Power grid fault prediction processing method and system based on panoramic situation awareness

Abstract

The application discloses a power grid fault prediction processing method and system based on panoramic situation awareness, and belongs to the field of power grid fault prediction, wherein the method comprises the following steps: collecting data of a target power grid through a panoramic situation awareness system to obtain a multi-source perception data set; building a power grid spatial topology structure; clustering each node in the power grid spatial topology structure to output a multi-layer topology network; constructing an intra-layer fault propagation model and a cross-layer fault transfer model; connecting the panoramic situation awareness system to obtain real-time power grid state data of the target power grid; and predicting faults based on the real-time power grid state data to output multiple fault early warning information. The application solves the technical problem that the power grid fault prediction in the prior art lacks multi-level dynamic analysis and cross-layer influence consideration, resulting in insufficient accuracy and timeliness of fault early warning, and achieves the technical effect of improving the accuracy and timeliness of power grid fault prediction through intra-layer fault propagation and cross-layer fault transfer of the multi-layer topology network.

Description

Technical Field

[0001] This invention relates to the field of power grid fault prediction, and specifically to a power grid fault prediction and processing method and system based on panoramic situational awareness. Background Technology

[0002] Existing power grid fault prediction methods are mainly based on single-level data analysis and simple network models, typically considering only local network structures and static fault modes. This makes it difficult to comprehensively reflect the multi-layered structural characteristics of the power grid and the dynamic fault propagation process. For example, existing methods focus on faults at the distribution network level while neglecting the interaction with the transmission network; or, while considering network topology, they fail to effectively simulate the fault transfer mechanisms between different levels. Therefore, the lack of multi-level dynamic analysis and consideration of cross-level impacts results in insufficient accuracy and timeliness of power grid fault early warning. Summary of the Invention

[0003] This application provides a power grid fault prediction and processing method and system based on panoramic situational awareness, aiming to solve the technical problem that the lack of multi-level dynamic analysis and cross-level impact consideration in the existing power grid fault prediction technology leads to insufficient accuracy and timeliness of fault early warning.

[0004] In view of the above problems, this application provides a power grid fault prediction and processing method and system based on panoramic situational awareness.

[0005] The first aspect disclosed in this application provides a power grid fault prediction and processing method based on panoramic situational awareness. The method includes: acquiring data from a target power grid using a panoramic situational awareness system to obtain a multi-source sensing dataset; constructing a power grid spatial topology based on the multi-source sensing dataset; clustering each node in the power grid spatial topology to output a multi-layer topology network; constructing an intra-layer fault propagation model for each layer of the multi-layer topology network, and a cross-layer fault transfer model between layers in the multi-layer topology network; connecting to the panoramic situational awareness system to obtain real-time power grid status data of the target power grid; and performing fault prediction on the real-time power grid status data based on the intra-layer fault propagation model and the cross-layer fault transfer model, outputting multiple fault warning messages.

[0006] Another aspect of this application discloses a power grid fault prediction and processing system based on panoramic situational awareness. This system includes: a data acquisition module for acquiring data from a target power grid through a panoramic situational awareness system to obtain a multi-source sensing dataset; a topology construction module for building a power grid spatial topology based on the multi-source sensing dataset; a multi-layer clustering module for clustering nodes in the power grid spatial topology to output a multi-layer topology network; a model construction module for constructing an intra-layer fault propagation model for each layer of the multi-layer topology network, and a cross-layer fault transfer model between layers in the multi-layer topology network; a real-time data acquisition module for connecting to the panoramic situational awareness system to acquire real-time power grid status data of the target power grid; and a fault prediction module for performing fault prediction on the real-time power grid status data based on the intra-layer fault propagation model and the cross-layer fault transfer model, and outputting multiple fault warning messages.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By employing a panoramic situational awareness system to collect data from the target power grid and acquiring a multi-source sensing dataset, a comprehensive understanding of the power grid's operational status is achieved, providing a rich data foundation for subsequent analysis. Based on the multi-source sensing dataset, a power grid spatial topology structure is constructed, laying the groundwork for subsequent multi-level analysis. Clustering of nodes within the power grid spatial topology structure outputs a multi-layer topology network, realizing a multi-level division of the power grid structure and reflecting its hierarchical characteristics, thus creating conditions for more refined fault analysis. Intra-layer fault propagation models for each layer of the multi-layer topology network are constructed, as well as cross-layer fault transfer models between layers in the multi-layer topology network, simulating fault propagation within a single layer while considering different layers. Inter-level fault transfer comprehensively characterizes the dynamic propagation characteristics of faults; connecting to a panoramic situational awareness system acquires real-time grid status data of the target power grid, enabling fault prediction to be based on the latest grid operating status; based on intra-layer fault propagation models and cross-layer fault transfer models, fault prediction is performed on real-time grid status data, outputting multiple fault warning messages, realizing an accurate and timely fault prediction and warning technical solution. This solves the technical problem in existing technologies where grid fault prediction lacks multi-level dynamic analysis and cross-layer impact considerations, resulting in insufficient accuracy and timeliness of fault warnings. It achieves the technical effect of improving the accuracy and timeliness of grid fault prediction through intra-layer fault propagation and cross-layer fault transfer in multi-layer topology networks.

[0009] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0010] Figure 1 A flowchart illustrating a power grid fault prediction and processing method based on panoramic situational awareness is provided for embodiments of this application.

[0011] Figure 2 A schematic diagram of a power grid fault prediction and processing system based on panoramic situational awareness is provided for the embodiments of this application.

[0012] Figure labeling: Data acquisition module 11, topology construction module 12, multi-layer clustering module 13, model construction module 14, real-time data acquisition module 15, fault prediction module 16. Detailed Implementation

[0013] The overall concept of the technical solution provided in this application is as follows:

[0014] This application provides a power grid fault prediction and processing method and system based on panoramic situational awareness. First, a panoramic situational awareness system is used to collect multi-source data to construct the spatial topology of the power grid. Then, the power grid structure is divided into multiple layers, forming a multi-layer topology network. Based on this, an intra-layer fault propagation model and a cross-layer fault transfer model are simultaneously constructed, enabling fault prediction to comprehensively consider the complex structure and dynamic characteristics of the power grid. Subsequently, real-time power grid status data is acquired and combined with the aforementioned models for fault prediction and early warning. Through a systematic and multi-layered analysis method, this approach effectively solves the problems of traditional power grid fault prediction methods, such as lack of consideration for the multi-layered structure of the power grid and inability to effectively simulate the dynamic propagation process of faults, thus improving the accuracy and timeliness of fault prediction.

[0015] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0016] Example 1, as Figure 1 As shown in the embodiments of this application, a power grid fault prediction and processing method based on panoramic situational awareness is provided. The method includes:

[0017] S1: Collect data from the target power grid using a panoramic situational awareness system to obtain a multi-source sensing dataset.

[0018] Specifically, a panoramic situational awareness system is used to comprehensively collect data from the target power grid, acquiring a multi-source sensing dataset. This panoramic situational awareness system is a comprehensive data acquisition platform that integrates various sensing devices distributed throughout the power grid, including high-precision measuring instruments installed in substations, smart meters connected to the distribution network, and online monitoring devices monitoring transmission lines. This forms a broad sensing network capable of capturing various operating parameters and status information of the power grid in real time. The multi-source sensing dataset collected by the panoramic situational awareness system contains rich and diverse information, covering basic electrical parameters such as voltage, current, and power; equipment operating conditions such as transformer temperature and switch status; and environmental factors such as ambient temperature and humidity. Furthermore, it includes precise geographical location information for each device, providing a foundation for subsequently constructing the spatial topology of the power grid.

[0019] Comprehensive data collection lays the foundation for subsequent power grid analysis and fault prediction, enabling a more accurate grasp of the overall operating status of the power grid and thus improving the accuracy and reliability of fault prediction.

[0020] S2: Based on the multi-source sensing dataset, construct the power grid spatial topology.

[0021] Specifically, firstly, the multi-source sensing dataset undergoes preprocessing and data fusion. Preprocessing includes, but is not limited to, data cleaning, outlier handling, and time series alignment to ensure data quality and consistency. Data fusion leverages the complementarity of multi-source data to integrate information from different sources, forming a more comprehensive and accurate description of the power grid's state. Subsequently, based on the processed data, graph theory and complex network theory are used to abstract the power grid into a topological structure composed of nodes and edges. Nodes represent key power equipment or facilities such as substations, distribution rooms, and important users, while edges represent power transmission paths between these nodes, such as transmission lines and distribution lines. Furthermore, considering the dynamic characteristics of the power grid, a dynamic topological model that evolves over time is established by analyzing topological changes in historical data, such as switching operations and line switching. This results in a spatial topological structure of the power grid that combines electrical characteristics, geographical information, and temporal dynamics, laying a structural foundation for achieving high-precision power grid fault prediction.

[0022] S3: Cluster the nodes in the power grid spatial topology and output a multi-layer topology network.

[0023] Specifically, firstly, the node characteristics of each node in the power grid spatial topology are obtained, including geographical distance characteristics, electrical similarity characteristics, and connection edge length characteristics. Then, based on these characteristics, a multi-dimensional similarity measurement method is used to calculate a comprehensive similarity index for each pair of nodes. For example, weighted Euclidean distance, cosine similarity, or other suitable metrics can be used to comprehensively reflect the degree of similarity between nodes. Subsequently, clustering algorithms are used to group the nodes, including but not limited to K-means, spectral clustering, and hierarchical clustering. During the clustering process, an adaptive parameter adjustment mechanism is introduced to ensure that the stability of each layer of the topology meets a preset threshold. The clustering process is iterative until all nodes in the power grid spatial topology are traversed, resulting in a multi-layered topology network structure, where each layer represents a set of nodes with similar characteristics.

[0024] By performing multi-level clustering of the power grid spatial topology, a structured framework is provided for subsequent fault propagation analysis, which helps to reduce complexity, improve computational efficiency, and more accurately characterize the propagation characteristics of faults at different scales and ranges, thus laying the foundation for achieving high-precision, multi-scale power grid fault prediction.

[0025] S4: Construct an intra-layer fault propagation model for each layer of the multi-layer topology network, and a cross-layer fault transfer model between layers in the multi-layer topology network.

[0026] Specifically, two key models are constructed in multi-layer topology networks: a fault propagation model within each layer of the topology network, and a cross-layer fault transfer model between layers, to comprehensively describe how power grid faults propagate within and between different layers.

[0027] For the intra-layer fault propagation model, simulation data containing fault propagation paths and probabilities was first collected. Based on this data, a random walk model was used to describe the spread of faults in the network. By calculating the propagation probabilities between nodes and considering the initial state and evolution rate of the fault, a mathematical model that accurately describes the characteristics of intra-layer fault propagation was finally obtained. When constructing the cross-layer fault transfer model, the connecting nodes between different layers were first identified. Then, based on the cross-layer connection relationships and fault transfer data, a probabilistic model describing how a fault propagates from one layer to another was established. Similarly, the random walk method was used, considering the initial conditions and evolution process of cross-layer propagation, to form a mathematical model for cross-layer fault transfer.

[0028] By employing a multi-level, cross-scale modeling approach, the complexity and hierarchy of the power grid system are taken into account. This approach can simultaneously capture both the micro-mechanisms and macro-trends of fault propagation, laying a solid theoretical and model foundation for subsequent high-precision fault prediction and contributing to a more comprehensive and accurate prediction of fault propagation in the power grid.

[0029] S5: Connect to the panoramic situational awareness system to obtain real-time power grid status data of the target power grid.

[0030] Specifically, by connecting to a panoramic situational awareness system, real-time status data of the target power grid is acquired. First, a real-time connection is established with the panoramic situational awareness system to ensure continuous acquisition of the latest power grid operation information. Then, through the panoramic situational awareness system, real-time power grid status data of the target power grid is acquired, including various electrical parameters, equipment status, environmental information, and user-side data. This allows for timely capture of dynamic changes in the power grid's operating status, providing the latest and most relevant input information for subsequent fault prediction, thereby improving the timeliness and accuracy of predictions.

[0031] S6: Based on the intra-layer fault propagation model and cross-layer fault transfer model, perform fault prediction on the real-time power grid status data and output multiple fault warning messages.

[0032] Specifically, firstly, the acquired real-time power grid status data is input into intra-layer fault propagation models and inter-layer fault transfer models for parallel computation. During the computation, a dynamic weight adjustment mechanism is employed to adaptively optimize the weights of different models based on real-time data characteristics and historical prediction accuracy. Based on the model output, comprehensive analysis and risk assessment are performed, including calculating the fault probability of each node, assessing potential propagation paths and impact ranges, and estimating the time window for fault occurrence. Subsequently, based on predefined risk thresholds, multiple levels of fault warning information are generated, including fault location, type, potential impact, and recommended measures, achieving comprehensive and accurate prediction of power grid faults and providing precise decision support for power grid operation and maintenance.

[0033] Furthermore, embodiments of this application also include:

[0034] Based on the multi-source sensing dataset, define the various power equipment components in the target power grid and the transmission paths between the power equipment components;

[0035] A geographic information system is used to map each power equipment component and the transmission path into a panoramic three-dimensional space to build a power grid spatial topology. The nodes of the power grid spatial topology are power equipment components, and the length of the edges of the power grid spatial topology corresponds to the size of the transmission path.

[0036] In one feasible implementation, firstly, information from different data sources in a multi-source sensing dataset is analyzed and integrated, including but not limited to equipment ledger data, real-time measurement data, and historical operation records. Through this data, key components in the power grid, such as substations, distribution rooms, and important user terminals, are identified, and the power transmission relationships between these components are determined. This considers not only physical connections but also electrical characteristics and operating modes, thus more comprehensively reflecting the actual structure and function of the power grid and determining the transmission paths between various power equipment components in the target power grid. Then, the further defined power equipment components and transmission paths are mapped onto a panoramic 3D space, thereby constructing a geographically-based power grid spatial topology. A Geographic Information System (GIS) is used to combine the abstract power grid structure with the actual geographic space. In this process, each power equipment component is assigned precise geographic coordinates, becoming a node in the power grid spatial topology. Simultaneously, the transmission paths between equipment components are transformed into edges in the topology, where the length of the edge corresponds to the physical or electrical distance of the actual transmission path.

[0037] By transforming complex power grid systems into spatial topologies with distinct geographical attributes, not only are the functional connections of the power grid preserved, but also real geospatial information is incorporated. This provides a more comprehensive and accurate foundational model for subsequent multi-level clustering analysis and fault propagation simulation, which helps to more accurately predict and analyze fault propagation behavior in the power grid.

[0038] Furthermore, embodiments of this application also include:

[0039] Obtain the node features of each node in the power grid spatial topology, including geographical location distance features, electrical similarity features, and connection edge length features;

[0040] Based on the geographical location distance characteristics, electrical similarity characteristics, and connection edge length characteristics, a similarity metric for each node is generated;

[0041] Nodes are assigned based on the similarity metric of each node until all nodes of the power grid spatial topology are traversed, and a multi-layer topology network is output, wherein the stability of each layer of the topology network meets a preset threshold.

[0042] In one feasible implementation, firstly, the node characteristics of each node in the power grid spatial topology are acquired. These characteristics include geographical distance features, electrical similarity features, and connection edge length features. Geographical distance features reflect the relative positions of nodes in physical space and are quantified using metrics such as Euclidean distance or Manhattan distance. Electrical similarity features describe the degree of similarity in electrical characteristics between nodes, including factors such as voltage level, load characteristics, and equipment type. Connection edge length features represent the length of the power transmission path between nodes. Then, based on the acquired node characteristics, similarity metrics for each node are generated. For example, a multi-dimensional similarity calculation method can be used, employing weighted Euclidean distance, cosine similarity, etc., to comprehensively consider geographical distance features, electrical similarity features, and connection edge length features, forming a unified similarity metric to reflect the degree of similarity between nodes. Next, based on the generated similarity metrics, nodes are assigned and clustered, outputting a multi-layer topology network. An iterative approach is used to traverse all nodes in the power grid spatial topology, clustering nodes with high similarity into the same level. At the same time, a preset threshold is introduced, that is, each layer of the topology network needs to meet the preset stability threshold. If the stability of a certain layer of the topology network does not reach the preset threshold, corresponding adjustment strategies are adopted, such as reallocating boundary nodes and adjusting clustering parameters, until the stability requirements are met.

[0043] By transforming the complex spatial topology of the power grid into a multi-layered topology network with hierarchical characteristics, not only is the key information of the original topology preserved, but also the potential functional modules and hierarchical relationships in the power grid are revealed through clustering. This provides a network model for subsequent fault propagation analysis, which helps to predict and analyze fault propagation behavior in the power grid more accurately and efficiently.

[0044] Furthermore, embodiments of this application also include:

[0045] Obtain an intra-layer fault simulation dataset, wherein the intra-layer fault simulation dataset includes the propagation path and propagation probability of fault samples between nodes within the layer;

[0046] Initialize the random walk model;

[0047] Based on the intra-layer fault simulation dataset, an intra-layer propagation probability matrix is ​​determined, wherein the element P in the intra-layer propagation probability matrix... ij This represents the probability that a fault propagates from node i to its neighboring node j;

[0048] Configure the initial state vector and time step for fault propagation within the configuration layer;

[0049] The initial random walk model is trained using the intra-layer propagation probability matrix, the initial state vector of intra-layer fault propagation, and the time step, and the output intra-layer fault propagation model reaches a steady-state distribution.

[0050] In a preferred embodiment, an intra-layer fault propagation model is constructed for each layer of a multi-layer topology network. First, an intra-layer fault simulation dataset is acquired, containing the propagation paths and probabilities of fault samples among nodes within the layer. Here, fault samples represent different types and severity of power grid fault cases, propagation paths describe how a fault spreads from one node to other nodes, and propagation probabilities quantify the likelihood of this spread. Next, a random walk model is initialized. A random walk model is a mathematical model describing the random movement of particles on a network, used to simulate the random propagation behavior of faults in a power grid. The initialization process involves defining the state space (i.e., all nodes in the network), setting initial transition rules, etc., to prepare for subsequent model training.

[0051] Next, the intra-layer propagation probability matrix is ​​determined based on the intra-layer fault simulation dataset. The element P in the intra-layer propagation probability matrix... ij This represents the probability that a fault propagates from node i to its neighboring node j. For example, through maximum likelihood estimation, the acquired data is transformed into a mathematical representation that the model can directly use, quantifying the complex characteristics of fault propagation into computable probability values. Subsequently, the initial state vector and time step for intra-layer fault propagation are configured. The initial state vector describes the state of each node at the initial stage of a fault, representing the location of the fault source; the time step defines the time dimension of the model's simulation of fault propagation. Then, the initialized random walk model is trained using the determined intra-layer propagation probability matrix, initial state vector, and time step. The training process employs an iterative approach, repeatedly applying the propagation probability matrix to the state vector until a steady-state distribution is reached. The steady-state distribution refers to a state where the model output no longer changes significantly in a statistical sense, reflecting the long-term trend of fault propagation. After training, the intra-layer fault propagation model can reliably predict the propagation status of a fault in that layer's topology.

[0052] By constructing a mathematical model that can accurately describe the characteristics of fault propagation within a layer, not only are the characteristics of the power grid topology considered, but also the randomness and dynamic characteristics of fault propagation are incorporated, providing support for achieving high-precision power grid fault prediction.

[0053] Furthermore, embodiments of this application also include:

[0054] Identify the cross-layer connection nodes between layers in the multi-layer topology network, wherein the cross-layer connection nodes are the critical paths for fault propagation from one layer of the network to another.

[0055] Define a cross-layer adjacency matrix based on the cross-layer connection nodes between layers in the multi-layer topology network;

[0056] Based on the cross-layer adjacency matrix, a cross-layer fault transfer model between layers in the multi-layer topology network is constructed through transfer simulation.

[0057] In one feasible implementation, firstly, cross-layer connection nodes between layers in a multi-layer topology network are identified. Cross-layer connection nodes represent the path for a fault to propagate from one layer to another, manifesting in a power grid as transformers, tie switches, and other equipment between different voltage levels. The identification process is achieved by analyzing the structural characteristics of the multi-layer topology network. Specifically, all nodes in the network are traversed, and each node is checked for direct connections to nodes in other layers. If such connections exist, the node is marked as a cross-layer connection node. Next, a cross-layer adjacency matrix is ​​defined based on the identified cross-layer connection nodes. This matrix is ​​a mathematical representation describing the connection relationships between nodes at different layers. Then, a transfer simulation is performed based on the cross-layer adjacency matrix to construct a cross-layer fault transfer model between layers in the multi-layer topology network. Specifically, the cross-layer adjacency matrix is ​​first normalized to obtain a transfer probability matrix. For each cross-layer connection node, a fault is simulated to start from that node and randomly walk to nodes in other layers according to the transfer probability matrix. Through numerous simulation experiments, the probability distribution of fault propagation from one layer to another is statistically determined, thus constructing the cross-layer fault transfer model.

[0058] By constructing a mathematical model describing the fault transfer characteristics between layers, the cross-layer fault transfer model not only considers the multi-layer structure of the power grid but also captures the dynamic process of fault propagation between different layers, providing an important tool for achieving comprehensive and accurate power grid fault prediction. Combined with the aforementioned intra-layer fault propagation model, this model can comprehensively describe the propagation and evolution of faults in the power grid, thereby improving the accuracy and reliability of fault prediction.

[0059] Furthermore, embodiments of this application also include:

[0060] Obtain a cross-layer fault simulation dataset, wherein the cross-layer fault simulation dataset includes the transfer paths and transfer probabilities of fault samples between layers;

[0061] Based on the cross-layer fault simulation dataset, a cross-layer propagation probability matrix is ​​determined, wherein the elements in the cross-layer propagation probability matrix are... This represents the probability that a fault propagates from node i in the k-th layer network to node j in the l-th layer network.

[0062] Configure the initial state vector and time step for cross-layer failover;

[0063] The initial random walk model is trained using the cross-layer propagation probability matrix, the initial state vector of cross-layer fault transfer, and the time step, and the output cross-layer fault transfer model reaches a steady-state distribution.

[0064] In a preferred embodiment, firstly, a cross-layer fault simulation dataset is acquired, which contains information on the transfer paths and probabilities of fault samples between layers. The transfer path describes how a fault propagates from a node in one layer to a node in another layer, while the transfer probability quantifies the likelihood of such cross-layer propagation. Next, a cross-layer propagation probability matrix is ​​determined based on the cross-layer fault simulation dataset. The elements within this matrix... This represents the probability that a fault propagates from node i in layer k to node j in layer l. For example, through maximum likelihood estimation, the obtained cross-layer fault simulation dataset is transformed into a mathematical representation that the model can directly use, quantifying the complex cross-layer fault propagation characteristics into computable probability values. Then, the initial state vector and time step for cross-layer fault transfer are configured. The initial state vector describes the state of each node in each layer at the initial stage of the fault, indicating which node in which layer the fault source is located; the time step defines the time dimension of the model's simulation of cross-layer fault propagation. Afterward, the initialized random walk model is trained using the determined cross-layer propagation probability matrix, initial state vector, and time step. The training process is iterative, repeatedly applying the cross-layer propagation probability matrix to the state vector until a steady-state distribution is reached. The steady-state distribution refers to a state where the model output no longer changes significantly in a statistical sense, reflecting the long-term trend of cross-layer fault propagation. After training, the cross-layer fault transfer model can reliably predict the cross-layer propagation of faults in multi-layer topology networks.

[0065] By constructing a mathematical model that accurately describes the characteristics of cross-layer fault propagation, this model not only considers the characteristics of the multi-layer topology of the power grid but also incorporates the randomness and dynamics of cross-layer fault propagation, laying a solid theoretical foundation for achieving high-precision power grid fault prediction. Combined with the aforementioned intra-layer fault propagation model, this model can comprehensively describe the propagation and evolution of faults in the power grid, thereby significantly improving the accuracy, comprehensiveness, and reliability of fault prediction.

[0066] Furthermore, embodiments of this application also include:

[0067] Based on the intra-layer fault propagation model, fault prediction is performed on the real-time power grid status data, and multiple intra-layer fault prediction indices corresponding to the multi-layer topology network are output.

[0068] Based on the cross-layer fault transfer model, fault prediction is performed on the real-time power grid status data, and multiple cross-layer fault prediction indicators are output.

[0069] Conditional probability calculations are performed on the multiple intra-layer fault prediction indicators and the multiple cross-layer fault prediction indicators to output multiple fault prediction indicators.

[0070] Based on the magnitude of the fault prediction index, multiple fault warning messages are output.

[0071] In one feasible implementation, firstly, fault prediction is performed on real-time power grid state data based on an intra-layer fault propagation model, outputting multiple intra-layer fault prediction indices corresponding to the multi-layer topology network. Specifically, real-time power grid state data is input into the constructed intra-layer fault propagation model, which uses a random walk algorithm to simulate the propagation process of faults within each layer of the topology network. Through multiple simulations, the probability of each node experiencing a fault within a specific future time period is calculated, constituting the intra-layer fault prediction indices. This process is performed on each layer of the multi-layer topology network, resulting in a set of multiple intra-layer fault prediction indices covering all layers. Next, fault prediction is performed on real-time power grid state data based on a cross-layer fault transfer model, outputting multiple cross-layer fault prediction indices. Specifically, real-time data is input into the cross-layer fault transfer model, which considers the propagation characteristics of faults between different layers, simulating the process of faults propagating from one layer to another. Through calculation, multiple cross-layer fault prediction indices describing the probability of fault propagation across layers are obtained, reflecting the potential diffusion trend of faults throughout the multi-layer network.

[0072] Subsequently, conditional probability calculations are performed on multiple intra-layer and cross-layer fault prediction indices to output multiple comprehensive fault prediction indices. For example, using Bayes' theorem, the comprehensive probability of each node failing is calculated given the intra-layer fault probability and cross-layer propagation probability, considering the mutual influence of fault propagation within and across layers, thus obtaining more comprehensive and accurate fault prediction indices. Then, based on the magnitude of the fault prediction indices, multiple fault warning messages are output. Specifically, the multiple fault prediction indices are transformed into multiple specific fault warning messages, including the possible location of the fault, the expected time of occurrence, and the potential scope of impact.

[0073] By providing comprehensive and accurate predictions of power grid faults, not only is the propagation of faults within a single level considered, but also the impact of cross-level propagation. This provides more comprehensive and accurate fault early warning information, improves the accuracy and timeliness of power grid fault early warnings, and provides strong support for the safe and stable operation of the power grid.

[0074] In summary, the power grid fault prediction and processing method based on panoramic situational awareness provided in this application has the following technical effects:

[0075] Data is collected from the target power grid using a panoramic situational awareness system to obtain a multi-source sensing dataset, ensuring the comprehensiveness and accuracy of the data. Based on the multi-source sensing dataset, a power grid spatial topology is constructed to obtain the connection relationships and spatial distribution between various power grid components, laying the foundation for subsequent multi-level analysis. Clustering of each node in the power grid spatial topology results in a multi-layer topology network, creating conditions for more refined and targeted fault analysis. Intra-layer fault propagation models for each layer of the multi-layer topology network and cross-layer fault transfer models between layers are constructed to comprehensively characterize the dynamic propagation characteristics of faults, improving the accuracy of fault prediction. Connecting to the panoramic situational awareness system allows for the acquisition of real-time power grid status data, enabling fault prediction to be based on the current actual situation, improving the timeliness and accuracy of predictions. Fault prediction is performed based on real-time power grid status data using intra-layer fault propagation and cross-layer fault transfer models, outputting multiple fault warning messages, improving the accuracy and timeliness of power grid fault prediction.

[0076] Example 2 is based on the same inventive concept as the power grid fault prediction and processing method based on panoramic situational awareness in the previous examples, such as... Figure 2 As shown in the figure, this application provides a power grid fault prediction and processing system based on panoramic situational awareness. The system includes:

[0077] Data acquisition module 11 is used to acquire data from the target power grid through the panoramic situational awareness system and obtain a multi-source sensing dataset;

[0078] Topology construction module 12 is used to build a power grid spatial topology structure based on the multi-source sensing dataset;

[0079] The multi-layer clustering module 13 is used to cluster each node in the power grid spatial topology and output a multi-layer topology network.

[0080] The model building module 14 is used to build the intra-layer fault propagation model corresponding to each layer of the multi-layer topology network, and the cross-layer fault transfer model between layers in the multi-layer topology network.

[0081] The real-time data acquisition module 15 is used to connect to the panoramic situational awareness system and acquire the real-time power grid status data of the target power grid.

[0082] The fault prediction module 16 is used to predict faults based on the intra-layer fault propagation model and the cross-layer fault transfer model, and output multiple fault warning messages.

[0083] Furthermore, the topology building module 12 includes the following execution steps:

[0084] Based on the multi-source sensing dataset, define the various power equipment components in the target power grid and the transmission paths between the power equipment components;

[0085] A geographic information system is used to map each power equipment component and the transmission path into a panoramic three-dimensional space to build a power grid spatial topology. The nodes of the power grid spatial topology are power equipment components, and the length of the edges of the power grid spatial topology corresponds to the size of the transmission path.

[0086] Furthermore, the multi-layer clustering module 13 includes the following execution steps:

[0087] Obtain the node features of each node in the power grid spatial topology, including geographical location distance features, electrical similarity features, and connection edge length features;

[0088] Based on the geographical location distance characteristics, electrical similarity characteristics, and connection edge length characteristics, a similarity metric for each node is generated;

[0089] Nodes are assigned based on the similarity metric of each node until all nodes of the power grid spatial topology are traversed, and a multi-layer topology network is output, wherein the stability of each layer of the topology network meets a preset threshold.

[0090] Furthermore, the model building module 14 includes the following execution steps:

[0091] Obtain an intra-layer fault simulation dataset, wherein the intra-layer fault simulation dataset includes the propagation path and propagation probability of fault samples between nodes within the layer;

[0092] Initialize the random walk model;

[0093] Based on the intra-layer fault simulation dataset, an intra-layer propagation probability matrix is ​​determined, wherein the element P in the intra-layer propagation probability matrix... ij This represents the probability that a fault propagates from node i to its neighboring node j;

[0094] Configure the initial state vector and time step for fault propagation within the configuration layer;

[0095] The initial random walk model is trained using the intra-layer propagation probability matrix, the initial state vector of intra-layer fault propagation, and the time step, and the output intra-layer fault propagation model reaches a steady-state distribution.

[0096] Furthermore, the model building module 14 also includes the following execution steps:

[0097] Identify the cross-layer connection nodes between layers in the multi-layer topology network, wherein the cross-layer connection nodes are the critical paths for fault propagation from one layer of the network to another.

[0098] Define a cross-layer adjacency matrix based on the cross-layer connection nodes between layers in the multi-layer topology network;

[0099] Based on the cross-layer adjacency matrix, a cross-layer fault transfer model between layers in the multi-layer topology network is constructed through transfer simulation.

[0100] Furthermore, the model building module 14 also includes the following execution steps:

[0101] Obtain a cross-layer fault simulation dataset, wherein the cross-layer fault simulation dataset includes the transfer paths and transfer probabilities of fault samples between layers;

[0102] Based on the cross-layer fault simulation dataset, a cross-layer propagation probability matrix is ​​determined, wherein the elements in the cross-layer propagation probability matrix are... This represents the probability that a fault propagates from node i in the k-th layer network to node j in the l-th layer network.

[0103] Configure the initial state vector and time step for cross-layer failover;

[0104] The initial random walk model is trained using the cross-layer propagation probability matrix, the initial state vector of cross-layer fault transfer, and the time step, and the output cross-layer fault transfer model reaches a steady-state distribution.

[0105] Furthermore, the fault prediction module 16 includes the following execution steps:

[0106] Based on the intra-layer fault propagation model, fault prediction is performed on the real-time power grid status data, and multiple intra-layer fault prediction indices corresponding to the multi-layer topology network are output.

[0107] Based on the cross-layer fault transfer model, fault prediction is performed on the real-time power grid status data, and multiple cross-layer fault prediction indicators are output.

[0108] Conditional probability calculations are performed on the multiple intra-layer fault prediction indicators and the multiple cross-layer fault prediction indicators to output multiple fault prediction indicators.

[0109] Based on the magnitude of the fault prediction index, multiple fault warning messages are output.

[0110] In summary, any step of the method described above can be stored as a computer instruction or program in an unrestricted computer memory, and can be called and identified by an unrestricted computer processor to implement any method in the embodiments of this application, without any additional restrictions.

[0111] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A power grid fault prediction and processing method based on panoramic situational awareness, characterized in that, The method includes: Data is collected from the target power grid using a panoramic situational awareness system to obtain a multi-source sensing dataset; Based on the multi-source sensing dataset, construct the power grid spatial topology; Cluster the nodes in the power grid spatial topology and output a multi-layer topology network; Construct an intra-layer fault propagation model for each layer of the multi-layer topology network, and a cross-layer fault transfer model between layers in the multi-layer topology network; Connect to the panoramic situational awareness system to obtain real-time power grid status data of the target power grid; Based on the intra-layer fault propagation model and cross-layer fault transfer model, fault prediction is performed on the real-time power grid status data, and multiple fault warning messages are output. The method for constructing the power grid spatial topology based on the multi-source sensing dataset further includes: Based on the multi-source sensing dataset, define the various power equipment components in the target power grid and the transmission paths between the power equipment components; A geographic information system is used to map each power equipment component and the transmission path to a panoramic three-dimensional space to build a power grid spatial topology. The nodes of the power grid spatial topology are power equipment components, and the length of the edges of the power grid spatial topology corresponds to the size of the transmission path. The method for constructing a cross-layer fault transfer model between layers in the multi-layer topology network includes: Identify the cross-layer connection nodes between layers in the multi-layer topology network, wherein the cross-layer connection nodes are the critical paths for fault propagation from one layer of the network to another. Define a cross-layer adjacency matrix based on the cross-layer connection nodes between layers in the multi-layer topology network; Based on the cross-layer adjacency matrix, a cross-layer fault transfer model is constructed between layers in the multi-layer topology network. The method includes: Obtain a cross-layer fault simulation dataset, wherein the cross-layer fault simulation dataset includes the transfer paths and transfer probabilities of fault samples between layers; Based on the cross-layer fault simulation dataset, a cross-layer propagation probability matrix is ​​determined, wherein the elements in the cross-layer propagation probability matrix represent the probability that a fault propagates from node i in the k-th layer network to node j in the l-th layer network. Configure the initial state vector and time step for cross-layer failover; The initial random walk model is trained using the cross-layer propagation probability matrix, the initial state vector of cross-layer fault transfer, and the time step, and the output cross-layer fault transfer model reaches a steady-state distribution.

2. The method as described in claim 1, characterized in that, Clustering of nodes in the power grid spatial topology to output a multi-layer topology network, the method includes: Obtain the node features of each node in the power grid spatial topology, including geographical location distance features, electrical similarity features, and connection edge length features; Based on the geographical location distance characteristics, electrical similarity characteristics, and connection edge length characteristics, a similarity metric for each node is generated; Nodes are assigned based on the similarity metric of each node until all nodes of the power grid spatial topology are traversed, and a multi-layer topology network is output, wherein the stability of each layer of the topology network meets a preset threshold.

3. The method as described in claim 1, characterized in that, The method for constructing an intra-layer fault propagation model for each layer of the multi-layer topology network includes: Obtain an intra-layer fault simulation dataset, wherein the intra-layer fault simulation dataset includes the propagation path and propagation probability of fault samples between nodes within the layer; Initialize the random walk model; Based on the intra-layer fault simulation dataset, an intra-layer propagation probability matrix is ​​determined, wherein the elements in the intra-layer propagation probability matrix represent the probability that a fault propagates from node i to the adjacent node j; Configure the initial state vector and time step for fault propagation within the configuration layer; The initial random walk model is trained using the intra-layer propagation probability matrix, the initial state vector of intra-layer fault propagation, and the time step, and the output intra-layer fault propagation model reaches a steady-state distribution.

4. The method as described in claim 1, characterized in that, The method for outputting multiple fault warning messages also includes: Based on the intra-layer fault propagation model, fault prediction is performed on the real-time power grid status data, and multiple intra-layer fault prediction indices corresponding to the multi-layer topology network are output. Based on the cross-layer fault transfer model, fault prediction is performed on the real-time power grid status data, and multiple cross-layer fault prediction indicators are output. Conditional probability calculations are performed on the multiple intra-layer fault prediction indicators and the multiple cross-layer fault prediction indicators to output multiple fault prediction indicators. Based on the magnitude of the fault prediction index, multiple fault warning messages are output.

5. A power grid fault prediction and processing system based on panoramic situational awareness, characterized in that, The method for implementing the power grid fault prediction and processing method based on panoramic situational awareness as described in any one of claims 1-4, the method comprising: The data acquisition module is used to acquire data from the target power grid through the panoramic situational awareness system and obtain multi-source sensing datasets. The topology construction module is used to build the power grid spatial topology structure based on the multi-source sensing dataset; A multi-layer clustering module is used to cluster each node in the power grid spatial topology and output a multi-layer topology network. The model building module is used to build the intra-layer fault propagation model corresponding to each layer of the multi-layer topology network, as well as the cross-layer fault transfer model between layers in the multi-layer topology network. The real-time data acquisition module is used to connect to the panoramic situational awareness system and acquire the real-time power grid status data of the target power grid. The fault prediction module is used to predict faults based on the intra-layer fault propagation model and the cross-layer fault transfer model, and output multiple fault warning messages.

Images