Power grid switching method, system and equipment based on aerial view platform, and storage medium

Through the One-Class SVM model of the Smart View platform, the power grid data is processed on the Smart View platform, and the computing and communication needs of power grid switching in high-proportion renewable energy and power electronic equipment systems are solved, and a method of quickly identifying abnormal locations of the power grid is realized. Ensure the stable operation of the power grid.

CN118983790AActive Publication Date: 2024-11-19GUANGDONG POWER GRID CO LTD +1
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202411079765.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-19
Estimated Expiration
2044-08-07

AI Technical Summary

Technical Problem

In power grid systems with high proportion of renewable energy and high proportion of power electronic equipment, massive distributed power supply and electric vehicle access cause grid switching to require processing a large number of dynamic components, resulting in increased computing and communication requirements, making it difficult to quickly determine the abnormal location of the power grid, affecting the impact of The power grid is operating stably.

Method used

Using a smart-view platform-based method, by obtaining environmental data, equipment status data and grid operation data, performing time alignment and standardization processing, building a One-Class SVM model for training, using this model for abnormal detection, generating grid switching instructions, and realizing Quickly identify abnormal locations of the power grid.

Benefits of technology

No additional filtering operation is required, the One-Class SVM model solves the problem of noise reduction and abnormal detection at the same time, quickly determines the abnormal location of the power grid, realizes fast and efficient grid switching, and ensures stable operation of the power grid.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118983790A_ABST
    Figure CN118983790A_ABST
Patent Text Reader

Abstract

The invention discloses a power grid switching method, system and device based on an aerial view platform, and a storage medium. The method comprises the following steps: obtaining first physical information collected by a data collection device; performing time alignment and standardization processing on the first physical information to obtain second physical information; the method comprises the following steps: constructing an One-Class SVM (Support Vector Machine) model based on training data generated by a pre-configured digital twin model, and training the One-Class SVM model to obtain a trained model; inputting the second physical information into the trained model for anomaly detection to obtain abnormal data and a power grid abnormal position; and generating a power grid switching instruction according to the abnormal data, and sending the power grid switching instruction to power grid switching execution equipment according to the power grid abnormal position. According to the method, two problems of noise reduction and anomaly recognition can be solved at the same time, and the abnormal position of the power grid can be quickly judged from mass data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of power grid switching technology, and in particular to a power grid switching method, system, device and storage medium based on a Zhikan platform. Background Art

[0002] With the development of social economy, electricity has become an important infrastructure to support social operation. The scale of my country's power grid continues to expand, and a large number of power electronic equipment and new energy sources are connected, resulting in increasing risks in the safe and stable operation of the power grid. In the process of safe operation of the power grid, grid switching usually refers to the need to switch between different power sources or parts of the power grid in the power system due to various reasons (such as equipment maintenance, fault handling, etc.) to ensure the continuity and stability of power supply.

[0003] The Southern Power Grid Intelligent Platform is based on a unified power grid data model, with maps as the entrance. It carries graphics, topology, and ledger management of all types of power grid equipment, realizes the integration of geographic, physical, and management data, and expands new energy and integrated energy models on this basis, deepening the platform's ability to support business, and providing support for distributed power access design and operation monitoring, and distribution network intelligent planning under the new power system.

[0004] A commonly used grid switching method is to reduce noise and detect faults on the collected grid data, and then generate grid switching instructions. However, in a "double-high" power system, that is, a system with a high proportion of renewable energy and a high proportion of power electronic equipment, due to the replacement of small power sources and the access of massive distributed power sources, electric vehicles, distributed energy storage, etc., the number of dynamic components that need to be considered in grid switching may reach 10 5 ~10 6 This leads to a "dimensionality explosion", which brings severe problems such as high computing and communication requirements to the stable operation of the power grid.

[0005] Faced with the ever-expanding scale of power grids, the above-mentioned power grid switching method requires filtering of massive data, which makes it difficult to quickly determine the abnormal location of the power grid, and is not conducive to the safe and stable operation of the power grid. Summary of the invention

[0006] The present invention provides a power grid switching method, system, device and storage medium based on the Zhikan platform, so as to simultaneously solve the two problems of noise reduction and anomaly identification, and quickly determine the abnormal location of the power grid from massive data.

[0007] In a first aspect, in order to solve the above technical problems, the present invention provides a power grid switching method based on the Zhikan platform, comprising: Acquire first physical information collected by a data collection device, wherein the first physical information includes environmental data, device status data, and power grid operation data; Performing time alignment and standardization processing on the first physical information to obtain second physical information; Building a One-Class SVM model based on training data generated by a pre-configured digital twin model, and training the One-Class SVM model to obtain a trained model, wherein the training data includes noise and normal data integrated with global power grid data; Inputting the second physical information into the trained model to perform anomaly detection to obtain abnormal data and abnormal position of the power grid; A power grid switching instruction is generated according to the abnormal data, and the power grid switching instruction is sent to a power grid switching execution device according to the abnormal position of the power grid.

[0008] As an optional implementation, the environmental data includes the temperature and humidity of the environment in which the data acquisition device is located, the device status data includes the location coordinates and mechanical loss degree of the data acquisition device, and the power grid operation data includes power grid load, voltage, and current.

[0009] As an optional implementation manner, time alignment and standardization processing is performed on the first physical information to obtain the second physical information, including: Time-align the first physical information to generate a multi-dimensional feature vector , including: represents the temperature of the i-th time window, represents the humidity in the i-th time window, represents the position coordinates of the i-th time window, represents the degree of mechanical loss in the i-th time window, represents the grid load in the i-th time window, represents the voltage in the i-th time window, represents the current in the i-th time window; The multidimensional feature vector is subjected to the standardization process in multiple time windows to generate the second physical information as described in the following formula: in, T Represents the number of time windows; each row in the second physical information represents the multidimensional feature vector within a time window; each column in the second physical information represents the change of the first physical information over time.

[0010] As an optional implementation, the one-class SVM model is constructed based on the training data generated by the pre-configured digital twin model, and the model is trained to obtain the trained model, including: A One-Class SVM model is constructed by using a radial basis function kernel as a kernel function and setting reasonable hyperparameters; wherein the radial basis function kernel is used to map input data to a high-dimensional space, and the hyperparameters are used to determine a hypersphere of the One-Class SVM model.

[0011] The training data generated by the digital twin model is passed to the Fit function configured by the One-Class SVM model for training to obtain the trained model.

[0012] As an optional implementation, the high-dimensional space is used to separate similar data points from dissimilar data points.

[0013] The hypersphere is a boundary generated by the One-Class SVM model based on the hyperparameters and the radial basis function kernel, and is used to determine abnormal data and normal data containing noise, wherein the test sample data within the boundary of the hypersphere is the normal data containing noise, and the test sample data within the boundary of the hypersphere is the abnormal data.

[0014] As an optional implementation manner, the step of inputting the second physical information into the trained model to perform anomaly detection to obtain abnormal data and abnormal positions of the power grid includes: The second physical information is passed as a test sample to the Predict function configured by the trained model for prediction to obtain a prediction result; wherein the Predict function is used to calculate the distance between the data of the test sample and the hypersphere configured by the trained model, the data whose distance is a first distance value is the abnormal data, the data whose distance is a second distance value is the normal data containing noise, and the abnormal position of the power grid is the position coordinates of the data acquisition device corresponding to the abnormal data.

[0015] As an optional implementation, the power grid switching instruction includes: connecting, disconnecting or isolating the power supply equipment at the abnormal location of the power grid.

[0016] In a second aspect, the present invention provides a power grid switching system based on the Zhikan platform, comprising: a data collection module, for acquiring first physical information, wherein the first physical information comprises: environmental data, equipment status data, and power grid operation data; A preprocessing module, used for performing time alignment and standardization processing on the first physical information to obtain second physical information; A model training module, used for building a One-Class SVM model according to training data generated by a pre-configured digital twin model, and training the One-Class SVM model to obtain a trained model, wherein the training data includes noise and normal data integrated with global power grid data; An anomaly detection module, used for inputting the second physical information into the trained model to perform anomaly detection, and obtain abnormal data and abnormal position of the power grid; The instruction sending module is used to generate a power grid switching instruction according to the abnormal data, and send the power grid switching instruction to the power grid switching execution device according to the abnormal position of the power grid.

[0017] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the power grid switching method based on the big data platform described above when executing the program.

[0018] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power grid switching method based on the big data platform as described above.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a power grid switching method, system and storage medium based on the Zhikan platform. The method is executed by a data terminal, including obtaining first physical information collected by a data acquisition device; performing time alignment and standardization processing on the first physical information to obtain second physical information; constructing a One-Class SVM model based on training data generated by a pre-configured digital twin model, training the One-Class SVM model to obtain a trained model; inputting the second physical information into the trained model for anomaly detection to obtain abnormal data and abnormal position of the power grid; generating a power grid switching instruction according to the abnormal data, and sending the power grid switching instruction to a power grid switching execution device according to the abnormal position of the power grid.

[0020] The method does not require additional filtering operations, and simultaneously solves the two problems of noise reduction and anomaly detection through the One-Class SVM model. It can quickly determine the abnormal location of the power grid from massive data, realize fast and efficient power grid switching operations, and is conducive to the stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1It is a flowchart of a power grid switching method based on the Zhikan platform provided in an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of a power grid switching system based on the Zhikan platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] An embodiment of the present invention provides a power grid switching method based on a big data platform, comprising the following steps: S11, acquiring first physical information collected by a data collection device, wherein the first physical information includes environmental data, device status data, and power grid operation data; S12, performing time alignment and standardization processing on the first physical information to obtain second physical information; S13, building a One-Class SVM model based on training data generated by a pre-configured digital twin model, and training the One-Class SVM model to obtain a trained model, wherein the training data includes noise and normal data integrated with global power grid data; S14, inputting the second physical information into the trained model to perform anomaly detection to obtain abnormal data and abnormal position of the power grid; S15, generating a power grid switching instruction according to the abnormal data, and sending the power grid switching instruction to a power grid switching execution device according to the abnormal position of the power grid.

[0025] In the present invention, the big data platform is a platform or data processing terminal that uses digital means to reengineer processes, drive service changes, and improve user experience. This platform uses map technology as a carrier, is driven by geographic, physical, and management data, and is one of the new generation of digital power grid operation basic platforms for the entire network and society. It integrates data from the field of power generation and production, explores multi-dimensional and three-dimensional fusion analysis and display of data, and realizes the seamless connection between business specifications and IT system construction. In addition, the big data platform also carries the graphics, topology, and ledger management of all types of power grid equipment, realizes the integration of geographic, physical, and management data, and expands applications such as new energy and integrated energy services on this basis.

[0026] Optionally, the big data platform includes the Zhikan platform, and may also be other data processing terminals with data comprehensive processing functions, which is not limited in the present invention.

[0027] Accordingly, refer to Figure 1 The embodiment of the present invention provides a power grid switching method based on the Zhikan platform, comprising the following steps: S11, acquiring first physical information collected by a data collection device, wherein the first physical information includes environmental data, device status data, and power grid operation data; S12, performing time alignment and standardization processing on the first physical information to obtain second physical information; S13, building a One-Class SVM model based on training data generated by a pre-configured digital twin model, and training the One-Class SVM model to obtain a trained model, wherein the training data includes noise and normal data integrated with global power grid data; S14, inputting the second physical information into the trained model to perform anomaly detection to obtain abnormal data and abnormal position of the power grid; S15, generating a power grid switching instruction according to the abnormal data, and sending the power grid switching instruction to a power grid switching execution device according to the abnormal position of the power grid.

[0028] In step S11, it should be noted that the environmental data includes the temperature and humidity of the environment in which the data acquisition device is located. The equipment status data includes the location coordinates and mechanical loss degree of the data acquisition device, and the power grid operation data includes the power grid load, voltage, and current in multiple time windows within the current detection cycle.

[0029] Furthermore, the data acquisition device is each sensor device configured for the power grid, including a power grid measurement unit, a temperature and humidity measurement unit, a coordinate positioning unit, and a network access unit. Exemplarily, the power grid measurement unit is used to measure the load, voltage, and current of the power grid, which helps to ensure the safety of the power grid. The temperature and humidity measurement unit is used to measure the temperature and humidity of the environment, monitor the ambient temperature, and help identify fires or other temperature anomalies. Monitor the ambient humidity and help prevent equipment problems caused by humidity. The coordinate positioning unit is used for coordinate positioning of the data collection module and obtaining geographic location data, for example, the geographic location data can be described as three-dimensional space coordinates. The network access unit is used to transmit each first physical information collected by the data acquisition device to the data terminal.

[0030] In step S12, it should be noted that the first physical information is time aligned to ensure that different physical information has a consistent time reference and to generate a multi-dimensional feature vector , which includes: represents the temperature of the i-th time window, represents the humidity in the i-th time window, represents the position coordinates of the i-th time window, represents the degree of mechanical loss in the i-th time window, represents the grid load in the i-th time window, represents the voltage of the ith time window, represents the current in the i-th time window; and then the multi-dimensional is normalized in multiple time windows, including superposition processing in multiple time windows, to generate the second physical information as described in the following formula: in, T Represents the number of time windows; each row in the second physical information represents the multidimensional feature vector within a time window; each column in the second physical information represents the change of the first physical information over time.

[0031] In step S13, it should be noted that a One-Class SVM model is constructed by using a radial basis function kernel (RBF) as a kernel function and setting reasonable hyperparameters; wherein the radial basis function kernel (RBF) is used to map the input data to a high-dimensional space, and the nonlinear problem that is difficult to handle is transformed into a linear problem after being mapped to the high-dimensional space, so as to separate similar data points from dissimilar data points.

[0032] In this embodiment, the hyperparameter is pre-set and is defined as the upper limit of the ratio of samples that violate the constraint to all samples, which is the upper limit of the sum of all slack variables divided by the number of samples, and is used to determine the hypersphere of the One-Class SVM model. Exemplarily, the hyperparameter can be set to 0.00001, and this parameter can be adjusted as needed with reference to the ratio of abnormal data to total sample data in the historical record data. The One-Class SVM model is an unsupervised machine learning model for anomaly detection, which belongs to the support vector machine (SVM) model family, but unlike the traditional SVM, the One-Class SVM model is specifically designed to handle situations where there is only one type of positive data (i.e., no clear negative examples), identify normal data in the data set, and treat any samples that deviate from this pattern as abnormal data.

[0033] It is worth noting that the hypersphere is a sphere in a feature space of three dimensions or more. The boundary is generated by the One-Class SVM model based on hyperparameters and training data, and is used to determine abnormal data and normal data containing noise. Among them, the test sample data outside the hypersphere boundary is determined as abnormal data and is marked as the first distance value "-1" in the One-Class SVM model; the test sample data within the hypersphere boundary is determined as normal data containing noise and is marked as the second distance value "1" in the One-Class SVM model. The hypersphere can be described by the following formula: in, O is the center of the hypersphere, r is the radius of the hypersphere, ξ i is the slack variable, l i is the penalty coefficient, i is a positive integer, x i is the training data. Further, the relaxation variable ξ i Indicates that training data is allowed x i Violation of the hypersphere definition constraint, penalty coefficient l i Represents the coefficient of the manually defined slack variable, which is used to weight the importance of training data and the penalty coefficient l i The larger it is, the more important the training data is, and the less likely it is that the training data will exceed the boundary of the hypersphere.

[0034] Further, the training data generated by the big data platform is passed to the Fit function configured by the One-Class SVM model for training to obtain the trained model. The big data platform includes the Zhikan platform, which integrates the global power grid data to establish a digital twin model. The digital twin model is a highly detailed virtual model that uses data from the physical world to create a digital replica of a real system or object. This technology is mainly used to simulate, analyze and predict the performance of complex systems so that they can be tested and optimized without affecting the real system. The digital twin model usually contains a large amount of real-time data and historical event data collected from similar situations in the past. These data are collected from their physical counterparts through sensors and used to update the model to reflect real-time conditions. The model integrates geographic, physical, management and business information to simulate the actual power grid and assist power grid staff in making power grid switching decisions. The digital twin model of the Zhikan platform can generate a large amount of data for machine learning model training by integrating and simulating the real-world power grid system.

[0035] In one embodiment, the digital twin model performs digital simulation on various devices in the actual power grid system, and uses the simulation data of each data acquisition device in the digital twin model as training data. It should be noted that the simulation data generated in the digital twin model contains noise.

[0036] It should be noted that the training data generated by the digital twin model is time-aligned and standardized according to the first physical information, and then passed to the Fit function configured by the One-Class SVM model for machine learning model training to obtain the trained model.

[0037] The Fit function is the core component of the One-Class SVM model. It receives the time-aligned and standardized training data and the One-Class SVM model, and treats the training data as normal data of the same category. Inside the Fit function, the One-Class SVM model constructs and solves an optimization problem, which aims to find a minimum hypersphere that contains all the training data as much as possible. In the process of solving the optimization problem, the Fit function determines the support vectors, which are located on or near the boundary of the hypersphere and are crucial to defining the optimal hypersphere. The output of the Fit function is the trained model. The trained model generates a minimum hypersphere based on the pre-set hyperparameters and training data, and tries to contain the training data within the boundary of the hypersphere, which is used to detect anomalies in the test sample data.

[0038] In step S14, the second physical information is input into the trained model for anomaly detection to obtain abnormal data and abnormal position of the power grid. It should be noted that the second physical information is passed as a test sample to the Predict function configured by the trained model for prediction to obtain a prediction result.

[0039] Since the training data contains noise, the trained model classifies noise and normal data into one category. Therefore, in the process of obtaining the first physical information collected by the data acquisition device from the data terminal to inputting the second physical information into the trained model, there is no need to perform noise reduction on the data. Compared with the existing power grid switching method, the noise reduction link is reduced, which is conducive to saving computing resources.

[0040] The Predict function is used to calculate the distance between the test sample data and the boundary of the hypersphere configured by the trained model, and then input the sign function (sgn function). The sign function (sgn function) is used to classify the input value. When the input value is a positive number, the sign function returns a value of "1", and when the input value is a negative number, the sign function returns a value of "-1". Therefore, when the final return value of the Predict function is the first distance value "-1", the test sample data is judged to be abnormal data, and when the final return value of the Predict function is the second distance value "1", the test sample data is judged to be normal data containing noise. The Predict function can be expressed as follows: in, x m For the test sample data, r is the radius of the hypersphere, O is the center of the hypersphere, It is the distance from the test sample data to the center of the hypersphere in high-dimensional space.

[0041] Then, according to the second physical information where the abnormal data is located, the location coordinates of the data acquisition device corresponding to the abnormal data are found, which is the abnormal location of the power grid. It is worth noting that the second physical information includes the location coordinates.

[0042] In step S15, a power grid switching instruction is generated according to the abnormal data, and the power grid switching instruction is sent to the power grid switching execution device according to the abnormal position of the power grid. It should be noted that the data terminal analyzes the abnormal data, determines the abnormal type, and generates a corresponding power grid switching instruction according to the abnormal type. Exemplarily, the abnormal type may include fire, typhoon, or other situations requiring power grid switching, which is not limited in the present invention. Among them, the power grid switching instruction includes connecting, disconnecting or isolating the power supply equipment at the abnormal position of the power grid.

[0043] The embodiment of the present invention also provides a power grid switching system based on a big data platform, which can implement the entire process of the above-mentioned power grid switching method based on a big data platform.

[0044] Reference Figure 2 , is a schematic diagram of an embodiment of a power grid switching system based on a big data platform provided by the present invention.

[0045] An embodiment of the present invention provides a power grid switching system based on a big data platform, comprising: The data collection module 201 is used to obtain first physical information, wherein the first physical information includes: environmental data, equipment status data, and power grid operation data; A preprocessing module 202, configured to perform time alignment and standardization processing on the first physical information to obtain second physical information; A model training module 203 is used to build a One-Class SVM model according to the training data generated by the pre-configured digital twin model, and train the One-Class SVM model to obtain a trained model, wherein the training data includes noise and normal data integrated with global power grid data; Anomaly detection module 204, used for inputting the second physical information into the trained model to perform anomaly detection, and obtain abnormal data and abnormal position of the power grid; The instruction sending module 205 is used to generate a power grid switching instruction according to the abnormal data, and send the power grid switching instruction to the power grid switching execution device according to the abnormal position of the power grid.

[0046] In a specific embodiment, the data collection module collects first physical information from each sensor unit configured by the data acquisition device, the environmental data includes the temperature and humidity of the environment in which the data acquisition device is located, the equipment status data includes the location coordinates and mechanical loss degree of the data acquisition device, and the power grid operation data includes the power grid load, voltage, and current.

[0047] Optionally, the data collection module 201 includes: The grid measurement unit is used to measure grid load, voltage, and current, which helps to ensure grid safety.

[0048] The temperature and humidity measurement unit is used to measure the temperature and humidity of the environment. Monitoring the ambient temperature helps to identify fire or other temperature anomalies, and monitoring the ambient humidity helps to prevent equipment problems caused by humidity.

[0049] The coordinate positioning unit is used for coordinate positioning of the data collection module to obtain geographic location data, for example, the geographic location data can be called three-dimensional space coordinates.

[0050] The network access unit is used to transmit each first physical information collected by the data collection device to the data terminal.

[0051] Optionally, the preprocessing module 202 includes: A feature vector generating unit, configured to perform the time alignment on the first physical information to generate a multi-dimensional feature vector , including: represents the temperature of the i-th time window, represents the humidity in the i-th time window, represents the position coordinates of the i-th time window, represents the degree of mechanical loss in the i-th time window, represents the grid load in the i-th time window, represents the voltage of the ith time window, represents the current in the i-th time window; The standardization processing unit is used to perform standardization processing on the multidimensional feature vector in multiple time windows to generate the second physical information as described in the following formula: in, T Represents the number of time windows; each row in the second physical information represents the multidimensional feature vector within a time window; each column in the second physical information represents the change of the first physical information over time.

[0052] Optionally, the model training module 203 includes: A model building unit is used to use a radial basis function kernel as a kernel function and set reasonable hyperparameters to build a One-Class SVM model; wherein the radial basis function kernel is used to map input data to a high-dimensional space, and the hyperparameters are used to determine the hypersphere of the One-Class SVM model. The high-dimensional space is used to separate similar data points from dissimilar data points; the hypersphere is a boundary generated by the One-Class SVM model based on the hyperparameters and the radial basis function kernel, and is used to determine abnormal data and normal data containing noise, wherein the test sample data within the hypersphere boundary is the normal data containing noise, and the test sample data within the hypersphere boundary is the abnormal data.

[0053] The training data generating unit is used to obtain training data by using the simulation data of each data acquisition device in the digital twin model as training data.

[0054] The training unit is used to pass the training data generated by the digital twin model to the Fit function configured by the One-Class SVM model for training to obtain a trained model.

[0055] Optionally, the anomaly detection module 204 includes: An abnormal data detection unit is used to pass the second physical information as a test sample to the Predict function configured by the trained model for prediction to obtain a prediction result; wherein the Predict function is used to calculate the distance between the data of the test sample and the hypersphere configured by the trained model, the data whose distance is the first distance value is the abnormal data, and the data whose distance is the second distance value is the normal data containing noise.

[0056] The power grid abnormal position detection unit is used to find the position coordinates of the data acquisition device corresponding to the abnormal data in the second physical information, and determine it as the abnormal position of the power grid.

[0057] Optionally, the instruction sending module 205 includes: The instruction generation unit is used to analyze the abnormal data, determine the abnormal type, and generate a corresponding power grid switching instruction according to the abnormal type. Exemplarily, the abnormal type may include fire, typhoon, or other situations requiring power grid switching, which is not limited in the present invention. The power grid switching instruction includes: connecting, disconnecting or isolating the power supply equipment at the abnormal position of the power grid.

[0058] An instruction transmission unit is used to transmit the power grid switching instruction to the power grid switching execution device according to the abnormal position of the power grid.

[0059] In summary, in the present invention, a power grid switching method, system, device and storage medium based on a big data platform are provided. The method is executed by a data terminal, including obtaining first physical information collected by a data acquisition device; performing time alignment and standardization processing on the first physical information to obtain second physical information; constructing a One-Class SVM model based on training data generated by a pre-configured digital twin model, training the One-Class SVM model, and obtaining a trained model; inputting the second physical information into the trained model for anomaly detection to obtain abnormal data and abnormal power grid positions; generating a power grid switching instruction based on the abnormal data, and sending the power grid switching instruction to a power grid switching execution device based on the abnormal power grid position. The method does not require additional filtering operations, and solves both noise reduction and anomaly detection problems through the One-Class SVM model. It can quickly determine the abnormal power grid position from massive data, realize fast and efficient power grid switching operations, and is conducive to the stable operation of the power grid.

[0060] The embodiment of the present invention further provides an electronic device. The terminal device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an authorization program for projector use. When the processor executes the computer program, the steps in the above-mentioned authorization method for projector use are implemented, such as Figure 1 Alternatively, the processor implements the functions of each module / unit in the above-mentioned system embodiments when executing the computer program.

[0061] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0062] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of terminal devices and do not constitute a limitation on the terminal device. The terminal device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0063] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0064] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0065] Wherein, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0066] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0067] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power grid switching method based on the Zhikan platform, characterized in that: Executed by the data terminal, including: Acquire first physical information collected by a data collection device, wherein the first physical information includes environmental data, device status data, and power grid operation data; Performing time alignment and standardization processing on the first physical information to obtain second physical information; Building a One-Class SVM model based on training data generated by a pre-configured digital twin model, and training the One-Class SVM model to obtain a trained model, wherein the training data includes noise and normal data integrated with global power grid data; Inputting the second physical information into the trained model to perform anomaly detection to obtain abnormal data and abnormal position of the power grid; A power grid switching instruction is generated according to the abnormal data, and the power grid switching instruction is sent to a power grid switching execution device according to the abnormal position of the power grid.

2. The power grid switching method based on the Zhikan platform according to claim 1 is characterized in that: The environmental data includes the temperature and humidity of the environment in which the data acquisition device is located, the device status data includes the location coordinates and mechanical loss degree of the data acquisition device, and the power grid operation data includes the power grid load, voltage, and current.

3. The power grid switching method based on the Zhikan platform according to claim 1 is characterized in that: The performing time alignment and standardization processing on the first physical information to obtain second physical information includes: Perform the time alignment on the first physical information to generate a multidimensional feature vector , including: represents the temperature of the i-th time window, represents the humidity in the i-th time window, represents the position coordinates of the i-th time window, represents the degree of mechanical loss in the i-th time window, represents the grid load in the i-th time window, represents the voltage of the ith time window, represents the current in the i-th time window; The multidimensional feature vector is subjected to the standardization process in multiple time windows to generate the second physical information as described in the following formula: in, T Represents the number of time windows; each row in the second physical information represents the multidimensional feature vector within a time window; each column in the second physical information represents the change of the first physical information over time.

4. The power grid switching method based on the Zhikan platform according to claim 1 is characterized in that: The one-class SVM model is constructed based on the training data generated by the pre-configured digital twin model, and the model is trained to obtain the trained model, including: A One-Class SVM model is constructed by using a radial basis function kernel as a kernel function and setting reasonable hyperparameters; wherein the radial basis function kernel is used to map input data to a high-dimensional space, and the hyperparameters are used to determine a hypersphere of the One-Class SVM model; The training data generated by the digital twin model is passed to the Fit function configured by the One-Class SVM model for training to obtain the trained model.

5. The power grid switching method based on the Zhikan platform according to claim 4 is characterized in that: The high-dimensional space is used to separate similar data points from dissimilar data points; The hypersphere is a boundary generated by the One-Class SVM model based on the hyperparameters and the radial basis function kernel, and is used to determine abnormal data and normal data containing noise, wherein the test sample data within the boundary of the hypersphere is the normal data containing noise, and the test sample data within the boundary of the hypersphere is the abnormal data.

6. The power grid switching method based on the Zhikan platform according to claim 1 is characterized in that: The step of inputting the second physical information into the trained model to perform anomaly detection to obtain abnormal data and abnormal positions of the power grid includes: The second physical information is passed as a test sample to the Predict function configured by the trained model for prediction to obtain a prediction result; wherein the Predict function is used to calculate the distance between the data of the test sample and the hypersphere configured by the trained model, the data whose distance is a first distance value is the abnormal data, the data whose distance is a second distance value is the normal data containing noise, and the abnormal position of the power grid is the position coordinates of the data acquisition device corresponding to the abnormal data.

7. The power grid switching method based on the Zhikan platform according to claim 1 is characterized in that: The power grid switching instruction includes: connecting, disconnecting or isolating the power supply equipment at the abnormal position of the power grid.

8. A power grid switching system based on the Zhikan platform, characterized in that: include: A data collection module, used to obtain first physical information, wherein the first physical information includes: environmental data, equipment status data, and power grid operation data; A preprocessing module, used for performing time alignment and standardization processing on the first physical information to obtain second physical information; A model training module, used for building a One-Class SVM model according to training data generated by a pre-configured digital twin model, training the One-Class SVM model to obtain a trained model, wherein the training data includes noise and normal data integrated with global power grid data; An anomaly detection module, used for inputting the second physical information into the trained model to perform anomaly detection, and obtain abnormal data and abnormal position of the power grid; The instruction sending module is used to generate a power grid switching instruction according to the abnormal data, and send the power grid switching instruction to the power grid switching execution device according to the abnormal position of the power grid.

9. A device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power grid switching method based on the Zhikan platform as described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Dual-channel network switching method, vehicle-mounted gateway system and computer-readable storage medium

    CN109151770A

  • Intelligent power data anomaly detection method and system

    CN114358152A

  • Induction motor rapid diagnosis method and system based on model search and reduction

    CN116047290A

  • Text sentiment classification method based on EEG (electroencephalogram) cognitive alignment knowledge graph

    CN117033638A

  • Power communication equipment data anomaly detection method and system and storage medium

    CN117034180A