Power monitoring optimization method based on situation awareness and intelligent diagnosis and related device

Abstract

The invention provides an electric power monitoring optimization method based on situation awareness and intelligent diagnosis and a related device. The method comprises the following steps: acquiring multi-source real-time operation data corresponding to a target electric power system and an electric power monitoring system; the power monitoring system is used for monitoring and adjusting the real-time operation state of the target power system; performing situation awareness analysis on the multi-source real-time operation data to obtain a situation assessment result; performing intelligent diagnosis analysis on the situation assessment result to obtain a fault diagnosis result; generating a monitoring optimization strategy according to the fault diagnosis result; and generating a plurality of target instruction sets according to the monitoring optimization strategy. Through deep fusion of situation awareness and an intelligent diagnosis technology, power monitoring parameters are optimized, so that the accuracy and the adaptivity of a power monitoring system are improved.

Description

Technical Field

[0001] This application relates to the field of power monitoring technology, and in particular to a power monitoring optimization method and related device based on situational awareness and intelligent diagnosis. Background Technology

[0002] Against the backdrop of rapid development in the power system, the large-scale integration of new energy sources and the surge in power equipment have led to more complex and volatile system operating conditions, posing serious challenges to the real-time performance, accuracy, and adaptability of traditional power monitoring systems. In particular, the sampling frequency, data transmission rules, and other monitoring parameters of traditional power monitoring systems are usually pre-configured and statically fixed. This can result in resource waste during normal power system operation, and in the event of a fault or abnormal trend, insufficient monitoring density makes it impossible to capture critical information in a timely manner, failing to meet dynamically changing security requirements.

[0003] Therefore, improving the accuracy and adaptability of power monitoring systems is an urgent issue that needs to be addressed. Summary of the Invention

[0004] This application provides a power monitoring optimization method and related device based on situational awareness and intelligent diagnosis. By deeply integrating situational awareness and intelligent diagnosis technologies, the monitoring parameters are transformed from static presets to dynamic adjustments based on real-time fault diagnosis results, thereby achieving precise focusing on high-risk areas and optimal resource allocation, ultimately improving the accuracy and adaptability of the power monitoring system.

[0005] In a first aspect, embodiments of this application provide a power monitoring optimization method based on situational awareness and intelligent diagnosis, the method comprising: Acquire multi-source real-time operational data and a power monitoring system corresponding to the target power system; the power monitoring system is used to monitor and adjust the real-time operational status of the target power system. Situational awareness analysis is performed on the multi-source real-time operational data to obtain situational assessment results; The situation assessment results are analyzed intelligently to obtain fault diagnosis results; A monitoring optimization strategy is generated based on the fault diagnosis results; Multiple target instruction sets are generated based on the monitoring optimization strategy; the target instruction sets are used to dynamically adjust the monitoring parameters of the power monitoring system for the equipment in the target power system.

[0006] Secondly, embodiments of this application provide a power monitoring optimization device based on situational awareness and intelligent diagnosis. The device includes an acquisition module, a first analysis module, a second analysis module, a first generation module, and a second generation module, wherein: The acquisition module is used to acquire multi-source real-time operating data and power monitoring system corresponding to the target power system; the power monitoring system is used to monitor and adjust the real-time operating status of the target power system. The first analysis module is used to perform situational awareness analysis on the multi-source real-time operating data to obtain situational assessment results; The second analysis module is used to perform intelligent diagnostic analysis on the situation assessment results to obtain fault diagnosis results; The first generation module is used to generate a monitoring optimization strategy based on the fault diagnosis results; The second generation module is used to generate multiple target instruction sets according to the monitoring optimization strategy; the target instruction sets are used to dynamically adjust the monitoring parameters of the power monitoring system for the equipment in the target power system.

[0007] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in any method of the first aspect of this application.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in any method of the first aspect of this application.

[0009] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of this application. The computer program product may be a software installation package.

[0010] By implementing the embodiments of this application, monitoring parameters can be transformed from static presets to dynamic adjustments based on real-time fault diagnosis results, based on situational awareness and intelligent diagnostic technology. This enables precise focusing on high-risk areas and optimal resource allocation, ultimately improving the accuracy and adaptability of the power monitoring system. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a system architecture diagram of a power monitoring system provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating the composition of a data processing unit provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 4 This is an application scenario diagram of a power monitoring system provided in an embodiment of this application; Figure 5 This is a flowchart illustrating a power monitoring optimization method based on situational awareness and intelligent diagnosis provided in an embodiment of this application. Figure 6 This is a schematic diagram of a situational awareness analysis process provided in an embodiment of this application; Figure 7 This is a schematic flowchart illustrating a method for generating a target instruction set, as provided in an embodiment of this application. Figure 8 This is a block diagram of the functional modules of a power monitoring and optimization device based on situational awareness and intelligent diagnosis provided in an embodiment of this application. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0014] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0015] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.

[0016] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0017] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.

[0018] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0019] Against the backdrop of rapid power system development, the large-scale integration of new energy sources and the surge in power equipment have led to more complex and volatile system operation, posing serious challenges to the real-time performance, accuracy, and adaptability of traditional power monitoring systems. In particular, the sampling frequency, data transmission rules, and other monitoring parameters of traditional power monitoring systems are usually pre-configured and statically fixed. This can result in resource waste during normal power system operation, and in the event of a fault or abnormal trend, insufficient monitoring density makes it impossible to capture critical information in a timely manner, failing to meet dynamically changing safety requirements. Therefore, improving the accuracy and adaptability of power monitoring systems is an urgent issue to be addressed.

[0020] To address the aforementioned issues, this application provides a power monitoring optimization method and related apparatus based on situational awareness and intelligent diagnosis. The method acquires multi-source real-time operational data and a power monitoring system corresponding to a target power system. The power monitoring system monitors and adjusts the real-time operational status of the target power system. Situational awareness analysis is performed on the multi-source real-time operational data to obtain a situational assessment result. Intelligent diagnostic analysis is performed on the situational assessment result to obtain a fault diagnosis result. A monitoring optimization strategy is generated based on the fault diagnosis result. Multiple target instruction sets are generated based on the monitoring optimization strategy. The target instruction sets are used to dynamically adjust the monitoring parameters of the power monitoring system for equipment in the target power system. By deeply integrating situational awareness and intelligent diagnosis technologies, and transforming the monitoring parameters from static presets to dynamic adjustments based on real-time fault diagnosis results, precise focusing on high-risk areas and optimal resource allocation are achieved, ultimately improving the accuracy and adaptability of the power monitoring system.

[0021] For easier understanding, please refer to Figure 1 , Figure 1 This is a system architecture diagram of a power monitoring system provided in an embodiment of this application. The power monitoring system includes a data acquisition unit, a data processing unit, a strategy generation unit, and an instruction execution unit.

[0022] The data acquisition unit collects multi-dimensional operational data in real time and accurately from various key nodes of the target power system, such as voltage, current, power, and frequency. The data acquisition unit consists of various sensors and intelligent electronic devices deployed on-site, such as voltage transformers for measuring voltage, current transformers for measuring current, frequency monitoring devices, power meters, and phase angle measurement units.

[0023] The data processing unit can perform a series of complex processing and intelligent analysis on the collected raw data. The data processing unit includes, but is not limited to: data preprocessing subunit, data fusion subunit, situational awareness subunit, and intelligent diagnosis subunit. No specific limitations are made here.

[0024] For easier understanding, please refer to Figure 2 , Figure 2This is a schematic diagram of a data processing unit provided in an embodiment of this application. The data preprocessing subunit cleans, denoises, aligns, and standardizes the raw data to eliminate noise and outliers, unify data format and dimensions, and ensure data quality. Next, the data fusion subunit performs feature-level fusion of preprocessed data from different data sources and of different types to generate a fused feature dataset, thus avoiding the limitations of a single data source. Based on this, the situational awareness subunit analyzes the fused feature dataset using a pre-defined situational assessment model, outputting a quantitative assessment of the overall system operating status, namely, the system stability level and risk warning indicators. Finally, the intelligent diagnosis subunit combines historical fault case databases and power system topology information to conduct in-depth analysis of potential faults, achieving accurate fault location and nature determination, and outputting fault type and probability.

[0025] The strategy generation unit can generate targeted and executable monitoring optimization strategies based on the target diagnostic results provided by the data processing unit. First, the strategy generation unit receives and parses key information such as fault type and fault probability from the data processing unit. Then, by querying a pre-set strategy knowledge base, the strategy generation unit can assess the impact level of the current fault on the system and identify target nodes that require focused monitoring. Based on these assessments, the strategy generation unit dynamically calculates an optimized monitoring frequency adjustment value for each target node. Simultaneously, it generates a prioritized data collection sequence for each target node based on the causal correlation strength between each state variable and the current fault, the urgency of the risk, and the current resource utilization of the system. Finally, the strategy generation unit integrates these decisions into a monitoring optimization strategy.

[0026] The instruction execution unit can transform the abstract monitoring and optimization strategies formulated by the strategy generation unit into a standardized instruction set that can be directly recognized and executed by the underlying devices of the power monitoring system. Then, the standardized instruction set is sent to the corresponding devices in the data acquisition unit via a pre-set communication link to dynamically adjust the relevant parameters of the data acquisition.

[0027] It is evident that through the collaborative efforts of various functional units within the power monitoring system, comprehensive perception, accurate diagnosis, and dynamic optimization of the target power system's operational status are achieved, significantly enhancing the accuracy and adaptability of system monitoring.

[0028] The following is combined Figure 3 The electronic devices in the embodiments of this application will be described. Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 3 As shown, the electronic device includes one or more processors, a memory, a communication interface, and one or more programs. The processor is connected to the memory and the communication interface via an internal communication bus.

[0029] The processor can be used for: Acquire multi-source real-time operational data and a power monitoring system corresponding to the target power system; the power monitoring system is used to monitor and adjust the real-time operational status of the target power system. Situational awareness analysis is performed on the multi-source real-time operational data to obtain situational assessment results; The situation assessment results are analyzed intelligently to obtain fault diagnosis results; A monitoring optimization strategy is generated based on the fault diagnosis results; Multiple target instruction sets are generated based on the monitoring optimization strategy; the target instruction sets are used to dynamically adjust the monitoring parameters of the power monitoring system for the equipment in the target power system.

[0030] The one or more programs are stored in the aforementioned memory and configured to be executed by the aforementioned processor, and the one or more programs include instructions for performing any step in the above method embodiments.

[0031] The processor can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, cells, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication unit can be a communication interface, transceiver, transceiver circuit, etc., and the storage unit can be a memory.

[0032] The memory can be volatile or non-volatile, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0033] It is understood that the electronic device may include more or fewer structural elements than those shown in the block diagram above, such as a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, a display module, etc., without limitation. It is understood that the electronic device may incorporate elements such as... Figure 1 The system architecture described above.

[0034] For easier understanding, please refer to Figure 4 , Figure 4 This is an application scenario diagram of a power monitoring system provided in an embodiment of this application. The target power system transmits multi-source real-time operating data (such as voltage, current, frequency, etc.) to the data acquisition unit of the power monitoring system. After receiving the external multi-source real-time operating data, the data acquisition unit of the power monitoring system transmits the data to the data processing unit for processing to obtain the processing result. The processing result is then input into the strategy generation unit to generate a monitoring optimization strategy. The instruction execution unit converts the monitoring optimization strategy into a target instruction set and sends it back to the data acquisition unit. This enables dynamic adjustment of the data acquisition behavior, thereby adapting to different operating scenarios of the target power system and facilitating accurate perception of the target power system's true operating status.

[0035] After understanding the software and hardware architecture of this application, the following will be combined with... Figure 5 This application describes a power monitoring optimization method based on situational awareness and intelligent diagnosis. Figure 5 This is a flowchart illustrating a power monitoring optimization method based on situational awareness and intelligent diagnosis provided in an embodiment of this application, specifically including the following steps: Step S501: Obtain multi-source real-time operation data and power monitoring system corresponding to the target power system.

[0036] The power monitoring system is used to monitor and adjust the real-time operating status of the target power system. This power monitoring system is a data acquisition and monitoring system matched to the target power system, possessing core functions such as data reception, status monitoring, parameter adjustment, and command issuance. It can obtain supplementary operating data (such as equipment ledgers and historical alarm records) from the target power system through a data receiving interface to assist in the verification and analysis of multi-source real-time operating data.

[0037] Specifically, a distributed data acquisition architecture can be adopted, which uses monitoring equipment deployed at key nodes of the target power system to synchronously collect multiple types of real-time operational data. The scope of this multi-source real-time operational data collection covers the generation side, transmission side, substation side, and distribution side of the target power system, including but not limited to: voltage deviation data, current fluctuation data, and frequency offset data. It can also be expanded to collect auxiliary operational data such as power factor, active power, and reactive power, which are not specifically limited here.

[0038] The calculation formulas for voltage deviation data, current fluctuation data, and frequency offset data are shown below:

[0039] in, It indicates voltage deviation and is used to reflect voltage stability; The actual voltage value at the time of acquisition; This refers to the system's rated voltage. For example, the rated voltage of a low-voltage system is 220V / 380V, the rated voltage of a medium-voltage system can be 6000V / 10000V, and the rated voltage of a high-voltage system is 35000V / 110000V. No specific limit is set here.

[0040]

[0041] in, The standard deviation of the current is used to represent the degree of current fluctuation. The larger the standard deviation of the current, the more severe the current fluctuation. It can be used to indicate abnormal load behavior. Within the preset time window The effective value of the current at each sampling point; The mean value of the current effective value within the time window is used as a benchmark value to calculate the degree of current fluctuation in order to determine whether there are abnormal behaviors such as load disturbances. This indicates the number of sampling points within the time window, and the value can range from 100 to 1000 to ensure that the sample size is sufficient for statistical validity.

[0042]

[0043] in, Indicates frequency offset; The actual frequency value at the time of acquisition; The system's rated frequency can be fixed at 50Hz, and no specific limit is specified here.

[0044] Step S502: Perform situational awareness analysis on the multi-source real-time operating data to obtain situational assessment results.

[0045] For easier understanding, please refer to Figure 6 , Figure 6 This is a schematic flowchart of a situational awareness analysis provided in an embodiment of this application. The multi-source real-time operating data includes voltage deviation data, current fluctuation data, and frequency offset data. The situational assessment result includes system stability level and risk warning indicators. The specific steps for performing situational awareness analysis on the multi-source real-time operating data to obtain the situational assessment result include: A1. Perform spatiotemporal alignment and preprocessing on the voltage deviation data, the current fluctuation data, and the frequency offset data to obtain first feature data, second feature data, and third feature data; A2. The first feature data, the second feature data, and the third feature data are fused to obtain a fused feature dataset; A3. Input the fused feature dataset into a preset situation assessment model to obtain the system stability level and the risk warning indicator.

[0046] In a specific embodiment, since voltage deviation data, current fluctuation data, and frequency offset data are collected by different types of monitoring equipment, and the sampling frequency, timestamp accuracy, and deployment location of each equipment differ, spatiotemporal alignment is required first. In the time dimension, linear interpolation is used to uniformly resample the data to the same time granularity, ensuring data synchronization in the time dimension. In the spatial dimension, based on the equipment ledger information of the target power system, a mapping relationship is established between data collection points and physical nodes of the power system, ensuring that each set of data corresponds to the same physical node or a node group with a clear electrical connection, achieving precise matching in the spatial dimension.

[0047] Then, the spatiotemporally aligned voltage deviation data, current fluctuation data, and frequency offset data are sequentially subjected to Z-Score normalization to obtain the first feature data, the second feature data, and the third feature data. The calculation formula for the normalization process is shown below:

[0048] in, Indicates at time The At the nth node, the nth The Z-score-standardized values ​​of class features can eliminate the differences in physical quantities, making the feature inputs have a consistent scale, which facilitates model convergence and generalization. Indicates at time The At the nth node, the nth Initial values ​​for class features; Features The mean and standard deviation of the sample set.

[0049] Next, the first, second, and third feature data are fused to obtain a fused feature dataset. Specifically, the first, second, and third feature data vectors within the same time window (e.g., 5 seconds) can be horizontally concatenated to form a fused feature vector. Then, all time windows are iterated through, and the fused feature vectors corresponding to each window are summarized to form the fused feature dataset. The expression for the fused feature dataset is as follows:

[0050] in, This represents a dataset with fused features. It represents the set of nodes in the target power system, including substation nodes, transmission line nodes, bus nodes, and user-end nodes, etc. This represents a set of feature categories, including voltage deviation, current fluctuation, and frequency offset. Represents a time series window.

[0051] Then, the fused feature dataset is input into a pre-defined situation assessment model, and the system stability level and risk warning indicator are obtained through model inference. The first expression corresponding to this situation assessment model is shown below:

[0052] in, The results of the situation assessment are indicated, including the system stability level and risk warning indicators; The situation assessment model, namely the deep spatiotemporal situation assessment model, consists of a hybrid structure of spatial attention layer and temporal attention layer. The number of model layers can be 2-6, the number of hidden dimensions is 64-256, and the number of attention heads is 4-8, without specific limitations.

[0053] The expression for the system stability level is as follows:

[0054] in, Indicates the system stability level, with a value range of [value range missing]. The closer the value is to 1, the more stable the target power system is; The core mapping relationship used to calculate the system stability level within the situation assessment model represents a complex nonlinear function learned by the model, from input features to stability level. For a moment Node active power, with a value range of: MW; For a moment Node reactive power, with a value range of: MVar is used for power flow distribution calculation and voltage safety margin estimation; For a moment Voltage values: Low-voltage systems range from 180-260V, medium-voltage systems range from 6000-20000V, and high-voltage systems range from 35000-500000V. For the future Voltage fluctuation prediction sequence of the step, The value can range from 5 to 20 steps; This is a future trend safety margin sequence, with the safety margin value ranging from 0 to 1. Values ​​less than 0.2 are considered high-risk.

[0055] Among them, the future power flow safety margin sequence is a normalized score that measures the margin between a node or line and its safe operating limit in the future. First, by predicting the system state variables at the current moment, the predicted active power load, reactive power load, and renewable energy output of each node in the next H steps can be obtained. The system state variables include: active power injection. Reactive power injection Voltage amplitude Then, using a pre-defined power flow calculation model, the predicted node states, such as voltage, current, and line power, are obtained for future times from t+1 to t+H. Then, for each time step... Calculate the following safety margin indicators:

[0056] in, Indicates voltage margin; Indicates time Node predicted voltage; For a moment The safe upper / lower limits of the node voltage range from 0.95 to 1.05. When the voltage approaches the upper / lower limit, the voltage margin decreases, and the voltage margin is negative under abnormal voltage.

[0057]

[0058] in, Indicates load margin; Is it the line or transformer in? Load power at any given moment; This is the rated capacity.

[0059]

[0060] in, Indicates the joint margin score; These are preset weighting coefficients, satisfying... .

[0061] Finally, output the future trend safety margin sequence. As shown below:

[0062] The expression for the risk warning indicator is as follows:

[0063] in, Indicates a risk warning sign; For the first Potential risk event types include voltage instability precursors, overload trends, and oscillation patterns; Total number of potential risk event types; This represents the confidence level of event recognition, with a value range of [value range missing]. This provides credibility support for the model output and helps distinguish noise from real risks; The risk urgency level can be divided into three levels: low, medium, and high.

[0064] It is evident that by preprocessing and fusing multi-source data, and utilizing situation assessment models, quantitative assessment and risk warning of the power system's operating status can be achieved, providing accurate and comprehensive decision-making basis for subsequent intelligent diagnosis and monitoring optimization.

[0065] Step S503: Perform intelligent diagnostic analysis on the situation assessment results to obtain fault diagnosis results.

[0066] The fault diagnosis result includes fault type and fault probability. The specific steps for performing intelligent diagnostic analysis on the situation assessment result to obtain the fault diagnosis result include: B1. Obtain the data subset in the fused feature dataset that corresponds to the risk warning sign, and obtain the reference data subset; B2. Determine the current risk type corresponding to the risk warning indicator; B3. Obtain historical failure cases that match the current risk type from the preset historical failure case library to obtain a reference failure case set; B4. Construct a diagnostic triplet based on the reference data subset, the reference fault case set, and the system stability level; B5. Input the diagnostic triplet into a preset fault diagnosis model to obtain the fault type and the fault probability.

[0067] In a specific embodiment, firstly, a subset of data corresponding to the risk warning flags in the fused feature dataset is obtained to obtain a reference data subset. Then, the risk warning flags are parsed to obtain the current risk type. Next, all historical fault cases matching the current risk type are retrieved from a preset historical fault case library to obtain a reference fault case set. This historical fault case library stores records of past fault events in the target power system; each record contains information such as the system state characteristics at the time of the fault, the fault phenomenon, the fault cause, and the handling measures.

[0068] Then, diagnostic triples are constructed based on the reference data subset, the reference fault case set, and the system stability level. The diagnostic triples are shown below:

[0069] in, Indicates a subset of reference data; Indicates a reference set of failure cases; This indicates the system's stability level.

[0070] Finally, the diagnostic triples are input into a pre-defined fault diagnosis model to obtain the fault type and fault probability. The fault diagnosis model includes a knowledge graph module and a data-driven module. The knowledge graph module includes power system equipment topology, component attributes, fault chains, and historical case paths. The data-driven module employs a graph neural network structure to process the input real-time feature data (i.e., a subset of reference data), historical fault cases (i.e., a set of reference fault cases), and stability scores (i.e., system stability levels) of the target power system, embedding them into the node representations in the knowledge graph to achieve high-dimensional fault reasoning.

[0071] It is evident that by integrating real-time data characteristics, historical fault experience, and system stability status to construct diagnostic criteria, intelligent diagnostic models can be used to accurately locate and determine the nature of potential faults in the power system.

[0072] The reference data subset includes multiple reference data records. The specific steps for inputting the diagnostic triplet into a preset fault diagnosis model to obtain the fault type and the fault probability include: C1. Obtain the global topology diagram corresponding to the target power system; C2. Obtain the reference node identifier corresponding to each of the plurality of reference data records to obtain the plurality of reference node identifiers; C3. Obtain the multiple reference nodes corresponding to the multiple reference node identifiers in the global topology diagram; C4. In the global topology diagram, taking each of the multiple reference nodes as the center, obtain all associated nodes with electrical connection within a preset adjacent range to obtain multiple sets of associated nodes. C5. Determine the sub-topology diagram based on the plurality of reference nodes and the plurality of associated node sets; C6. Analyze the diagnostic triplet and the sub-topology diagram according to the fault diagnosis model to obtain the fault type and the fault probability.

[0073] In a specific embodiment, firstly, a global topology diagram of the target power system is retrieved from a pre-defined power system resource database. This global topology diagram is stored in the form of graphical or structured data, accurately describing the generators, transformers, buses, lines, and other equipment (nodes) in the target power system and their electrical connections. Then, each reference data record in the reference data subset is traversed, and the corresponding reference node identifier is extracted from the metadata of each reference data record to obtain multiple reference node identifiers. Multiple reference nodes matching the multiple reference node identifiers are then obtained from the global topology diagram.

[0074] Next, in the global topology graph, taking each of the multiple reference nodes as the center, all associated nodes with electrical connections within a preset adjacency range are obtained, resulting in multiple sets of associated nodes. Then, the multiple sets of reference nodes and associated nodes are merged, and duplicate nodes are removed to obtain a comprehensive node set. Then, a corresponding sub-topology graph is constructed based on the nodes and branches corresponding to the comprehensive node set. Finally, a preset fault diagnosis model is invoked. This fault diagnosis model first processes the sub-topology graph, learns the embedded representation of each node in the sub-topology graph, and captures its position and connection characteristics in the network; then it fuses the node embedding with the information in the diagnostic triplet; finally, it performs inference through a multi-layer network to output the corresponding fault type and fault probability.

[0075] It should be noted that each node (corresponding to the target power system equipment) in the knowledge graph of the fault diagnosis model can be initialized as an embedding vector. This embedding vector contains static semantic information of the node (equipment attributes and topological relationships from the knowledge graph) and dynamic feature information (features of the reference data subset, the reference fault case set, and the system stability level). Then, the state representation of each node is iteratively updated through a hierarchical propagation mechanism: each node receives information from its neighboring nodes (corresponding to associated equipment in the physical topology); through feature aggregation and nonlinear transformation, the information of the neighboring nodes is fused into its node representation. After the graph propagation is completed, the focus is on the target equipment node, and its final embedding representation is input into the fault classifier. The fault classifier combines the node's own representation with the contextual information in the graph structure to output the fault type and fault probability.

[0076] It is evident that by deeply integrating real-time data with the power system topology, the location accuracy and analysis efficiency of fault diagnosis are significantly improved.

[0077] Step S504: Generate a monitoring optimization strategy based on the fault diagnosis results.

[0078] The fault type includes fault location information and fault nature information. The specific steps for generating a monitoring optimization strategy based on the fault diagnosis results include: D1. Parse the fault nature information to obtain the fault type identifier; D2. Determine the fault confidence score based on the fault probability; D3. Obtain the fault impact level corresponding to the fault type identifier in the preset strategy knowledge base; D3. Determine the monitoring frequency adjustment value based on the fault confidence score, the fault impact level, and the system stability level; D5. Obtain the target node corresponding to the fault location information in the sub-topology diagram to obtain multiple target nodes; D6. Obtain all state variables of each of the multiple target nodes to obtain multiple state variable sets; each state variable set corresponds to one target node. D7. Determine multiple target data acquisition sequences based on the multiple sets of state variables; D8. Generate the monitoring optimization strategy based on the monitoring frequency adjustment value and the multiple target data acquisition sequences.

[0079] In a specific embodiment, firstly, the fault nature information is parsed to obtain a fault phenomenon description, such as "single-phase ground fault," "three-phase imbalance," or "overload." Then, by querying a preset fault type mapping dictionary, the fault phenomenon description is converted into a corresponding fault type identifier. Next, the fault probability is converted into a fault confidence score. Then, the fault impact level corresponding to the fault type identifier is obtained from a preset strategy knowledge base. Based on the fault confidence score, fault impact level, and system stability level, a monitoring frequency adjustment value is calculated. The calculation formula for the monitoring frequency adjustment value is as follows:

[0080] in, This indicates the monitoring frequency adjustment value, used to dynamically adjust the sampling frequency; This represents the scaling factor, which is used to adjust the global sampling increase. The value range is 1-5, and it is the result of a trade-off between monitoring sensitivity control, system load tolerance, and deployment flexibility. Indicates the fault confidence score; Indicates the fault type identifier The level of impact on system stability, i.e. the level of failure impact.

[0081] Next, the target nodes corresponding to the fault location information in the sub-topology diagram are obtained, resulting in multiple target nodes. Then, all state variables of each target node are obtained, resulting in multiple state variable sets, each set corresponding to one target node. The state variables in the set include, but are not limited to, voltage, current, and frequency, without specific limitations here.

[0082] Finally, multiple target data acquisition sequences are determined based on multiple sets of state variables, and a monitoring optimization strategy is generated based on the monitoring frequency adjustment value and the multiple target data acquisition sequences.

[0083] It is evident that by comprehensively assessing the characteristics of the fault, its impact, and the system status, dynamic, accurate, and prioritized configuration of monitoring resources has been achieved.

[0084] The specific steps of determining multiple target data acquisition sequences based on the multiple sets of state variables include: E1. Determine the causal association strength between each state variable in the first set of state variables and the fault type based on the strategy knowledge base, and obtain multiple causal association strengths; the first set of state variables is any one of the multiple sets of state variables. E2. Determine the risk urgency level corresponding to the risk warning indicator; E3. Determine multiple data collection priorities based on the preset resource scheduling coefficient, the risk urgency level, and each of the multiple causal correlation strengths; E4. Sort the multiple data acquisition priorities from high to low to obtain the first priority sequence; E5. Determine the target data acquisition sequence corresponding to the first state variable set among the plurality of target data acquisition sequences according to the first priority sequence.

[0085] In a specific embodiment, any one of the multiple sets of state variables is defined as the first set of state variables. The causal correlation strength between each state variable in the first set of state variables and the fault type is determined based on the policy knowledge base, resulting in multiple causal correlation strengths. The causal correlation strength is a value between 0 and 1; a higher value indicates that the state variable is more critical for diagnosing this type of fault. Risk warning indicators are parsed to obtain the risk urgency level. Multiple data collection priorities are calculated based on a preset resource scheduling coefficient, the risk urgency level, and each causal correlation strength among the multiple causal correlation strengths. The calculation formula for the data collection priority is as follows:

[0086] in, Indicates the first Data acquisition priority for each state variable; This represents the resource scheduling coefficient, which controls the distribution range of the overall priority level, and its value ranges from 1. 10; State variables Fault type identifier The strength of causal association, with a value range of ; The value indicates the level of risk urgency, with a value of 1 for low level, 2 for medium level, and 3 for high level.

[0087] Then, the multiple data acquisition priorities are sorted from highest to lowest to obtain the first priority sequence. The first priority sequence is then associated with its corresponding state variables to obtain the target data acquisition sequence corresponding to the first set of state variables in the multiple target data acquisition sequences. For each set of state variables, steps E1 to E5 are repeated to ultimately obtain the multiple target data acquisition sequences.

[0088] It is evident that by introducing domain knowledge and real-time risk assessment, data collection can be prioritized to ensure that the most critical operational data is acquired first when resources are limited, thereby maximizing the value of monitoring information.

[0089] Step S505: Generate multiple target instruction sets according to the monitoring optimization strategy.

[0090] For easier understanding, please refer to Figure 7 , Figure 7 This is a flowchart illustrating the generation of a target instruction set according to an embodiment of this application. The target instruction set is used to dynamically adjust the monitoring parameters of the power monitoring system for equipment in the target power system. The specific steps of generating multiple target instruction sets according to the monitoring optimization strategy include: F1. Determine the multiple target node identifiers corresponding to the multiple target nodes based on the sub-topology diagram; F2. Obtain multiple initial sampling frequencies corresponding to the multiple target nodes; F3. Adjust the multiple initial sampling frequencies according to the monitoring frequency adjustment value to obtain multiple target sampling frequencies; F4. Generate the multiple target instruction sets based on the multiple target node identifiers, the multiple target sampling frequencies, and the multiple target data acquisition sequences.

[0091] In a specific embodiment, in the sub-topology diagram, the corresponding target node identifier is extracted from the attribute information of each target node among multiple target nodes to obtain multiple target node identifiers. A preset monitoring parameter configuration library is queried to obtain the initial sampling frequency corresponding to each target node among the multiple target nodes, resulting in multiple initial sampling frequencies. Then, the multiple initial sampling frequencies are adjusted according to the monitoring frequency adjustment value to obtain multiple target sampling frequencies.

[0092] Finally, multiple target instruction sets are generated based on multiple target node identifiers, multiple target sampling frequencies, and multiple target data acquisition sequences. The expressions for these multiple target instruction sets are shown below:

[0093] in, Represents a set of multiple target instruction sets; Indicates the first Each target node identifier is typically a 16-64 bit code. The device corresponding to this target node identifier is a monitoring terminal or control node device that is currently in a potentially risky area and requires key supervision or policy intervention. Indicates the first One target sampling frequency; Indicates the first A target data acquisition sequence.

[0094] It is evident that by transforming monitoring optimization strategies into a standardized instruction set that the power monitoring system can directly execute, precise and dynamic adjustment of the monitoring parameters of the target equipment is achieved.

[0095] In one possible embodiment, multiple target instruction sets can be pushed in real time to multiple target devices corresponding to multiple target node identifiers through a unified instruction distribution channel built into the power monitoring system. These multiple target devices are all located within the fault location area and its electrical associated range, and include data acquisition devices and communication management units. Upon receiving the first target instruction set, the first target device (i.e., any one of the multiple target devices) adjusts the sampling frequency of its internal sensors (ranging from 0.1 to 10 Hz) according to the first target sampling frequency and updates its local cache mechanism, such as shortening the cache refresh cycle and increasing the memory cleaning priority. The first communication management unit adjusts the communication link bandwidth allocation weight, data packet upload order, latency tolerance threshold, packet loss tolerance range, or duplicate transmission mechanism under abnormal conditions based on the first target data acquisition sequence. High-priority status variables are allocated more bandwidth, shorter queuing times, and stricter transmission guarantees to ensure that their data can be transmitted to the target power system preferentially and stably.

[0096] In one possible embodiment, a preset observation period is observed after the application of the monitoring optimization strategy. It can continuously collect and update multi-source real-time operational data. Based on the existing fault diagnosis results, the actual effectiveness of the monitoring optimization strategy is evaluated, and a set of strategy effectiveness indicators is output. The expression for the strategy effectiveness indicator set is as follows:

[0097] in, This represents a set of indicators indicating the effectiveness of a strategy. Indicates the accuracy of fault status tracking; Indicates the false alarm / missed alarm rate for early warnings; This indicates the degree of improvement in the utilization rate of monitoring resources.

[0098]

[0099] in, Indicates the observation period The number of sampling points that correctly track the fault evolution process; This represents the total number of sampling points in the same area / device, with a range of 0-1. The closer to 1, the more accurate the tracking.

[0100]

[0101] in, Indicates the number of false alarms; Indicates the number of missed reports; This indicates the total number of all warning events.

[0102]

[0103] in, The effective data collection ratio per unit bandwidth / computing resource before the application of monitoring optimization strategies; The ratio of effective collected data per unit bandwidth / computing resource after the application of monitoring optimization strategies can reflect the contribution of optimization strategies to the overall resource scheduling efficiency of the system.

[0104] The strategy effectiveness metrics set can be compared item by item with the preset performance threshold set to obtain the comparison results, as shown below:

[0105] in, Represents a set of preset performance thresholds; This represents the minimum acceptable fault tracing accuracy threshold, with a value range of [value missing]. ; This represents the maximum tolerable false alarm / false alarm rate threshold, with a value range of [value missing]. ; This represents the minimum threshold for improving resource utilization, and its corresponding value range is... .

[0106] Among these features, a multi-target adjustment instruction set can be generated based on the direction and severity of the deviation of the indicators in the comparison results. It is used for the model parameters and strategy rules of the fine control system.

[0107] When the fault status tracking accuracy is insufficient, i.e. At that time, the weights of some features in the fault diagnosis model are automatically adjusted. As shown below:

[0108]

[0109] in, This represents the updated feature weights; Indicates the feature weights before the update; This represents the weight adjustment value; This represents the gradient of fault tracking accuracy with respect to feature weights.

[0110] Among them, when the false alarm rate of the early warning is too high, that is It can update the risk event judgment threshold in the situation assessment model. Simultaneously revise the relevant triggering conditions in the strategy knowledge base, reduce the probability of non-critical factors being triggered, and update the risk event judgment thresholds. The expression is as follows:

[0111] in, This indicates the updated risk event determination threshold; This indicates the risk event judgment threshold before the update; This represents the threshold correction amount, and its value is positively correlated with the degree to which the false alarm rate exceeds the limit.

[0112] Among them, when the improvement in resource utilization rate is lower than expected, that is It can dynamically adjust the parameters in the policy mapping rules, including the sampling frequency scaling factor. Data acquisition priority amplification factor This is to increase the weight of critical path resource allocation or increase the scheduling scope.

[0113] The above primarily describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0114] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0115] When dividing each function into modules according to its corresponding function. Figure 8This is a functional module block diagram of a power monitoring and optimization device based on situational awareness and intelligent diagnosis provided in an embodiment of this application. The power monitoring and optimization device 800 based on situational awareness and intelligent diagnosis includes an acquisition module 810, a first analysis module 820, a second analysis module 830, a first generation module 840, and a second generation module 850, wherein: The acquisition module 810 is used to acquire multi-source real-time operating data and power monitoring system corresponding to the target power system; the power monitoring system is used to monitor and adjust the real-time operating status of the target power system. The first analysis module 820 is used to perform situational awareness analysis on the multi-source real-time operating data to obtain situational assessment results; The second analysis module 830 is used to perform intelligent diagnostic analysis on the situation assessment results to obtain fault diagnosis results; The first generation module 840 is used to generate a monitoring optimization strategy based on the fault diagnosis results; The second generation module 850 is used to generate multiple target instruction sets according to the monitoring optimization strategy; the target instruction sets are used to dynamically adjust the monitoring parameters of the power monitoring system for the equipment in the target power system.

[0116] Optionally, the multi-source real-time operating data includes voltage deviation data, current fluctuation data, and frequency offset data, and the situation assessment result includes system stability level and risk warning indicator. Regarding the situation awareness analysis of the multi-source real-time operating data to obtain the situation assessment result, the first analysis module 820 is specifically used for: The voltage deviation data, the current fluctuation data, and the frequency offset data are spatiotemporally aligned and preprocessed to obtain first feature data, second feature data, and third feature data. The first feature data, the second feature data, and the third feature data are fused to obtain a fused feature dataset. The fused feature dataset is input into a preset situation assessment model to obtain the system stability level and the risk warning indicator.

[0117] Optionally, the fault diagnosis result includes fault type and fault probability. Regarding the intelligent diagnostic analysis of the situation assessment result to obtain the fault diagnosis result, the second analysis module 830 is specifically used for: Obtain the data subset in the fused feature dataset that corresponds to the risk warning flag to obtain the reference data subset; Determine the current risk type corresponding to the risk warning indicator; A reference failure case set is obtained by retrieving historical failure cases that match the current risk type from a preset historical failure case library; Construct a diagnostic triplet based on the reference data subset, the reference fault case set, and the system stability level; The diagnostic triplet is input into a preset fault diagnosis model to obtain the fault type and the fault probability.

[0118] Optionally, the reference data subset includes multiple reference data records. Regarding inputting the diagnostic triplet into a preset fault diagnosis model to obtain the fault type and the fault probability, the second analysis module 830 is further specifically used for: Obtain the global topology diagram corresponding to the target power system; Obtain the reference node identifier corresponding to each of the plurality of reference data records to obtain a plurality of reference node identifiers; Obtain the identifiers of the multiple reference nodes corresponding to the multiple reference nodes in the global topology graph; In the global topology diagram, taking each of the multiple reference nodes as the center, all associated nodes with electrical connection to it within a preset adjacency range are obtained, resulting in multiple sets of associated nodes; The sub-topology diagram is determined based on the plurality of reference nodes and the plurality of associated node sets; The fault type and the fault probability are obtained by analyzing the diagnostic triplet and the sub-topology diagram based on the fault diagnosis model.

[0119] Optionally, the fault type includes fault location information and fault nature information. In generating the monitoring optimization strategy based on the fault diagnosis result, the first generation module 840 is specifically used for: The fault nature information is parsed to obtain the fault type identifier; The failure confidence score is determined based on the failure probability. Obtain the fault impact level corresponding to the fault type identifier in the preset strategy knowledge base; The monitoring frequency adjustment value is determined based on the fault confidence score, the fault impact level, and the system stability level. Obtain the target node corresponding to the fault location information in the sub-topology diagram to obtain multiple target nodes; Obtain all state variables of each of the multiple target nodes to obtain multiple sets of state variables; each set of state variables corresponds to one target node. Multiple target data acquisition sequences are determined based on the multiple sets of state variables; The monitoring optimization strategy is generated based on the monitoring frequency adjustment value and the multiple target data acquisition sequences.

[0120] Optionally, in determining the multiple target data acquisition sequences based on the multiple sets of state variables, the first generation module 840 is further specifically used for: Based on the strategy knowledge base, the causal association strength between each state variable in the first set of state variables and the fault type is determined to obtain multiple causal association strengths; the first set of state variables is any one of the multiple sets of state variables. Determine the risk urgency level corresponding to the risk warning indicator; Multiple data collection priorities are determined based on preset resource scheduling coefficients, the risk urgency level, and each of the multiple causal correlation strengths. The multiple data acquisition priorities are sorted from high to low to obtain the first priority sequence; The target data acquisition sequence corresponding to the first set of state variables among the plurality of target data acquisition sequences is determined based on the first priority sequence.

[0121] Optionally, in generating multiple target instruction sets according to the monitoring optimization strategy, the second generation module 850 is specifically used for: Based on the sub-topology diagram, determine the multiple target node identifiers corresponding to the multiple target nodes; Obtain multiple initial sampling frequencies corresponding to the multiple target nodes; The multiple initial sampling frequencies are adjusted according to the monitoring frequency adjustment value to obtain multiple target sampling frequencies; The multiple target instruction sets are generated based on the multiple target node identifiers, the multiple target sampling frequencies, and the multiple target data acquisition sequences.

[0122] It is evident that by deeply integrating situational awareness and intelligent diagnostic technologies, and transforming monitoring parameters from static presets to dynamic adjustments based on real-time fault diagnosis results, precise focusing on high-risk areas and optimal resource allocation can be achieved, ultimately improving the accuracy and adaptability of the power monitoring system.

[0123] It should be noted that the specific implementation of each operation can be described in the corresponding description of the method embodiments shown above. The power monitoring and optimization device 800 based on situational awareness and intelligent diagnosis can be used to execute the above method embodiments of this application, and will not be described again here.

[0124] This application also provides a computer-readable storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0125] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0126] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0127] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0128] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0129] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0130] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0131] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on the processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented through a software program that runs on the processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0132] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A power monitoring optimization method based on situational awareness and intelligent diagnosis, characterized in that, The method includes: Acquire multi-source real-time operational data and a power monitoring system corresponding to the target power system; the power monitoring system is used to monitor and adjust the real-time operational status of the target power system. Situational awareness analysis is performed on the multi-source real-time operational data to obtain situational assessment results; The situation assessment results are analyzed intelligently to obtain fault diagnosis results; A monitoring optimization strategy is generated based on the fault diagnosis results; Multiple target instruction sets are generated based on the monitoring optimization strategy; the target instruction sets are used to dynamically adjust the monitoring parameters of the power monitoring system for the equipment in the target power system.

2. The method as described in claim 1, characterized in that, The multi-source real-time operating data includes voltage deviation data, current fluctuation data, and frequency offset data. The situation assessment results include system stability level and risk warning indicators. The situation awareness analysis of the multi-source real-time operating data to obtain the situation assessment results includes: The voltage deviation data, the current fluctuation data, and the frequency offset data are spatiotemporally aligned and preprocessed to obtain first feature data, second feature data, and third feature data. The first feature data, the second feature data, and the third feature data are fused to obtain a fused feature dataset. The fused feature dataset is input into a preset situation assessment model to obtain the system stability level and the risk warning indicator.

3. The method as described in claim 2, characterized in that, The fault diagnosis result includes fault type and fault probability. The intelligent diagnostic analysis of the situation assessment result to obtain the fault diagnosis result includes: Obtain the data subset in the fused feature dataset that corresponds to the risk warning flag to obtain the reference data subset; Determine the current risk type corresponding to the risk warning indicator; A reference failure case set is obtained by retrieving historical failure cases that match the current risk type from a preset historical failure case library; Construct a diagnostic triplet based on the reference data subset, the reference fault case set, and the system stability level; The diagnostic triplet is input into a preset fault diagnosis model to obtain the fault type and the fault probability.

4. The method as described in claim 3, characterized in that, The reference data subset includes multiple reference data records. The step of inputting the diagnostic triplet into a preset fault diagnosis model to obtain the fault type and the fault probability includes: Obtain the global topology diagram corresponding to the target power system; Obtain the reference node identifier corresponding to each of the plurality of reference data records to obtain a plurality of reference node identifiers; Obtain the identifiers of the multiple reference nodes corresponding to the multiple reference nodes in the global topology graph; In the global topology diagram, taking each of the multiple reference nodes as the center, all associated nodes with electrical connection to it within a preset adjacency range are obtained, resulting in multiple sets of associated nodes; The sub-topology diagram is determined based on the plurality of reference nodes and the plurality of associated node sets; The fault type and the fault probability are obtained by analyzing the diagnostic triplet and the sub-topology diagram based on the fault diagnosis model.

5. The method as described in claim 4, characterized in that, The fault type includes fault location information and fault nature information. The step of generating a monitoring optimization strategy based on the fault diagnosis results includes: The fault nature information is parsed to obtain the fault type identifier; The failure confidence score is determined based on the failure probability. Obtain the fault impact level corresponding to the fault type identifier in the preset strategy knowledge base; The monitoring frequency adjustment value is determined based on the fault confidence score, the fault impact level, and the system stability level. Obtain the target node corresponding to the fault location information in the sub-topology diagram to obtain multiple target nodes; Obtain all state variables of each of the multiple target nodes to obtain multiple sets of state variables; each set of state variables corresponds to one target node. Multiple target data acquisition sequences are determined based on the multiple sets of state variables; The monitoring optimization strategy is generated based on the monitoring frequency adjustment value and the multiple target data acquisition sequences.

6. The method as described in claim 5, characterized in that, The step of determining multiple target data acquisition sequences based on the multiple sets of state variables includes: Based on the strategy knowledge base, the causal association strength between each state variable in the first set of state variables and the fault type is determined to obtain multiple causal association strengths; the first set of state variables is any one of the multiple sets of state variables. Determine the risk urgency level corresponding to the risk warning indicator; Multiple data collection priorities are determined based on preset resource scheduling coefficients, the risk urgency level, and each of the multiple causal correlation strengths. The multiple data acquisition priorities are sorted from high to low to obtain the first priority sequence; The target data acquisition sequence corresponding to the first set of state variables among the plurality of target data acquisition sequences is determined based on the first priority sequence.

7. The method as described in claim 5 or 6, characterized in that, The generation of multiple target instruction sets based on the monitoring optimization strategy includes: Based on the sub-topology diagram, determine the multiple target node identifiers corresponding to the multiple target nodes; Obtain multiple initial sampling frequencies corresponding to the multiple target nodes; The multiple initial sampling frequencies are adjusted according to the monitoring frequency adjustment value to obtain multiple target sampling frequencies; The multiple target instruction sets are generated based on the multiple target node identifiers, the multiple target sampling frequencies, and the multiple target data acquisition sequences.

8. A power monitoring and optimization device based on situational awareness and intelligent diagnosis, characterized in that, The device includes an acquisition module, a first analysis module, a second analysis module, a first generation module, and a second generation module, wherein: The acquisition module is used to acquire multi-source real-time operating data and power monitoring system corresponding to the target power system; the power monitoring system is used to monitor and adjust the real-time operating status of the target power system. The first analysis module is used to perform situational awareness analysis on the multi-source real-time operating data to obtain situational assessment results; The second analysis module is used to perform intelligent diagnostic analysis on the situation assessment results to obtain fault diagnosis results; The first generation module is used to generate a monitoring optimization strategy based on the fault diagnosis results; The second generation module is used to generate multiple target instruction sets according to the monitoring optimization strategy; the target instruction sets are used to dynamically adjust the monitoring parameters of the power monitoring system for the equipment in the target power system.

9. An electronic device, characterized in that, include: Processor, memory, communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-7.

Images