power resource dynamic allocation strategy is generated; the power resource dynamic allocation strategy is used to adjust the load balancing path and device control priority in the power network; the power resource dynamic allocation strategy is fed back to the power network control system to activate the authority configuration update operation, and the authority configuration update operation includes adjusting the user operation authority range and the resource response rules of the power equipment.

[0007] In a second aspect, an embodiment of the present application provides a power network data-driven optimization system, which includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0008] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program runs on a power network data-driven optimization system, the computer program is used to enable the power network data-driven optimization system to execute the steps of the above method.

[0009] In the implementation of this application, the flexibility and security response capability of power network resource management are significantly improved through dynamic permission modeling and data-driven optimization mechanism. First, based on the multi-dimensional data fusion analysis of real-time device status, user operation behavior and network topology relationship, a user permission feature set and a device permission feature set are constructed to accurately characterize the minimum access requirements of users with different roles and the dynamic boundaries of device resource allocation, thereby avoiding the disadvantages of over-authorization or insufficient authority under traditional fixed permission rules. Secondly, through dynamic allocation strategy generation and processing, user permission features and device permission features are collaboratively mapped, load balancing paths and device control priorities are optimized in real time, ensuring that the power network quickly matches the optimal resource scheduling solution in high-concurrency operations or sudden failure scenarios. For example, when user operation permissions are dynamically reduced, the system can simultaneously increase the resource response weight of key devices, preventing the risk of unauthorized operations while maintaining core business continuity. In addition, through the real-time feedback mechanism of permission configuration update operations, the system can actively adapt to changes in the power grid operating environment (such as new equipment, topology reconstruction or security threat escalation), so that permission rules and resource allocation strategies are always consistent, thereby improving the efficiency of power network operation while achieving a transition from passive response to active prediction of security protection. Therefore, through the deep coupling of the authority model and resource scheduling, a technical path that takes into account both flexibility and reliability is provided for the intelligent upgrade of the power system, which can enhance the adaptability and risk resistance of the power network in complex operating environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of a power network data-driven optimization method based on dynamic authority modeling provided in an embodiment of the present application.

[0011] Figure 2 A schematic diagram of the structure of a power network data-driven optimization system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] See also Figure 1 , which is a power network data-driven optimization method based on dynamic authority modeling provided in an embodiment of the present application. This method can be applied to a power network data-driven optimization system. The specific process is as follows: step S110 to step S140.

[0013] Step S110: Acquire a power network operation data set, wherein the power network operation data set includes real-time device status data, user operation behavior logs, and network topology connection relationships.

[0014] In the application scenario of a large-scale power grid system involved in the embodiments of this application, the large-scale power grid system includes numerous different types of widely distributed power equipment. Real-time equipment status data details the operating parameters of various types of equipment. For example, generator A has an output power of 600 MW, a voltage of 230 kV, a frequency of 50 Hz, and an internal temperature of 58°C. Transformer B has a ratio of 110 / 10 kV, a load factor of 75%, and an oil temperature of 48°C. These parameters change in real time as the equipment operates.

[0015] Optionally, the user operation behavior log details the operations performed by different user roles on power equipment. For example, at 10:00 AM, operator C adjusted the power of generator A from 550 MW to 600 MW. At 2:00 PM, dispatcher D issued a command to adjust the tap of transformer B to optimize voltage distribution. The log precisely records information such as the operation type, operation time, and operator role, comprehensively reflecting the interaction between users and power equipment.

[0016] Optionally, the network topology clearly illustrates the physical connections between various devices in the power network. For example, generator A is connected to transformer B via transmission line L1, and transformer B is connected to multiple distribution nodes via transmission line L2. This connection clearly defines the path and direction of power transmission, providing a foundational framework for subsequent analysis and control. By comprehensively acquiring this data, the operational status of the power network can be fully visualized, providing rich and accurate data support for subsequent dynamic permission modeling and resource allocation strategy formulation.

[0017] Step S120: Dynamic permission modeling is performed on the power network operation data set to generate a user permission feature set and a device permission feature set; the user permission feature set represents the access control parameters of different user roles to power resources, and the device permission feature set represents the resource allocation permissions of different power equipment in the operating environment.

[0018] In one implementation, the step S120 of performing dynamic authority modeling on the power network operation data set to generate a user authority feature set and a device authority feature set includes:

[0019] Step S121: extracting an operation type sequence and an operation timestamp sequence from the user operation behavior log, wherein the operation type sequence includes the control instruction type of the user role on the power equipment and the corresponding operation times.

[0020] In an embodiment of the present application, the operation type sequence and the operation timestamp sequence are extracted based on the information recorded in the user operation behavior log. For example, with respect to the operation records of operation and maintenance personnel C, in the logs of the past week, three power increase instructions, two power reduction instructions, and four equipment status check instructions were executed on generator A; one tap adjustment instruction and three equipment maintenance instructions were executed on transformer B. These instruction types and their corresponding number of operations constitute an operation type sequence. At the same time, the specific time at which each operation occurs is recorded, such as the first power increase instruction for generator A was executed at 9 am on Monday, the second was executed at 3 pm on Tuesday, etc. These specific times form an operation timestamp sequence. Through the above-mentioned extraction method, it is possible to clearly understand the user's operation status on different power equipment at different times, and provide a detailed data basis for the subsequent generation of a dynamic evolution map of user permissions.

[0021] Step S122: Generate a user authority dynamic evolution map based on the operation type sequence and the operation timestamp sequence; the user authority dynamic evolution map includes a trajectory of operation authority changes of the user role within a preset time window.

[0022] Optionally, generating a user authority dynamic evolution graph based on the operation type sequence and the operation timestamp sequence in step S122 includes:

[0023] Step S1221: perform permission impact assessment on the operation type sequence, calculate the probability of different operation types triggering permission adjustment in historical permission change records, and determine the impact weight of each operation type on user permission change.

[0024] In an embodiment of the present application, the authority impact of each operation in the operation type sequence can be evaluated in combination with historical authority change records. For example, based on historical records, it can be seen that in the past 100 power boost operations, 30 triggered authority adjustments, so the probability of the power boost operation triggering authority adjustments is 30%; and the device status check operation has only triggered authority adjustments 20 times in the past 200 executions, with a trigger probability of 10%. Based on the above probabilities, a higher influence weight is assigned to the power boost operation, for example, set to 0.6; and a lower influence weight is assigned to the device status check operation, such as 0.1. In this way, the influence weight of each operation type on the user authority change can be determined, providing a quantitative basis for the subsequent analysis of the dynamic changes in user authority.

[0025] Step S1222: Generate a permission change time interval distribution based on the operation timestamp sequence, where the time interval distribution is used to characterize the dynamic correlation between the time intensity of the user's operation behavior and the frequency of permission adjustment.

[0026] In this application scenario, the operation timestamp sequence is analyzed to generate the permission change time interval distribution. Taking the operation record of operation and maintenance personnel C on generator A as an example, the time interval between two adjacent operations is counted. For example, the first power increase operation is performed at 9 am on Monday, and the second is performed at 3 pm on Tuesday, with a time interval of about 30 hours; the interval between the second power increase operation and the third is 22 hours. By counting and analyzing a series of operation time intervals, a permission change time interval distribution chart is drawn. Based on the permission change time interval distribution chart, it can be determined that: when the operation time interval of operation and maintenance personnel C on generator A is short, that is, the operation behavior is more intensive, the frequency of permission adjustment is relatively high; conversely, when the operation time interval is long, the frequency of permission adjustment is low. The permission change time interval distribution chart shows the dynamic correlation between the time intensity of user operation behavior and the frequency of permission adjustment.

[0027] Step S1223: Perform correlation analysis on the influence weight and the time interval distribution, calculate the correlation strength of the user role's authority status in the continuous time window, and generate the node connection strength parameter in the user authority dynamic evolution graph; the node connection strength parameter quantifies the probability and timing dependency of the authority status transfer in adjacent time windows.

[0028] In an embodiment of the present application, the previously determined influence weight is associated with the generated time interval distribution for analysis. For example, within a certain week's time window, operation and maintenance personnel C performed 3 operations on generator A, including 2 power boost operations (influence weight 0.6) and 1 device status check operation (influence weight 0.1). The time intervals of these 3 operations were 20 hours and 25 hours respectively. According to the corresponding calculation method (taking into account the number of operations, influence weight and time interval, an exemplary calculation method can be: (number of power boost operations × power boost influence weight + number of device status check operations × device status check influence weight) ÷ total operation time interval), the user role's authority state association strength for generator A within the week is calculated. The strength value is used as the connection strength parameter of the corresponding node in the user authority dynamic evolution map. The connection strength parameter quantifies the probability and temporal dependency of the authority state transfer in adjacent time windows. For example, a higher connection strength parameter indicates that within the adjacent time window, the probability of authority state transfer is greater, and there is a stronger temporal dependency, that is, the subsequent authority state is largely affected by the previous state operation.

[0029] Step S1224: Construct a dynamic permission state transfer matrix based on the node connection strength parameters, wherein: the row dimension of the matrix represents the permission state set of the current time window, the column dimension represents the permission state set of the next time window, and the matrix element value is obtained by normalizing the corresponding node connection strength parameters, which is used to reflect the transfer weight of the permission state across time windows.

[0030] In this application scenario, a dynamic permission state transition matrix is ​​constructed using the example of user permission states being divided into three states: "high permission," "medium permission," and "low permission." For example, the previous calculations yield node connection strength parameters within several consecutive time windows. For example, the node connection strength parameter from the "medium permission" state in the current time window to the "high permission" state in the next time window is 0.4, the parameter to the "medium permission" state is 0.3, and the parameter to the "low permission" state is 0.2. To construct the matrix, these parameters are first normalized. For example, if the total strength parameter is 0.4 + 0.3 + 0.2 = 0.9, then after normalization, the matrix element value from "medium permission" to "high permission" is 0.4 ÷ 0.9 ≈ 0.44, the element value to "medium permission" is 0.3 ÷ 0.9 ≈ 0.33, and the element value to "low permission" is 0.2 ÷ 0.9 ≈ 0.22. According to the matrix construction rules, the row dimension represents the permission status of the current time window ("high permission", "medium permission", "low permission"), and the column dimension represents the permission status of the next time window (also "high permission", "medium permission", "low permission"). These normalized element values ​​are filled in the corresponding positions of the matrix. The dynamic permission state transfer matrix constructed in this way can clearly reflect the transfer weight of the permission state across time windows, providing key data support for generating the spatiotemporal topological structure of the user permission dynamic evolution map.

[0031] Step S1225: Generate the spatiotemporal topological structure of the user authority dynamic evolution graph based on the dynamic authority state transition matrix: map the authority state of each time window to a time series node with a timestamp attribute, and connect adjacent time series nodes in the order of time evolution to form directed edges, and each directed edge carries a normalized connection strength weight value.

[0032] In an embodiment of the present application, the spatiotemporal topological structure of the dynamic evolution graph of user permissions is constructed based on the dynamic permission state transfer matrix. For example, the time window of each day in the past week is used as the basis for node construction. The permission state on Monday is "medium permission", which is mapped to a time series node with a Monday timestamp attribute; the permission state on Tuesday is "high permission", which is mapped to a time series node with a Tuesday timestamp. According to the time evolution order, the nodes on Monday and Tuesday are connected with a directed edge. The weight value of this directed edge is the transfer weight value (set to 0.44) from the "medium permission" state on Monday to the "high permission" state on Tuesday obtained by normalization. In the same way, the time series nodes of other adjacent time windows are connected in sequence to form a complete spatiotemporal topological structure. Thus, through the above-mentioned visual structure, the evolution path of user permissions in the time dimension and the probability relationship of permission state transfer between different time windows can be intuitively seen.

[0033] Step S1226: embedding a multi-dimensional permission feature vector in the timing node, wherein the multi-dimensional permission feature vector is composed of the statistical features of the operation type distribution histogram, the permission influence cumulative value and the time interval distribution in the corresponding time window.

[0034] In this application scenario, a multidimensional permission feature vector is embedded at each time series node. For example, during the time window on Tuesday, maintenance operator C performed one power increase and one device status check on generator A. The operation type distribution histogram shows that power increase operations account for 50% and device status check operations account for 50%. The cumulative permission impact is calculated by adding the impact weights of each operation within the time window. For example, if the power increase has an impact weight of 0.6 and the device status check has an impact weight of 0.1, the cumulative permission impact is 0.6 + 0.1 = 0.7. The statistical characteristics of the time interval distribution, such as the average time interval between operations within the time window, are set to 24 hours. This information is then combined into a multidimensional vector and embedded into the time series node on Tuesday. By embedding this multidimensional permission feature vector at each time series node, the dynamic properties of user permissions within each time window can be more comprehensively described, enriching the information content of the user permissions dynamic evolution graph.

[0035] Step S1227: Generate the user authority dynamic evolution map by fusing the spatiotemporal topological structure and the multi-dimensional authority feature vector, wherein: the topological edge weights of the user authority dynamic evolution map represent the probability of authority state transition, the node feature vectors represent the dynamic attributes of the authority state, and the user authority dynamic evolution map is a visual map model that includes the evolution path of the time dimension and the authority association rules of the space dimension.

[0036] In an embodiment of the present application, the spatiotemporal topological structure and the multidimensional permission feature vector constructed above are fused. The spatiotemporal topological structure composed of each time-stamped time series node and the directed edges connecting them are combined with the multidimensional permission feature vector embedded in the node to generate a dynamic evolution graph of user permissions. The weight of the topological edge intuitively shows the probability of permission state transfer between different time windows. For example, the edge weight from one node to another is 0.4, indicating that the probability of permission transfer from one state to another is 40%. The node feature vector, that is, the embedded multidimensional permission feature vector, characterizes the dynamic properties of the permission state of each time window in detail, including information such as the distribution of operation types and the cumulative value of permission influence. It can be understood that this visual graph model not only contains the evolution path of user permissions in the time dimension, showing how permissions change over time, but also reflects the association rules between different permission states in the spatial dimension, providing a comprehensive and intuitive tool for analyzing the dynamic changes of user permissions.

[0037] Step S123: performing device association analysis on the network topology connection relationship to generate a device permission dependency graph; the device permission dependency graph reflects the resource call relationship and permission sharing constraint conditions between power devices.

[0038] In one implementation, performing device association analysis on the network topology connection relationship to generate a device permission dependency graph in step S123 includes:

[0039] Step S1231: parsing the device hierarchical structure in the network topology connection relationship to determine the resource calling path between the master device and the controlled device.

[0040] In the power network of the embodiment of the present application, the network topology connection relationship is deeply analyzed to determine the device hierarchy structure and resource call path. For example, taking a subnet containing multiple transformers and distribution nodes as an example, by analyzing the network topology connection relationship diagram, it can be determined that transformer T3 is at a higher level and is the master device, and multiple distribution nodes P1, P2, P3, etc. are controlled devices. Transformer T3 transmits electricity to each distribution node through different transmission lines, forming a resource call path. Specifically, transformer T3 transmits electricity to distribution node P1 through transmission line L31, transmits electricity to P2 through L32, and transmits electricity to P3 through L33.

[0041] Step S1232: Calculate the resource contention coefficient between the master device and the controlled device based on the resource occupancy data in the real-time device status data; the resource contention coefficient reflects the conflict probability when the master device allocates resources to the controlled device.

[0042] In an embodiment of the present application, the resource competition coefficient is calculated in combination with the resource occupancy data in the real-time device status data. Taking transformer T3 and distribution node P1 as an example, for example, the rated capacity of transformer T3 is 800 MW, and the current real-time resource occupancy rate is 70%, that is, the actual output power is 560 MW; the demand power of distribution node P1 is 150 MW, and the maximum carrying capacity of the transmission line L31 connecting P1 and transformer T3 is 120 MW. According to the preset calculation method (for example, resource competition coefficient = (demand power - line carrying capacity) / rated capacity), the resource competition coefficient between transformer T3 and distribution node P1 is calculated to be (150-120) ÷ 800 = 0.0375. This coefficient reflects the probability of conflict when transformer T3 allocates resources to distribution node P1. The higher the coefficient, the greater the possibility of resource conflict. By performing the above calculations between all master control devices and controlled devices, the resource competition situation between power equipment can be fully understood.

[0043] Step S1233: Based on the resource call path and the resource competition coefficient, generate the device node weights and edge connection rules corresponding to the device authority dependency graph; the device node weights are used to identify the priority of power equipment in resource allocation, and the edge connection rules are used to constrain the maximum resource threshold for authority sharing between devices.

[0044] In this application scenario, device node weights and edge connection rules are generated based on the resource call path and resource competition coefficient. For device node weights, considering the core position of transformer T3 in resource allocation and its importance to multiple distribution nodes, it is given a higher weight, such as 0.8; while for distribution node P1, due to its relatively minor position in resource allocation, it is given a weight of 0.3. For edge connection rules, they are determined based on the resource competition coefficient and the security constraints of the system. For example, when the resource competition coefficient exceeds 0.05, the maximum resource threshold for inter-device permission sharing is set at 15% of the rated capacity. Therefore, by clarifying the device node weights and edge connection rules, specific parameters and constraints are provided for constructing the device permission dependency graph.

[0045] Step S1234: Generate a device permission dependency graph based on the device node weights and the edge connection rules.

[0046] In an embodiment of the present application, a device permission dependency graph is generated based on the device node weights and edge connection rules determined previously. Graphically, transformer T3 and distribution nodes P1, P2, P3, etc. are drawn as nodes in the graph, and the corresponding weight value is marked for each node. Then, according to the resource call path, each node is connected with an edge, and information related to the edge connection rules, such as the maximum resource threshold, is marked on the edge. For example, the edge connecting transformer T3 and distribution node P1 is marked with a maximum resource threshold of 15% of the rated capacity of transformer T3. Thus, the generated device permission dependency graph shows the resource call relationship and permission sharing constraints between power equipment, providing an important basis for the subsequent formulation of power resource allocation strategies.

[0047] Step S130: generating a power resource dynamic allocation strategy based on the user authority feature set and the device authority feature set; the power resource dynamic allocation strategy is used to adjust the load balancing path and device control priority in the power network.

[0048] In one implementation, generating a power resource dynamic allocation strategy based on the user authority feature set and the device authority feature set in step S130 includes:

[0049] Step S131: Calculate the matching degree between the access frequency feature in the user authority feature set and the resource occupancy rate feature in the device authority feature set to generate a user-device authority matching matrix.

[0050] In the embodiment of the present application, for the convenience of calculation, the access frequency feature can be simplified to the corresponding number of access frequencies, and the resource occupancy rate feature can be simplified to the corresponding resource occupancy rate. The matching degree calculation is performed by taking the operation and maintenance personnel E and multiple power equipment as an example. The access frequency of the operation and maintenance personnel E to the generator F is 6 times a week, and the resource occupancy rate of the generator F is 75%; the access frequency to the transformer G is 4 times a week, and the resource occupancy rate of the transformer G is 60%. Through the preset matching degree calculation method (for example, matching degree = access frequency / resource occupancy rate, the embodiment of the present application exemplarily maps the access frequency feature to 6 and 4), it is calculated that the matching degree of the operation and maintenance personnel E with the generator F is 6÷0.75=8, and the matching degree with the transformer G is 4÷0.6≈6.67. Similar calculations are performed for all user roles and power equipment, and the above calculation results are organized into a two-dimensional matrix, namely the user-device permission matching matrix. The rows of the user-device permission matching matrix represent user roles, the columns represent power equipment, and the matrix element values ​​are the corresponding matching degrees. Through this matrix, the permission matching between users and devices can be intuitively seen.

[0051] Step S132: determining a target power device set with resource conflicts based on the user-device authority matching matrix; the resource conflicts include user access requests exceeding device resource capacity or authority sharing rules not meeting security constraints.

[0052] In this application scenario, the user-device permission matching matrix is ​​analyzed to determine the target set of power equipment with resource conflicts. For example, based on the user-device permission matching matrix, it can be determined that dispatcher F has a high frequency of access to transformer H, reaching 10 times per week, while transformer H's resource utilization rate is as high as 90%, and its rated capacity is limited. Based on the current access frequency and resource utilization, user access requests exceed the device resource capacity, which may cause unstable device operation. At the same time, in terms of permission sharing, the permission sharing rules between some devices may not meet security constraints under the current load conditions. Through a comprehensive analysis of the matrix, devices such as transformer H that have these resource conflicts are identified as the target set of power equipment, providing a target basis for the subsequent formulation of targeted power resource allocation strategies.

[0053] Step S133: Based on the resource conflict type of the target power equipment set, a dynamic load balancing path and a permission priority adjustment instruction are generated, and the dynamic allocation strategy of power resources is determined in combination with the dynamic load balancing path and the permission priority adjustment instruction; the dynamic load balancing path is used to reallocate resource call links between power equipment, and the permission priority adjustment instruction is used to limit the access rights of low-priority users to critical load equipment.

[0054] In an embodiment of the present application, a dynamic load balancing path and authority priority adjustment instruction are generated according to the resource conflict type presented by the target power equipment set.

[0055] To generate dynamic load balancing paths, the real-time load rate data and topological connection status of each device in the power network are first obtained. For example, in a local power network area covering multiple generators, transformers, and distribution lines, the real-time load rate of generator G1 is 85%, and the load rate of generator G2 is 60%. Transformer T1 is connected to a high-load distribution area and has a load rate of 90%, while the load rate of transformer T2 is only 50%. At the same time, the topological connection relationship between each device is clarified. For example, generator G1 is connected to transformer T1 via transmission line L1, and generator G2 is connected to transformer T2 via transmission line L2. There is also a connecting line L3 between transformers T1 and T2.

[0056] Then, a heat map of the equipment load distribution is constructed based on these real-time load rate data. In the heat map, the load conditions of each device are intuitively displayed in different colors. For example, the high-load equipment area (such as a load rate of more than 80%) is displayed in red, representing a high load and potential overload risk; the medium-load area (load rate between 60%-80%) is displayed in yellow; the low-load area (load rate below 60%) is displayed in green. Through the heat map, you can clearly see the resource surplus capacity and overload risk level of power equipment in different areas. For example, in the above example, the area where transformer T1 is located is red, indicating that it is under high load and there is a risk of overload; the area where transformer T2 is located is green, indicating that it has more resource surplus capacity.

[0057] Furthermore, based on the device load distribution heat map and topological connection status, multiple candidate load balancing paths are generated. For example, considering the low load of generator G2 and the remaining resource capacity of transformer T2, a candidate path is generated: part of the power originally transmitted from generator G1 to transformer T1 is transferred to transformer T2 through the interconnection line L3, and then distributed to other demand areas by transformer T2. This candidate load balancing path includes the target device set for resource reallocation (such as generators G1, G2, transformers T1, T2 and related distribution nodes) and data transmission delay parameters. For example, after analyzing and estimating factors such as line length and transmission medium, the data transmission delay of this path is 40 milliseconds. At the same time, other candidate paths can also be generated, such as using backup generator G3 to share part of the load, but the data transmission delay of this path may be 60 milliseconds and involve adjustments to more equipment.

[0058] Next, based on the data transmission delay parameters and overload risk level, the optimal path is selected from the candidate load balancing paths as the dynamic load balancing path. When comparing the candidate paths, two key factors are comprehensively considered: data transmission delay and overload risk. Regarding data transmission delay, lower latency means faster and more stable power transmission, reducing the impact on the real-time operation of the power system; the overload risk level is directly related to the safe and stable operation of power equipment. For example, of the two candidate paths mentioned above, although the path using backup generator G3 can share more load, it has a longer data transmission delay and involves changes to more equipment, which may bring more potential risks. In contrast, the path that transfers power through interconnection line L3 has a relatively low data transmission delay of 40 milliseconds and effectively reduces the overload risk of transformer T1. Therefore, this path is selected as the dynamic load balancing path to achieve a reasonable reallocation of resources among power equipment.

[0059] In addition, regarding the generation of permission priority adjustment instructions, since the access of low-priority users to critical load equipment may affect the normal operation of the equipment, corresponding instructions need to be formulated to restrict such access. For example, the frequent routine maintenance operations of ordinary operation and maintenance personnel on the critical transformer T1 in a high-load state may interfere with the stable operation of the equipment and increase the risk of overload. Therefore, a permission priority adjustment instruction is generated, stipulating that when the load rate of transformer T1 exceeds 85%, ordinary operation and maintenance personnel are only allowed to perform emergency troubleshooting operations and are prohibited from performing routine maintenance operations. The above instructions clarify the access permission priorities of different user roles in different equipment states, ensuring that critical load equipment can prioritize power supply and stable operation when under high load.

[0060] Finally, the generated dynamic load balancing path and authority priority adjustment instructions are combined to form a complete dynamic allocation strategy for power resources. On the one hand, this dynamic allocation strategy for power resources redistributes the resource call links between power devices through dynamic load balancing paths, optimizes the distribution of power resources, and reduces the risk of equipment overload; on the other hand, it limits the access rights of low-priority users to key load devices through authority priority adjustment instructions to ensure the normal operation of the equipment and the stability of the power network. The above comprehensive strategy can effectively adjust the load balancing path and device control priority in the power network to achieve reasonable and efficient allocation of power resources.

[0061] Step S140: Feedback the power resource dynamic allocation strategy to the power network control system to activate the authority configuration update operation, which includes adjusting the user operation authority range and the resource response rules of the power equipment.

[0062] In one implementation, step S140 of feeding back the power resource dynamic allocation strategy to the power network control system to activate the authority configuration update operation includes:

[0063] Step S141: receiving a dynamic load balancing path and authority priority adjustment instruction through a policy parsing interface of the power network control system.

[0064] In the embodiments of the present application, the policy parsing interface of the power network control system is a module with intelligent recognition and parsing capabilities that can accurately receive and interpret these complex instruction information. For example, when dynamic load balancing path information is sent to the policy parsing interface in a preset data format (such as a data packet containing detailed information such as the target device set and path direction) and a permission priority adjustment instruction (such as a text instruction that clearly stipulates the permission restrictions for ordinary operation and maintenance personnel under the target device status), the interface can quickly recognize and convert it into an internal instruction form that the system can understand for subsequent processing.

[0065] Step S142: generating a path configuration confirmation signal based on the dynamic load balancing path, and transmitting the path configuration confirmation signal to a target power device controller to activate a link switching operation.

[0066] Taking the previously determined dynamic load-balancing path for transferring power via interconnection line L3 as an example, the system generates a path configuration confirmation signal based on this path information. This signal contains detailed path parameters, such as the starting device (generator G1), the intermediate transfer device (transformer T2), the target device (the relevant distribution node), and key information such as the path switching time requirements. The signal is accurately transmitted to the controllers of generator G1, transformers T1 and T2, and the relevant distribution nodes. For example, upon receiving the signal, the controller of generator G1 gradually adjusts its output power distribution according to the signal requirements, switching some power output to interconnection line L3. The controller of transformer T2 then prepares to receive and redistribute power, adjusting its internal voltage conversion and power distribution parameters to ensure smooth power flow and distribution to the appropriate distribution nodes. These actions activate the link switching operation, achieving path adjustment for power resource redistribution.

[0067] Step S143: Capturing a device response status code when the link switching operation is completed, and performing synchronization verification between the device response status code and the permission priority adjustment instruction.

[0068] As you can understand, after generator G1, transformers T1 and T2, and related distribution nodes complete the link switching operation, the controllers of each device will return a device response status code. For example, if the controller of generator G1 returns a status code of "200," indicating that the power output adjustment and link switching operation were successful; if the controller of transformer T2 returns a status code of "200," indicating that power reception and distribution are ready, these status codes are collected and synchronized with the permission priority adjustment instruction for verification. This verification process not only checks whether the device operation was successful, but also verifies whether the parameters and logic in the permission priority adjustment instruction comply with the system's preset rules. For example, it checks whether the permission restrictions for general operation and maintenance personnel on critical equipment specified in the permission priority adjustment instruction are within the system's security and management rules. If all devices respond with a status code of "200" and the logic and parameters of the permission priority adjustment instruction comply with the preset rules, the verification passes. If any device returns a status code other than "200," or if the permission priority adjustment instruction contains a logical error, such as a permission range setting that does not meet security standards, the verification will fail.

[0069] Step S144: triggering the update process of the user role access control list according to the device response status code that has passed the verification, and generating a user authority configuration table including the new authority range.

[0070] As you can understand, once the verification is passed, the system automatically initiates the update process for the user role access control list. For example, for ordinary operation and maintenance personnel, based on the permission priority adjustment instructions, when the load rate of transformer T1 exceeds 85%, their operating permissions are strictly limited to emergency troubleshooting operations. The system will accurately record the new permission range of ordinary operation and maintenance personnel in this situation in the user role access control list. A detailed user permission configuration table is then generated, which clearly lists the specific operating permissions of each user role under different equipment states. For example, the table clearly records that ordinary operation and maintenance personnel can perform routine maintenance and troubleshooting operations when the load rate of transformer T1 is less than 85%; when the load rate exceeds 85%, they can only perform emergency troubleshooting operations.

[0071] Step S145: writing the user authority configuration table into the access authorization database of the power network control system, and updating the priority sorting parameters of the device resource response rules at the same time.

[0072] For example, the system will accurately write the generated user permission configuration table into the access authorization database. In the database, the permission record field corresponding to the general operation and maintenance personnel is found and the new permission range information is updated. The priority sorting parameters of the equipment resource response rules will also be adjusted accordingly according to the dynamic allocation strategy of power resources. For example, for the high-load transformer T1, its resource response priority for emergency fault handling is increased, and the priority of routine maintenance operations is reduced. This means that when allocating and responding to equipment resources, the system will give priority to the resources and response speed required for emergency fault handling, ensuring that the equipment can operate safely and stably under special circumstances such as high load.

[0073] Step S146: obtaining the write completion flag of the access authorization database in real time, and activating the network-wide permission policy effectiveness instruction based on the write completion flag.

[0074] After the access authorization database successfully writes the user permission configuration table and updates the device resource response rule priority parameters, the database system returns a write completion indicator. The power network control system monitors this indicator in real time. Once it receives this indicator, it immediately activates the network-wide permission policy enforcement instruction to notify the entire power network system to begin implementing the new permission configuration policy.

[0075] Step S147: driving the power network control system to execute permission configuration synchronization broadcast through the network-wide permission policy validation instruction, and generating a permission update broadcast confirmation queue.

[0076] It is understood that after the network-wide permission policy is issued, the power network control system will send permission configuration update information to all devices and user terminals in the network. This information is sent in the form of a broadcast to ensure that every relevant device and user in the network can receive it. For example, through the communication protocol and signal transmission mechanism in the power network, the new user permission range and device resource response rules are sent to each generator, transformer, distribution node, and user operation terminal. After receiving the information, each device and user terminal will automatically parse and process it and return a confirmation response. These confirmation responses will form a permission update broadcast confirmation queue. The system monitors this queue to confirm that all relevant devices and users have received and approved the new permission configuration information.

[0077] Step S148: After all the electric devices in the permission update broadcast confirmation queue return confirmation responses, a permission configuration update completion flag is generated and stored in the system log.

[0078] Optionally, when the last power device in the queue (such as a small distribution device located in a remote area) returns a confirmation response, the system will determine that the permission configuration update operation has been successfully completed and generate a permission configuration update completion flag. This flag will be accurately recorded in the system log. The system log records in detail the time of the permission configuration update, the devices and user roles involved, the specific content of the update, and other information. For example, the system log will record "The permission configuration update was completed at [specific time], involving the adjustment of the permissions of general operation and maintenance personnel and the update of the priority of the resource response rules of equipment such as transformer T1." The above record provides detailed historical data for subsequent system audits, troubleshooting, and operation management, making it convenient for management personnel to check and understand changes in the system permission configuration at any time.

[0079] In another implementation, the training process of the target dynamic permission model is also included:

[0080] Step S210: Acquire historical power network operation data sets and corresponding optimization strategy execution effect data.

[0081] In the power network system involved in the embodiment of the present application, the acquisition of historical power network operation data sets covers multiple data sources and a long time span. From the perspective of data sources, it mainly includes data records collected in real time by various monitoring devices in the power network, detailed logs of user operation behaviors, and records of changes in network topology. For example, in the past three years, the power monitoring equipment in the system has continuously recorded the output power data of each generator. Taking generator M as an example, on January 1, 2020, its output power was 300 MW, 320 MW, etc. at different times; the voltage monitoring equipment records the voltage data of each node, such as the voltage of a distribution node at the target time is 10.5 kilovolts. The user operation behavior log records in detail the operations of different user roles on various power equipment at different times, such as the operation and maintenance personnel N performed maintenance operations on transformer O on March 5, 2021, and recorded the specific content and operation time of the operation. The change record of the network topology records the changes in the connection relationship of equipment in the power network. For example, in July 2022, a new transmission line was added to connect two originally isolated areas.

[0082] The corresponding optimization strategy execution performance data provides a detailed record of the optimization strategies implemented for different operating conditions and their subsequent effects. For example, during a period of time, voltage instability occurred in parts of the power network. To address this issue, an optimization strategy was implemented that adjusted transformer tap settings and optimized generator reactive power output. After implementing this strategy, continuous monitoring of voltage data in the relevant areas revealed a reduction in voltage fluctuations from ±5% to ±3%, and an improvement in power factor from 0.85 to 0.9. Furthermore, observation of equipment operating status revealed a significant decrease in overload warnings for transmission lines that had previously frequently issued overload warnings due to voltage issues. This data details changes in power network operating parameters, improvements in equipment status, and improvements in overall power supply quality before and after the optimization strategy was implemented. This provides rich and realistic sample data for subsequent model training, helping to develop a more accurate and effective dynamic permission model.

[0083] Step S220: extracting authority features and marking conflict events from the historical power network operation dataset to generate a model training sample set.

[0084] In an embodiment of the present application, permission feature extraction and conflict event labeling are carried out on a historical power network operation dataset.

[0085] For permission feature extraction, user permission features are analyzed from the perspective of user operation behavior. For example, dispatcher P is examined in depth in historical data. Over the past two years, dispatcher P has performed a series of operations on various generators and transformers. The number of power adjustment operations performed on the generators is counted. For example, on generator Q, 15 power increases and 10 power decreases were performed over different time periods. The time of each operation and the equipment's operating status at the time are also recorded. For example, a power increase was performed when generator Q's load factor reached 75%. By analyzing this operation data, user permission features are extracted, including the frequency of dispatcher P's operations on generator Q (e.g., the average number of operations per month), the distribution of operation times (e.g., the time periods in which operations are concentrated), and the correlation between operations and equipment status (e.g., the tendency to operate at different equipment load factors).

[0086] Extract device authority features from the device perspective, combining real-time device status data and network topology connection relationships. For example, for transformer R, analyze its resource occupancy data at different times, calculate its average resource occupancy rate and the fluctuation range of resource occupancy rate. At the same time, consider the position of transformer R in the network topology and its connection relationship with other devices, and analyze its resource call situation. For example, transformer R is connected to multiple distribution nodes, and in some time periods, due to changes in the demand of some distribution nodes, the resource allocation of transformer R fluctuates. Through these analyses, the resource occupancy rate characteristics, resource competition coefficient characteristics (such as the degree of resource competition with other adjacent transformers), and resource call path characteristics (such as the main resource output direction and path) of transformer R are extracted as device authority features.

[0087] While extracting permission features, conflict events in the dataset are annotated. Carefully review historical operating data to look for events where resource conflicts or permission issues occur. For example, at a certain moment, it is found that the output power of generator S suddenly increases significantly, causing the transmission line connecting it to transformer T to overload and the line temperature to rise sharply. This is a typical resource conflict event. The event is annotated in detail, recording the exact time of the event (such as 14:30 on September 15, 2021), the equipment involved (generator S, transformer T and related transmission lines), the type of conflict (power overload conflict) and the severity of the conflict (such as the specific value of the line temperature exceeding the safety threshold). By comprehensively extracting permission features from the historical power network operation dataset and accurately annotating conflict events, a rich, detailed and targeted model training sample set is generated, providing high-quality data support for subsequent model training, so that the trained model can more accurately simulate and analyze permission management and resource allocation issues in the power network.

[0088] Step S230: using a reinforcement learning algorithm to train the initial dynamic authority model to obtain a target dynamic authority model; the target dynamic authority model outputs a user authority feature set and a device authority feature set that match the optimization strategy execution effect data based on the input power network operation data set.

[0089] In an embodiment of the present application, a reinforcement learning algorithm may be used to train the initial dynamic permission model to obtain a target dynamic permission model.

[0090] The core idea of ​​reinforcement learning algorithms is to learn optimal strategies through the interaction between an agent and its environment. In this scenario, the initial dynamic authority model can be understood as an agent with preliminary capabilities for analyzing power grid data. However, its performance is still imperfect and requires continuous learning to improve its accuracy and effectiveness.

[0091] At the beginning of training, a historical power network operation dataset is fed into the initial dynamic permission model. Based on this data, the model attempts to output a set of user permission features and a set of device permission features. For example, given a set of historical data on the operating status of power equipment and user operations during a target time period, the model, based on its internal algorithms and parameters, outputs predictions of user permission features, such as the predicted frequency of operations performed by the target dispatcher on the target generator and the legitimacy of these operations. It also outputs predictions of device permission features, such as the resource utilization characteristics of a transformer and permission conflict detection parameters.

[0092] Next, the model output is compared with the optimization strategy execution performance data. For example, the model predicts that the resource utilization characteristic of a certain transformer is 70%, but after the optimization strategy is implemented, the transformer's resource utilization rate is actually 75%, as shown by actual monitoring data. This indicates that there is a certain deviation in the model prediction. Through this comparison, the error between the model output and the actual data is calculated.

[0093] Based on the error, the reinforcement learning algorithm adjusts the parameters of the initial dynamic permissions model. Based on the magnitude and direction of the error, the algorithm applies a pre-defined optimization method to update the model's weights and parameters. For example, if the user permissions predicted by the model deviate significantly from the actual value, the algorithm will adjust the parameters related to calculating the user permissions accordingly, so that the model's next prediction is closer to the actual value. This adjustment process is repeated continuously, and with the continuous input of training data and the continuous adjustment of model parameters, the model's prediction accuracy will gradually improve.

[0094] After a large number of training iterations, when the output of the initial dynamic permission model matches the optimization strategy execution effect data to a satisfactory degree, the target dynamic permission model is obtained. This target dynamic permission model can accurately output a user permission feature set and a device permission feature set that match the optimization strategy execution effect data based on the input power network operation data set. For example, when a new set of power network operation data is input, the target dynamic permission model can quickly and accurately analyze the data and output a user permission feature set that conforms to the actual situation, such as accurately predicting the access frequency of different user roles to various types of power equipment, operation legitimacy labels, etc.; at the same time, it outputs an accurate device permission feature set, such as the resource occupancy rate characteristics of power equipment, permission conflict detection parameters, etc. These output results are highly matched with the optimization strategy execution effect data, which means that the model can effectively simulate and reflect the actual permission management and resource allocation situation in the power network.

[0095] For example, when faced with a newly input power network operation data set, it contains information such as recent changes in generator output power, transformer load conditions, and user operation records. After training, the target dynamic permission model can accurately analyze the permission characteristics of different user roles (such as dispatchers, operation and maintenance personnel, etc.) based on these data. For example, for a dispatcher, the model may output that the frequency of operation of a certain generator under the target operating state is 5 times a week, and the operation legality label is compliant, which is consistent with the frequency and specifications of the dispatcher's reasonable operation of the generator according to power demand in actual conditions. For device permission characteristics, for a certain transformer, the model outputs its resource occupancy rate characteristic as 78%, and the permission conflict detection parameters show that there is no obvious conflict with the surrounding equipment at present, which is also consistent with the actual monitored transformer resource usage and the relationship between devices.

[0096] Through the above training process, the target dynamic permission model learns the inherent laws and associations between power network operation data and user permission characteristics and equipment permission characteristics. It can accurately generate corresponding feature sets based on input data, providing a reliable basis for the formulation of subsequent dynamic allocation strategies for power resources, and further ensuring the stable and efficient operation of the power network.

[0097] Step S240: deploying the target dynamic authority model to the power network control system to achieve real-time authority modeling and resource allocation strategy generation.

[0098] In an embodiment of the present application, the trained target dynamic authority model is integrated into the power network control system, aiming to realize real-time authority modeling and resource allocation strategy generation functions, thereby improving the intelligence and optimization level of power network operation.

[0099] First, the target dynamic permission model is deployed, which involves effectively integrating the model with the various components of the power network control system. The power network control system contains multiple subsystems and modules, such as data acquisition modules, monitoring modules, and decision-making modules. The target dynamic permission model needs to be closely connected with the data acquisition module to obtain the latest power network operation data set in real time. For example, the data acquisition module continuously collects real-time equipment status data from various power equipment, including parameters such as the output power, voltage, and frequency of the generator, the load rate and oil temperature of the transformer, as well as user operation behavior log information and any changes in network topology connection relationships. The target dynamic permission model receives this data in real time through the interface to ensure the timeliness and accuracy of its input data.

[0100] The target dynamic permission model works in tandem with the monitoring module: the monitoring module monitors the power network's operating status in real time, while the target dynamic permission model analyzes and processes the received data. For example, if the monitoring module detects an abnormal fluctuation in the load of power equipment in a certain area, the target dynamic permission model immediately analyzes the relevant data. Using its internal algorithms and learned patterns, it quickly generates a set of user and device permission feature sets for that area. These feature sets provide the basis for subsequent resource allocation strategies.

[0101] To achieve real-time permission modeling, the target dynamic permission model continuously and dynamically generates sets of user permission characteristics and device permission characteristics based on continuously updated power network operation data. For example, when new user operation behavior records are collected or the operating status of power equipment changes, the model will quickly recalculate and update the corresponding permission characteristics. For example, if a new operator joins the system and begins operating a generator, the target dynamic permission model will adjust the operator's user permission characteristics, such as operation frequency characteristics and operation legitimacy labels, in real time based on the operator's operation type, frequency, and the device's response. At the same time, the target dynamic permission model will update the generator's device permission characteristics, such as resource utilization characteristics and permission conflict detection parameters, in response to changes in the generator's operating parameters. Through this real-time update method, dynamic modeling of permissions in the power network is achieved, reflecting the ever-changing actual situation.

[0102] In terms of resource allocation strategy generation, the target dynamic permission model leverages the generated user permission feature set and device permission feature set to rapidly develop a reasonable dynamic power resource allocation strategy. For example, when the model detects that a transformer is overloaded and that there are other transformers with redundant resources nearby, it combines user permission features (such as the dispatcher's access to the device) and device permission features (such as resource call relationships and permission constraints between transformers) to generate a dynamic load balancing path. This path may involve transferring some power from the high-load transformer to the low-load transformer. It also generates permission priority adjustment instructions to restrict low-priority users from performing non-essential operations on the high-load transformer at this time, thereby ensuring the stable operation of the power network.

[0103] By deploying the target dynamic permission model into the power network control system, an integrated process from real-time data collection, permission modeling, to resource allocation strategy generation is achieved. Based on real-time operational data, the power network control system can quickly and accurately perform permission modeling and resource allocation strategy formulation using the target dynamic permission model. This effectively optimizes power network operation, improves power resource utilization efficiency, and ensures the stability and reliability of power supply.

[0104] In a non-limiting implementation, after feeding back the power resource dynamic allocation strategy to the power network control system to activate the authority configuration update operation, the method further includes:

[0105] Step S310: collecting the current resource occupancy rate and user operation log of the power equipment after the authority configuration is updated in real time.

[0106] In an embodiment of the present application, when the power resource dynamic allocation strategy is fed back to the power network control system and the authority configuration update operation is successfully activated, the system begins to collect relevant data in real time to continuously monitor and evaluate the operating status of the power network.

[0107] To collect the current resource utilization of power equipment, real-time data is acquired through sensors and monitoring devices distributed across various power devices. For example, a power sensor is installed on each generator to monitor the generator's output power in real time, thereby reflecting the generator's resource utilization. For example, at a certain moment after the permission configuration of generator A is updated, the power sensor shows that its output power is 550 megawatts. This data is a reflection of the current resource utilization of generator A at that moment. For transformers, resource utilization information is obtained by monitoring their load rate. For example, the load rate monitoring device of transformer B shows that its load rate is 72%, indicating the current resource utilization of transformer B. These sensors and monitoring devices transmit the real-time collected data to the data acquisition center of the power network control system, ensuring that the system can obtain the latest resource utilization data of power equipment in a timely manner.

[0108] At the same time, the system collects user operation logs in real time. User operation logs record all user operations on power equipment. For example, if a dispatcher issues a new power generation plan adjustment instruction after updating the permission configuration, this operation will be recorded in detail in the user operation log, including information such as the operation time (such as [specific time]), the operator role (dispatcher), the operation object (generator C), and the operation content (power generation plan adjustment, adjusting the output power from 600 MW to 620 MW). Through various user operation terminals and system recording mechanisms, all user operation behaviors are ensured to be accurately and promptly recorded and transmitted to the data storage module of the power network control system for subsequent analysis and processing.

[0109] By collecting the current resource utilization rate and user operation logs of power equipment in real time, the power network control system can fully and timely grasp the operating dynamics of the power network after the authority configuration is updated. This data provides an important basis for subsequent analysis of the operating effect of the power network, detection of abnormal conditions, and further optimization of power resource allocation strategies.

[0110] Step S320: performing a difference calculation between the current resource occupancy rate and the expected allocation value in the dynamic load balancing path to generate a resource deviation index of each power device.

[0111] In an embodiment of the present application, in order to evaluate the degree of conformity between the actual resource occupancy of each power device in the power network and the expected allocation value of the dynamic load balancing path, a difference calculation is performed to generate a resource deviation index.

[0112] First, define the expected allocation values ​​within the dynamic load balancing path. For example, when developing a dynamic load balancing path, generator A's output power is expected to stabilize at 500 megawatts to achieve load balancing and stable operation of the power network. Transformer B's load factor is expected to remain around 65%. These expected allocation values ​​are set based on the overall needs of the power network, equipment performance, and the goal of optimizing resource allocation.

[0113] The current resource utilization rate, collected in real time, is then compared with the expected allocation. For example, for generator A, the current output power is 550 megawatts, which differs from the expected allocation of 500 megawatts. The difference is 550-500 = 50 megawatts. To more intuitively reflect the degree of deviation, a resource deviation index is calculated. For example, using the relative deviation method, the resource deviation index = (current resource utilization rate - expected allocation value) / expected allocation value × 100%. Therefore, the resource deviation index for generator A is (550-500) / 500 × 100% = 10%.

[0114] For transformer B, the current collected load rate is 72%, and the expected load rate is 65%. According to the same calculation method, the difference is 72%-65%=7%, and the resource deviation index is (72%-65%) / 65%×100%≈10.77%.

[0115] By performing this difference calculation on each power device, we generate corresponding resource deviation indicators. These indicators clearly reflect the degree to which each power device's actual resource usage deviates from the expected allocation value along the dynamic load balancing path. A larger resource deviation indicator indicates a greater discrepancy between the device's actual operation and the expected value, potentially indicating issues such as improper power resource allocation or abnormal device operation. This provides a quantitative basis for subsequent analysis and adjustments.

[0116] Step S330: When a resource deviation index exceeds a preset threshold, a secondary calculation instruction for dynamic authority modeling is triggered.

[0117] In this embodiment of the present application, to ensure the stable operation of the power network and the rational allocation of resources, a preset threshold is set to monitor the resource deviation of power equipment. Once a resource deviation indicator exceeds the preset threshold, the system will automatically trigger the secondary calculation instruction of dynamic permission modeling.

[0118] Preset thresholds are determined based on a combination of factors, including power network operational experience, equipment performance, and safety standards. For example, for critical equipment like generators and transformers, the resource deviation threshold is set at 8%. This indicates that when the resource deviation index for a piece of power equipment exceeds 8%, the system determines that the equipment's operating status deviates significantly from the expected dynamic load balancing path, potentially impacting the overall performance and stability of the power network.

[0119] For example, if Generator C's resource deviation index reaches 12%, exceeding the preset threshold of 8%, the system immediately triggers a secondary calculation for dynamic authority modeling and notifies the power network control system to restart the dynamic authority modeling process to address potential resource allocation issues within the power network.

[0120] The purpose of triggering the secondary calculation instruction is to re-examine and analyze the power network's operational data, re-determine the user and device permission profiles based on the latest information, and then generate a dynamic power resource allocation strategy that better meets actual needs. This allows the system to timely adjust the power network's operating mode, optimize resource allocation, ensure that power equipment operates within a reasonable range, and improve the reliability and stability of the power network.

[0121] Step S340: Based on the secondary calculation instruction, the dynamic permission modeling process is re-executed with the latest collected resource occupancy rate and user operation log to generate a user permission update feature set and a device permission update feature set.

[0122] In an embodiment of the present application, upon receiving a secondary calculation instruction for dynamic permission modeling, the system restarts the dynamic permission modeling processing flow based on the latest collected resource occupancy rate and user operation log.

[0123] First, we conducted another in-depth analysis of user operation logs. For example, a review of the most recently recorded user operation behaviors revealed changes in the frequency and method of operations performed by O&M personnel on some equipment after the permission configuration was updated. For example, in the past week, the O&M personnel's inspection operations on Transformer D increased significantly compared to before, and in some cases, the operation time also differed from previous times. Through a detailed analysis of these operation behaviors, we extracted the operation type sequence and operation timestamp sequence. The operation type sequence clearly defines the specific operations performed by the O&M personnel, such as equipment inspection and parameter adjustment; the operation timestamp sequence records the specific time of each operation.

[0124] Then, based on these sequences, the impact of permissions is assessed. Combined with historical permission change records, the weight of the impact of these operations on user permission changes is analyzed. For example, historical data shows that frequent equipment inspections may, under certain conditions, affect the scope of operation and maintenance personnel's access to the equipment. After calculation and analysis, the weight of the impact of this equipment inspection on the operator's permission changes is determined to be 0.3. Furthermore, a distribution of permission change intervals generated based on the operation timestamp sequence reveals that the intervals between the operator's operations on transformer D are gradually decreasing, indicating more intensive operation behavior. By analyzing the dynamic correlation between this time interval distribution and the frequency of permission adjustments, a basis is provided for the subsequent calculation of the strength of the permission state association.

[0125] The generation of the device permission feature set is based on the latest collected resource utilization data and network topology connection relationships. For example, the latest resource utilization data for transformer D shows that its load rate is 78%, which is an increase from the previous one. At the same time, considering the position of transformer D in the network topology and its connection relationship with other devices, its resource call situation and possible permission sharing constraints are analyzed. It was found that due to the load changes of some surrounding devices, the resource competition pressure on transformer D increased. Through these analyses, the resource utilization characteristics, resource competition coefficient characteristics, and resource call path characteristics of transformer D were extracted as part of the device permission update feature set.

[0126] By re-executing the dynamic permission modeling process, taking into account the latest collected data and actual operation conditions, user permission update feature sets and device permission update feature sets are generated. These updated feature sets can more accurately reflect the current operating status of the power network and the actual conditions of user permissions and device permissions, providing a more reliable basis for the subsequent regeneration of the dynamic allocation strategy of power resources.

[0127] Step S350: regenerate the power resource dynamic allocation strategy according to the user authority update feature set and the device authority update feature set and trigger the authority configuration overwriting operation.

[0128] In an embodiment of the present application, based on the newly generated user authority update feature set and device authority update feature set, the power resource dynamic allocation strategy is generated again, and the authority configuration overwrite operation is triggered to adapt to the current operating conditions of the power network.

[0129] First, we conducted an in-depth analysis of the user permission update feature set and the device permission update feature set. For example, the user permission update feature set indicated that due to changes in the operator's operating behavior on transformer D, their operating permissions for this device might need to be adjusted. Furthermore, the device permission update feature set indicated that transformer D's resource utilization rate had increased, along with increasing resource competition, necessitating a replanning of its resource allocation path.

[0130] Based on these feature sets, the user-device permission matching is recalculated. For example, the new matching degree between the operator and transformer D is calculated. For example, if the operator's access frequency on transformer D increases, and transformer D's resource utilization rate increases, the new matching degree value is calculated using the preset calculation method (matching degree = access frequency / resource utilization rate, as mentioned previously). When compared with the previous matching degree, a significant difference is found, indicating that the power resource allocation strategy needs to be adjusted.

[0131] A new dynamic load balancing path is generated based on factors such as the new matching degree and the resource competition among devices. For example, considering the high load and resource competition pressure of transformer D, it is found that the adjacent transformer E has a lower load and corresponding redundant resources. Therefore, a new dynamic load balancing path is developed to transfer some power from the line where transformer D is located to transformer E, which then distributes it to other demand areas. This new path includes the target device set for resource reallocation (such as transformers D and E and related distribution nodes) and data transmission delay parameters.

[0132] At the same time, permission priority adjustment instructions are generated. For example, since the operation and maintenance personnel's operations on transformer D may affect its stable operation, it is stipulated that when the load rate of transformer D exceeds 80%, some non-emergency operation permissions of the operation and maintenance personnel will be further restricted to ensure the normal operation of the equipment.

[0133] The newly generated dynamic load balancing path is combined with the permission priority adjustment instructions to form a new dynamic power resource allocation strategy. Then, a permission configuration overwrite operation is triggered. The system overwrites the permission configuration information in the new dynamic power resource allocation strategy, such as adjustments to user permission ranges and updates to device resource response rules, with the original permission configuration. This ensures that the power network control system operates according to the new strategy, achieves a reasonable redistribution of power resources, and improves the operational efficiency and stability of the power network to address resource allocation issues and user permission changes that currently occur in the power network.

[0134] In a non-limiting implementation, after feeding back the power resource dynamic allocation strategy to the power network control system to activate the authority configuration update operation, the method further includes:

[0135] Step S410: intercepting all users' access requests to key power equipment within a preset time period.

[0136] In an embodiment of the present application, after the dynamic allocation strategy of power resources is fed back to the power network control system and the authority configuration update operation is activated, in order to ensure the stable operation of critical power equipment during the authority configuration update, the system will intercept all users' access requests to critical power equipment within a preset time period.

[0137] The preset time period is based on experience and considerations for the stability of the power network system. For example, the next 30 minutes after the permission configuration update operation is completed is set as the preset time period. During this time period, the system intercepts all access requests sent to critical power equipment through the access control mechanism. Critical power equipment refers to equipment that is critical to the operation of the power network, such as large generators and core transformers. For example, generator F, as the main power supply equipment in the power network, and transformer G, as a hub equipment connecting multiple important areas, are both considered critical power equipment.

[0138] When users initiate access requests to critical power equipment, the system automatically detects these requests and intercepts them. For example, if a dispatcher attempts to issue a power adjustment command to generator F during a preset time period, the request will be recognized and intercepted by the system's access control module. The system will then send a prompt to the dispatcher, informing them that access to critical power equipment is temporarily restricted during the preset time period to ensure stable equipment operation and smooth permission configuration updates. This prevents problems such as abnormal power equipment operation or confusion in permission configurations caused by improper user access during the permission configuration update period, thus ensuring a stable transition of the power network.

[0139] Step S420: performing a real-time comparison between the user role identifier in the access request and the latest permission range in the user permission configuration table.

[0140] In an embodiment of the present application, after intercepting a user's access request to critical power equipment, the system will perform a real-time comparison of the user role identifier in the access request with the latest permission range in the user permission configuration table to determine whether the access request is legitimate.

[0141] The system first extracts the user role identifier from the access request. For example, when a dispatcher initiates an access request for generator F, the request includes the dispatcher's identity. The system then quickly queries the user permissions configuration table, which stores the latest user permission range information. For example, the user permissions configuration table specifies the scope of operation permissions for the dispatcher role under target conditions (such as when generator F is partially operational or during a permissions configuration update). For example, during the current permissions configuration update, the dispatcher's operation permissions on generator F are limited to emergency troubleshooting operations.

[0142] The system compares the extracted user role identifier with the corresponding permission range in the user permission configuration table in real time. Using a precise matching algorithm, it checks whether the dispatcher's access request is within the permission range specified in the permission configuration table. For example, if the dispatcher initiates a request to perform a routine power adjustment on generator F, and the user permission configuration table explicitly prohibits such operations during the current preset time period, the comparison result will indicate that the access request exceeds the permission range. Conversely, if the dispatcher initiates a request to handle a sudden emergency failure of generator F, and the request meets the permission requirements for emergency situations in the user permission configuration table, the comparison result will indicate that the access request is within the permission range.

[0143] The above-mentioned real-time comparison mechanism can ensure that only access requests that comply with the latest permission range can be further processed, effectively preventing users from performing illegal access operations due to unclear permissions or changes in permissions, ensuring the security and stability of key power equipment during special periods (such as during permission configuration updates), and maintaining the order and reliability of power network operation.

[0144] Step S430: When an unauthorized access request is detected, a permission interception log is generated and a temporary locking instruction of a device resource response rule is triggered.

[0145] In an embodiment of the present application, once the system detects an unauthorized access request after comparing the user role identifier in the access request with the latest permission range in the user permission configuration table in real time, it will perform a series of corresponding operations to ensure the safe and stable operation of the power network.

[0146] First, the system generates a permission interception log. The permission interception log records detailed information about each unauthorized access request, including the time the request was initiated, the user role initiating the request, the key power equipment attempted to be accessed, and the reason for the unauthorized access. For example, at [specific time], dispatcher [name] initiated an access request to perform a non-emergency power adjustment on generator F. Because this operation was not within the scope of the permissions specified in the current user permission configuration table, the system determined the request to be unauthorized access and recorded this information in the permission interception log. This log record not only facilitates subsequent auditing and tracing of system security incidents, but also provides data support for analyzing user permission usage and optimizing permission configuration.

[0147] At the same time, the system triggers a temporary lock command within the device resource response rule. This command is intended to prevent unauthorized access from potentially negatively impacting critical power equipment. For example, when an unauthorized access request is detected for generator F, the system sends a temporary lock command to its controller. Upon receiving the command, the controller immediately activates the appropriate protection mechanism, temporarily locking some of the device's resource response functions. For example, modifications to generator F's power regulation parameters are prohibited, and interfaces for non-emergency maintenance operations are closed. This temporary lock ensures that important parameters and operations of critical power equipment cannot be arbitrarily altered during unauthorized access, thereby safeguarding the stable operation of the equipment and the security of the power network.

[0148] By generating permission interception logs and temporary locking instructions that trigger device resource response rules, the system can respond to unauthorized access requests in a timely manner, record relevant information for subsequent analysis and processing, and take effective measures to protect critical power equipment and prevent power network failures or safety hazards caused by illegal operations.

[0149] Step S440: based on the permission interception log, trace back to the user permission dynamic evolution map and modify the judgment threshold of the operation legitimacy label.

[0150] In an embodiment of the present application, the system modifies the operation legitimacy label determination threshold in the user authority dynamic evolution graph based on the generated authority interception log to further optimize user authority management and improve the security of the power network.

[0151] Permission interception logs provide detailed information about unauthorized access requests, providing key clues for tracing the dynamic evolution of user permissions. For example, permission interception logs show that over a period of time, operations performed by maintenance personnel on a transformer were repeatedly identified as unauthorized access. By analyzing these logs, the specific types of these unauthorized access operations, their occurrence times, and the associated user roles and device information can be determined.

[0152] Based on this information, we traced back to the user permissions dynamic evolution map. The user permissions dynamic evolution map records the changes in the permissions status of user roles at different times and the relationship between operations and permissions. For example, the map shows the operation traces of maintenance personnel on transformers at different times and the corresponding operation legitimacy labels. Analysis revealed that the current operation legitimacy label determination threshold may not be set accurately enough, resulting in some operations that should have been restricted not being promptly identified as illegal operations.

[0153] Based on this, the judgment threshold of the operation legitimacy label is revised. For example, if it is found that some non-essential operations performed by operation and maintenance personnel when the equipment load rate is high are frequently intercepted, it means that the current threshold for judging the legitimacy of these operations may be too high. Therefore, the legitimacy judgment threshold of the operation under high load conditions is lowered. Specifically, when the equipment load rate reaches 80%, an operation and maintenance operation is still judged as legal. Now the judgment threshold is adjusted to 75%. That is, when the equipment load rate reaches 75% or above, the operation and maintenance operation will be judged as illegal.

[0154] Therefore, based on actual unauthorized access, the threshold for determining the legitimacy of operations in the user rights dynamic evolution graph is dynamically adjusted and optimized. This makes user rights determination more accurate and rigorous, better adapting to the actual operational needs of the power grid, further ensuring the safe and stable operation of the power grid, and preventing potential risks caused by improper rights management.

[0155] Step S450: regenerate the device control priority update parameter through the revised user authority dynamic evolution map, and send the device control priority update parameter to the device controller in real time.

[0156] In an embodiment of the present application, the revised user authority dynamic evolution map is used to regenerate the device control priority update parameters to ensure that the power equipment can be controlled and managed according to reasonable priorities under different circumstances, thereby ensuring the stable operation of the power network.

[0157] The revised user rights dynamic evolution diagram more accurately reflects the relationship between user rights and operations, as well as the legality of operations in different situations. Based on this diagram, we analyze the changes in the operational rights of different user roles for various types of power equipment, as well as the changes in the operating status of the equipment itself. For example, the diagram shows that as the rights of operation and maintenance personnel are adjusted and operating parameters such as equipment load rate change, the control priority of some equipment may need to be reassessed.

[0158] For important equipment such as generators, the information in the map is combined with the impact of different user operations on their operational stability and the overall needs of the power network to recalculate the equipment control priority update parameters. For example, if it is found that the dispatcher's operating authority over the generator has changed under the target situation, and this change will affect the generator's power supply priority in the power network, then the new equipment control priority is calculated based on the relevant data and rules in the map. For example, the original control priority of the generator during normal operation was 3 (the priority is divided into 5 levels, 1 is the highest and 5 is the lowest). After analysis, it was found that under the current user authority adjustment and equipment operation status, in order to ensure the stability and reliability of the power supply, its control priority was increased to 2.

[0159] Optionally, after generating these device control priority update parameters, the system sends them to the device controller in real time. Through the communication mechanism of the power network control system, the updated parameters are accurately transmitted to the controllers of each relevant device. For example, for the above-mentioned generator, after its controller receives the instruction with the updated control priority parameter of 2, it will immediately adjust the internal control strategy. In the subsequent operation process, when faced with multiple operation requests or resource allocation decisions, the generator controller will process them according to the new priority parameters and give priority to responding to high-priority operation requests to ensure that the operation of the generator can better meet the overall needs of the power network and improve the efficiency and stability of the power network operation. Therefore, the revised user authority dynamic evolution map is used to realize the dynamic adjustment and optimization of device control priority, ensuring that the power network can operate safely, stably and efficiently under various circumstances.

[0160] In a non-limiting embodiment, after feeding back the power resource dynamic allocation strategy to the power network control system to activate the authority configuration update operation, the method further includes:

[0161] Step S510: Continuously monitor the actual response delay data of each link in the dynamic load balancing path.

[0162] Continuously monitoring actual response delay data aims to promptly identify link response delays exceeding expected ranges and any instability or abnormal fluctuations. This is crucial for ensuring the normal operation of the power grid, as excessively long or unstable response delays can lead to untimely power distribution and difficulties in equipment coordination, impacting the overall performance and reliability of the grid. By monitoring this data in real time, the system can take timely measures to address potential issues and ensure the stable operation of dynamic load balancing paths.

[0163] Step S520: When it is detected that the delay data of the target link exceeds the maximum constraint value in the device authority dependency graph, a path switching trigger signal is generated.

[0164] In this embodiment of the present application, to avoid adverse effects on the power network caused by excessive delays, the system immediately generates a path switching trigger signal and notifies the power network control system that it needs to adjust the current dynamic load balancing path, switching to an alternative path or replanning the path to ensure timely and stable power transmission to the required location. The path switching trigger signal includes information such as the target link identifier, delay data, and related path switching requirements, so that the power network control system can accurately perform subsequent operations based on the signal, quickly respond to and resolve issues caused by excessive link delays, and maintain the stable and reliable operation of the power network.

[0165] Step S530: extracting redundant resource parameters of the backup device from the network topology connection relationship according to the path switching trigger signal.

[0166] In an embodiment of the present application, upon receiving a path switching trigger signal, the system extracts the redundant resource parameters of the backup device from the network topology connection relationship based on the signal, providing the necessary information for subsequent replanning of the power transmission path. For example, by extracting the redundant resource parameters of the backup device from the network topology connection relationship, the system obtains the key information required for replanning the power transmission path. These parameters can help the system evaluate whether the backup device can meet the current power transmission requirements, as well as the transmission capacity and stability of the backup path, laying the foundation for subsequently generating a new load migration path based on this information and ensuring the normal operation of the power network.

[0167] Step S540: recalculating the load migration path based on the redundant resource parameters and generating a local load balancing optimization instruction.

[0168] In the embodiment of the present application, after obtaining the redundant resource parameters of the backup device, the system recalculates the load migration path based on these parameters to generate local load balancing optimization instructions, thereby achieving reasonable adjustment and optimization of the load in the power network. It can be understood that by generating local load balancing optimization instructions, the system provides clear operational guidance to the power network control system, so that load migration operations can be performed quickly and accurately, achieving load balancing in local areas, improving the operating efficiency and stability of the power network, resolving load imbalances caused by problems such as link delays, and ensuring the reliability of power supply.

[0169] Step S550: inserting the optimization instruction into the current execution queue of the power network control system, interrupting the resource allocation of the original path and activating the real-time response of the new path.

[0170] In an embodiment of the present application, after generating a local load balancing optimization instruction, the system inserts the instruction into the current execution queue of the power network control system, thereby interrupting the resource allocation of the original path and activating the real-time response of the new path, ensuring that the power network can quickly adjust to the new load balancing state. It can be understood that by inserting the optimization instruction into the execution queue, interrupting the resource allocation of the original path and activating the real-time response of the new path, the power network control system can quickly respond to problems such as link delays, promptly adjust the power transmission path, ensure the stable operation of the power network, avoid problems such as power supply shortages or equipment overloads caused by abnormalities in the original path, and ensure that the power network can continuously and reliably provide power services to users.

[0171] Based on the same inventive concept, the present application also provides a power network data driven optimization system. Figure 2 , which is a structural diagram of a possible power network data-driven optimization system provided in an embodiment of the present application, Figure 2 In the embodiment, the power network data-driven optimization system 200 includes a processor 210 and a memory 220. The memory 220 stores a computer program executable by the processor 210. The processor 210 executes the instructions stored in the memory 220 to perform the steps of the power network data-driven optimization method based on dynamic authority modeling.

[0172] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, which includes a computer program. When the computer program runs on a power network data-driven optimization system, the computer program is used to enable the power network data-driven optimization system to execute the steps of the above-mentioned power network data-driven optimization method based on dynamic authority modeling. In some possible implementations, various aspects of the power network data-driven optimization method based on dynamic authority modeling provided by the present application can also be implemented in the form of a program product, which includes a computer program. When the program product runs on a power network data-driven optimization system, the computer program is used to enable the power network data-driven optimization system to execute the steps of the above-mentioned power network data-driven optimization method based on dynamic authority modeling. For example, the power network data-driven optimization system can execute the following steps: Figure 1 Follow the steps shown in .

[0173] In the technical solutions involved in the above-mentioned embodiments of the present invention, whether it is performing comparison calculations of multi-dimensional features or constructing composite parameters, if there are problems caused by significant differences in the number of dimensions, dimensional units and semantic meanings of different features, technical personnel in this field, based on their professional knowledge and past practical experience, are fully able to understand that these differences need to be properly handled so that the calculation results are accurate and comparable, and avoid situations such as logical confusion and unclear mathematical meaning.

[0174] The formulas and calculation processes involved in the embodiments of the present application, whether used for multidimensional feature comparison or composite loss function construction, strictly follow the principle of dimensional correspondence. The variables in each formula have clear and definite physical meanings, and their operation logic is also fully consistent with basic mathematical and physical logic. The operation results must be the reasonable results expected by this application. Those skilled in the art have the ability to comprehensively apply the above-mentioned general technical means according to specific data conditions and business needs, and effectively solve the various problems caused by the number of dimensions, dimensional differences, etc. in the multidimensional feature comparison calculation and composite loss function construction in the embodiments, and ensure the accuracy, reliability and feasibility of the technical solution of the present invention.

Claims

1. A data-driven optimization method for power networks based on dynamic authority modeling, characterized in that: The method comprises: Acquire a power network operation data set, wherein the power network operation data set includes real-time device status data, user operation behavior logs, and network topology connection relationships; Dynamic permission modeling is performed on the power network operation data set to generate a user permission feature set and a device permission feature set; the user permission feature set represents access control parameters for different user roles to power resources, and the device permission feature set represents resource allocation permissions for different power devices under the operating environment; generating a power resource dynamic allocation strategy based on the user authority feature set and the device authority feature set; the power resource dynamic allocation strategy is used to adjust the load balancing path and device control priority in the power network; The power resource dynamic allocation strategy is fed back to the power network control system to activate the authority configuration update operation, which includes adjusting the user operation authority range and the resource response rules of the power equipment.

2. The method according to claim 1, wherein The performing dynamic authority modeling processing on the power network operation data set to generate a user authority feature set and a device authority feature set includes: Extracting an operation type sequence and an operation timestamp sequence from the user operation behavior log, wherein the operation type sequence includes a control instruction type of the user role on the power equipment and a corresponding operation number; Based on the operation type sequence and the operation timestamp sequence, a user authority dynamic evolution map is generated; the user authority dynamic evolution map includes a trajectory of changes in the operation authority of the user role within a preset time window; Performing device association analysis on the network topology connection relationship to generate a device permission dependency map; the device permission dependency map reflects the resource call relationship and permission sharing constraints between power devices; According to the user authority dynamic evolution graph and the device authority dependency graph, a user authority feature set and a device authority feature set are constructed; wherein, the user authority feature set includes the user role's access frequency characteristics and operation legitimacy labels to the target power equipment, and the device authority feature set includes the power equipment's resource occupancy characteristics and authority conflict detection parameters.

3. The method according to claim 2, wherein Generating a user authority dynamic evolution graph based on the operation type sequence and the operation timestamp sequence includes: Performing a permissions impact assessment on the operation type sequence, and calculating the probability of different operation types triggering permissions adjustments in historical permissions change records, to determine the impact weight of each operation type on user permissions changes; generating a permission change time interval distribution based on the operation timestamp sequence, wherein the time interval distribution is used to characterize the dynamic correlation between the time intensity of the user's operation behavior and the frequency of permission adjustment; The influence weight is correlated with the time interval distribution, and the correlation strength of the user role's authority status in the continuous time window is calculated to generate a node connection strength parameter in the user authority dynamic evolution graph; the node connection strength parameter quantifies the probability and temporal dependency of the authority status transition in adjacent time windows; A dynamic permission state transfer matrix is ​​constructed based on the node connection strength parameter, wherein: the matrix row dimension represents the permission state set of the current time window, the column dimension represents the permission state set of the next time window, and the matrix element value is obtained by normalizing the corresponding node connection strength parameter, which is used to reflect the transfer weight of the permission state across time windows; Generate a spatiotemporal topological structure of a user authority dynamic evolution graph based on the dynamic authority state transition matrix: map the authority state of each time window to a time series node with a timestamp attribute, connect adjacent time series nodes in the order of time evolution to form directed edges, and each directed edge carries a normalized connection strength weight value; Embed a multi-dimensional permission feature vector in the time series node, wherein the multi-dimensional permission feature vector is composed of a distribution histogram of operation types within a corresponding time window, a cumulative value of permission influence, and statistical characteristics of time interval distribution; By fusing the spatiotemporal topological structure and the multi-dimensional permission feature vector, the user permission dynamic evolution map is generated, wherein: the topological edge weights of the user permission dynamic evolution map represent the permission state transition probability, the node feature vectors represent the dynamic properties of the permission state, and the user permission dynamic evolution map is a visual map model that includes the evolution path of the time dimension and the permission association rules of the space dimension.

4. The method according to claim 2, wherein The performing device association analysis on the network topology connection relationship to generate a device permission dependency graph includes: Analyzing the device hierarchical structure in the network topology connection relationship to determine the resource call path between the master device and the controlled device; Calculating a resource contention coefficient between the master device and the controlled device based on the resource occupancy rate data in the real-time device status data; the resource contention coefficient reflects the probability of conflict when the master device allocates resources to the controlled device; Based on the resource call path and the resource competition coefficient, a device node weight and an edge connection rule corresponding to the device permission dependency graph are generated; the device node weight is used to identify the priority of the power equipment in resource allocation, and the edge connection rule is used to constrain the maximum resource threshold for permission sharing between devices; Based on the device node weights and the edge connection rules, a device permission dependency graph is generated.

5. The method according to claim 1, wherein Generating a dynamic power resource allocation strategy according to the user authority feature set and the device authority feature set includes: Calculating the matching degree between the access frequency feature in the user authority feature set and the resource occupancy rate feature in the device authority feature set to generate a user-device authority matching matrix; Determining a target power device set with resource conflicts based on the user-device authority matching matrix; the resource conflicts include user access requests exceeding device resource capacity or authority sharing rules not meeting security constraints; Based on the resource conflict type of the target power equipment set, a dynamic load balancing path and a permission priority adjustment instruction are generated, and the dynamic allocation strategy of power resources is determined in combination with the dynamic load balancing path and the permission priority adjustment instruction; the dynamic load balancing path is used to reallocate resource call links between power equipment, and the permission priority adjustment instruction is used to limit the access rights of low-priority users to critical load equipment.

6. The method according to claim 5, wherein The step of generating a dynamic load balancing path includes: Obtain real-time load rate data and topological connection status of each device in the power network; Constructing a device load distribution heat map based on the real-time load rate data, wherein the device load distribution heat map reflects the resource remaining capacity and overload risk level of power equipment in different areas; Based on the device load distribution heat map and the topological connection state, a plurality of candidate load balancing paths are generated; each candidate load balancing path includes a target device set for resource reallocation and a data transmission delay parameter; selecting an optimal path from candidate load balancing paths as a dynamic load balancing path according to the data transmission delay parameter and the overload risk level; The generating of multiple candidate load balancing paths based on the device load distribution heat map and the topological connection state includes: Identifying a standby device node having redundant resource capacity in the network topology connection relationship; Generate a backup resource call link based on the remaining resource capacity of the backup device node and the physical distance from the key load device; The backup resource call link is combined with the current resource call path to form a candidate load balancing path including N levels of resource allocation hierarchy; wherein the N levels of resource allocation hierarchy correspond to load migration solutions with different response speeds.

7. The method according to claim 1, wherein Feeding back the power resource dynamic allocation strategy to the power network control system to activate the authority configuration update operation includes: Receive dynamic load balancing path and authority priority adjustment instructions through the policy parsing interface of the power network control system; generating a path configuration confirmation signal based on the dynamic load balancing path, and transmitting the path configuration confirmation signal to a target power device controller to activate a link switching operation; capturing a device response status code when the link switching operation is completed, and synchronously verifying the device response status code with the permission priority adjustment instruction; Trigger the update process of the user role access control list based on the response status code of the device that has passed the verification, and generate a user permission configuration table containing the new permission range; Writing the user authority configuration table into the access authorization database of the power network control system and updating the priority sorting parameters of the device resource response rules; Acquire the write completion flag of the access authorization database in real time, and activate the network-wide permission policy effectiveness instruction based on the write completion flag; The power network control system is driven to execute permission configuration synchronization broadcast through the network-wide permission policy validation instruction, and a permission update broadcast confirmation queue is generated; After all the electric devices in the permission update broadcast confirmation queue return confirmation responses, a permission configuration update completion flag is generated and stored in the system log.

8. The method according to claim 7, wherein The real-time monitoring of the power network operation status after the authority configuration is updated includes: Periodically poll the device resource occupancy rate collection interface of the power network control system to extract the updated real-time resource occupancy rate data set; Synchronously scan the storage partition of the user operation behavior log to obtain the user operation response log records after the permission configuration is updated; Comparing the real-time resource occupancy rate dataset with the benchmark resource allocation template of the expected load balancing path item by item to generate a device-level resource deviation indicator set; Synchronously verify the legitimacy of the user operation response log record with the user authority configuration table to generate a list of user operation violation events; Aggregating the device-level resource deviation indicator set and the user operation violation event list to generate a global resource allocation anomaly detection report; When the global resource allocation anomaly detection report contains a device-level resource deviation indicator exceeding a preset threshold or a non-empty user operation violation event, a permission conflict alarm trigger signal is generated; Invoke the restart interface of the dynamic permission modeling process according to the permission conflict alarm trigger signal, and inject the latest device status snapshot and user operation record into the power network operation data set; After the injection is completed, the regeneration process of the user permission dynamic evolution graph and the device permission dependency graph is activated to trigger the calculation of a new allocation strategy.

9. The method according to claim 1, wherein The method also includes a training process of a target dynamic permission model: Obtain historical power network operation data sets and corresponding optimization strategy execution effect data; Extracting authority features and annotating conflict events from the historical power network operation dataset to generate a model training sample set; A reinforcement learning algorithm is used to train the initial dynamic authority model to obtain a target dynamic authority model; the target dynamic authority model outputs a user authority feature set and a device authority feature set that match the optimization strategy execution effect data based on the input power network operation data set; The target dynamic authority model is deployed to the power network control system to achieve real-time authority modeling and resource allocation strategy generation.

10. A power network data-driven optimization system, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any one of the methods of claims 1 to 9.

Images