A power substation anti-electricity-stealing inspection monitoring method and system based on Beidou technology

Abstract

The application relates to the technical field of anti-electricity-stealing monitoring, and discloses a power substation anti-electricity-stealing inspection and monitoring method and system based on Beidou technology, the method comprising the following steps: deploying power parameter sensors with Beidou positioning functions in a power distribution network structure of a power substation based on an optimized global energy consumption strategy; collecting power parameter data of the power substation in real time, and preprocessing the power parameter data; and constructing an electricity-stealing identification model to detect and monitor video collection of electricity-stealing behaviors of the preprocessed power parameter data. The distance between the power parameter sensors and the power substation is taken as the communication energy consumption, the deployment position is iterated in combination with the historical optimal positions in different triangular network structures, the power parameter sensor deployment result with the lowest global energy consumption is obtained, power parameter data collection is realized, the multi-scale features of the power parameter data and the effective neighborhood information representing the change of the power parameter data of the nearest power substation are combined, and electricity-stealing behavior detection is realized.

Description

Technical Field

[0001] This invention relates to the field of anti-electricity theft monitoring, and in particular to a method and system for anti-electricity theft inspection and monitoring of substations based on Beidou technology. Background Technology

[0002] With the continuous growth of electricity demand and the expanding coverage of power networks, substations, as a crucial component of the power system, are of paramount importance for their safety and stability. However, electricity theft not only threatens the economic interests of power companies but also poses a potential threat to the stable operation of the power system. Therefore, effective methods for investigating and monitoring electricity theft have become an urgent problem for the power industry. The BeiDou Navigation Satellite System, with its high positioning accuracy and strong anti-interference capabilities, has broad application prospects in the power industry, particularly in precise positioning, spatiotemporal synchronization, and security monitoring, providing solutions for investigating and monitoring electricity theft. Summary of the Invention

[0003] In view of this, the present invention proposes a method for monitoring and investigating electricity theft in substations based on BeiDou technology. The aim is to utilize the technical advantages of the BeiDou system and combine it with modern information and communication technology to achieve comprehensive monitoring and management of substations and power grids, thereby effectively preventing and combating electricity theft.

[0004] To achieve the above objectives, this invention provides a substation anti-electricity theft inspection and monitoring method based on BeiDou technology, comprising the following steps:

[0005] S1: Based on the substation power distribution network structure, power parameter sensors with BeiDou positioning function are deployed in the substation power distribution network structure based on the global energy consumption optimization strategy. The power parameter sensors include current sensors, voltage sensors and temperature sensors.

[0006] S2: Real-time collection of substation power parameter data using deployed power parameter sensors, and transmission of the power parameter data to the central monitoring system via narrowband Internet of Things for preprocessing to obtain preprocessed power parameter data;

[0007] S3: In the central monitoring system, an electricity theft identification model is constructed to detect electricity theft behavior on preprocessed power parameter data, wherein the abnormal behavior identification by multi-scale feature fusion is the implementation method of the electricity theft identification model;

[0008] S4: If electricity theft is detected, dispatch the corresponding high-definition camera at the substation to collect monitoring video of the substation location area.

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

[0010] Optionally, obtaining the substation power distribution network structure in step S1 includes:

[0011] The location set of substations is obtained using BeiDou technology, where the location set of substations is as follows:

[0012] {L n |n∈[1,N]}

[0013] in:

[0014] L n This indicates the location of the nth substation, and N represents the total number of substations.

[0015] The substation distribution network structure is constructed based on the location set of substations. The construction process of the substation distribution network structure is as follows:

[0016] Step 1: Initialize and construct the substation triangular network structure set. The constructed substation triangular network structure set is initially empty.

[0017] Step 2: Construct a super triangle network structure that includes all substation locations, and put the super triangle network structure into the substation triangle network structure set;

[0018] Step 3: Insert the substation locations in the location set into the triangular network structures in the substation triangular network structure set in turn. The inserted substation locations are inside any triangular network structure in the substation triangular network structure set.

[0019] The triangular network structure of the substation is obtained by traversing the set of triangular network structures of the substation whose circumscribed circle contains the location of the substation. The triangular network structure obtained by traversing the set of triangular network structures forms a polygon structure.

[0020] All the triangular network structures inside the polygon structure are deleted, and the vertices of the polygon structure are connected to the substation locations to form multiple new triangular network structures.

[0021] Step 4: Repeat step 3 until all substation locations in the location set are inserted into the substation triangular network structure set, so that the super triangular network structure is divided into multiple triangular network structures.

[0022] Step 5: Delete the triangular network structures whose vertices are the same as those of the super triangle network structure to form the substation power distribution network structure. The substation power distribution network structure contains M triangular network structures, and the vertex of each triangular network structure is the location of the substation.

[0023] Based on the strategy of optimizing global energy consumption, power parameter sensors with BeiDou positioning function are deployed in the substation power distribution network structure.

[0024] Optionally, the deployment of power parameter sensors with BeiDou positioning function in the substation distribution network structure based on the optimized global energy consumption strategy includes:

[0025] Based on an optimized global energy consumption strategy, power parameter sensors with BeiDou positioning capabilities are deployed in the substation distribution network structure. These power parameter sensors include current sensors, voltage sensors, and temperature sensors. The deployment process for these power parameter sensors is as follows:

[0026] S11: Obtain M triangular mesh structures, where the vertices of the m-th triangular mesh structure are:

[0027] S12: Constructing an objective function for deploying power parameter sensors based on an optimized global energy consumption strategy:

[0028]

[0029] θ=(θ(1),θ(2),...,θ(m),...,θ(M))

[0030] in:

[0031] F(θ) represents the objective function for deploying power parameter sensors, and θ represents the deployment result of power parameter sensors;

[0032] θ(m) represents the deployment location of the power parameter sensor deployed in the m-th triangular mesh structure;

[0033] w m This represents the importance weight of the m-th triangular mesh structure;

[0034] A m This represents the average annual power transmission capacity of the strain power station corresponding to the three vertices of the m-th triangular mesh structure;

[0035] The location θ (m) of the power parameter sensor deployment position and the vertex The distance between them;

[0036] This indicates the communication distance threshold for power parameter sensors;

[0037] S13: Initialize and generate the deployment results of U groups of power parameter sensors, where the initial generated deployment result of the u-th group of power parameter sensors is:

[0038]

[0039] in:

[0040] This represents the deployment result of the u-th group of power parameter sensors generated during initialization;

[0041] Indicates the deployment results of power parameter sensors The deployment location of the power parameter sensor deployed in the m-th triangular mesh structure;

[0042] S14: Let the current iteration number of the power parameter sensor deployment results be t, and the maximum iteration number be Max. Then, the t-th iteration result of the u-th group of power parameter sensor deployment results is: The initial value of t is 0;

[0043] S15: Iterate the deployment results of the power parameter sensors until the preset maximum number of iterations is reached, and substitute the U sets of power parameter sensor deployment results obtained in the current iteration into the power parameter sensor deployment objective function. Select the power parameter sensor deployment result with the smallest power parameter sensor deployment objective function value for power parameter sensor deployment.

[0044] S16: N substations send information to the nearest power parameter sensor, count the number of messages received by each power parameter sensor, and remove power parameter sensors that have not received messages.

[0045] Optionally, step S15 iterates over the deployment results of the power parameter sensors, including:

[0046] S151: Calculate the location information of the power parameter sensor deployment locations, where the power parameter sensor deployment locations are... The location information is:

[0047]

[0048]

[0049] in:

[0050] Indicates the deployment location of the power parameter sensor Location information;

[0051] The locations of the power parameter sensors are shown in sequence. For the three vertices Position weight;

[0052] exp(·) denotes an exponential function with the natural constant as its base;

[0053] S152: Calculate the fitness of different power parameter sensor deployment locations, where the power parameter sensor deployment locations... The fitness is:

[0054]

[0055] in:

[0056] Indicates the deployment location of the power parameter sensor The fitness of;

[0057] Record the deployment location of the power parameter sensor with the minimum fitness among different triangular mesh structures during t iterations, as the historical best position of the triangular mesh structure, where the historical best position of the m-th triangular mesh structure after t iterations is denoted as best. m (t);

[0058] S153: Iterate on the deployment results of the power parameter sensors, whereby the deployment results of the power parameter sensors... The iterative formula is:

[0059]

[0060] in:

[0061] rand(-1,1) represents a random number between -1 and 1;

[0062] c represents the control parameter;

[0063] W1 represents the mapping matrix of location information, and T represents the transpose;

[0064] This represents the sequence of historical optimal deployment locations after t iterations;

[0065] S154: Let t = t + 1, then return to step S151.

[0066] Optionally, step S2 involves using deployed power parameter sensors to collect substation power parameter data in real time, including:

[0067] The substation sends power parameter data to the nearest power parameter sensor, where the power parameter data of the nth substation is:

[0068]

[0069] in:

[0070] I n This represents the power parameter data of the nth substation;

[0071] The current data sequence, voltage data sequence, and temperature data sequence of the nth substation are represented sequentially.

[0072] Represents a data sequence The G sampled data values ​​in the data. Represents a data sequence The g-th sampled data value in the dataset; in this embodiment of the invention, These represent the current, voltage, and temperature values ​​of the nth substation at the g-th sampling time, respectively.

[0073] Power parameter data is transmitted to a central monitoring system via narrowband Internet of Things (IoT) for preprocessing, resulting in preprocessed power parameter data, where power parameter data I... n Medium sampled data values The preprocessing formula is:

[0074]

[0075] in:

[0076] Indicates the sampled data value The preprocessing results;

[0077] max i min represents the maximum threshold value for the i-th type of power parameter. i This represents the minimum threshold value for the i-th type of power parameter; in this embodiment of the invention, the first to third types of power parameters are current, voltage, and temperature, respectively.

[0078] Power Parameter Data I n The corresponding preprocessing result is x n :

[0079]

[0080] in:

[0081] The current data sequence is as follows. Voltage data sequence and temperature data sequences The preprocessing results.

[0082] Optionally, transmitting power parameter data to the central monitoring system via narrowband Internet of Things includes:

[0083] Power parameter data is transmitted to a central monitoring system via narrowband Internet of Things (IoT), where power parameter data I n The transmission process is as follows:

[0084] S21: Calculate the power parameter data I from different power parameter sensors. n Transmission capability:

[0085]

[0086] in:

[0087] R(I n ) represents any power parameter sensor for power parameter data I n Transmission capability;

[0088] B(I n ) represents power parameter data I n The number of bits transmitted, where byte represents the preset transmission bit threshold;

[0089] E indicates the current power level of the power parameter sensor;

[0090] DIS(I n ) represents the power parameter sensor and power parameter data I n Distance between current locations;

[0091] Dis represents the distance between the power parameter sensor and the central monitoring system, and γ represents the preset transmission distance threshold.

[0092] S22: Transfer power parameter data I n Transmitted to the power parameter sensor with the strongest transmission capacity;

[0093] S23: Repeat step S22 until the power parameter data I is obtained. n Transmitted to the central monitoring system.

[0094] Optionally, step S3 involves constructing an electricity theft detection model to detect electricity theft behavior from the preprocessed power parameter data, including:

[0095] A model for identifying electricity theft is constructed, wherein the abnormal behavior identification through multi-scale feature fusion is the implementation method of the electricity theft identification model. The electricity theft identification model takes preprocessed power parameter data as input and electricity theft behavior detection results as output. The electricity theft identification model includes an input layer, a multi-scale feature extraction layer, a neighborhood information extraction layer, a feature fusion layer, and a behavior recognition layer.

[0096] The input layer is used to receive preprocessed power parameter data;

[0097] The multi-scale feature extraction layer is a convolutional layer structure in a convolutional neural network, used to perform multi-scale convolution operations on preprocessed power parameter data to form multi-scale power parameter features.

[0098] The neighborhood information extraction layer is a long short-term memory network structure, which is used to extract effective neighborhood information of neighboring substations based on the location information of the substations corresponding to the preprocessed power parameter data.

[0099] The feature fusion layer is used to fuse multi-scale power parameter features and effective neighborhood information to form power parameter fusion features.

[0100] The behavior recognition layer is a fully connected layer structure in a convolutional neural network, used to map the fusion features of power parameters into the results of electricity theft behavior recognition;

[0101] The electricity theft detection model is used to detect electricity theft behavior using preprocessed power parameter data, where the preprocessed power parameter data x n The procedure for detecting electricity theft is as follows:

[0102] S31: The input layer receives preprocessed power parameter data x n ;

[0103] S32: Multi-scale feature extraction layer for preprocessed power parameter data x n Perform multi-scale convolution operations to construct multi-scale power parameter features:

[0104]

[0105]

[0106] in:

[0107] f n This represents the preprocessed power parameter data x. n Multi-scale electrical parameter characteristics;

[0108] W k×k This represents a k-row, k-column convolution weight matrix, where * represents the convolution operator;

[0109] This represents the preprocessed power parameter data x. n Electricity parameter characteristics at scale k;

[0110] S33: Neighborhood information extraction layer is based on preprocessed power parameter data x n Based on the location information of the corresponding substation, extract the effective neighborhood information of neighboring substations:

[0111]

[0112] in:

[0113] Q n This represents the valid neighborhood information of neighboring substations;

[0114] Indicates with x n The preprocessed power parameter data of the substation with the shortest transmission line and the corresponding power station are characterized by power parameter features at scale K.

[0115] S34: Feature fusion layer for multi-scale power parameter features f n And effective neighborhood information Q n Feature fusion is performed to form the power parameter fusion feature Z. n :

[0116]

[0117] S35: The behavior recognition layer fuses power parameters with feature Z. n Mapped to electricity theft behavior identification results:

[0118]

[0119] in:

[0120] Y n This represents the preprocessed power parameter data x. n The corresponding electricity theft behavior identification result; if Y n If the value is higher than the preset threshold, it indicates that there is electricity theft; otherwise, there is no electricity theft.

[0121] W2 represents the mapping weight matrix.

[0122] Optionally, step S4 involves scheduling the corresponding high-definition camera at the substation to collect monitoring video of the substation location area, including:

[0123] If preprocessed power parameter data x is detected n If electricity theft is detected, the high-definition cameras of the nth substation will be dispatched to monitor and collect video footage of the substation's location. Based on the video footage, an anti-electricity theft investigation will be conducted at the substation.

[0124] To address the aforementioned problems, this invention provides a substation anti-electricity theft inspection and monitoring system based on BeiDou technology, characterized in that the system comprises:

[0125] The sensor deployment module is used to deploy power parameter sensors with BeiDou positioning function in the substation power distribution network structure based on the global energy consumption optimization strategy, according to the substation power distribution network structure.

[0126] The data acquisition module is used to collect power parameter data of the substation in real time using deployed power parameter sensors, and transmit the power parameter data to the central monitoring system via narrowband Internet of Things for preprocessing to obtain preprocessed power parameter data.

[0127] The electricity theft detection device is used to build an electricity theft identification model to detect electricity theft behavior on pre-processed power parameter data. If electricity theft behavior is detected, the corresponding high-definition camera in the substation is dispatched to collect monitoring video of the substation location area.

[0128] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0129] Memory, storing at least one instruction;

[0130] Communication interfaces enable communication between electronic devices; and

[0131] The processor executes the instructions stored in the memory to implement the above-described substation anti-electricity theft inspection and monitoring method based on Beidou technology.

[0132] 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 substation anti-electricity theft inspection and monitoring method based on BeiDou technology.

[0133] Compared with existing technologies, this invention proposes a substation anti-electricity theft inspection and monitoring method based on BeiDou technology, which has the following advantages:

[0134] First, this scheme, based on the location distribution of substations, divides the substation power distribution network into several triangular network structures, where the vertices of the triangular network structures represent the substation locations. The distance between the power parameter sensors and the substations is used as the communication energy consumption to construct the objective function for deploying the power parameter sensors. By combining the historical best positions in different triangular network structures, the deployment positions are iterated to obtain the power parameter sensor deployment result with the lowest global energy consumption. The position of the power parameter sensors is controlled to iterate within the triangular network structure to avoid the proximity of different power parameter sensors, which would affect data communication transmission.

[0135] Meanwhile, this solution selects the next-hop power parameter sensor for power parameter data transmission step by step based on the distance between different power parameter sensors and the current location of power parameter data, the sensor's power level, and the distance to the central monitoring system. It also combines the multi-scale characteristics of power parameter data and the effective neighborhood information of the nearest substation to perform fusion features that characterize changes in power parameter data. Based on these fusion features, it detects electricity theft. If electricity theft is detected, it dispatches the corresponding high-definition camera at the substation to collect monitoring video of the substation location area, thereby realizing anti-electricity theft inspection and monitoring at the substation. Attached Figure Description

[0136] Figure 1This is a flowchart illustrating a method for monitoring and investigating electricity theft in a substation based on BeiDou technology, provided in an embodiment of the present invention.

[0137] Figure 2 This is a functional module diagram of a substation anti-electricity theft inspection and monitoring system based on Beidou technology provided in an embodiment of the present invention;

[0138] Figure 2 In the middle: 100 Substation anti-electricity theft inspection and monitoring system based on Beidou technology, 101 Sensor deployment module, 102 Data acquisition module, 103 Electricity theft detection device;

[0139] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing a substation anti-electricity theft inspection and monitoring method based on Beidou technology, according to an embodiment of the present invention.

[0140] Figure 3 In Chinese: 1. Electronic device; 10. Processor; 11. Memory; 12. Program; 13. Communication interface;

[0141] 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

[0142] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0143] This application provides a method for monitoring and investigating electricity theft in substations 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 can be executed by software or hardware installed on a terminal device or server device, and the software may 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.

[0144] Example 1:

[0145] S1: Based on the substation power distribution network structure, power parameter sensors with BeiDou positioning function are deployed in the substation power distribution network structure based on the global energy consumption optimization strategy. The power parameter sensors include current sensors, voltage sensors and temperature sensors.

[0146] The step S1, obtaining the substation power distribution network structure, includes:

[0147] The location set of substations is obtained using BeiDou technology, where the location set of substations is as follows:

[0148] {L n |n∈[1,N]}

[0149] in:

[0150] L n This indicates the location of the nth substation, and N represents the total number of substations.

[0151] The substation distribution network structure is constructed based on the location set of substations. The construction process of the substation distribution network structure is as follows:

[0152] Step 1: Initialize and construct the substation triangular network structure set. The constructed substation triangular network structure set is initially empty.

[0153] Step 2: Construct a super triangle network structure that includes all substation locations, and put the super triangle network structure into the substation triangle network structure set;

[0154] Step 3: Insert the substation locations in the location set into the triangular network structures in the substation triangular network structure set in turn. The inserted substation locations are inside any triangular network structure in the substation triangular network structure set.

[0155] The triangular network structure of the substation is obtained by traversing the set of triangular network structures of the substation whose circumscribed circle contains the location of the substation. The triangular network structure obtained by traversing the set of triangular network structures forms a polygon structure.

[0156] All the triangular network structures inside the polygon structure are deleted, and the vertices of the polygon structure are connected to the substation locations to form multiple new triangular network structures.

[0157] Step 4: Repeat step 3 until all substation locations in the location set are inserted into the substation triangular network structure set, so that the super triangular network structure is divided into multiple triangular network structures.

[0158] Step 5: Delete the triangular network structures whose vertices are the same as those of the super triangle network structure to form the substation power distribution network structure. The substation power distribution network structure contains M triangular network structures, and the vertex of each triangular network structure is the location of the substation.

[0159] Based on the strategy of optimizing global energy consumption, power parameter sensors with BeiDou positioning function are deployed in the substation power distribution network structure.

[0160] The deployment of power parameter sensors with BeiDou positioning function in the substation distribution network structure based on the optimized global energy consumption strategy includes:

[0161] Based on an optimized global energy consumption strategy, power parameter sensors with BeiDou positioning capabilities are deployed in the substation distribution network structure. These power parameter sensors include current sensors, voltage sensors, and temperature sensors. The deployment process for these power parameter sensors is as follows:

[0162] S11: Obtain M triangular mesh structures, where the vertices of the m-th triangular mesh structure are:

[0163] S12: Constructing an objective function for deploying power parameter sensors based on an optimized global energy consumption strategy:

[0164]

[0165] θ=(θ(1),θ(2),...,θ(m),...,θ(M))

[0166] in:

[0167] F(θ) represents the objective function for deploying power parameter sensors, and θ represents the deployment result of power parameter sensors;

[0168] θ(m) represents the deployment location of the power parameter sensor deployed in the m-th triangular mesh structure;

[0169] w m This represents the importance weight of the m-th triangular mesh structure;

[0170] A m This represents the average annual power transmission capacity of the strain power station corresponding to the three vertices of the m-th triangular mesh structure;

[0171] The location θ (m) of the power parameter sensor deployment position and the vertex The distance between them;

[0172] This indicates the communication distance threshold for power parameter sensors;

[0173] S13: Initialize and generate the deployment results of U groups of power parameter sensors, where the initial generated deployment result of the u-th group of power parameter sensors is:

[0174]

[0175] in:

[0176] This represents the deployment result of the u-th group of power parameter sensors generated during initialization;

[0177] Indicates the deployment results of power parameter sensors The deployment location of the power parameter sensor deployed in the m-th triangular mesh structure;

[0178] S14: Let the current iteration number of the power parameter sensor deployment results be t, and the maximum iteration number be Max. Then, the t-th iteration result of the u-th group of power parameter sensor deployment results is: The initial value of t is 0;

[0179] S15: Iterate the deployment results of the power parameter sensors until the preset maximum number of iterations is reached, and substitute the U sets of power parameter sensor deployment results obtained in the current iteration into the power parameter sensor deployment objective function. Select the power parameter sensor deployment result with the smallest power parameter sensor deployment objective function value for power parameter sensor deployment.

[0180] S16: N substations send information to the nearest power parameter sensor, count the number of messages received by each power parameter sensor, and remove power parameter sensors that have not received messages.

[0181] Step S15 iterates over the deployment results of the power parameter sensors, including:

[0182] S151: Calculate the location information of the power parameter sensor deployment locations, where the power parameter sensor deployment locations are... The location information is:

[0183]

[0184]

[0185] in:

[0186] Indicates the deployment location of the power parameter sensor Location information;

[0187] The locations of the power parameter sensors are shown in sequence. For the three vertices Position weight;

[0188] exp(·) denotes an exponential function with the natural constant as its base;

[0189] S152: Calculate the fitness of different power parameter sensor deployment locations, where the power parameter sensor deployment locations... The fitness is:

[0190]

[0191] in:

[0192] Indicates the deployment location of the power parameter sensor The fitness of;

[0193] Record the deployment location of the power parameter sensor with the minimum fitness among different triangular mesh structures during t iterations, as the historical best position of the triangular mesh structure, where the historical best position of the m-th triangular mesh structure after t iterations is denoted as best. m (t);

[0194] S153: Iterate on the deployment results of the power parameter sensors, whereby the deployment results of the power parameter sensors... The iterative formula is:

[0195]

[0196] in:

[0197] rand(-1,1) represents a random number between -1 and 1;

[0198] c represents the control parameter;

[0199] W1 represents the mapping matrix of location information, and T represents the transpose;

[0200] This represents the sequence of historical optimal deployment locations after t iterations;

[0201] S154: Let t = t + 1, then return to step S151.

[0202] S2: Real-time collection of substation power parameter data is achieved using deployed power parameter sensors, and the power parameter data is transmitted to the central monitoring system via narrowband Internet of Things for preprocessing to obtain preprocessed power parameter data.

[0203] In step S2, the deployed power parameter sensors are used to collect power parameter data of the substation in real time, including:

[0204] The substation sends power parameter data to the nearest power parameter sensor, where the power parameter data of the nth substation is:

[0205]

[0206] in:

[0207] I n This represents the power parameter data of the nth substation;

[0208] The current data sequence, voltage data sequence, and temperature data sequence of the nth substation are represented sequentially.

[0209] Represents a data sequence The G sampled data values ​​in the data. Represents a data sequence The g-th sampled data value in the dataset; in this embodiment of the invention, These represent the current, voltage, and temperature values ​​of the nth substation at the g-th sampling time, respectively.

[0210] Power parameter data is transmitted to a central monitoring system via narrowband Internet of Things (IoT) for preprocessing, resulting in preprocessed power parameter data, where power parameter data I... n Medium sampled data values The preprocessing formula is:

[0211]

[0212] in:

[0213] Indicates the sampled data value The preprocessing results;

[0214] max i min represents the maximum threshold value for the i-th type of power parameter. i This represents the minimum threshold value for the i-th type of power parameter; in this embodiment of the invention, the first to third types of power parameters are current, voltage, and temperature, respectively.

[0215] Power Parameter Data I n The corresponding preprocessing result is x n :

[0216]

[0217] in:

[0218] The current data sequence is as follows. Voltage data sequence and temperature data sequences The preprocessing results.

[0219] The transmission of power parameter data to the central monitoring system via narrowband Internet of Things includes:

[0220] Power parameter data is transmitted to a central monitoring system via narrowband Internet of Things (IoT), where power parameter data I n The transmission process is as follows:

[0221] S21: Calculate the power parameter data I from different power parameter sensors. n Transmission capability:

[0222]

[0223] in:

[0224] R(I n ) represents any power parameter sensor for power parameter data I n Transmission capability;

[0225] B(I n ) represents power parameter data I n The number of bits transmitted, where byte represents the preset transmission bit threshold;

[0226] E indicates the current power level of the power parameter sensor;

[0227] DIS(I n ) represents the power parameter sensor and power parameter data I n Distance between current locations;

[0228] Dis represents the distance between the power parameter sensor and the central monitoring system, and γ represents the preset transmission distance threshold.

[0229] S22: Transfer power parameter data I n Transmitted to the power parameter sensor with the strongest transmission capacity;

[0230] S23: Repeat step S22 until the power parameter data I is obtained. n Transmitted to the central monitoring system.

[0231] S3: In the central monitoring system, a theft detection model is built to detect theft behavior on pre-processed power parameter data.

[0232] Step S3 involves constructing an electricity theft detection model to detect electricity theft behavior from the preprocessed power parameter data, including:

[0233] A model for identifying electricity theft is constructed, wherein the abnormal behavior identification through multi-scale feature fusion is the implementation method of the electricity theft identification model. The electricity theft identification model takes preprocessed power parameter data as input and electricity theft behavior detection results as output. The electricity theft identification model includes an input layer, a multi-scale feature extraction layer, a neighborhood information extraction layer, a feature fusion layer, and a behavior recognition layer.

[0234] The input layer is used to receive preprocessed power parameter data;

[0235] The multi-scale feature extraction layer is a convolutional layer structure in a convolutional neural network, used to perform multi-scale convolution operations on preprocessed power parameter data to form multi-scale power parameter features.

[0236] The neighborhood information extraction layer is a long short-term memory network structure, which is used to extract effective neighborhood information of neighboring substations based on the location information of the substations corresponding to the preprocessed power parameter data.

[0237] The feature fusion layer is used to fuse multi-scale power parameter features and effective neighborhood information to form power parameter fusion features.

[0238] The behavior recognition layer is a fully connected layer structure in a convolutional neural network, used to map the fusion features of power parameters into the results of electricity theft behavior recognition;

[0239] The electricity theft detection model is used to detect electricity theft behavior using preprocessed power parameter data, where the preprocessed power parameter data x n The procedure for detecting electricity theft is as follows:

[0240] S31: The input layer receives preprocessed power parameter data x n ;

[0241] S32: Multi-scale feature extraction layer for preprocessed power parameter data x n Perform multi-scale convolution operations to construct multi-scale power parameter features:

[0242]

[0243]

[0244] in:

[0245] f n This represents the preprocessed power parameter data x. n Multi-scale electrical parameter characteristics;

[0246] W k×k This represents a k-row, k-column convolution weight matrix, where * represents the convolution operator;

[0247] This represents the preprocessed power parameter data x. n Electricity parameter characteristics at scale k;

[0248] S33: Neighborhood information extraction layer is based on preprocessed power parameter data x n Based on the location information of the corresponding substation, extract the effective neighborhood information of neighboring substations:

[0249]

[0250] in:

[0251] Q n This represents the valid neighborhood information of neighboring substations;

[0252] Indicates with x n The preprocessed power parameter data of the substation with the shortest transmission line and the corresponding power station are characterized by power parameter features at scale K.

[0253] S34: Feature fusion layer for multi-scale power parameter features f n And effective neighborhood information Q n Feature fusion is performed to form the power parameter fusion feature Z. n :

[0254]

[0255] S35: The behavior recognition layer fuses power parameters with feature Z. n Mapped to electricity theft behavior identification results:

[0256]

[0257] in:

[0258] Y n This represents the preprocessed power parameter data x. n The corresponding electricity theft behavior identification result; if Y n If the value is higher than the preset threshold, it indicates that there is electricity theft; otherwise, there is no electricity theft.

[0259] W2 represents the mapping weight matrix.

[0260] S4: If electricity theft is detected, dispatch the corresponding high-definition camera at the substation to collect monitoring video of the substation location area.

[0261] Step S4 involves scheduling the corresponding high-definition cameras at the substation to collect monitoring video of the substation's location area, including:

[0262] If preprocessed power parameter data x is detected n If electricity theft is detected, the high-definition cameras of the nth substation will be dispatched to monitor and collect video footage of the substation's location. Based on the video footage, an anti-electricity theft investigation will be conducted at the substation.

[0263] Example 2:

[0264] like Figure 2 The diagram shown is a functional block diagram of a substation anti-electricity theft inspection and monitoring system based on Beidou technology provided in an embodiment of the present invention, which can realize the substation anti-electricity theft inspection and monitoring method based on Beidou technology in Embodiment 1.

[0265] The substation anti-electricity theft inspection and monitoring system 100 based on BeiDou technology described in this invention can be installed in an electronic device. Depending on the functions implemented, the BeiDou-based substation anti-electricity theft inspection and monitoring system may include a sensor deployment module 101, a data acquisition module 102, and an electricity theft detection device 103. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0266] The sensor deployment module 101 is used to deploy power parameter sensors with BeiDou positioning function in the substation power distribution network structure according to the substation power distribution network structure and based on the global energy consumption optimization strategy.

[0267] The data acquisition module 102 is used to collect power parameter data of the substation in real time using deployed power parameter sensors, and transmit the power parameter data to the central monitoring system for preprocessing via narrowband Internet of Things to obtain preprocessed power parameter data.

[0268] The electricity theft detection device 103 is used to build an electricity theft identification model to detect electricity theft behavior on preprocessed power parameter data. If electricity theft behavior is detected, the corresponding high-definition camera of the substation is dispatched to collect monitoring video of the substation location area.

[0269] In detail, the modules in the substation anti-electricity theft inspection and monitoring system 100 based on Beidou technology described in this embodiment of the invention adopt the same approach as described above when in use. Figure 1 The method used is the same as the BeiDou-based substation anti-electricity theft inspection and monitoring method described in the article, and can produce the same technical effect, so it will not be elaborated here.

[0270] Example 3:

[0271] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing a substation anti-electricity theft inspection and monitoring method based on Beidou technology, according to an embodiment of the present invention.

[0272] 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.

[0273] 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.

[0274] 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 substation anti-electricity theft inspection and monitoring based on Beidou technology), and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0275] 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.

[0276] 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.

[0277] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 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.

[0278] 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.

[0279] 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.

[0280] 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.

[0281] 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.

[0282] 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.

[0283] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for monitoring and investigating electricity theft in substations based on BeiDou technology, characterized in that, The method includes: S1: Based on the substation power distribution network structure, power parameter sensors with BeiDou positioning function are deployed in the substation power distribution network structure based on the global energy consumption optimization strategy. The power parameter sensors include current sensors, voltage sensors and temperature sensors. S2: Real-time collection of substation power parameter data using deployed power parameter sensors, and transmission of the power parameter data to the central monitoring system via narrowband Internet of Things for preprocessing to obtain preprocessed power parameter data; S3: In the central monitoring system, a model for identifying electricity theft is built to detect electricity theft behavior from pre-processed power parameter data; S4: If electricity theft is detected, dispatch the corresponding high-definition camera at the substation to monitor and collect video footage of the substation's location area. The step S1, obtaining the substation power distribution network structure, includes: The location set of substations is obtained using BeiDou technology, where the location set of substations is as follows: in: This indicates the location of the nth substation, and N represents the total number of substations. The substation distribution network structure is constructed based on the location set of substations. The construction process of the substation distribution network structure is as follows: Step 1: Initialize and construct the substation triangular network structure set. The constructed substation triangular network structure set is initially empty. Step 2: Construct a super triangle network structure that includes all substation locations, and put the super triangle network structure into the substation triangle network structure set; Step 3: Insert the substation locations in the location set into the triangular network structures in the substation triangular network structure set in turn. The inserted substation locations are inside any triangular network structure in the substation triangular network structure set. The triangular network structure of the substation is obtained by traversing the set of triangular network structures of the substation whose circumscribed circle contains the location of the substation. The triangular network structure obtained by traversing the set of triangular network structures forms a polygon structure. All the triangular network structures inside the polygon structure are deleted, and the vertices of the polygon structure are connected to the substation locations to form multiple new triangular network structures. Step 4: Repeat step 3 until all substation locations in the location set are inserted into the substation triangular network structure set, so that the super triangular network structure is divided into multiple triangular network structures. Step 5: Delete the triangular network structures whose vertices are the same as those of the super triangle network structure to form the substation power distribution network structure. The substation power distribution network structure contains M triangular network structures, and the vertex of each triangular network structure is the location of the substation. Based on the strategy of optimizing global energy consumption, deploy power parameter sensors with BeiDou positioning function in the substation power distribution network structure; The deployment of power parameter sensors with BeiDou positioning function in the substation distribution network structure based on the optimized global energy consumption strategy includes: Based on an optimized global energy consumption strategy, power parameter sensors with BeiDou positioning capabilities are deployed in the substation distribution network structure. These power parameter sensors include current sensors, voltage sensors, and temperature sensors. The deployment process for these power parameter sensors is as follows: S11: Obtain M triangular mesh structures, where the vertices of the m-th triangular mesh structure are: ; S12: Constructing an objective function for deploying power parameter sensors based on an optimized global energy consumption strategy: in: This represents the objective function for deploying power parameter sensors. This indicates the deployment results of the power parameter sensors; This indicates the deployment location of the power parameter sensor deployed in the m-th triangular mesh structure; This represents the importance weight of the m-th triangular mesh structure; This represents the average annual power transmission capacity of the strain power station corresponding to the three vertices of the m-th triangular mesh structure; Indicates the deployment location of the power parameter sensor With vertex The distance between them; This indicates the communication distance threshold for power parameter sensors; S13: Initialize and generate the deployment results of U groups of power parameter sensors, where the initial generated deployment result of the u-th group of power parameter sensors is: in: This represents the deployment result of the u-th group of power parameter sensors generated during initialization; Indicates the deployment results of power parameter sensors The deployment location of the power parameter sensor deployed in the m-th triangular mesh structure; S14: Let the current iteration number of the power parameter sensor deployment results be t, and the maximum iteration number be Max. Then, the t-th iteration result of the u-th group of power parameter sensor deployment results is: The initial value of t is 0; S15: Iterate the deployment results of the power parameter sensors until the preset maximum number of iterations is reached, and substitute the U sets of power parameter sensor deployment results obtained in the current iteration into the power parameter sensor deployment objective function. Select the power parameter sensor deployment result with the smallest power parameter sensor deployment objective function value for power parameter sensor deployment. S16: N substations send information to the nearest power parameter sensor, count the number of messages received by each power parameter sensor, and remove power parameter sensors that have not received messages.

2. The method for monitoring and investigating electricity theft in substations based on BeiDou technology as described in claim 1, characterized in that, Step S15 iterates over the deployment results of the power parameter sensors, including: S151: Calculate the location information of the power parameter sensor deployment locations, where the power parameter sensor deployment locations are... The location information is: in: Indicates the deployment location of the power parameter sensor Location information; The locations of the power parameter sensors are shown in sequence. For the three vertices Position weight; Represents an exponential function with the natural constant as its base; S152: Calculate the fitness of different power parameter sensor deployment locations, where the power parameter sensor deployment locations... The fitness is: in: Indicates the deployment location of the power parameter sensor The fitness of; Record the deployment location of the power parameter sensor with the minimum fitness among different triangular mesh structures during t iterations, as the historical best location of the triangular mesh structure, where the historical best location of the m-th triangular mesh structure after t iterations is: ; S153: Iterate on the deployment results of the power parameter sensors, whereby the deployment results of the power parameter sensors... The iterative formula is: in: Represents a random number between -1 and 1; c represents the control parameter; The mapping matrix represents the location information, where T denotes transpose; This represents the sequence of historical optimal deployment locations after t iterations; S154: Let t = t + 1, then return to step S151.

3. The method for anti-electricity theft detection and monitoring of substations based on BeiDou technology as described in claim 1, characterized in that, In step S2, the deployed power parameter sensors are used to collect power parameter data of the substation in real time, including: The substation sends power parameter data to the nearest power parameter sensor, where the power parameter data of the nth substation is: in: This represents the power parameter data of the nth substation; The current data sequence, voltage data sequence, and temperature data sequence of the nth substation are represented sequentially. Represents a data sequence The G sampled data values ​​in the data. Represents a data sequence The g-th sampled data value in the sample; Power parameter data is transmitted to a central monitoring system via narrowband Internet of Things (IoT) for preprocessing, resulting in preprocessed power parameter data. Medium sampled data values The preprocessing formula is: in: Indicates the sampled data value The preprocessing results; This represents the maximum threshold value for the i-th type of power parameter. This represents the minimum threshold value for the i-th type of power parameter. Power parameter data The corresponding preprocessing result is : in: The current data sequence is as follows. Voltage data sequence and temperature data sequences The preprocessing results.

4. The method for anti-electricity theft detection and monitoring of substations based on Beidou technology as described in claim 3, characterized in that, The transmission of power parameter data to the central monitoring system via narrowband Internet of Things includes: Power parameter data is transmitted to a central monitoring system via narrowband Internet of Things (IoT). The transmission process is as follows: S21: Calculate the power parameter data for different power parameter sensors. Transmission capability: in: This indicates that any power parameter sensor provides power parameter data. Transmission capability; Represents power parameter data Number of bits transmitted This indicates the preset transmission bit threshold; E indicates the current power level of the power parameter sensor; Indicates power parameter sensors and power parameter data Distance between current locations; This indicates the distance between the power parameter sensor and the central monitoring system. This indicates the preset transmission distance threshold; S22: Transfer power parameter data Transmitted to the power parameter sensor with the strongest transmission capacity; S23: Repeat step S22 until the power parameter data is obtained. Transmitted to the central monitoring system.

5. The method for anti-electricity theft inspection and monitoring of substations based on Beidou technology as described in claim 1, characterized in that, Step S3 involves constructing an electricity theft detection model to detect electricity theft behavior from the preprocessed power parameter data, including: A model for identifying electricity theft is constructed. The model takes preprocessed power parameter data as input and the results of electricity theft detection as output. The model includes an input layer, a multi-scale feature extraction layer, a neighborhood information extraction layer, a feature fusion layer, and a behavior recognition layer. The input layer is used to receive preprocessed power parameter data; The multi-scale feature extraction layer is a convolutional layer structure in a convolutional neural network, used to perform multi-scale convolution operations on preprocessed power parameter data to form multi-scale power parameter features. The neighborhood information extraction layer is a long short-term memory network structure, which is used to extract effective neighborhood information of neighboring substations based on the location information of the substations corresponding to the preprocessed power parameter data. The feature fusion layer is used to fuse multi-scale power parameter features and effective neighborhood information to form power parameter fusion features. The behavior recognition layer is a fully connected layer structure in a convolutional neural network, used to map the fusion features of power parameters into the results of electricity theft behavior recognition; The electricity theft detection model is used to detect electricity theft behavior using preprocessed power parameter data. The procedure for detecting electricity theft is as follows: S31: The input layer receives preprocessed power parameter data. ; S32: Multi-scale feature extraction layer for preprocessed power parameter data Perform multi-scale convolution operations to construct multi-scale power parameter features: in: This indicates the preprocessed power parameter data. Multi-scale electrical parameter characteristics; This represents a k-row, k-column convolution weight matrix. This represents the convolution operator; This indicates the preprocessed power parameter data. Electricity parameter characteristics at scale k; S33: Neighborhood information extraction layer is based on preprocessed power parameter data Based on the location information of the corresponding substation, extract the effective neighborhood information of neighboring substations: in: This represents the valid neighborhood information of neighboring substations; Indicates and The preprocessed power parameter data of the substation with the shortest transmission line and the corresponding power station are characterized by power parameter features at scale K. S34: Feature fusion layer for multi-scale power parameter features and effective neighborhood information Feature fusion is performed to form power parameter fusion features. ; S35: The behavior recognition layer integrates power parameters with features. Mapped to electricity theft behavior identification results: in: This indicates the preprocessed power parameter data. The corresponding electricity theft behavior identification results; if If the value is higher than the preset threshold, it indicates that there is electricity theft; otherwise, there is no electricity theft. This represents the mapping weight matrix.

6. The method for anti-electricity theft detection and monitoring of substations based on Beidou technology as described in claim 5, characterized in that, Step S4 involves scheduling the corresponding high-definition cameras at the substation to collect monitoring video of the substation's location area, including: If preprocessed power parameter data is detected If electricity theft is detected, the high-definition cameras of the nth substation will be dispatched to monitor and collect video footage of the substation's location. Based on the video footage, an anti-electricity theft investigation will be conducted at the substation.

7. A substation anti-electricity theft detection and monitoring system based on BeiDou technology, characterized in that, The system includes: The sensor deployment module is used to deploy power parameter sensors with BeiDou positioning function in the substation power distribution network structure based on the global energy consumption optimization strategy, according to the substation power distribution network structure. The data acquisition module is used to collect power parameter data of the substation in real time using deployed power parameter sensors, and transmit the power parameter data to the central monitoring system via narrowband Internet of Things for preprocessing to obtain preprocessed power parameter data. An electricity theft detection device is used to construct an electricity theft identification model to detect electricity theft behavior on preprocessed power parameter data. If electricity theft behavior is detected, the corresponding high-definition camera of the substation is dispatched to collect monitoring video of the substation location area, so as to realize a substation anti-electricity theft inspection and monitoring method based on Beidou technology as described in any one of claims 1-6.

Images