A method and system for monitoring and warning of abnormal conditions in a power transmission channel

Abstract

The present invention proposes a method and system for monitoring and warning of abnormal situations in a power transmission channel. Channel data is obtained based on the power grid resource business middle platform, regional data is obtained based on the power grid power consumption information collection system, and historical meteorological grid data is obtained based on the meteorological center; a channel-to-region mapping relationship model and a different-to-different matching relationship model are constructed based on the channel data and the regional data; the historical meteorological grid data and the abnormal event data recorded in the channel data are aligned in time series and space, and data preprocessing and feature engineering operations are performed on the historical meteorological grid data and the corresponding abnormal event data to form an input sequence. The GD-Informer model is trained and optimized based on the input sequence to obtain the best model; real-time prediction is performed on new meteorological data based on the best model to obtain a prediction result, and result analysis and abnormal situation warning are carried out based on the prediction result and the two relationship models. The present invention can accurately and timely warn of abnormal situations in the power transmission channel and regional abnormal situations.

Description

Technical Field

[0001] The present invention relates to the technical field of early warning of abnormal conditions in power transmission channels, and particularly to a method and system for monitoring and early warning of abnormal conditions in power transmission channels. Background Art

[0002] As an important part of the power system, power transmission lines undertake the task of transmitting electric energy from power plants to end-users. Their operating status is related to the safe and stable operation of the power system and the sustainable and healthy development of the economy and society.

[0003] When various types of faults occur in power transmission lines, they will seriously threaten the safe and stable operation of the power system. The current correlation monitoring method based on a single data source and the early warning method with a coarse-grained and region-wide full coverage have limitations such as low flexibility and high omission rate during the inspection and monitoring processes, resulting in problems such as insufficient prediction refinement and frequent false alarms and missed alarms. In addition, the current power grid is facing increasingly severe challenges from meteorological disasters. Accurately monitoring and early warning the abnormal problems of multi-source and complex power transmission lines has become a severe test for ensuring the stable operation of the power system. Therefore, there is an urgent need for a method and system for monitoring and early warning of abnormal conditions in power transmission channels with strong systematicness, good generality, high standardization, and excellent accuracy. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for monitoring and early warning of abnormal conditions in power transmission channels, which comprehensively uses deep learning technology and data processing and analysis technology, and effectively improves the accuracy, real-time performance, and reliability of monitoring abnormal conditions in power transmission channels.

[0005] In the first aspect, the present invention provides a method for monitoring and early warning of abnormal conditions in power transmission channels, specifically including:

[0006] Obtain channel data based on the power grid resource business middle platform, where the channel data includes power transmission channel spatial data and recorded abnormal event data, obtain regional data based on the power grid power consumption information collection system, and obtain historical meteorological grid data based on the meteorological center, where the meteorological grid data includes meteorological data and grid data;

[0007] Construct a channel-to-region mapping relationship model and an abnormal-to-abnormal matching relationship model based on the channel data and the regional data;

[0008] After performing time series alignment and spatial alignment on the historical meteorological grid data and the abnormal event data recorded in the channel data, perform data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence, and train and optimize the GD-Informer model based on the input sequence to obtain a trained GD-Informer model;

[0009] Based on the trained GD-Informer model, real-time prediction is performed on new meteorological data to obtain prediction results, and result analysis and early warning of abnormal situations are carried out based on the prediction results, the channel-to-region mapping relationship model, and the anomaly-to-anomaly matching relationship model.

[0010] Further, the meteorological data includes temperature, humidity, wind speed, wind direction, and precipitation, and the grid data includes prediction time, report time, longitude, and latitude.

[0011] Further, constructing the channel-to-region mapping relationship model and the anomaly-to-anomaly matching relationship model based on channel data and region data includes:

[0012] Based on channel data and region data, region matching and anomaly pairing are performed to construct the channel-to-region mapping relationship model and the anomaly-to-anomaly matching relationship model.

[0013] Further, constructing the channel-to-region mapping relationship model based on channel data and region data includes:

[0014] Based on channel data and region data, the channel-to-region mapping relationship model is constructed by identifying key points and channels, analyzing the power grid topology relationship, establishing an influence matrix, and parameterizing the relationship.

[0015] Further, constructing the anomaly-to-anomaly matching relationship model based on channel data and region data includes:

[0016] Based on channel data and region data, the anomaly-to-anomaly matching relationship model is constructed by determining the fault type and the type of adverse impact, establishing a relationship matrix, and parameterizing the relationship.

[0017] Further, after performing time-series alignment and spatial alignment on the abnormal event data recorded in the historical grid meteorological data and channel data, data preprocessing and feature engineering operations are performed on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence, and the GD-Informer model is trained and optimized based on the input sequence to obtain the trained GD-Informer model, including:

[0018] Perform time-series alignment operation and spatial alignment operation on the abnormal event data recorded in the historical meteorological grid data and channel data;

[0019] Divide the abnormal event data recorded in the historical meteorological grid data and channel data into training samples and test samples;

[0020] Perform data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence;

[0021] Train, test, and tune the GD-Informer model based on the input sequence to obtain a trained GD-Informer model.

[0022] Further, perform time-series alignment operations and spatial alignment operations on the abnormal event data recorded in the historical meteorological raster data and channel data, including:

[0023] The time-series alignment operation includes timestamp merging, finding common timestamps, and data alignment;

[0024] The spatial alignment operation is based on the location data in the raster data and abnormal event data for region division and matching.

[0025] Further, perform data preprocessing on the abnormal event data in the historical meteorological raster data and corresponding channel data, including:

[0026] Perform data cleaning, normalization, and data splitting operations on the abnormal event data in the historical meteorological raster data and corresponding channel data.

[0027] Further, perform feature engineering operations on the abnormal event data in the historical meteorological raster data and corresponding channel data, including:

[0028] Perform feature selection, feature construction, and sequence construction operations on the abnormal event data in the historical meteorological raster data and corresponding channel data.

[0029] Further, perform real-time prediction on new meteorological data based on the trained GD-Informer model to obtain prediction results, and perform result analysis and abnormal situation warning based on the prediction results, channel-to-region mapping relationship model, and anomaly-to-anomaly matching relationship model, including:

[0030] Perform real-time prediction on the obtained meteorological data based on the trained GD-Informer model to obtain prediction results;

[0031] After obtaining the prediction results, use the channel-to-region mapping relationship model and anomaly-to-anomaly matching relationship model for result analysis and abnormal situation warning.

[0032] Further, after obtaining the prediction results, use the channel-to-region mapping relationship model and anomaly-to-anomaly matching relationship model for result analysis and abnormal situation warning, including:

[0033] Result analysis is to form a heat map and a case report based on the prediction results using the channel-to-region mapping relationship model and anomaly-to-anomaly matching relationship model. The heat map shows the predicted distribution of abnormal situations in different regional transmission channels, and the case report prepares a detailed case report for the predicted event, recording the event process and subsequent actions;

[0034] The abnormal situation warning conducts threshold warning according to the impact degrees of different abnormal events. When the impact degree reaches the preset threshold, the corresponding emergency procedure is initiated, and real-time push is carried out through the SMS and enterprise-level message push platform to notify the duty personnel to make corresponding handling. The push content includes time, weather, transmission channel, affected area and impact degree.

[0035] In a second aspect, the present invention also provides a monitoring and warning system for abnormal situations of transmission channels, specifically including:

[0036] A data acquisition module, which obtains channel data based on the power grid resource business middle platform, obtains regional data based on the power grid electricity consumption information acquisition system, and obtains historical meteorological grid data based on the meteorological center;

[0037] A relationship model construction module, which constructs a mapping relationship model of the channel to the region and a different-to-different matching relationship model based on the obtained channel data and regional data;

[0038] A model training module, which performs time series alignment and spatial alignment on the abnormal event data recorded in the historical meteorological grid data and channel data, performs data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological grid data and corresponding channel data to form an input sequence, and trains and tunes the GD-Informer model based on the input sequence to obtain a trained GD-Informer model;

[0039] A result determination and output module, which performs real-time prediction on new meteorological data based on the trained GD-Informer model to obtain a prediction result, then performs result analysis based on the prediction result, the channel-to-region mapping relationship model, and the different-to-different matching relationship model, and warns of the abnormal situations of the transmission channels and regional abnormal situations through the SMS and enterprise-level message push platform.

[0040] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0041] The present invention comprehensively applies deep learning technology and data processing and analysis technology, effectively improving the accuracy, real-time performance, and reliability of the monitoring of abnormal conditions in transmission channels, facilitating the timely grasp of abnormal conditions in transmission channels; effectively integrating multi-source data such as spatial data of transmission channels, power grid regional data, and historical meteorological grid data to provide more comprehensive, accurate, and in-depth information analysis and improve the prediction accuracy of the model; using the self-built G-DAE model to replace the input layer of the Informer model to build the GD-Informer model, effectively learning robust and representative latent features from time series data, not only reducing the data dimension, reducing the influence of noise and outliers, but also improving the generalization ability of the model, preventing overfitting, and making the model more focused on the key information of the data; based on the GD-Informer for time series prediction, effectively capturing the time dependence in the data and the interaction between variables, reducing the number of parameters to reduce the risk of overfitting, and providing comprehensive, accurate, and efficient prediction capabilities; combining the self-built mapping relationship model between transmission channels and power grid regions and the different-to-different matching relationship model, comprehensively analyzing and outputting accurate monitoring and warning results of abnormal conditions in transmission channels; real-time pushing through the SMS and enterprise-level message push platform, enabling staff to take corresponding preventive measures in a timely manner, and at the same time being able to conduct retrospective analysis and dynamic adjustment. The present invention can accurately and timely warn of abnormal conditions in transmission channels and regional abnormal conditions, reduce the impact of severe weather on power grid equipment and regions, reduce the possibility of major accidents, and reduce social and economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is the overall flowchart of a method for monitoring and warning abnormal conditions in a transmission channel according to the present invention;

[0043] Figure 2 is the overall structure diagram of the GD-Informer model of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] In order to more clearly elaborate the purpose, technical solutions, and their advantages of the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be described in detail below. Obviously, the provided embodiments only represent a part of the embodiments of the present invention, not all. According to the embodiments described in the present invention, any other embodiments conceived by any person skilled in the art without creative efforts shall fall within the protection scope of the present invention. Unless otherwise specified, the technical terms or scientific terms used herein shall be interpreted according to the general meanings understood by those of ordinary skill in the art. The similar expressions such as "including" used herein are intended to indicate that the elements or objects covered include the subsequently listed elements or objects and their equivalents, but do not exclude other elements or objects.

[0045] An embodiment of the present invention provides a method for monitoring and warning abnormal situations in a power transmission channel. Refer to Figure 1 , including the following steps:

[0046] S1. Obtain channel data based on the power grid resource business middle platform. The channel data includes power transmission channel spatial data and recorded abnormal event data. Obtain regional data based on the power grid power consumption information collection system. The regional data includes interval abnormal data. Obtain historical meteorological grid data based on the meteorological center. The meteorological grid data includes meteorological data and grid data;

[0047] S2. Construct a channel-to-region mapping relationship model and an abnormal-to-abnormal matching relationship model based on the channel data and the regional data;

[0048] S3. After performing time series alignment and spatial alignment on the historical meteorological grid data and the abnormal event data recorded in the channel data, perform data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence. Train and optimize the GD-Informer model based on the input sequence to obtain a trained GD-Informer model;

[0049] S4. Perform real-time prediction on new meteorological data based on the trained GD-Informer model to obtain a prediction result, and perform result analysis and abnormal situation warning based on the prediction result, the channel-to-region mapping relationship model, and the abnormal-to-abnormal matching relationship model.

[0050] In some embodiments, when performing step S1, the meteorological data includes temperature, humidity, wind speed, wind direction, and precipitation, and the grid data includes prediction time, report time, longitude, and latitude.

[0051] In some embodiments, when performing step S2, it specifically includes:

[0052] S2-1. Based on the channel data and the regional data, construct a channel-to-region mapping relationship model by identifying key points and channels, analyzing the power grid topology relationship, establishing an influence matrix, and parameterizing the relationship;

[0053] S2-2. Based on the channel data and the regional data, construct an abnormal-to-abnormal matching relationship model by determining the fault type and the type of adverse impact, and establishing a relationship matrix and a parameterized relationship.

[0054] Specifically, when performing step S2-1, based on the channel data and the regional data, construct a channel-to-region mapping relationship model by identifying key points and channels, analyzing the power grid topology relationship, establishing an influence matrix, and parameterizing the relationship, including:

[0055] S2-1-1. Determine the key nodes and key channels in the spatial channel based on the transmission spatial channel data and interval anomaly data;

[0056] S2-1-2. Analyze the topological connection between the spatial channel and the affected area, and determine the current direction and possible fault propagation paths;

[0057] S2-1-3. Establish an influence matrix, where the rows represent each interval of the spatial channel, the columns represent each sub-region of the affected area, and the matrix elements represent the degree of influence of the state of a certain channel interval on a certain sub-region;

[0058] S2-1-4. Assign specific values to the influence matrix according to the transmission spatial channel data and interval anomaly data, and parameterize the relationship to construct a channel-to-region mapping relationship model;

[0059] Specifically, when performing step S2-2, based on the channel data and region data, by determining the fault type and type of adverse effects, establishing a relationship matrix and parameterizing the relationship to construct a different-to-different matching relationship model, including:

[0060] S2-2-1. Determine the channel fault type and the type of adverse effects generated in different regions. The channel fault types include short circuit, open circuit, grounding, overvoltage, overload, insulation fault, etc., and the influence types include economic influence, ecological environment influence, safety hazard influence, etc.;

[0061] S2-2-2. Establish a relationship matrix, where the rows represent the channel fault types and the columns represent the types of adverse effects generated in different regions, and the matrix elements represent the degree of entanglement between different channel fault types and various influence types;

[0062] S2-2-3. Assign specific values to the influence matrix according to the transmission spatial channel data and interval anomaly data, parameterize the relationship, and construct a different-to-different matching relationship model.

[0063] In some embodiments, when performing step S3, after performing time series alignment and spatial alignment on the historical meteorological grid data and the abnormal event data recorded in the channel data, perform data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence, and train and optimize the GD-Informer model based on the input sequence to obtain a trained GD-Informer model, including:

[0064] S3-1. Perform time series alignment operations and spatial alignment operations on the abnormal event data recorded in the historical meteorological grid data and the channel data;

[0065] S3-2. Divide the abnormal event data recorded in the historical meteorological grid data and the channel data into training samples and test samples;

[0066] S3-3. Perform data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological raster data and the corresponding channel data to form an input sequence;

[0067] S3-4. Train, test, and optimize the GD-Informer model based on the input sequence to obtain a trained GD-Informer model.

[0068] Specifically, when performing step S3-1, perform time series alignment operations and spatial alignment operations on the abnormal event data recorded in the historical meteorological raster data and the channel data, including:

[0069] S3-1-1. Perform time series alignment operations such as timestamp merging, finding common timestamps, and data alignment on the historical meteorological raster data and the abnormal event data;

[0070] S3-1-2. Perform spatial alignment by performing regional division and matching operations on the bit field data in the historical meteorological raster data and the abnormal event data;

[0071] Specifically, when performing step S3-3, perform data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological raster data and the corresponding channel data to form an input sequence, including:

[0072] S3-3-1. Perform data preprocessing operations such as data cleaning, normalization, and data splitting on the abnormal event data in the historical meteorological raster data and the corresponding channel data;

[0073] S3-3-2. Perform feature engineering operations such as feature selection, feature construction, and sequence construction on the abnormal event data in the historical meteorological raster data and the corresponding channel data;

[0074] Specifically, when performing step S3-3-2, perform feature engineering operations such as feature selection, feature construction, and sequence construction on the abnormal event data in the historical meteorological raster data and the corresponding channel data, including:

[0075] S3-3-2-1. Feature selection: Based on the abnormal event data in the historical meteorological raster data and the corresponding channel data, evaluate the correlation between each meteorological feature and the abnormal event, and eliminate redundant or irrelevant features to improve the prediction performance and interpretability of the model;

[0076] S3-3-2-2. Feature construction: Create interaction terms by combining different features based on the historical meteorological raster data;

[0077] S3-3-2-3. Sequence construction: For historical meteorological grid data, define a time window and then slide this window on the sequence to create fixed-length subsequences as input sequences for subsequent training of the GD-Informer model.

[0078] Specifically, when performing step S3-4, train, test, and optimize the GD-Informer model based on the input sequence to obtain a trained GD-Informer model, including:

[0079] S3-4-1. Build a G-DAE denoising autoencoder based on GRU, using GRU as the encoder (encode) and decoder (decode), effectively learning robust and representative latent features from time series data, not only reducing the data dimension, minimizing the impact of noise and outliers, but also improving the generalization ability of the model, preventing overfitting, and enabling the model to focus more on the key information of the data.

[0080] Among them, the calculation process of the encoder (Encoder)-GRU:

[0081] Reset gate: ;

[0082] Update gate: ;

[0083] Candidate hidden state: ;

[0084] Hidden state: ,

[0085] Among them represents the output of the reset gate at time step t, represents the input vector to the reset gate weight matrix, represents the weight matrix from the previous hidden state to the reset gate weight matrix, represents the bias vector of the reset gate, represents the output of the update gate at time step t, represents the input vector to the update gate weight matrix, represents the weight matrix from the previous hidden state to the update gate weight matrix, represents the bias vector of the update gate, represents the candidate hidden state vector at time step t, represents the input vector to the candidate hidden state weight matrix, represents the hidden state at the previous moment after being processed by the reset gate to the candidate hidden state weight matrix, represents the bias vector of the candidate hidden state, is the sigmoid function, and tanh is the hyperbolic tangent function, represents element-wise multiplication;

[0086] Final encoding: After T time steps of calculation, the final hidden state is the encoded representation of the input noise sequence, denoted as c = ;

[0087] Among them, the calculation process of the decoder (Decoder)-GRU:

[0088] Initial state: Use the final hidden state c of the encoder as the initial state of the decoder ;

[0089] At each time step t of the decoder, according to the current hidden state generate the output , and the calculation process is similar to that of the encoder:

[0090] Reset gate: ;

[0091] Update gate: ;

[0092] Candidate hidden state: ;

[0093] Hidden state: ;

[0094] Output: , after T time steps, obtain the reconstructed sequence ={ , ,…, };

[0095] Among them represents the output of the reset gate at time step t in the d-th layer, represents the input vector in the d-th layer to the reset gate weight matrix, represents the input vector at time step t - 1, represents the hidden state at the previous moment in the d-th layer to the reset gate weight matrix, represents the hidden state vector at time step t-1 in the d-th layer, represents the bias vector of the reset gate in the d-th layer, represents the output of the update gate at time step t in the d-th layer, represents the input vector in the d-th layer to the update gate weight matrix, represents the previous hidden state in the d-th layer to the update gate weight matrix, represents the bias vector of the update gate in the d-th layer, represents the input vector in the d-th layer to the candidate hidden state weight matrix, represents the previous hidden state after being processed by the reset gate in the d-th layer to the candidate hidden state weight matrix, represents the bias vector of the candidate hidden state in the d-th layer, represents the hidden state in the d-th layer to the output weight matrix, represents the bias vector of the output in the d-th layer.

[0096] S3-4-2. Initially train the G-DAE model based on the abnormal event data in the historical meteorological grid data and the corresponding channel data. For the original data ={ ,…, ,…, }, where ∈ , is the sequence length, d is the feature dimension of each time step. Add noise to the original data with a certain probability to obtain the noisy data ={ };

[0097] Perform encoding and decoding on to obtain the final result . During the whole process, aim to minimize the difference between the reconstructed sequence and the original clean sequence , that is, min = + , represents the regularization parameter, represents penalizing the sum of squares of the model parameters, Denote the Frobenius norm, and use the Adam optimizer to minimize the loss function , update the parameters (weight matrices W, U, and bias vector b) of the GRUs in the encoder and decoder through the backpropagation algorithm, and continuously iterate the training until the loss function converges or reaches the predetermined number of training times;

[0098] S3-4-3. Take G-DAE as the input layer and replace the embedding layer of the Informer model to form the GD-Informer model. The overall structure is as Figure 2 shown. Use the input sequence formed by processing the historical meteorological grid data and the abnormal event data in the corresponding channel data to train, test, and tune the GD-Informer model to obtain the trained GD-Informer model:

[0099] Among them, the key component is ProbSparse Attention (reducing the computational complexity):

[0100] ,

[0101] In the formula ∈ , is the th query vector, K belongs to , K is the key matrix ( is the sequence length), represents the key vector, represents the dimension of the key vector, and select the top-u queries (u = , c is a constant);

[0102] Distillation layer, reducing the sequence length: , where represents a one-dimensional convolution operation, represents a non-linear activation function, represents the original sequence data input to this operation sequence, and compress the sequence length to 1 / 2 through convolution;

[0103] Model training and tuning:

[0104] 1. Two-stage training strategy:

[0105] Pre-train G-DAE: = + , : L2 regularization coefficient,

[0106] Joint fine-tuning of GD-Informer: = , , represents the prediction loss, represents the length of the prediction range, represents the actual observed value at time point t, represents the output predicted value of the model at time point t, represents the total loss function, : the weight of reconstruction and prediction loss (initially 0.5, dynamically decaying),

[0107] 2. Dynamic learning: , represents the learning rate obtained with time variation, represents the decay rate, , represents the minimum value of the learning rate decay, where E is the total number of training epochs;

[0108] In some embodiments, when performing step S4, based on the trained GD-Informer model, real-time prediction is performed on new meteorological data to obtain a prediction result. Based on the prediction result, the channel-to-region mapping relationship model, and the different-to-different matching relationship model, result analysis and early warning of abnormal situations are carried out, including:

[0109] S4-1. Based on the trained GD-Informer model, real-time prediction is performed on new meteorological data to obtain a prediction result;

[0110] S4-2. After obtaining the prediction result, use the channel-to-region mapping relationship model and the different-to-different matching relationship model to perform result analysis and early warning of abnormal situations;

[0111] Specifically, when performing step S4-2, after obtaining the prediction result, use the channel-to-region mapping relationship model and the different-to-different matching relationship model to perform result analysis and early warning of abnormal situations, including:

[0112] S4-2-1. Result analysis is based on the prediction result and the two relationship models to form a heat map and a case report. The heat map mainly shows the predicted distribution of abnormal situations in different regional power transmission channels. The case report is prepared for important prediction events, compiling a detailed case report to record the event process and subsequent actions;

[0113] S4-2-2. Early warning of abnormal situations mainly performs threshold early warning for the impact degrees of different abnormal events. When the impact degree reaches the preset threshold, start the corresponding emergency procedure, and perform real-time push through the SMS and enterprise-level message push platform to notify the on-duty personnel to perform corresponding processing. The push content includes time, weather, power transmission channel, affected area, and impact degree, etc.

[0114] In an embodiment of the present invention, a monitoring and warning system for abnormal conditions of a power transmission channel is further provided, including:

[0115] A data acquisition module, which obtains channel data based on the power grid resource business middle platform, obtains regional data based on the power grid power consumption information acquisition system, and obtains historical meteorological grid data based on the meteorological center;

[0116] A relationship model construction module, which constructs a mapping relationship model of the channel to the region and a different-to-different matching relationship model based on the obtained channel data and regional data;

[0117] A model training module, which performs time series alignment and spatial alignment on the historical meteorological grid data and the abnormal event data recorded in the channel data, performs data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence, and trains and tunes the GD-Informer model based on the input sequence to obtain a trained GD-Informer model;

[0118] A result determination and output module, which performs real-time prediction on new meteorological data based on the trained GD-Informer model to obtain a prediction result, then analyzes the result based on the prediction result, the channel-to-region mapping relationship model, and the different-to-different matching relationship model, and warns of the abnormal conditions of the power transmission channel and the regional abnormal conditions through text messages and the enterprise-level message push platform.

[0119] Although the embodiments of the present invention have been described in detail above, it is obvious to those skilled in the art that various modifications and changes can be made to these embodiments. However, it should be understood that such modifications and changes are all within the scope and spirit of the present invention described in the claims. Moreover, the present invention described herein may have other embodiments and can be implemented or realized in various ways.

Claims

1. A method for monitoring and warning abnormal conditions of a power transmission channel, characterized in that, It includes the following steps: Obtain channel data based on the power grid resource business mid - platform. The channel data includes transmission channel spatial data and recorded abnormal event data. Obtain regional data based on the power grid power consumption information acquisition system, and obtain historical meteorological grid data based on the meteorological center. The meteorological grid data includes meteorological data and grid data; Construct a channel - to - region mapping relationship model and an abnormal - to - abnormal matching relationship model based on the channel data and regional data; After performing time - series alignment and spatial alignment on the historical meteorological grid data and the abnormal event data recorded in the channel data, perform data pre - processing and feature engineering operations on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence. Train and optimize the GD - Informer model based on the input sequence to obtain a trained GD - Informer model; Perform real - time prediction on new meteorological data based on the trained GD - Informer model to obtain a prediction result, and perform result analysis and abnormal situation early warning based on the prediction result, the channel - to - region mapping relationship model, and the abnormal - to - abnormal matching relationship model; Among them, constructing a channel - to - region mapping relationship model and an abnormal - to - abnormal matching relationship model based on the channel data and regional data includes: Determine the key nodes and key channels in the spatial channel according to the transmission spatial channel data and the interval abnormal data, analyze the topological connection between the spatial channel and the affected area, determine the current direction and possible fault propagation paths, establish an influence matrix, and assign specific values to the influence matrix according to the transmission spatial channel data and the interval abnormal data, and parameterize the relationship to construct the channel - to - region mapping relationship model; Determine the channel fault types and the types of adverse effects generated in different regions. The channel fault types include short - circuit, open - circuit, grounding, over - voltage, over - load, and insulation fault. The influence types include economic influence, ecological environment influence, and safety hazard influence. Establish a relationship matrix, assign specific values to the influence matrix according to the transmission spatial channel data and the interval abnormal data, and parameterize the relationship to construct the abnormal - to - abnormal matching relationship model; The rows of the influence matrix represent each interval of the spatial channel, the columns represent each sub - region of the affected area, and the matrix elements represent the degree of influence of the state of a certain channel interval on a certain sub - region; The rows of the relationship matrix represent the channel fault types, the columns represent the types of adverse effects generated in different regions, and the matrix elements represent the degree of association between different channel fault types and various influence types; The GD - Informer model represents a G - DAE denoising auto - encoder built based on GRU, using GRU as the encoder and decoder, and preliminarily training the G - DAE model based on the abnormal event data in the historical meteorological grid data and the corresponding channel data, and forming a model by replacing the embedding layer of the Informer model with the G - DAE as the input layer.

2. The monitoring and early warning method for abnormal conditions of a power transmission channel according to claim 1, characterized in that, The meteorological data includes temperature, humidity, wind speed, wind direction, and precipitation. The grid data includes prediction time, report time, longitude, and latitude.

3. The monitoring and early warning method for abnormal conditions of a power transmission channel according to claim 1, characterized in that, After performing temporal alignment and spatial alignment on the historical meteorological grid data and the abnormal event data recorded in the channel data, data preprocessing and feature engineering operations are carried out on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence. Based on the input sequence, the GD-Informer model is trained and optimized to obtain a trained GD-Informer model, including: Perform temporal alignment operations and spatial alignment operations on the abnormal event data recorded in the historical meteorological grid data and the channel data; Divide the abnormal event data recorded in the historical meteorological grid data and the channel data into training samples and test samples; Perform data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence. The data preprocessing includes data cleaning, normalization, and data segmentation operations. The feature engineering operations include feature selection, feature construction, and sequence construction; Based on the input sequence, train, test, and optimize the GD-Informer model to obtain a trained GD-Informer model.

4. A method for monitoring and warning abnormal conditions of a power transmission channel according to claim 1, characterized in that, Based on the trained GD-Informer model, perform real-time prediction on new meteorological data to obtain a prediction result. Based on the prediction result, the channel-to-region mapping relationship model, and the anomaly-to-anomaly matching relationship model, perform result analysis and anomaly warning, including: Based on the trained GD-Informer model, perform real-time prediction on the obtained meteorological data to obtain a prediction result; After obtaining the prediction result, use the channel-to-region mapping relationship model and the anomaly-to-anomaly matching relationship model to perform result analysis and anomaly warning.

5. A method for monitoring and warning of abnormal conditions in a power transmission channel according to claim 3, characterized in that, Perform temporal alignment operations and spatial alignment operations on the abnormal event data recorded in the historical meteorological grid data and the channel data, including: The temporal alignment operation includes timestamp merging, finding common timestamps, and data alignment; The spatial alignment operation is based on the grid data and the bit field data in the abnormal event data for region division and matching.

6. The monitoring and early warning method for abnormal conditions of a power transmission channel according to claim 4, characterized in that, After obtaining the prediction result, use the channel-to-region mapping relationship model and the anomaly-to-anomaly matching relationship model to perform result analysis and anomaly warning, including: The result analysis is to use the channel-to-region mapping relationship model and the anomaly-to-anomaly matching relationship model to analyze the prediction result to form a heat map and a case report. The heat map shows the predicted distribution of abnormal conditions of transmission channels in different regions. The case report compiles a detailed case report for the predicted event, recording the event process and subsequent actions; The anomaly warning is to perform threshold warning for different degrees of impact of abnormal events. When the degree of impact reaches the preset threshold, start the corresponding emergency procedure and push it in real time through the SMS and enterprise-level message push platform to notify the duty personnel to take corresponding measures. The push content includes time, weather, transmission channel, affected area, and degree of impact.

7. A monitoring and early warning system for abnormal conditions of a power transmission channel, which is used to implement the monitoring and early warning method for abnormal conditions of a power transmission channel according to any one of claims 1-6, characterized in that, Including: The data acquisition module obtains channel data based on the power grid resource business middle platform, obtains regional data based on the power grid electricity information acquisition system, and obtains historical meteorological grid data based on the meteorological center; The relationship model construction module constructs a mapping relationship model of channels to regions and a heterogeneous-to-heterogeneous matching relationship model based on the acquired channel data and region data; The model training module performs temporal alignment and spatial alignment on the historical meteorological grid data and the abnormal event data recorded in the channel data, conducts data preprocessing and feature engineering operations on the abnormal event data in the historical meteorological grid data and the corresponding channel data to form an input sequence, and trains and tunes the GD-Informer model based on the input sequence to obtain a trained GD-Informer model; The result determination and output module performs real-time prediction on new meteorological data based on the trained GD-Informer model to obtain prediction results, then conducts result analysis based on the prediction results, the channel-to-region mapping relationship model, and the heterogeneous-to-heterogeneous matching relationship model, and issues early warnings about the abnormal conditions of transmission channels and regional abnormalities through text messages and the enterprise-level message push platform; Among them, constructing a channel-to-region mapping relationship model and a heterogeneous-to-heterogeneous matching relationship model based on channel data and region data includes: Determine the key nodes and key channels in the spatial channel according to the transmission spatial channel data and interval abnormal data, analyze the topological connection between the spatial channel and the affected region, determine the current direction and possible fault propagation paths, establish an influence matrix, and assign specific values to the influence matrix according to the transmission spatial channel data and interval abnormal data, and parameterize the relationship to construct a channel-to-region mapping relationship model; Determine the types of channel faults and the types of adverse effects generated in different regions. The types of channel faults include short circuit, open circuit, grounding, overvoltage, overload, and insulation fault. The types of effects include economic impact, ecological environment impact, and safety hazard impact. Establish a relationship matrix, assign specific values to the influence matrix according to the transmission spatial channel data and interval abnormal data, parameterize the relationship, and construct a heterogeneous-to-heterogeneous matching relationship model; The rows of the influence matrix represent each interval of the spatial channel, the columns represent each sub-region of the affected region, and the matrix elements represent the degree of influence of the state of a certain channel interval on a certain sub-region; The rows of the relationship matrix represent the types of channel faults, the columns represent the types of adverse effects generated in different regions, and the matrix elements represent the degree of entanglement between different channel fault types and various types of effects; The GD-Informer model represents a G-DAE denoising autoencoder based on GRU, uses GRU as the encoder and decoder, and conducts preliminary training on the G-DAE model based on the abnormal event data in the historical meteorological grid data and the corresponding channel data, and forms a model by using G-DAE as the input layer to replace the embedding layer of the Informer model.

Images