A power failure area accurate identification method based on Beidou technology

Abstract

The application relates to the technical field of power fault positioning, and discloses a power fault area positioning precision identification method based on Beidou technology, which comprises the following steps: collecting power grid line data, filling in missing values according to contexts, and constructing a target area power network topology; constructing a regional convergence access equipment deployment optimization objective function and solving the function to obtain an optimal access equipment deployment position scheme and deploy the scheme; converging target area power sensor data by using the deployed access equipment, constructing a power fault identification model, and identifying and positioning power faults of the target area converged power sensor data. The application carries out information fusion based on the position information of adjacent power sensors and the time sequence information of power sensor data, obtains a feature vector representing the abnormal state of the power sensor data, identifies power faults of the power sensor data, and positions the power faults according to the transmission direction of the power sensor data by the access equipment.

Description

Technical Field

[0001] This invention relates to the technical field of power fault location, and in particular to a method for accurate identification of power fault locations based on BeiDou technology. Background Technology

[0002] With the continuous development of society and the increasing demand for electricity, power systems are developing towards large-scale, high-efficiency, and intelligent directions. However, various faults exist in power systems, such as line short circuits and equipment failures. These faults pose serious safety hazards to the operation of power systems and may even lead to accidents. How to quickly and accurately identify faults in power systems has become an urgent problem to be solved in the operation and management of power systems. The BeiDou Navigation Satellite System, as a satellite navigation system independently developed by my country, has the characteristics of global coverage, high precision, high reliability, and high robustness. BeiDou technology has wide applications in positioning, navigation, and time services, and its performance and coverage are constantly improving, making it an important member of the global satellite navigation system. Applying BeiDou technology to the accurate identification of fault locations in power systems is expected to achieve rapid location and accurate identification of fault locations through its high-precision positioning and navigation capabilities, thereby improving the safety and reliability of power systems. Therefore, this invention proposes a method for accurate identification of power fault locations based on BeiDou technology. By combining BeiDou technology with power systems, it provides new ideas and methods for the intelligent operation and management of power systems, promoting the modernization of power systems. Summary of the Invention

[0003] In view of this, the present invention provides a method for accurate identification of power fault locations based on BeiDou technology. The purpose is to: 1) iterate the missing value filling results based on the deviation between the power grid line data after filling missing values ​​and the original power grid line data, obtaining the missing value filling result with the highest structural similarity, thereby achieving missing value filling of power grid line data, and constructing the power network topology of the target area, using transmission stations as nodes and the power grid lines between transmission stations as edges, and deploying power sensors at transmission stations to sense the transmission capacity of the transmission stations, constructing an optimization objective function for the deployment of regional aggregation access equipment, with the coverage and coverage accuracy of the access equipment to the nodes as the optimization objectives, and adopting an improved dung beetle optimization algorithm, using different types of dung beetles to iteratively process the access equipment deployment location scheme in various ways. 1) Obtain the optimal deployment location scheme for the access devices and use the access devices to aggregate and transmit power sensor data within the coverage area; 2) Use the deployed access devices to aggregate power sensor data in the target area, construct a power fault identification model, perform information fusion based on the location information of neighboring power sensors and the time sequence information of power sensor data, obtain feature vectors representing the abnormal state of power sensor data, perform power fault identification on the power sensor data aggregated in the target area, and locate the power sensors with identified power faults according to the transmission direction of the power sensor data, identify the power sensor data with power faults, and take the node location of the power sensor as the location of the power fault area, so as to achieve accurate identification of power fault location based on power sensor data information and Beidou positioning technology.

[0004] To achieve the above objectives, this invention provides a method for accurate identification of power fault locations based on BeiDou technology, comprising the following steps:

[0005] S1: Collect power grid line data and fill in missing values ​​according to the context to obtain preprocessed power grid line data. Construct the power network topology of the target area based on the preprocessed power grid line data, and deploy power sensors in the power network topology of the target area.

[0006] S2: Construct an objective function for optimizing the deployment of regional aggregation access devices. The objective function takes the deployment location of the access devices as the independent variable and the coverage and accuracy of the access devices on the power network topology of the target area as the optimization objectives. The access devices are regional data aggregation access points with BeiDou positioning function, which are responsible for aggregating and transmitting power sensor data within the coverage area.

[0007] S3: With the goal of maximizing the coverage and coverage accuracy of the access devices to the power network topology of the target area, the objective function for the deployment of regional aggregation access devices is optimized and solved to obtain the optimal access device deployment location scheme and then deployed. The improved dung beetle optimization algorithm is the main implementation method for the optimization solution.

[0008] S4: Utilize the deployed access devices to aggregate power sensor data in the target area, construct a power fault identification model, identify power faults in the aggregated power sensor data in the target area, identify power sensor data with power faults, and use the access devices to locate the identified power sensors to obtain the location of the power fault area.

[0009] As a further improvement of the present invention:

[0010] Optionally, in step S1, collecting power grid line data and filling in missing values ​​according to the context to obtain preprocessed power grid line data includes:

[0011] Collect power grid line data, wherein the collected power grid line data is in the following format:

[0012] {L n |n∈[1,N]}

[0013] L n =(L n (1),L n (2),...,L n (m),...,L n (M))

[0014] in:

[0015] L n This represents the power grid line data collected for the nth power grid line, where N represents the total number of power grid lines; the power grid lines are the transmission lines between power transmission stations.

[0016] L n (1),L n (2),...,L n (m),...,L n (M) represents the current value collected by the nth power grid line at the Mth sampling time, L n (m) represents the current value of the nth power grid line at the mth sampling time, where m∈[1,M];

[0017] Fill in missing values ​​in the power grid line data based on context, where the power grid line data L n Missing value L n The filling process for (q) is as follows:

[0018] S11: Initialize and generate U missing value imputation results, where the initial generated u-th missing value imputation result is:

[0019] S12: Set the current iteration number of the missing value imputation result to t, with an initial value of 0 and a maximum value of Max. Then the missing value imputation result... The result of the t-th iteration is

[0020] S13: Fill the missing value filling results into the power grid line data L n In the process, the corresponding power grid line data is obtained, including the results of filling in missing values. The power grid line data is

[0021] Calculate power grid line data Data L of power grid lines n The error between them is used as the missing value to fill in the result. fitness:

[0022]

[0023] in:

[0024] Indicates the result of missing value filling. The fitness of;

[0025] μ n Represents power grid line data L n The mean, Represents power grid line data The mean;

[0026] σ n Represents power grid line data L n standard deviation Represents power grid line data Standard deviation;

[0027] ∈1, ∈2 represent adjustment coefficients;

[0028] S14: Select the missing value imputation result with the lowest fitness among the U missing value imputation results, and take it as the optimal imputation result obtained in the t-th iteration.

[0029] S15: Iterate through the missing value imputation results, where the missing value imputation results... The iterative formula is:

[0030]

[0031] in:

[0032] rand(0,1) represents a random number between 0 and 1;

[0033] c1 and c2 represent the control parameters;

[0034] exp(·) denotes an exponential function with the natural constant as its base;

[0035] express The result of filling missing values ​​with the lowest fitness;

[0036] S16: Let t = t + 1, return to step S13, and continue until the maximum number of iterations is reached. Select the missing value filling result with the lowest fitness from the U missing value filling results obtained in the final iteration, and use the selected missing value filling result as the power grid line data L. n Missing value L n The fill value of (q) is used to obtain the power grid line data L. n Preprocessing results l ′ n ;

[0037] The power network topology of the target area is constructed based on the preprocessed power grid line data.

[0038] Optionally, constructing the target area power network topology based on the preprocessed power grid line data includes:

[0039] The target area power network topology is constructed based on the preprocessed power grid line data. The construction process of the target area power network topology is as follows:

[0040] The power transmission stations in the power grid are treated as nodes in the target area's power grid, and the power lines between the transmission stations are treated as edges between the nodes, thus constructing the topology of the target area's power grid:

[0041] G = (E, V)

[0042] E={e s |s∈[1,S]}

[0043]

[0044] in:

[0045] G represents the power network topology of the target area;

[0046] E represents the set of nodes in the target area's power network, e s Let S represent the s-th node in the target area power network, and let S represent the total number of nodes in the target area power network.

[0047] V represents the set of edges in the power network of the target region. Represents node e s With e i The edge between;

[0048] The weights of the edges in the power network topology of the target area are calculated, where the edges... The transmission weight is:

[0049]

[0050] in:

[0051] Representing an edge The transmission weight; in this embodiment of the invention.

[0052] mean(·) means to calculate the mean. express The corresponding preprocessed power grid line data;

[0053] Deploy power sensors in the power network topology of the target area.

[0054] Optionally, deploying power sensors in the target area's power network topology includes:

[0055] The power sensors are deployed at the locations of S nodes in the power network topology of the target area, forming a power sensor set:

[0056] h = {h s |s∈[1,S]}

[0057] in:

[0058] h represents the set of power sensors, h s This represents the s-th node e deployed in the power network topology of the target area. s The power sensor at the location.

[0059] Optionally, the objective function for optimizing the deployment of regional aggregation access devices in step S2 includes:

[0060] An optimization objective function for the deployment of regional aggregation access devices is constructed, where the deployment location of the access devices is the independent variable, and the coverage and accuracy of the access devices over the target area's power network topology are the optimization objectives. The access devices are regional data aggregation access points with BeiDou positioning capabilities, responsible for aggregating and transmitting power sensor data within the coverage area. The constructed optimization objective function for the deployment of regional aggregation access devices is as follows:

[0061]

[0062] θ=(θ1,θ2,...,θ k ,...,θ K )

[0063] in:

[0064] F(·) represents the objective function for optimizing the deployment of regional aggregation access devices, θ represents the deployment location scheme of the access devices, and θ1, θ2, ..., θ3 represent the deployment location scheme of the access devices. k ,...,θ K Let θ represent the deployment locations of K access devices in the access device deployment location scheme θ, and let F(θ) represent the objective function value of the access device deployment location scheme θ.

[0065] W s Represents node e s Transmission weight, Ω s In the target area power network topology, node e represents the node... s Let c be the set of edges with endpoints Ω. s c represents the set Ω s For any edge c in the array, w(c) represents the transmission weight of edge c; where the transmission weight... Used to indicate the coverage accuracy of access devices;

[0066] α(θ k ,e s ) indicates deployment at θ k The access device for node e s The coverage, max{α(θ) k ,e s )|k∈[1,K]} represents the access device deployment location scheme θ for node e. s Coverage;

[0067] R represents the convergence radius of the access device;

[0068] dis(θ k ,e s ) represents θ k With node e s The distance between the locations.

[0069] Optionally, in step S3, the optimization objective is to maximize the coverage and accuracy of the access device's coverage of the target area's power network topology. The optimization objective function for the deployment of the regional aggregation access device is then solved, including:

[0070] With the optimization objective of maximizing the coverage and accuracy of the power network topology of the target area by the access devices, the objective function for optimizing the deployment of regional aggregation access devices is solved. The improved dung beetle optimization algorithm is the main implementation method for this optimization solution. The optimization solution process for the objective function for the deployment of regional aggregation access devices is as follows:

[0071] S31: Initialize the positions of D dung beetles, where the formula for initializing the position of the d-th dung beetle is:

[0072]

[0073] in:

[0074] Let represent the initial position of the d-th dung beetle, where d∈[1,D]; in this embodiment of the invention, The location is randomly generated;

[0075] S32: Let the current iteration number of the dung beetle's position be z, and the maximum iteration number be Z. Then the z-th iteration position of the d-th dung beetle is...

[0076]

[0077] in:

[0078] The k-th dimension coordinates represent the iteration position, corresponding to the deployment position of the k-th access device;

[0079] S33: Using the dung beetle's iteration position as the input value to the objective function for optimizing the deployment of the regional aggregation access device, the objective function value corresponding to the iteration position is obtained, where the iteration position... The corresponding objective function value is

[0080] Sort the D groups of iteration positions obtained in the z-th iteration according to the objective function value in descending order, and divide the sorting results equally to obtain 3 groups of iteration position sequences, where each group of iteration position sequences contains D / 3 groups of iteration positions;

[0081] S34: Use the iteration position in the first iteration position sequence as the position of the dung beetle, and perform the dung beetle position iteration:

[0082]

[0083] in:

[0084] σ represents the deflection coefficient, and σ is set to 0.2;

[0085] This represents the iteration position with the minimum objective function value among the D group of iteration positions obtained in the z-th iteration;

[0086] The iteration positions in the second set of iteration positions are taken as the positions of the dancing dung beetle, and the position of the dancing dung beetle is iterated:

[0087]

[0088] in:

[0089] τ represents a random angle in (0, π / 2);

[0090] The iteration positions in the third set of iteration positions are used as the breeding positions of the dung beetles, and the breeding position iteration is performed:

[0091]

[0092] in:

[0093] This represents the iteration position with the largest objective function value among the D group of iteration positions obtained in the z-th iteration;

[0094] S35: Let d = d + 1, return to step S33, until the maximum number of iterations is reached, and take the position of the dung beetle with the largest objective function value after the maximum number of iterations is reached as the optimal access device deployment location scheme, and deploy the access device.

[0095] Optionally, in step S4, the deployed access devices aggregate power sensor data from the target area to construct a power fault identification model, including:

[0096] The deployed access devices aggregate power sensor data from the target area, uploading the data sensed by the power sensors to the access devices. The power sensor h... s The sensed power sensor data is H s :

[0097] H s =(H s (1),H s (2),...,H s (a),...,H s (A))

[0098] in:

[0099] H s (1),H s (2),...,H s (a),...,H s (A) indicates the power sensor h s Sensed node es The power transmission sequence,

[0100] H s (a) represents node e s The amount of electricity transmitted at the a-th transmission time, where A represents the number of transmission times, and a∈[1,A];

[0101] A power fault identification model is constructed, which includes an input layer, a location association information extraction layer, a time series information extraction layer, an information fusion layer, and a fault identification layer.

[0102] The input layer receives power sensor data to be identified and associated neighboring power sensor data. There is an uninterrupted power grid line between the power sensor and the nodes where the neighboring power sensors are deployed. The neighboring power sensor data is the data sensed by the neighboring power sensors. The location association information extraction layer extracts the location association information between the neighboring power sensors and the power sensor to be identified. The time series information extraction layer extracts the time series information of the power sensor data and the associated neighboring power sensor data respectively. The information fusion layer fuses the location association information and the time series information to form a feature vector characterizing the abnormal state of the power sensor data. The fault identification layer converts the feature vector into a fault probability. If the fault probability is higher than a preset threshold, it indicates that there is a power fault in the power sensor data.

[0103] Power fault identification is performed on the power sensor data collected in the target area to identify power sensor data with power faults.

[0104] Optionally, the step of using a power fault identification model to identify power faults in the power sensor data aggregated in the target area, and identifying power sensor data containing power faults, includes:

[0105] Power fault identification is performed using a power fault identification model on power sensor data aggregated in a target area, where the power sensor data H... s The power fault identification process is as follows:

[0106] S41: The input layer receives power sensor data H to be identified for fault identification. s and associated data from nearby power sensors Where B represents the power sensor data H s The total number of nearby power sensor data, H represents power sensor data s The data of the b-th nearest power sensor, where b∈[1,B];

[0107] S42: The location association information extraction layer extracts the data of nearby power sensors and the corresponding nearby power sensor h. sLocation correlation information between them, including data from nearby power sensors. Corresponding nearby power sensors With power sensor h s The location association information between them is as follows:

[0108]

[0109] in:

[0110] Indicates proximity power sensor With power sensor h s Location association information between them;

[0111] Indicates proximity power sensor With power sensor h s The distance between the deployed locations;

[0112] Indicates proximity power sensor With power sensor h s The transmission weight of the power grid lines between the corresponding nodes;

[0113] S43: The time-series information extraction layer extracts the time-series information of the power sensor data and the associated neighboring power sensor data, where the power sensor data H s The results of time series information extraction are as follows:

[0114]

[0115] in:

[0116] W 1 This represents a convolution matrix for temporal information, and * represents the convolution operator.

[0117] F2(H s ) represents power sensor data H s The results of extracting time-series information;

[0118] S44: The information fusion layer fuses location-related information and temporal information to form a feature vector characterizing the abnormal state of power sensor data.

[0119]

[0120] in:

[0121] F3(H s ) represents the power sensor data H s Feature vectors of abnormal states;

[0122] S45: The fault identification layer will use feature vector F3(H) s Converting ) to failure probability P(H) s If the failure probability P(H) s If the value is higher than the preset threshold, it indicates that the power sensor data H... s There is a power failure, where the failure probability P(H) s The conversion formula for ) is:

[0123]

[0124] in:

[0125] W 2 Represents the probability mapping convolution matrix;

[0126] The access device locates the power sensor that has detected a power fault based on the transmission direction of the power sensor data, and uses the node location where the power sensor is located as the location of the power fault area.

[0127] To address the above problems, the present invention provides an electronic device, the electronic device comprising:

[0128] Memory, storing at least one instruction;

[0129] Communication interfaces enable communication between electronic devices; and

[0130] The processor executes the instructions stored in the memory to implement the above-described method for accurate identification of power fault locations based on BeiDou technology.

[0131] To address the aforementioned issues, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned method for accurate identification of power fault locations based on BeiDou technology.

[0132] Compared with existing technologies, this invention proposes a method for accurate identification of power fault locations based on BeiDou technology, which has the following advantages:

[0133] First, this solution proposes an access device deployment scheme and constructs an optimization objective function for the deployment of regional aggregation access devices. This objective function uses the deployment location of the access devices as the independent variable and the coverage and accuracy of the access devices over the target area's power network topology as the optimization objectives. The access devices are regional data aggregation access points with BeiDou positioning capabilities, responsible for aggregating and transmitting power sensor data within the coverage area. The constructed optimization objective function for the deployment of regional aggregation access devices is as follows:

[0134]

[0135] θ=(θ1,θ2,...,θ k ,...,θ K )

[0136] Where: F(·) represents the objective function for optimizing the deployment of regional aggregation access devices, θ represents the deployment location scheme of access devices, and θ1,θ2,...,θ k ,...,θ K Let F(θ) represent the deployment locations of K access devices in the access device deployment location scheme θ, and let F(θ) represent the objective function value of the access device deployment location scheme θ. s Represents node e s Transmission weight, Ω s In the target area power network topology, node e represents the node... s Let c be the set of edges with endpoints Ω. s c represents the set Ω s For any edge c in the array, w(c) represents the transmission weight of edge c; where the transmission weight... Used to represent the coverage accuracy of access devices; α(θ) k ,e s ) indicates deployment at θ k The access device for node e s The coverage, max{α(θ) k ,e s )|k∈[1,K]} represents the access device deployment location scheme θ for node e. s Coverage; R represents the convergence radius of the access device; dis(θ) k ,e s ) represents θ k With node e s The distance between locations. This scheme iterates the missing value filling results based on the deviation between the power grid line data after filling missing values ​​and the original power grid line data, obtaining the missing value filling result with the highest structural similarity, thus realizing the missing value filling of power grid line data, and constructing the power network topology of the target area, with transmission stations as nodes and power grid lines between transmission stations as edges, and deploying power sensors at transmission stations to sense the power transmission capacity of the transmission stations. An optimization objective function for the deployment of regional aggregation access devices is constructed, with the coverage and coverage accuracy of the access devices to the nodes as the optimization objectives. An improved dung beetle optimization algorithm is adopted, iterating the access device deployment location scheme in various ways with different types of dung beetles to obtain the optimal access device deployment location scheme, and using the access devices to aggregate and transmit power sensor data within the coverage area.

[0137] Meanwhile, this solution proposes a power fault identification and fault location method based on power sensor data. It utilizes a power fault identification model to identify power faults in the target area based on the power sensor data collected from the target area. The power sensor data H... s The power fault identification process is as follows: The input layer receives the power sensor data H to be identified. s And associated nearby power sensor data; the location association information extraction layer extracts the nearby power sensor data and the corresponding nearby power sensor and power sensor h. s Location correlation information between them, including data from nearby power sensors. Corresponding nearby power sensors With power sensor h s The location association information between them is as follows:

[0138]

[0139] in: Indicates proximity power sensor With power sensor h s Location association information between them;

[0140] Indicates proximity power sensor With power sensor h s The distance between the deployed locations; Indicates proximity power sensor With power sensor h s The transmission weights of the power grid lines between the corresponding nodes; the time-series information extraction layer extracts the time-series information of the power sensor data and the associated neighboring power sensor data, where the power sensor data H s The results of time series information extraction are as follows:

[0141]

[0142] Among them: W 1 F2(H) represents a convolution matrix containing temporal information, where * represents the convolution operator; s ) represents power sensor data H s The time-series information extraction results; the information fusion layer fuses location correlation information and time-series information to form a feature vector characterizing the abnormal state of power sensor data:

[0143]

[0144] Among them: F3(H s ) represents the power sensor data H s Feature vector of abnormal state; the fault identification layer will use feature vector F3(H) sConverting ) to failure probability P(H) s If the failure probability P(H) s If the value is higher than the preset threshold, it indicates that the power sensor data H... s There is a power failure, where the failure probability P(H) s The conversion formula for ) is:

[0145]

[0146] Among them: W 2 This represents a probability mapping convolution matrix. The access device locates the power sensors that have detected power faults based on the transmission direction of the power sensor data, and uses the node location of the power sensor as the location of the power fault area. This solution utilizes the deployed access devices to aggregate power sensor data from the target area, constructs a power fault identification model, and performs information fusion based on the location information of neighboring power sensors and the temporal information of the power sensor data to obtain a feature vector characterizing the abnormal state of the power sensor data. This model identifies power faults in the aggregated power sensor data of the target area. The access device locates the power sensors that have detected power faults based on the transmission direction of the power sensor data, identifies the power sensor data containing the power fault, and uses the node location of the power sensor as the location of the power fault area, thus achieving accurate identification of power fault locations based on power sensor data information and BeiDou positioning technology. Attached Figure Description

[0147] Figure 1 This is a flowchart illustrating a method for accurate identification of power fault locations based on BeiDou technology, provided in an embodiment of the present invention.

[0148] Figure 2 This is a schematic diagram of the structure of an electronic device that implements a method for accurate identification of power fault locations based on BeiDou technology, according to an embodiment of the present invention.

[0149] In the diagram: 1. Electronic device, 10. Processor, 11. Memory, 12. Program, 13. Communication interface.

[0150] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0151] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0152] This application provides a method for accurate identification of power fault locations based on BeiDou technology. The executing entity of this method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the method for accurate identification of power fault locations based on BeiDou technology can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0153] Example 1:

[0154] S1: Collect power grid line data and fill in missing values ​​according to the context to obtain preprocessed power grid line data. Construct the power network topology of the target area based on the preprocessed power grid line data, and deploy power sensors in the power network topology of the target area.

[0155] In step S1, power grid line data is collected and missing values ​​are filled in according to the context to obtain preprocessed power grid line data, including:

[0156] Collect power grid line data, wherein the collected power grid line data is in the following format:

[0157] {L n |n∈[1,N]}

[0158] L n =(L n (1),L n (2),...,L n (m),...,L n (M))

[0159] in:

[0160] L n This represents the power grid line data collected for the nth power grid line, where N represents the total number of power grid lines; the power grid lines are the transmission lines between power transmission stations.

[0161] L n (1),L n (2),...,L n (m),...,L n (M) represents the current value collected by the nth power grid line at the Mth sampling time, L n (m) represents the current value of the nth power grid line at the mth sampling time, where m∈[1,M];

[0162] Fill in missing values ​​in the power grid line data based on context, where the power grid line data L nMissing value L n The filling process for (q) is as follows:

[0163] S11: Initialize and generate U missing value imputation results, where the initial generated u-th missing value imputation result is:

[0164] S12: Set the current iteration number of the missing value imputation result to t, with an initial value of 0 and a maximum value of Max. Then the missing value imputation result... The result of the t-th iteration is

[0165] S13: Fill the missing value filling results into the power grid line data L n In the process, the corresponding power grid line data is obtained, including the results of filling in missing values. The power grid line data is

[0166] Calculate power grid line data Data L of power grid lines n The error between them is used as the missing value to fill in the result. fitness:

[0167]

[0168] in:

[0169] Indicates the result of missing value filling. The fitness of;

[0170] μ n Represents power grid line data L n The mean, Represents power grid line data The mean;

[0171] σ n Represents power grid line data L n standard deviation Represents power grid line data Standard deviation;

[0172] ∈1, ∈2 represent adjustment coefficients;

[0173] S14: Select the missing value imputation result with the lowest fitness among the U missing value imputation results, and take it as the optimal imputation result obtained in the t-th iteration.

[0174] S15: Iterate through the missing value imputation results, where the missing value imputation results... The iterative formula is:

[0175]

[0176] in:

[0177] rand(0,1) represents a random number between 0 and 1;

[0178] c1 and c2 represent the control parameters;

[0179] exp(·) denotes an exponential function with the natural constant as its base;

[0180] express The result of filling missing values ​​with the lowest fitness;

[0181] S16: Let t = t + 1, return to step S13, and continue until the maximum number of iterations is reached. Select the missing value filling result with the lowest fitness from the U missing value filling results obtained in the final iteration, and use the selected missing value filling result as the power grid line data L. n Missing value L n The fill value of (q) is used to obtain the power grid line data L. n Preprocessing results l ′ n ;

[0182] The power network topology of the target area is constructed based on the preprocessed power grid line data.

[0183] The construction of the target area power network topology based on the preprocessed power grid line data includes:

[0184] The target area power network topology is constructed based on the preprocessed power grid line data. The construction process of the target area power network topology is as follows:

[0185] The power transmission stations in the power grid are treated as nodes in the target area's power grid, and the power lines between the transmission stations are treated as edges between the nodes, thus constructing the topology of the target area's power grid:

[0186] G = (E, V)

[0187] E={e s |s∈[1,S]}

[0188]

[0189] in:

[0190] G represents the power network topology of the target area;

[0191] E represents the set of nodes in the target area's power network, e s Let S represent the s-th node in the target area power network, and let S represent the total number of nodes in the target area power network.

[0192] V represents the set of edges in the power network of the target region. Represents node e s With e i The edge between;

[0193] The weights of the edges in the power network topology of the target area are calculated, where the edges... The transmission weight is:

[0194]

[0195] in:

[0196] Representing an edge The transmission weight; in this embodiment of the invention.

[0197] mean(·) means to calculate the mean. express The corresponding preprocessed power grid line data;

[0198] Deploy power sensors in the power network topology of the target area.

[0199] The deployment of power sensors in the target area's power network topology includes:

[0200] The power sensors are deployed at the locations of S nodes in the power network topology of the target area, forming a power sensor set:

[0201] h = {h s |s∈[1,S]}

[0202] in:

[0203] h represents the set of power sensors, h s This represents the s-th node e deployed in the power network topology of the target area. s The power sensor at the location.

[0204] S2: Construct an objective function for optimizing the deployment of regional aggregation access devices, where the deployment location of the access devices is the independent variable, and the coverage and accuracy of the access devices on the power network topology of the target area are the optimization objectives.

[0205] The objective function for optimizing the deployment of regional aggregation access devices, as described in step S2, includes:

[0206] An optimization objective function for the deployment of regional aggregation access devices is constructed, where the deployment location of the access devices is the independent variable, and the coverage and accuracy of the access devices over the target area's power network topology are the optimization objectives. The access devices are regional data aggregation access points with BeiDou positioning capabilities, responsible for aggregating and transmitting power sensor data within the coverage area. The constructed optimization objective function for the deployment of regional aggregation access devices is as follows:

[0207]

[0208] θ=(θ1,θ2,...,θ k ,...,θ K )

[0209] in:

[0210] F(·) represents the objective function for optimizing the deployment of regional aggregation access devices, θ represents the deployment location scheme of the access devices, and θ1, θ2, ..., θ3 represent the deployment location scheme of the access devices. k ,...,θ K Let θ represent the deployment locations of K access devices in the access device deployment location scheme θ, and let F(θ) represent the objective function value of the access device deployment location scheme θ.

[0211] W s Represents node e s Transmission weight, Ω s In the target area power network topology, node e represents the node... s Let c be the set of edges with endpoints Ω. s c represents the set Ω s For any edge c in the array, w(c) represents the transmission weight of edge c; where the transmission weight... Used to indicate the coverage accuracy of access devices;

[0212] α(θ k ,e s ) indicates deployment at θ k The access device for node e s The coverage, max{α(θ) k ,e s )|k∈[1,K]} represents the access device deployment location scheme θ for node e. s Coverage;

[0213] R represents the convergence radius of the access device;

[0214] dis(θ k ,e s ) represents θ k With node e s The distance between the locations.

[0215] S3: With the goal of maximizing the coverage and accuracy of the access devices to the power network topology of the target area, the objective function for optimizing the deployment of regional aggregation access devices is optimized and solved to obtain the optimal deployment location scheme for the access devices and then the deployment is carried out.

[0216] In step S3, the optimization objective is to maximize the coverage and accuracy of the access devices on the target area's power network topology. The objective function for optimizing the deployment of regional aggregation access devices is solved, including:

[0217] With the optimization objective of maximizing the coverage and accuracy of the power network topology in the target area by the access devices, the optimization objective function for the deployment of regional aggregation access devices is solved. The optimization solution process for the deployment objective function of regional aggregation access devices is as follows:

[0218] S31: Initialize the positions of D dung beetles, where the formula for initializing the position of the d-th dung beetle is:

[0219]

[0220] in:

[0221] Let represent the initial position of the d-th dung beetle, where d∈[1,D]; in this embodiment of the invention, The location is randomly generated;

[0222] S32: Let the current iteration number of the dung beetle's position be z, and the maximum iteration number be Z. Then the z-th iteration position of the d-th dung beetle is...

[0223]

[0224] in:

[0225] The k-th dimension coordinates represent the iteration position, corresponding to the deployment position of the k-th access device;

[0226] S33: Using the dung beetle's iteration position as the input value to the objective function for optimizing the deployment of the regional aggregation access device, the objective function value corresponding to the iteration position is obtained, where the iteration position... The corresponding objective function value is

[0227] Sort the D groups of iteration positions obtained in the z-th iteration according to the objective function value in descending order, and divide the sorting results equally to obtain 3 groups of iteration position sequences, where each group of iteration position sequences contains D / 3 groups of iteration positions;

[0228] S34: Use the iteration position in the first iteration position sequence as the position of the dung beetle, and perform the dung beetle position iteration:

[0229]

[0230] in:

[0231] σ represents the deflection coefficient, and σ is set to 0.2;

[0232] This represents the iteration position with the minimum objective function value among the D group of iteration positions obtained in the z-th iteration;

[0233] The iteration positions in the second set of iteration positions are taken as the positions of the dancing dung beetle, and the position of the dancing dung beetle is iterated:

[0234]

[0235] in:

[0236] τ represents a random angle in (0, π / 2);

[0237] The iteration positions in the third set of iteration positions are used as the breeding positions of the dung beetles, and the breeding position iteration is performed:

[0238]

[0239] in:

[0240] This represents the iteration position with the largest objective function value among the D group of iteration positions obtained in the z-th iteration;

[0241] S35: Let d = d + 1, return to step S33, until the maximum number of iterations is reached, and take the position of the dung beetle with the largest objective function value after the maximum number of iterations is reached as the optimal access device deployment location scheme, and deploy the access device.

[0242] S4: Utilize the deployed access devices to aggregate power sensor data in the target area, construct a power fault identification model, identify power faults in the aggregated power sensor data in the target area, identify power sensor data with power faults, and use the access devices to locate the identified power sensors to obtain the location of the power fault area.

[0243] Step S4 utilizes the deployed access devices to aggregate power sensor data from the target area and constructs a power fault identification model, including:

[0244] The deployed access devices aggregate power sensor data from the target area, uploading the data sensed by the power sensors to the access devices. The power sensor h...s The sensed power sensor data is H s :

[0245] H s =(H s (1),H s (2),...,H s (a),...,H s (A))

[0246] in:

[0247] H s (1),H s (2),...,H s (a),...,H s (A) indicates the power sensor h s Sensed node e s The power transmission sequence,

[0248] H s (a) represents node e s The amount of electricity transmitted at the a-th transmission time, where A represents the number of transmission times, and a∈[1,A];

[0249] A power fault identification model is constructed, which includes an input layer, a location association information extraction layer, a time series information extraction layer, an information fusion layer, and a fault identification layer.

[0250] The input layer receives power sensor data to be identified and associated neighboring power sensor data. There is an uninterrupted power grid line between the power sensor and the nodes where the neighboring power sensors are deployed. The neighboring power sensor data is the data sensed by the neighboring power sensors. The location association information extraction layer extracts the location association information between the neighboring power sensors and the power sensor to be identified. The time series information extraction layer extracts the time series information of the power sensor data and the associated neighboring power sensor data respectively. The information fusion layer fuses the location association information and the time series information to form a feature vector characterizing the abnormal state of the power sensor data. The fault identification layer converts the feature vector into a fault probability. If the fault probability is higher than a preset threshold, it indicates that there is a power fault in the power sensor data.

[0251] Power fault identification is performed on the power sensor data collected in the target area to identify power sensor data with power faults.

[0252] The method of using a power fault identification model to identify power faults in the power sensor data aggregated in the target area, and identifying power sensor data containing power faults, includes:

[0253] Power fault identification is performed using a power fault identification model on power sensor data aggregated in a target area, where the power sensor data H... s The power fault identification process is as follows:

[0254] S41: The input layer receives power sensor data H to be identified for fault identification. s and associated data from nearby power sensors Where B represents the power sensor data H s The total number of nearby power sensor data, H represents power sensor data s The data of the b-th nearest power sensor, where b∈[1,B];

[0255] S42: The location association information extraction layer extracts the data of nearby power sensors and the corresponding nearby power sensor h. s Location correlation information between them, including data from nearby power sensors. Corresponding nearby power sensors With power sensor h s The location association information between them is as follows:

[0256]

[0257] in:

[0258] Indicates proximity power sensor With power sensor h s Location association information between them;

[0259] Indicates proximity power sensor With power sensor h s The distance between the deployed locations;

[0260] Indicates proximity power sensor With power sensor h s The transmission weight of the power grid lines between the corresponding nodes;

[0261] S43: The time-series information extraction layer extracts the time-series information of the power sensor data and the associated neighboring power sensor data, where the power sensor data H s The results of time series information extraction are as follows:

[0262]

[0263] in:

[0264] W 1This represents a convolution matrix for temporal information, and * represents the convolution operator.

[0265] F2(H s ) represents power sensor data H s The results of extracting time-series information;

[0266] S44: The information fusion layer fuses location-related information and temporal information to form a feature vector characterizing the abnormal state of power sensor data.

[0267]

[0268] in:

[0269] F3(H s ) represents the power sensor data H s Feature vectors of abnormal states;

[0270] S45: The fault identification layer will use the feature vector F s (H s Converting ) to failure probability P(H) s If the failure probability P(H) s If the value is higher than the preset threshold, it indicates that the power sensor data H... s There is a power failure, where the failure probability P(H) s The conversion formula for ) is:

[0271]

[0272] in:

[0273] W 2 Represents the probability mapping convolution matrix;

[0274] The access device locates the power sensor that has detected a power fault based on the transmission direction of the power sensor data, and uses the node location where the power sensor is located as the location of the power fault area.

[0275] Example 2:

[0276] like Figure 2 The diagram shown is a structural schematic of an electronic device for implementing a method for accurate identification of power fault locations based on BeiDou technology, according to an embodiment of the present invention.

[0277] The electronic device 1 may include a processor 10, a memory 11, a communication interface 13 and a bus, and may also include a computer program, such as program 12, stored in the memory 11 and executable on the processor 10.

[0278] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 can include both internal and external storage units of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of program 12, but also to temporarily store data that has been output or will be output.

[0279] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (such as program 12 for accurate identification of power fault locations based on BeiDou technology) and calls data stored in the memory 11 to perform various functions and process data in the electronic device 1.

[0280] The communication interface 13 may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices, and to enable communication between internal components of the electronic device.

[0281] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0282] Figure 2 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 2 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0283] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0284] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0285] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0286] The program 12 stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, which, when run in the processor 10, can achieve the following:

[0287] Collect power grid line data and fill in missing values ​​according to the context to obtain preprocessed power grid line data. Construct the power network topology of the target area based on the preprocessed power grid line data, and deploy power sensors in the power network topology of the target area.

[0288] Construct an objective function to optimize the deployment of regional aggregation access devices;

[0289] With the goal of maximizing the coverage and accuracy of the access devices to the power network topology of the target area, the objective function for the deployment of regional aggregation access devices is optimized and solved to obtain the optimal deployment location scheme for the access devices and then the deployment is carried out.

[0290] By using the deployed access devices to aggregate power sensor data in the target area, a power fault identification model is constructed. Power faults are identified in the aggregated power sensor data in the target area. Power sensor data with power faults are identified. The access devices are used to locate the power sensors with identified power faults to obtain the location of the power fault area.

[0291] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 2 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0292] It should be noted that the sequence numbers of the above embodiments of the present invention are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0293] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0294] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for accurate identification of power fault locations based on BeiDou technology, characterized in that, The method includes: S1: Collect power grid line data and fill in missing values ​​to obtain preprocessed power grid line data. Construct the power network topology of the target area based on the preprocessed power grid line data, and deploy power sensors in the power network topology of the target area. S2: Construct an objective function for optimizing the deployment of regional aggregation access devices, where the deployment location of the access devices is the independent variable, and the coverage and accuracy of the access devices on the power network topology of the target area are the optimization objectives. S3: With the goal of maximizing the coverage and accuracy of the access devices to the power network topology of the target area, the objective function for the deployment of regional aggregation access devices is optimized and solved to obtain the optimal deployment location scheme for the access devices and then the deployment is carried out. S4: Use the deployed access devices to aggregate power sensor data in the target area, build a power fault identification model, identify power faults in the aggregated power sensor data in the target area, identify power sensor data with power faults, use the access devices to locate the identified power sensors with power faults, and obtain the location of the power fault area. The objective function for optimizing the deployment of regional aggregation access devices, as described in step S2, includes: An optimization objective function for the deployment of regional aggregation access devices is constructed, where the deployment location of the access devices is the independent variable, and the coverage and accuracy of the access devices over the target area's power network topology are the optimization objectives. The access devices are regional data aggregation access points with BeiDou positioning capabilities, responsible for aggregating and transmitting power sensor data within the coverage area. The constructed optimization objective function for the deployment of regional aggregation access devices is as follows: in: This represents the objective function for optimizing the deployment of regional aggregation access devices. This indicates the deployment location plan for the access devices. Indicates the deployment location scheme of access devices The deployment locations of the K access devices in the middle, Indicates the deployment location scheme of access devices The objective function value; Represents a node Transmission weight, Indicates the topology of the power network in the target area as nodes Let be the set of edges with endpoints. c represents a set Any edge in, Let represent the transmission weight of edge c; where the transmission weight Used to indicate the coverage accuracy of access devices; Indicates deployment at Access devices for nodes coverage, Indicates the deployment location scheme of access devices For nodes Coverage; Indicates the convergence radius of the access device; express With nodes The distance between the locations; In step S3, the optimization objective is to maximize the coverage and accuracy of the access devices on the target area's power network topology. The objective function for optimizing the deployment of regional aggregation access devices is solved, including: With the optimization objective of maximizing the coverage and accuracy of the power network topology in the target area by the access devices, the optimization objective function for the deployment of regional aggregation access devices is solved. The optimization solution process for the deployment objective function of regional aggregation access devices is as follows: S31: Initialize the positions of D dung beetles, where the formula for initializing the position of the d-th dung beetle is: in: This represents the initial position of the d-th dung beetle. ; S32: Let the current iteration number of the dung beetle's position be z, and the maximum iteration number be Z. Then the z-th iteration position of the d-th dung beetle is... : in: The k-th dimension coordinates represent the iteration position, corresponding to the deployment position of the k-th access device; S33: Using the dung beetle's iteration position as the input value to the objective function for optimizing the deployment of the regional aggregation access device, the objective function value corresponding to the iteration position is obtained, where the iteration position... The corresponding objective function value is ; Sort the D iteration positions obtained from the z-th iteration in descending order of objective function values, and divide the sorted results equally to obtain 3 sets of iteration position sequences. Each set of iteration position sequences contains... Group iteration position; S34: Take the iteration position in the first set of iteration position sequences as the position of the dung beetle and perform the dung beetle position iteration; The iterative positions in the second set of iterative position sequences are taken as the positions of the dancing dung beetle, and the position of the dancing dung beetle is iterated. The iteration positions in the third set of iteration position sequences are used as the breeding positions of dung beetles, and the breeding position iteration is performed. S35: Let d = d + 1, return to step S33, until the maximum number of iterations is reached, and take the position of the dung beetle with the largest objective function value after the maximum number of iterations is reached as the optimal access device deployment location scheme, and deploy the access device.

2. The method for accurate identification of power fault locations based on BeiDou technology as described in claim 1, characterized in that, In step S1, power grid line data is collected and missing values ​​are filled to obtain preprocessed power grid line data, including: Collect power grid line data, wherein the collected power grid line data is in the following format: in: This represents the power grid line data collected for the nth power grid line, where N represents the total number of power grid lines; the power grid lines are the transmission lines between power transmission stations. Indicates that the nth power grid line is in The current value collected at each acquisition moment. This represents the current value of the nth power grid line at the m-th data collection time. ; Fill in missing values ​​in the power grid line data based on context, where the power grid line data Missing values The filling process is as follows: S11: Initialize and generate U missing value imputation results, where the initial generated u-th missing value imputation result is: , ; S12: Set the current iteration number of the missing value imputation result to t, with an initial value of 0 and a maximum value of Max. Then the missing value imputation result... The result of the t-th iteration is ; S13: Fill the missing value filling results into the power grid line data. In the process, the corresponding power grid line data is obtained, including the results of filling in missing values. The power grid line data is ; Calculate power grid line data Data on power grid lines The error between them is used as the missing value to fill in the result. fitness ; S14: Select the missing value imputation result with the lowest fitness among the U missing value imputation results, and take it as the optimal imputation result obtained in the t-th iteration. ; S15: Iterate through the results of filling missing values; S16: Let t = t + 1, return to step S13, and continue until the maximum number of iterations is reached. Select the missing value filling result with the lowest fitness from the U missing value filling results obtained in the final iteration, and use the selected missing value filling result as the power grid line data. Missing values The filled values ​​are used to obtain the power grid line data. Preprocessing results , ; The power network topology of the target area is constructed based on the preprocessed power grid line data.

3. The method for accurate identification of power fault locations based on BeiDou technology as described in claim 2, characterized in that, The construction of the target area power network topology based on the preprocessed power grid line data includes: The target area power network topology is constructed based on the preprocessed power grid line data. The construction process of the target area power network topology is as follows: The power transmission stations in the power grid are treated as nodes in the target area's power grid, and the power lines between the transmission stations are treated as edges between the nodes, thus constructing the topology of the target area's power grid: in: G represents the power network topology of the target area; E represents the set of nodes in the target area's power network. Let S represent the s-th node in the target area power network, and let S represent the total number of nodes in the target area power network. This represents the set of edges in the power network of the target region. Represents a node and The edge between; The weights of the edges in the power network topology of the target area are calculated, where the edges... The transmission weight is: in: Representing an edge Transmission weight; This indicates the calculation of the mean. express The corresponding preprocessed power grid line data; Deploy power sensors in the power network topology of the target area.

4. The method for accurate identification of power fault locations based on BeiDou technology as described in claim 3, characterized in that, The deployment of power sensors in the target area's power network topology includes: The power sensors are deployed at the locations of S nodes in the power network topology of the target area, forming a power sensor set: in: Represents a collection of power sensors. This indicates the s-th node deployed in the power network topology of the target area. The power sensor at the location.

5. The method for accurate identification of power fault locations based on BeiDou technology as described in claim 1, characterized in that, Step S4 utilizes the deployed access devices to aggregate power sensor data from the target area and constructs a power fault identification model, including: The deployed access devices aggregate power sensor data from the target area, uploading the data sensed by the power sensors to the access devices. The power sensor data that was sensed is : in: Indicates power sensor Sensed nodes The power transmission sequence, Represents a node The amount of electricity transmitted at the a-th transmission time, where A represents the number of transmission times. ; A power fault identification model is constructed, which includes an input layer, a location association information extraction layer, a time series information extraction layer, an information fusion layer, and a fault identification layer. The input layer receives power sensor data to be identified and associated neighboring power sensor data. There is an uninterrupted power grid line between the power sensor and the nodes where the neighboring power sensors are deployed. The neighboring power sensor data is the data sensed by the neighboring power sensors. The location association information extraction layer extracts the location association information between the neighboring power sensors and the power sensor to be identified. The time series information extraction layer extracts the time series information of the power sensor data and the associated neighboring power sensor data respectively. The information fusion layer fuses the location association information and the time series information to form a feature vector characterizing the abnormal state of the power sensor data. The fault identification layer converts the feature vector into a fault probability. If the fault probability is higher than a preset threshold, it indicates that there is a power fault in the power sensor data. Power fault identification is performed on the power sensor data collected in the target area to identify power sensor data with power faults.

6. The method for accurate identification of power fault locations based on BeiDou technology as described in claim 5, characterized in that, The method of using a power fault identification model to identify power faults in the power sensor data aggregated in the target area, and identifying power sensor data containing power faults, includes: Power fault identification is performed using a power fault identification model on power sensor data collected from a target area. The power fault identification process is as follows: S41: The input layer receives power sensor data for fault identification. and associated data from nearby power sensors Where B represents power sensor data The total number of nearby power sensor data, Represents power sensor data The data from the b-th nearest power sensor, ; S42: Location association information extraction layer extracts the data of nearby power sensors and the corresponding nearby power sensors. Location correlation information between them, including data from nearby power sensors. Corresponding nearby power sensors With power sensors The location association information between them is as follows: in: Indicates proximity power sensor With power sensors Location association information between them; Indicates proximity power sensor With power sensors The distance between the deployed locations; Indicates proximity power sensor With power sensors The transmission weight of the power grid lines between the corresponding nodes; S43: The time-series information extraction layer extracts the time-series information of the power sensor data and the associated neighboring power sensor data, whereby the power sensor data... The results of time series information extraction are as follows: in: Represents the convolution matrix of temporal information. This represents the convolution operator; Represents power sensor data The results of extracting time-series information; S44: The information fusion layer fuses location-related information and temporal information to form a feature vector characterizing the abnormal state of power sensor data. in: Represents the data from power sensor Feature vectors of abnormal states; S45: The fault identification layer will use feature vectors Converted to failure probability If the failure probability If the value is higher than a preset threshold, it indicates that the power sensor data... There is a power outage, where the probability of the outage is... The conversion formula is: in: Represents the probability mapping convolution matrix; The access device locates the power sensor that has detected a power fault based on the transmission direction of the power sensor data, and uses the node location where the power sensor is located as the location of the power fault area.

Images